diff --git a/sahara/plugins/vanilla/hadoop2/run_scripts.py b/sahara/plugins/vanilla/hadoop2/run_scripts.py index 73559e2..319850e 100644 --- a/sahara/plugins/vanilla/hadoop2/run_scripts.py +++ b/sahara/plugins/vanilla/hadoop2/run_scripts.py @@ -192,6 +192,8 @@ def _oozie_share_lib(remote): 'hadoop fs -mkdir /user && ' 'hadoop fs -mkdir /user/hadoop && ' 'hadoop fs -put /tmp/oozielib/share /user/hadoop/ && ' + 'hadoop fs -put /opt/oozie/libtools/commons-httpclient-3.1.jar ' + '/user/hadoop/share/lib/oozie/ &&' 'rm -rf /tmp/oozielib" hadoop') LOG.debug("Creating sqlfile for Oozie") @@ -278,8 +280,10 @@ def start_hiveserver_process(pctx, instance): if not oozie or instance.hostname() != oozie.hostname(): _start_mysql(r) + version = instance.cluster.hadoop_version sql_script = files.get_file_text( - 'plugins/vanilla/hadoop2/resources/create_hive_db.sql' + 'plugins/vanilla/v{}/resources/create_hive_db.sql'.format( + version.replace('.', '_')) ) sql_script = sql_script.replace( diff --git a/sahara/plugins/vanilla/hadoop2/resources/create_hive_db.sql b/sahara/plugins/vanilla/v2_7_1/resources/create_hive_db.sql similarity index 100% rename from sahara/plugins/vanilla/hadoop2/resources/create_hive_db.sql rename to sahara/plugins/vanilla/v2_7_1/resources/create_hive_db.sql diff --git a/sahara/plugins/vanilla/v2_8_2/__init__.py b/sahara/plugins/vanilla/v2_8_2/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/sahara/plugins/vanilla/v2_8_2/config_helper.py b/sahara/plugins/vanilla/v2_8_2/config_helper.py new file mode 100644 index 0000000..447ff93 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/config_helper.py @@ -0,0 +1,126 @@ +# Copyright (c) 2015 Mirantis Inc. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or +# implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from oslo_config import cfg +import six + +from sahara.plugins import provisioning as p +from sahara.plugins.vanilla.hadoop2 import config_helper as c_helper +from sahara.utils import xmlutils as x + +CONF = cfg.CONF +CONF.import_opt("enable_data_locality", "sahara.topology.topology_helper") + +CORE_DEFAULT = x.load_hadoop_xml_defaults( + 'plugins/vanilla/v2_8_2/resources/core-default.xml') + +HDFS_DEFAULT = x.load_hadoop_xml_defaults( + 'plugins/vanilla/v2_8_2/resources/hdfs-default.xml') + +MAPRED_DEFAULT = x.load_hadoop_xml_defaults( + 'plugins/vanilla/v2_8_2/resources/mapred-default.xml') + +YARN_DEFAULT = x.load_hadoop_xml_defaults( + 'plugins/vanilla/v2_8_2/resources/yarn-default.xml') + +OOZIE_DEFAULT = x.load_hadoop_xml_defaults( + 'plugins/vanilla/v2_8_2/resources/oozie-default.xml') + +HIVE_DEFAULT = x.load_hadoop_xml_defaults( + 'plugins/vanilla/v2_8_2/resources/hive-default.xml') + +XML_CONFS = { + "Hadoop": [CORE_DEFAULT], + "HDFS": [HDFS_DEFAULT], + "YARN": [YARN_DEFAULT], + "MapReduce": [MAPRED_DEFAULT], + "JobFlow": [OOZIE_DEFAULT], + "Hive": [HIVE_DEFAULT] +} + +ENV_CONFS = { + "YARN": { + 'ResourceManager Heap Size': 1024, + 'NodeManager Heap Size': 1024 + }, + "HDFS": { + 'NameNode Heap Size': 1024, + 'SecondaryNameNode Heap Size': 1024, + 'DataNode Heap Size': 1024 + }, + "MapReduce": { + 'JobHistoryServer Heap Size': 1024 + }, + "JobFlow": { + 'Oozie Heap Size': 1024 + } +} + +# Initialise plugin Hadoop configurations +PLUGIN_XML_CONFIGS = c_helper.init_xml_configs(XML_CONFS) +PLUGIN_ENV_CONFIGS = c_helper.init_env_configs(ENV_CONFS) + + +def _init_all_configs(): + configs = [] + configs.extend(PLUGIN_XML_CONFIGS) + configs.extend(PLUGIN_ENV_CONFIGS) + configs.extend(c_helper.PLUGIN_GENERAL_CONFIGS) + configs.extend(_get_spark_configs()) + configs.extend(_get_zookeeper_configs()) + return configs + + +def _get_spark_configs(): + spark_configs = [] + for service, config_items in six.iteritems(c_helper.SPARK_CONFS): + for item in config_items['OPTIONS']: + cfg = p.Config(name=item["name"], + description=item["description"], + default_value=item["default"], + applicable_target=service, + scope="cluster", is_optional=True, + priority=item["priority"]) + spark_configs.append(cfg) + return spark_configs + + +def _get_zookeeper_configs(): + zk_configs = [] + for service, config_items in six.iteritems(c_helper.ZOOKEEPER_CONFS): + for item in config_items['OPTIONS']: + cfg = p.Config(name=item["name"], + description=item["description"], + default_value=item["default"], + applicable_target=service, + scope="cluster", is_optional=True, + priority=item["priority"]) + zk_configs.append(cfg) + return zk_configs + + +PLUGIN_CONFIGS = _init_all_configs() + + +def get_plugin_configs(): + return PLUGIN_CONFIGS + + +def get_xml_configs(): + return PLUGIN_XML_CONFIGS + + +def get_env_configs(): + return ENV_CONFS diff --git a/sahara/plugins/vanilla/v2_8_2/edp_engine.py b/sahara/plugins/vanilla/v2_8_2/edp_engine.py new file mode 100644 index 0000000..3b7d174 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/edp_engine.py @@ -0,0 +1,81 @@ +# Copyright (c) 2015 Red Hat, Inc. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or +# implied. +# See the License for the specific language governing permissions and +# limitations under the License. +import os + +from sahara import exceptions as ex +from sahara.i18n import _ +from sahara.plugins import utils as plugin_utils +from sahara.plugins.vanilla import confighints_helper as ch_helper +from sahara.plugins.vanilla.hadoop2 import edp_engine +from sahara.plugins.vanilla import utils as v_utils +from sahara.service.edp.spark import engine as edp_spark_engine +from sahara.utils import edp + + +class EdpOozieEngine(edp_engine.EdpOozieEngine): + @staticmethod + def get_possible_job_config(job_type): + if edp.compare_job_type(job_type, edp.JOB_TYPE_HIVE): + return {'job_config': ch_helper.get_possible_hive_config_from( + 'plugins/vanilla/v2_8_2/resources/hive-default.xml')} + if edp.compare_job_type(job_type, + edp.JOB_TYPE_MAPREDUCE, + edp.JOB_TYPE_MAPREDUCE_STREAMING): + return {'job_config': ch_helper.get_possible_mapreduce_config_from( + 'plugins/vanilla/v2_8_2/resources/mapred-default.xml')} + if edp.compare_job_type(job_type, edp.JOB_TYPE_PIG): + return {'job_config': ch_helper.get_possible_pig_config_from( + 'plugins/vanilla/v2_8_2/resources/mapred-default.xml')} + return edp_engine.EdpOozieEngine.get_possible_job_config(job_type) + + +class EdpSparkEngine(edp_spark_engine.SparkJobEngine): + + edp_base_version = "2.8.2" + + def __init__(self, cluster): + super(EdpSparkEngine, self).__init__(cluster) + self.master = plugin_utils.get_instance(cluster, + "spark history server") + self.plugin_params["spark-user"] = "sudo -u hadoop " + self.plugin_params["spark-submit"] = os.path.join( + plugin_utils.get_config_value_or_default( + "Spark", "Spark home", self.cluster), + "bin/spark-submit") + self.plugin_params["deploy-mode"] = "cluster" + self.plugin_params["master"] = "yarn" + + driver_cp = plugin_utils.get_config_value_or_default( + "Spark", "Executor extra classpath", self.cluster) + self.plugin_params["driver-class-path"] = driver_cp + + @staticmethod + def edp_supported(version): + return version >= EdpSparkEngine.edp_base_version + + @staticmethod + def job_type_supported(job_type): + return (job_type in + edp_spark_engine.SparkJobEngine.get_supported_job_types()) + + def validate_job_execution(self, cluster, job, data): + if (not self.edp_supported(cluster.hadoop_version) or + not v_utils.get_spark_history_server(cluster)): + + raise ex.InvalidDataException( + _('Spark {base} or higher required to run {type} jobs').format( + base=EdpSparkEngine.edp_base_version, type=job.type)) + + super(EdpSparkEngine, self).validate_job_execution(cluster, job, data) diff --git a/sahara/plugins/vanilla/v2_8_2/resources/README.rst b/sahara/plugins/vanilla/v2_8_2/resources/README.rst new file mode 100644 index 0000000..1819db6 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/README.rst @@ -0,0 +1,27 @@ +Apache Hadoop Configurations for Sahara +======================================= + +This directory contains default XML configuration files: + +* core-default.xml +* hdfs-default.xml +* mapred-default.xml +* yarn-default.xml +* oozie-default.xml +* hive-default.xml + +These files are applied for Sahara's plugin of Apache Hadoop version 2.8.2 + + +Files were taken from here: + +* `core-default.xml `_ +* `hdfs-default.xml `_ +* `yarn-default.xml `_ +* `mapred-default.xml `_ +* `oozie-default.xml `_ + +XML configs are used to expose default Hadoop configurations to the users +through Sahara's REST API. It allows users to override some config values which +will be pushed to the provisioned VMs running Hadoop services as part of +appropriate xml config. diff --git a/sahara/plugins/vanilla/v2_8_2/resources/core-default.xml b/sahara/plugins/vanilla/v2_8_2/resources/core-default.xml new file mode 100644 index 0000000..f319205 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/core-default.xml @@ -0,0 +1,2414 @@ + + + + + + + + + + + + + + + hadoop.common.configuration.version + 0.23.0 + version of this configuration file + + + + hadoop.tmp.dir + /tmp/hadoop-${user.name} + A base for other temporary directories. + + + + io.native.lib.available + true + Controls whether to use native libraries for bz2 and zlib + compression codecs or not. The property does not control any other native + libraries. + + + + + hadoop.http.filter.initializers + org.apache.hadoop.http.lib.StaticUserWebFilter + A comma separated list of class names. Each class in the list + must extend org.apache.hadoop.http.FilterInitializer. The corresponding + Filter will be initialized. Then, the Filter will be applied to all user + facing jsp and servlet web pages. The ordering of the list defines the + ordering of the filters. + + + + + + hadoop.security.authorization + false + Is service-level authorization enabled? + + + + hadoop.security.instrumentation.requires.admin + false + + Indicates if administrator ACLs are required to access + instrumentation servlets (JMX, METRICS, CONF, STACKS). + + + + + hadoop.security.authentication + simple + Possible values are simple (no authentication), and kerberos + + + + + hadoop.security.group.mapping + org.apache.hadoop.security.JniBasedUnixGroupsMappingWithFallback + + Class for user to group mapping (get groups for a given user) for ACL. + The default implementation, + org.apache.hadoop.security.JniBasedUnixGroupsMappingWithFallback, + will determine if the Java Native Interface (JNI) is available. If JNI is + available the implementation will use the API within hadoop to resolve a + list of groups for a user. If JNI is not available then the shell + implementation, ShellBasedUnixGroupsMapping, is used. This implementation + shells out to the Linux/Unix environment with the + bash -c groups command to resolve a list of groups for a user. + + + + + hadoop.security.dns.interface + + The name of the Network Interface from which the service should determine + its host name for Kerberos login. e.g. eth2. In a multi-homed environment, + the setting can be used to affect the _HOST subsitution in the service + Kerberos principal. If this configuration value is not set, the service + will use its default hostname as returned by + InetAddress.getLocalHost().getCanonicalHostName(). + + Most clusters will not require this setting. + + + + + hadoop.security.dns.nameserver + + The host name or IP address of the name server (DNS) which a service Node + should use to determine its own host name for Kerberos Login. Requires + hadoop.security.dns.interface. + + Most clusters will not require this setting. + + + + + hadoop.security.dns.log-slow-lookups.enabled + false + + Time name lookups (via SecurityUtil) and log them if they exceed the + configured threshold. + + + + + hadoop.security.dns.log-slow-lookups.threshold.ms + 1000 + + If slow lookup logging is enabled, this threshold is used to decide if a + lookup is considered slow enough to be logged. + + + + + hadoop.security.groups.cache.secs + 300 + + This is the config controlling the validity of the entries in the cache + containing the user->group mapping. When this duration has expired, + then the implementation of the group mapping provider is invoked to get + the groups of the user and then cached back. + + + + + hadoop.security.groups.negative-cache.secs + 30 + + Expiration time for entries in the the negative user-to-group mapping + caching, in seconds. This is useful when invalid users are retrying + frequently. It is suggested to set a small value for this expiration, since + a transient error in group lookup could temporarily lock out a legitimate + user. + + Set this to zero or negative value to disable negative user-to-group caching. + + + + + hadoop.security.groups.cache.warn.after.ms + 5000 + + If looking up a single user to group takes longer than this amount of + milliseconds, we will log a warning message. + + + + + hadoop.security.groups.cache.background.reload + false + + Whether to reload expired user->group mappings using a background thread + pool. If set to true, a pool of + hadoop.security.groups.cache.background.reload.threads is created to + update the cache in the background. + + + + + hadoop.security.groups.cache.background.reload.threads + 3 + + Only relevant if hadoop.security.groups.cache.background.reload is true. + Controls the number of concurrent background user->group cache entry + refreshes. Pending refresh requests beyond this value are queued and + processed when a thread is free. + + + + + hadoop.security.group.mapping.ldap.connection.timeout.ms + 60000 + + This property is the connection timeout (in milliseconds) for LDAP + operations. If the LDAP provider doesn't establish a connection within the + specified period, it will abort the connect attempt. Non-positive value + means no LDAP connection timeout is specified in which case it waits for the + connection to establish until the underlying network times out. + + + + + hadoop.security.group.mapping.ldap.read.timeout.ms + 60000 + + This property is the read timeout (in milliseconds) for LDAP + operations. If the LDAP provider doesn't get a LDAP response within the + specified period, it will abort the read attempt. Non-positive value + means no read timeout is specified in which case it waits for the response + infinitely. + + + + + hadoop.security.group.mapping.ldap.url + + + The URL of the LDAP server to use for resolving user groups when using + the LdapGroupsMapping user to group mapping. + + + + + hadoop.security.group.mapping.ldap.ssl + false + + Whether or not to use SSL when connecting to the LDAP server. + + + + + hadoop.security.group.mapping.ldap.ssl.keystore + + + File path to the SSL keystore that contains the SSL certificate required + by the LDAP server. + + + + + hadoop.security.group.mapping.ldap.ssl.keystore.password.file + + + The path to a file containing the password of the LDAP SSL keystore. + + IMPORTANT: This file should be readable only by the Unix user running + the daemons. + + + + + hadoop.security.group.mapping.ldap.bind.user + + + The distinguished name of the user to bind as when connecting to the LDAP + server. This may be left blank if the LDAP server supports anonymous binds. + + + + + hadoop.security.group.mapping.ldap.bind.password.file + + + The path to a file containing the password of the bind user. + + IMPORTANT: This file should be readable only by the Unix user running + the daemons. + + + + + hadoop.security.group.mapping.ldap.base + + + The search base for the LDAP connection. This is a distinguished name, + and will typically be the root of the LDAP directory. + + + + + hadoop.security.group.mapping.ldap.search.filter.user + (&(objectClass=user)(sAMAccountName={0})) + + An additional filter to use when searching for LDAP users. The default will + usually be appropriate for Active Directory installations. If connecting to + an LDAP server with a non-AD schema, this should be replaced with + (&(objectClass=inetOrgPerson)(uid={0}). {0} is a special string used to + denote where the username fits into the filter. + + If the LDAP server supports posixGroups, Hadoop can enable the feature by + setting the value of this property to "posixAccount" and the value of + the hadoop.security.group.mapping.ldap.search.filter.group property to + "posixGroup". + + + + + hadoop.security.group.mapping.ldap.search.filter.group + (objectClass=group) + + An additional filter to use when searching for LDAP groups. This should be + changed when resolving groups against a non-Active Directory installation. + + See the description of hadoop.security.group.mapping.ldap.search.filter.user + to enable posixGroups support. + + + + + hadoop.security.group.mapping.ldap.search.attr.member + member + + The attribute of the group object that identifies the users that are + members of the group. The default will usually be appropriate for + any LDAP installation. + + + + + hadoop.security.group.mapping.ldap.search.attr.group.name + cn + + The attribute of the group object that identifies the group name. The + default will usually be appropriate for all LDAP systems. + + + + + hadoop.security.group.mapping.ldap.posix.attr.uid.name + uidNumber + + The attribute of posixAccount to use when groups for membership. + Mostly useful for schemas wherein groups have memberUids that use an + attribute other than uidNumber. + + + + + hadoop.security.group.mapping.ldap.posix.attr.gid.name + gidNumber + + The attribute of posixAccount indicating the group id. + + + + + hadoop.security.group.mapping.ldap.directory.search.timeout + 10000 + + The attribute applied to the LDAP SearchControl properties to set a + maximum time limit when searching and awaiting a result. + Set to 0 if infinite wait period is desired. + Default is 10 seconds. Units in milliseconds. + + + + + hadoop.security.group.mapping.providers + + + Comma separated of names of other providers to provide user to group + mapping. Used by CompositeGroupsMapping. + + + + + hadoop.security.group.mapping.providers.combined + true + + true or false to indicate whether groups from the providers are combined or + not. The default value is true. If true, then all the providers will be + tried to get groups and all the groups are combined to return as the final + results. Otherwise, providers are tried one by one in the configured list + order, and if any groups are retrieved from any provider, then the groups + will be returned without trying the left ones. + + + + + hadoop.security.service.user.name.key + + + For those cases where the same RPC protocol is implemented by multiple + servers, this configuration is required for specifying the principal + name to use for the service when the client wishes to make an RPC call. + + + + + + hadoop.security.uid.cache.secs + 14400 + + This is the config controlling the validity of the entries in the cache + containing the userId to userName and groupId to groupName used by + NativeIO getFstat(). + + + + + hadoop.rpc.protection + authentication + A comma-separated list of protection values for secured sasl + connections. Possible values are authentication, integrity and privacy. + authentication means authentication only and no integrity or privacy; + integrity implies authentication and integrity are enabled; and privacy + implies all of authentication, integrity and privacy are enabled. + hadoop.security.saslproperties.resolver.class can be used to override + the hadoop.rpc.protection for a connection at the server side. + + + + + hadoop.security.saslproperties.resolver.class + + SaslPropertiesResolver used to resolve the QOP used for a + connection. If not specified, the full set of values specified in + hadoop.rpc.protection is used while determining the QOP used for the + connection. If a class is specified, then the QOP values returned by + the class will be used while determining the QOP used for the connection. + + + + + hadoop.security.sensitive-config-keys + + secret$ + password$ + ssl.keystore.pass$ + fs.s3.*[Ss]ecret.?[Kk]ey + fs.azure.account.key.* + credential$ + oauth.*token$ + hadoop.security.sensitive-config-keys + + A comma-separated or multi-line list of regular expressions to + match configuration keys that should be redacted where appropriate, for + example, when logging modified properties during a reconfiguration, + private credentials should not be logged. + + + + + hadoop.workaround.non.threadsafe.getpwuid + true + Some operating systems or authentication modules are known to + have broken implementations of getpwuid_r and getpwgid_r, such that these + calls are not thread-safe. Symptoms of this problem include JVM crashes + with a stack trace inside these functions. If your system exhibits this + issue, enable this configuration parameter to include a lock around the + calls as a workaround. + + An incomplete list of some systems known to have this issue is available + at http://wiki.apache.org/hadoop/KnownBrokenPwuidImplementations + + + + + hadoop.kerberos.kinit.command + kinit + Used to periodically renew Kerberos credentials when provided + to Hadoop. The default setting assumes that kinit is in the PATH of users + running the Hadoop client. Change this to the absolute path to kinit if this + is not the case. + + + + + hadoop.kerberos.min.seconds.before.relogin + 60 + The minimum time between relogin attempts for Kerberos, in + seconds. + + + + + hadoop.security.auth_to_local + + Maps kerberos principals to local user names + + + + + io.file.buffer.size + 4096 + The size of buffer for use in sequence files. + The size of this buffer should probably be a multiple of hardware + page size (4096 on Intel x86), and it determines how much data is + buffered during read and write operations. + + + + io.bytes.per.checksum + 512 + The number of bytes per checksum. Must not be larger than + io.file.buffer.size. + + + + io.skip.checksum.errors + false + If true, when a checksum error is encountered while + reading a sequence file, entries are skipped, instead of throwing an + exception. + + + + io.compression.codecs + + A comma-separated list of the compression codec classes that can + be used for compression/decompression. In addition to any classes specified + with this property (which take precedence), codec classes on the classpath + are discovered using a Java ServiceLoader. + + + + io.compression.codec.bzip2.library + system-native + The native-code library to be used for compression and + decompression by the bzip2 codec. This library could be specified + either by by name or the full pathname. In the former case, the + library is located by the dynamic linker, usually searching the + directories specified in the environment variable LD_LIBRARY_PATH. + + The value of "system-native" indicates that the default system + library should be used. To indicate that the algorithm should + operate entirely in Java, specify "java-builtin". + + + + io.serializations + org.apache.hadoop.io.serializer.WritableSerialization, org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization, org.apache.hadoop.io.serializer.avro.AvroReflectSerialization + A list of serialization classes that can be used for + obtaining serializers and deserializers. + + + + io.seqfile.local.dir + ${hadoop.tmp.dir}/io/local + The local directory where sequence file stores intermediate + data files during merge. May be a comma-separated list of + directories on different devices in order to spread disk i/o. + Directories that do not exist are ignored. + + + + + io.map.index.skip + 0 + Number of index entries to skip between each entry. + Zero by default. Setting this to values larger than zero can + facilitate opening large MapFiles using less memory. + + + + io.map.index.interval + 128 + + MapFile consist of two files - data file (tuples) and index file + (keys). For every io.map.index.interval records written in the + data file, an entry (record-key, data-file-position) is written + in the index file. This is to allow for doing binary search later + within the index file to look up records by their keys and get their + closest positions in the data file. + + + + + + + fs.defaultFS + file:/// + The name of the default file system. A URI whose + scheme and authority determine the FileSystem implementation. The + uri's scheme determines the config property (fs.SCHEME.impl) naming + the FileSystem implementation class. The uri's authority is used to + determine the host, port, etc. for a filesystem. + + + + fs.default.name + file:/// + Deprecated. Use (fs.defaultFS) property + instead + + + + fs.trash.interval + 0 + Number of minutes after which the checkpoint + gets deleted. If zero, the trash feature is disabled. + This option may be configured both on the server and the + client. If trash is disabled server side then the client + side configuration is checked. If trash is enabled on the + server side then the value configured on the server is + used and the client configuration value is ignored. + + + + + fs.trash.checkpoint.interval + 0 + Number of minutes between trash checkpoints. + Should be smaller or equal to fs.trash.interval. If zero, + the value is set to the value of fs.trash.interval. + Every time the checkpointer runs it creates a new checkpoint + out of current and removes checkpoints created more than + fs.trash.interval minutes ago. + + + + + fs.protected.directories + + A comma-separated list of directories which cannot + be deleted even by the superuser unless they are empty. This + setting can be used to guard important system directories + against accidental deletion due to administrator error. + + + + + fs.AbstractFileSystem.file.impl + org.apache.hadoop.fs.local.LocalFs + The AbstractFileSystem for file: uris. + + + + fs.AbstractFileSystem.har.impl + org.apache.hadoop.fs.HarFs + The AbstractFileSystem for har: uris. + + + + fs.AbstractFileSystem.hdfs.impl + org.apache.hadoop.fs.Hdfs + The FileSystem for hdfs: uris. + + + + fs.AbstractFileSystem.viewfs.impl + org.apache.hadoop.fs.viewfs.ViewFs + The AbstractFileSystem for view file system for viewfs: uris + (ie client side mount table:). + + + + fs.AbstractFileSystem.ftp.impl + org.apache.hadoop.fs.ftp.FtpFs + The FileSystem for Ftp: uris. + + + + fs.AbstractFileSystem.webhdfs.impl + org.apache.hadoop.fs.WebHdfs + The FileSystem for webhdfs: uris. + + + + fs.AbstractFileSystem.swebhdfs.impl + org.apache.hadoop.fs.SWebHdfs + The FileSystem for swebhdfs: uris. + + + + fs.ftp.host + 0.0.0.0 + FTP filesystem connects to this server + + + + fs.ftp.host.port + 21 + + FTP filesystem connects to fs.ftp.host on this port + + + + + fs.df.interval + 60000 + Disk usage statistics refresh interval in msec. + + + + fs.du.interval + 600000 + File space usage statistics refresh interval in msec. + + + + fs.s3.block.size + 67108864 + Block size to use when writing files to S3. + + + + fs.s3.buffer.dir + ${hadoop.tmp.dir}/s3 + Determines where on the local filesystem the s3:/s3n: filesystem + should store files before sending them to S3 + (or after retrieving them from S3). + + + + + fs.s3.maxRetries + 4 + The maximum number of retries for reading or writing files to S3, + before we signal failure to the application. + + + + + fs.s3.sleepTimeSeconds + 10 + The number of seconds to sleep between each S3 retry. + + + + + fs.swift.impl + org.apache.hadoop.fs.swift.snative.SwiftNativeFileSystem + The implementation class of the OpenStack Swift Filesystem + + + + fs.automatic.close + true + By default, FileSystem instances are automatically closed at program + exit using a JVM shutdown hook. Setting this property to false disables this + behavior. This is an advanced option that should only be used by server applications + requiring a more carefully orchestrated shutdown sequence. + + + + + fs.s3n.block.size + 67108864 + Block size to use when reading files using the native S3 + filesystem (s3n: URIs). + + + + fs.s3n.multipart.uploads.enabled + false + Setting this property to true enables multiple uploads to + native S3 filesystem. When uploading a file, it is split into blocks + if the size is larger than fs.s3n.multipart.uploads.block.size. + + + + + fs.s3n.multipart.uploads.block.size + 67108864 + The block size for multipart uploads to native S3 filesystem. + Default size is 64MB. + + + + + fs.s3n.multipart.copy.block.size + 5368709120 + The block size for multipart copy in native S3 filesystem. + Default size is 5GB. + + + + + fs.s3n.server-side-encryption-algorithm + + Specify a server-side encryption algorithm for S3. + Unset by default, and the only other currently allowable value is AES256. + + + + + fs.s3a.access.key + AWS access key ID used by S3A file system. Omit for IAM role-based or provider-based authentication. + + + + fs.s3a.secret.key + AWS secret key used by S3A file system. Omit for IAM role-based or provider-based authentication. + + + + fs.s3a.aws.credentials.provider + + Comma-separated class names of credential provider classes which implement + com.amazonaws.auth.AWSCredentialsProvider. + + These are loaded and queried in sequence for a valid set of credentials. + Each listed class must implement one of the following means of + construction, which are attempted in order: + 1. a public constructor accepting java.net.URI and + org.apache.hadoop.conf.Configuration, + 2. a public static method named getInstance that accepts no + arguments and returns an instance of + com.amazonaws.auth.AWSCredentialsProvider, or + 3. a public default constructor. + + Specifying org.apache.hadoop.fs.s3a.AnonymousAWSCredentialsProvider allows + anonymous access to a publicly accessible S3 bucket without any credentials. + Please note that allowing anonymous access to an S3 bucket compromises + security and therefore is unsuitable for most use cases. It can be useful + for accessing public data sets without requiring AWS credentials. + + If unspecified, then the default list of credential provider classes, + queried in sequence, is: + 1. org.apache.hadoop.fs.s3a.BasicAWSCredentialsProvider: supports static + configuration of AWS access key ID and secret access key. See also + fs.s3a.access.key and fs.s3a.secret.key. + 2. com.amazonaws.auth.EnvironmentVariableCredentialsProvider: supports + configuration of AWS access key ID and secret access key in + environment variables named AWS_ACCESS_KEY_ID and + AWS_SECRET_ACCESS_KEY, as documented in the AWS SDK. + 3. org.apache.hadoop.fs.s3a.SharedInstanceProfileCredentialsProvider: + a shared instance of + com.amazonaws.auth.InstanceProfileCredentialsProvider from the AWS + SDK, which supports use of instance profile credentials if running + in an EC2 VM. Using this shared instance potentially reduces load + on the EC2 instance metadata service for multi-threaded + applications. + + + + + fs.s3a.session.token + Session token, when using org.apache.hadoop.fs.s3a.TemporaryAWSCredentialsProvider + as one of the providers. + + + + + fs.s3a.security.credential.provider.path + + + Optional comma separated list of credential providers, a list + which is prepended to that set in hadoop.security.credential.provider.path + + + + + fs.s3a.connection.maximum + 15 + Controls the maximum number of simultaneous connections to S3. + + + + fs.s3a.connection.ssl.enabled + true + Enables or disables SSL connections to S3. + + + + fs.s3a.endpoint + AWS S3 endpoint to connect to. An up-to-date list is + provided in the AWS Documentation: regions and endpoints. Without this + property, the standard region (s3.amazonaws.com) is assumed. + + + + + fs.s3a.path.style.access + false + Enable S3 path style access ie disabling the default virtual hosting behaviour. + Useful for S3A-compliant storage providers as it removes the need to set up DNS for virtual hosting. + + + + + fs.s3a.proxy.host + Hostname of the (optional) proxy server for S3 connections. + + + + fs.s3a.proxy.port + Proxy server port. If this property is not set + but fs.s3a.proxy.host is, port 80 or 443 is assumed (consistent with + the value of fs.s3a.connection.ssl.enabled). + + + + fs.s3a.proxy.username + Username for authenticating with proxy server. + + + + fs.s3a.proxy.password + Password for authenticating with proxy server. + + + + fs.s3a.proxy.domain + Domain for authenticating with proxy server. + + + + fs.s3a.proxy.workstation + Workstation for authenticating with proxy server. + + + + fs.s3a.attempts.maximum + 20 + How many times we should retry commands on transient errors. + + + + fs.s3a.connection.establish.timeout + 5000 + Socket connection setup timeout in milliseconds. + + + + fs.s3a.connection.timeout + 200000 + Socket connection timeout in milliseconds. + + + + fs.s3a.socket.send.buffer + 8192 + Socket send buffer hint to amazon connector. Represented in bytes. + + + + fs.s3a.socket.recv.buffer + 8192 + Socket receive buffer hint to amazon connector. Represented in bytes. + + + + fs.s3a.paging.maximum + 5000 + How many keys to request from S3 when doing + directory listings at a time. + + + + fs.s3a.threads.max + 10 + The total number of threads available in the filesystem for data + uploads *or any other queued filesystem operation*. + + + + fs.s3a.threads.keepalivetime + 60 + Number of seconds a thread can be idle before being + terminated. + + + + fs.s3a.max.total.tasks + 5 + The number of operations which can be queued for execution + + + + fs.s3a.multipart.size + 100M + How big (in bytes) to split upload or copy operations up into. + A suffix from the set {K,M,G,T,P} may be used to scale the numeric value. + + + + + fs.s3a.multipart.threshold + 2147483647 + How big (in bytes) to split upload or copy operations up into. + This also controls the partition size in renamed files, as rename() involves + copying the source file(s). + A suffix from the set {K,M,G,T,P} may be used to scale the numeric value. + + + + + fs.s3a.multiobjectdelete.enable + true + When enabled, multiple single-object delete requests are replaced by + a single 'delete multiple objects'-request, reducing the number of requests. + Beware: legacy S3-compatible object stores might not support this request. + + + + + fs.s3a.acl.default + Set a canned ACL for newly created and copied objects. Value may be Private, + PublicRead, PublicReadWrite, AuthenticatedRead, LogDeliveryWrite, BucketOwnerRead, + or BucketOwnerFullControl. + + + + fs.s3a.multipart.purge + false + True if you want to purge existing multipart uploads that may not have been + completed/aborted correctly. The corresponding purge age is defined in + fs.s3a.multipart.purge.age. + If set, when the filesystem is instantiated then all outstanding uploads + older than the purge age will be terminated -across the entire bucket. + This will impact multipart uploads by other applications and users. so should + be used sparingly, with an age value chosen to stop failed uploads, without + breaking ongoing operations. + + + + + fs.s3a.multipart.purge.age + 86400 + Minimum age in seconds of multipart uploads to purge. + + + + + fs.s3a.server-side-encryption-algorithm + Specify a server-side encryption algorithm for s3a: file system. + Unset by default, and the only other currently allowable value is AES256. + + + + + fs.s3a.signing-algorithm + Override the default signing algorithm so legacy + implementations can still be used + + + + fs.s3a.block.size + 32M + Block size to use when reading files using s3a: file system. + A suffix from the set {K,M,G,T,P} may be used to scale the numeric value. + + + + + fs.s3a.buffer.dir + ${hadoop.tmp.dir}/s3a + Comma separated list of directories that will be used to buffer file + uploads to. + + + + fs.s3a.fast.upload + false + + Use the incremental block-based fast upload mechanism with + the buffering mechanism set in fs.s3a.fast.upload.buffer. + + + + + fs.s3a.fast.upload.buffer + disk + + The buffering mechanism to use when using S3A fast upload + (fs.s3a.fast.upload=true). Values: disk, array, bytebuffer. + This configuration option has no effect if fs.s3a.fast.upload is false. + + "disk" will use the directories listed in fs.s3a.buffer.dir as + the location(s) to save data prior to being uploaded. + + "array" uses arrays in the JVM heap + + "bytebuffer" uses off-heap memory within the JVM. + + Both "array" and "bytebuffer" will consume memory in a single stream up to the number + of blocks set by: + + fs.s3a.multipart.size * fs.s3a.fast.upload.active.blocks. + + If using either of these mechanisms, keep this value low + + The total number of threads performing work across all threads is set by + fs.s3a.threads.max, with fs.s3a.max.total.tasks values setting the number of queued + work items. + + + + + fs.s3a.fast.upload.active.blocks + 4 + + Maximum Number of blocks a single output stream can have + active (uploading, or queued to the central FileSystem + instance's pool of queued operations. + + This stops a single stream overloading the shared thread pool. + + + + + fs.s3a.readahead.range + 64K + Bytes to read ahead during a seek() before closing and + re-opening the S3 HTTP connection. This option will be overridden if + any call to setReadahead() is made to an open stream. + A suffix from the set {K,M,G,T,P} may be used to scale the numeric value. + + + + + fs.s3a.user.agent.prefix + + + Sets a custom value that will be prepended to the User-Agent header sent in + HTTP requests to the S3 back-end by S3AFileSystem. The User-Agent header + always includes the Hadoop version number followed by a string generated by + the AWS SDK. An example is "User-Agent: Hadoop 2.8.0, aws-sdk-java/1.10.6". + If this optional property is set, then its value is prepended to create a + customized User-Agent. For example, if this configuration property was set + to "MyApp", then an example of the resulting User-Agent would be + "User-Agent: MyApp, Hadoop 2.8.0, aws-sdk-java/1.10.6". + + + + + fs.s3a.impl + org.apache.hadoop.fs.s3a.S3AFileSystem + The implementation class of the S3A Filesystem + + + + fs.AbstractFileSystem.s3a.impl + org.apache.hadoop.fs.s3a.S3A + The implementation class of the S3A AbstractFileSystem. + + + + + + fs.adl.impl + org.apache.hadoop.fs.adl.AdlFileSystem + + + + fs.AbstractFileSystem.adl.impl + org.apache.hadoop.fs.adl.Adl + + + + + + io.seqfile.compress.blocksize + 1000000 + The minimum block size for compression in block compressed + SequenceFiles. + + + + + io.mapfile.bloom.size + 1048576 + The size of BloomFilter-s used in BloomMapFile. Each time this many + keys is appended the next BloomFilter will be created (inside a DynamicBloomFilter). + Larger values minimize the number of filters, which slightly increases the performance, + but may waste too much space if the total number of keys is usually much smaller + than this number. + + + + + io.mapfile.bloom.error.rate + 0.005 + The rate of false positives in BloomFilter-s used in BloomMapFile. + As this value decreases, the size of BloomFilter-s increases exponentially. This + value is the probability of encountering false positives (default is 0.5%). + + + + + hadoop.util.hash.type + murmur + The default implementation of Hash. Currently this can take one of the + two values: 'murmur' to select MurmurHash and 'jenkins' to select JenkinsHash. + + + + + + + + ipc.client.idlethreshold + 4000 + Defines the threshold number of connections after which + connections will be inspected for idleness. + + + + + ipc.client.kill.max + 10 + Defines the maximum number of clients to disconnect in one go. + + + + + ipc.client.connection.maxidletime + 10000 + The maximum time in msec after which a client will bring down the + connection to the server. + + + + + ipc.client.connect.max.retries + 10 + Indicates the number of retries a client will make to establish + a server connection. + + + + + ipc.client.connect.retry.interval + 1000 + Indicates the number of milliseconds a client will wait for + before retrying to establish a server connection. + + + + + ipc.client.connect.timeout + 20000 + Indicates the number of milliseconds a client will wait for the + socket to establish a server connection. + + + + + ipc.client.connect.max.retries.on.timeouts + 45 + Indicates the number of retries a client will make on socket timeout + to establish a server connection. + + + + + ipc.client.tcpnodelay + true + Use TCP_NODELAY flag to bypass Nagle's algorithm transmission delays. + + + + + ipc.client.low-latency + false + Use low-latency QoS markers for IPC connections. + + + + + ipc.client.ping + true + Send a ping to the server when timeout on reading the response, + if set to true. If no failure is detected, the client retries until at least + a byte is read or the time given by ipc.client.rpc-timeout.ms is passed. + + + + + ipc.ping.interval + 60000 + Timeout on waiting response from server, in milliseconds. + The client will send ping when the interval is passed without receiving bytes, + if ipc.client.ping is set to true. + + + + + ipc.client.rpc-timeout.ms + 0 + Timeout on waiting response from server, in milliseconds. + If ipc.client.ping is set to true and this rpc-timeout is greater than + the value of ipc.ping.interval, the effective value of the rpc-timeout is + rounded up to multiple of ipc.ping.interval. + + + + + ipc.server.listen.queue.size + 128 + Indicates the length of the listen queue for servers accepting + client connections. + + + + + ipc.server.log.slow.rpc + false + This setting is useful to troubleshoot performance issues for + various services. If this value is set to true then we log requests that + fall into 99th percentile as well as increment RpcSlowCalls counter. + + + + + ipc.maximum.data.length + 67108864 + This indicates the maximum IPC message length (bytes) that can be + accepted by the server. Messages larger than this value are rejected by the + immediately to avoid possible OOMs. This setting should rarely need to be + changed. + + + + + ipc.maximum.response.length + 134217728 + This indicates the maximum IPC message length (bytes) that can be + accepted by the client. Messages larger than this value are rejected + immediately to avoid possible OOMs. This setting should rarely need to be + changed. Set to 0 to disable. + + + + + + + hadoop.security.impersonation.provider.class + + A class which implements ImpersonationProvider interface, used to + authorize whether one user can impersonate a specific user. + If not specified, the DefaultImpersonationProvider will be used. + If a class is specified, then that class will be used to determine + the impersonation capability. + + + + + hadoop.rpc.socket.factory.class.default + org.apache.hadoop.net.StandardSocketFactory + Default SocketFactory to use. This parameter is expected to be + formatted as "package.FactoryClassName". + + + + + hadoop.rpc.socket.factory.class.ClientProtocol + + SocketFactory to use to connect to a DFS. If null or empty, use + hadoop.rpc.socket.class.default. This socket factory is also used by + DFSClient to create sockets to DataNodes. + + + + + + + hadoop.socks.server + + Address (host:port) of the SOCKS server to be used by the + SocksSocketFactory. + + + + + + net.topology.node.switch.mapping.impl + org.apache.hadoop.net.ScriptBasedMapping + The default implementation of the DNSToSwitchMapping. It + invokes a script specified in net.topology.script.file.name to resolve + node names. If the value for net.topology.script.file.name is not set, the + default value of DEFAULT_RACK is returned for all node names. + + + + + net.topology.impl + org.apache.hadoop.net.NetworkTopology + The default implementation of NetworkTopology which is classic three layer one. + + + + + net.topology.script.file.name + + The script name that should be invoked to resolve DNS names to + NetworkTopology names. Example: the script would take host.foo.bar as an + argument, and return /rack1 as the output. + + + + + net.topology.script.number.args + 100 + The max number of args that the script configured with + net.topology.script.file.name should be run with. Each arg is an + IP address. + + + + + net.topology.table.file.name + + The file name for a topology file, which is used when the + net.topology.node.switch.mapping.impl property is set to + org.apache.hadoop.net.TableMapping. The file format is a two column text + file, with columns separated by whitespace. The first column is a DNS or + IP address and the second column specifies the rack where the address maps. + If no entry corresponding to a host in the cluster is found, then + /default-rack is assumed. + + + + + + file.stream-buffer-size + 4096 + The size of buffer to stream files. + The size of this buffer should probably be a multiple of hardware + page size (4096 on Intel x86), and it determines how much data is + buffered during read and write operations. + + + + file.bytes-per-checksum + 512 + The number of bytes per checksum. Must not be larger than + file.stream-buffer-size + + + + file.client-write-packet-size + 65536 + Packet size for clients to write + + + + file.blocksize + 67108864 + Block size + + + + file.replication + 1 + Replication factor + + + + + + s3.stream-buffer-size + 4096 + The size of buffer to stream files. + The size of this buffer should probably be a multiple of hardware + page size (4096 on Intel x86), and it determines how much data is + buffered during read and write operations. + + + + s3.bytes-per-checksum + 512 + The number of bytes per checksum. Must not be larger than + s3.stream-buffer-size + + + + s3.client-write-packet-size + 65536 + Packet size for clients to write + + + + s3.blocksize + 67108864 + Block size + + + + s3.replication + 3 + Replication factor + + + + + + s3native.stream-buffer-size + 4096 + The size of buffer to stream files. + The size of this buffer should probably be a multiple of hardware + page size (4096 on Intel x86), and it determines how much data is + buffered during read and write operations. + + + + s3native.bytes-per-checksum + 512 + The number of bytes per checksum. Must not be larger than + s3native.stream-buffer-size + + + + s3native.client-write-packet-size + 65536 + Packet size for clients to write + + + + s3native.blocksize + 67108864 + Block size + + + + s3native.replication + 3 + Replication factor + + + + + ftp.stream-buffer-size + 4096 + The size of buffer to stream files. + The size of this buffer should probably be a multiple of hardware + page size (4096 on Intel x86), and it determines how much data is + buffered during read and write operations. + + + + ftp.bytes-per-checksum + 512 + The number of bytes per checksum. Must not be larger than + ftp.stream-buffer-size + + + + ftp.client-write-packet-size + 65536 + Packet size for clients to write + + + + ftp.blocksize + 67108864 + Block size + + + + ftp.replication + 3 + Replication factor + + + + + + tfile.io.chunk.size + 1048576 + + Value chunk size in bytes. Default to + 1MB. Values of the length less than the chunk size is + guaranteed to have known value length in read time (See also + TFile.Reader.Scanner.Entry.isValueLengthKnown()). + + + + + tfile.fs.output.buffer.size + 262144 + + Buffer size used for FSDataOutputStream in bytes. + + + + + tfile.fs.input.buffer.size + 262144 + + Buffer size used for FSDataInputStream in bytes. + + + + + + + hadoop.http.authentication.type + simple + + Defines authentication used for Oozie HTTP endpoint. + Supported values are: simple | kerberos | #AUTHENTICATION_HANDLER_CLASSNAME# + + + + + hadoop.http.authentication.token.validity + 36000 + + Indicates how long (in seconds) an authentication token is valid before it has + to be renewed. + + + + + hadoop.http.authentication.signature.secret.file + ${user.home}/hadoop-http-auth-signature-secret + + The signature secret for signing the authentication tokens. + The same secret should be used for JT/NN/DN/TT configurations. + + + + + hadoop.http.authentication.cookie.domain + + + The domain to use for the HTTP cookie that stores the authentication token. + In order to authentiation to work correctly across all Hadoop nodes web-consoles + the domain must be correctly set. + IMPORTANT: when using IP addresses, browsers ignore cookies with domain settings. + For this setting to work properly all nodes in the cluster must be configured + to generate URLs with hostname.domain names on it. + + + + + hadoop.http.authentication.simple.anonymous.allowed + true + + Indicates if anonymous requests are allowed when using 'simple' authentication. + + + + + hadoop.http.authentication.kerberos.principal + HTTP/_HOST@LOCALHOST + + Indicates the Kerberos principal to be used for HTTP endpoint. + The principal MUST start with 'HTTP/' as per Kerberos HTTP SPNEGO specification. + + + + + hadoop.http.authentication.kerberos.keytab + ${user.home}/hadoop.keytab + + Location of the keytab file with the credentials for the principal. + Referring to the same keytab file Oozie uses for its Kerberos credentials for Hadoop. + + + + + + Enable/disable the cross-origin (CORS) filter. + hadoop.http.cross-origin.enabled + false + + + + Comma separated list of origins that are allowed for web + services needing cross-origin (CORS) support. Wildcards (*) and patterns + allowed + hadoop.http.cross-origin.allowed-origins + * + + + + Comma separated list of methods that are allowed for web + services needing cross-origin (CORS) support. + hadoop.http.cross-origin.allowed-methods + GET,POST,HEAD + + + + Comma separated list of headers that are allowed for web + services needing cross-origin (CORS) support. + hadoop.http.cross-origin.allowed-headers + X-Requested-With,Content-Type,Accept,Origin + + + + The number of seconds a pre-flighted request can be cached + for web services needing cross-origin (CORS) support. + hadoop.http.cross-origin.max-age + 1800 + + + + dfs.ha.fencing.methods + + + List of fencing methods to use for service fencing. May contain + builtin methods (eg shell and sshfence) or user-defined method. + + + + + dfs.ha.fencing.ssh.connect-timeout + 30000 + + SSH connection timeout, in milliseconds, to use with the builtin + sshfence fencer. + + + + + dfs.ha.fencing.ssh.private-key-files + + + The SSH private key files to use with the builtin sshfence fencer. + + + + + + + + The user name to filter as, on static web filters + while rendering content. An example use is the HDFS + web UI (user to be used for browsing files). + + hadoop.http.staticuser.user + dr.who + + + + ha.zookeeper.quorum + + A list of ZooKeeper server addresses, separated by commas, that are + to be used by the ZKFailoverController in automatic failover. + + + + + ha.zookeeper.session-timeout.ms + 5000 + + The session timeout to use when the ZKFC connects to ZooKeeper. + Setting this value to a lower value implies that server crashes + will be detected more quickly, but risks triggering failover too + aggressively in the case of a transient error or network blip. + + + + + ha.zookeeper.parent-znode + /hadoop-ha + + The ZooKeeper znode under which the ZK failover controller stores + its information. Note that the nameservice ID is automatically + appended to this znode, so it is not normally necessary to + configure this, even in a federated environment. + + + + + ha.zookeeper.acl + world:anyone:rwcda + + A comma-separated list of ZooKeeper ACLs to apply to the znodes + used by automatic failover. These ACLs are specified in the same + format as used by the ZooKeeper CLI. + + If the ACL itself contains secrets, you may instead specify a + path to a file, prefixed with the '@' symbol, and the value of + this configuration will be loaded from within. + + + + + ha.zookeeper.auth + + + A comma-separated list of ZooKeeper authentications to add when + connecting to ZooKeeper. These are specified in the same format + as used by the "addauth" command in the ZK CLI. It is + important that the authentications specified here are sufficient + to access znodes with the ACL specified in ha.zookeeper.acl. + + If the auths contain secrets, you may instead specify a + path to a file, prefixed with the '@' symbol, and the value of + this configuration will be loaded from within. + + + + + + + hadoop.ssl.keystores.factory.class + org.apache.hadoop.security.ssl.FileBasedKeyStoresFactory + + The keystores factory to use for retrieving certificates. + + + + + hadoop.ssl.require.client.cert + false + Whether client certificates are required + + + + hadoop.ssl.hostname.verifier + DEFAULT + + The hostname verifier to provide for HttpsURLConnections. + Valid values are: DEFAULT, STRICT, STRICT_I6, DEFAULT_AND_LOCALHOST and + ALLOW_ALL + + + + + hadoop.ssl.server.conf + ssl-server.xml + + Resource file from which ssl server keystore information will be extracted. + This file is looked up in the classpath, typically it should be in Hadoop + conf/ directory. + + + + + hadoop.ssl.client.conf + ssl-client.xml + + Resource file from which ssl client keystore information will be extracted + This file is looked up in the classpath, typically it should be in Hadoop + conf/ directory. + + + + + hadoop.ssl.enabled + false + + Deprecated. Use dfs.http.policy and yarn.http.policy instead. + + + + + hadoop.ssl.enabled.protocols + TLSv1 + + Protocols supported by the ssl. + + + + + hadoop.jetty.logs.serve.aliases + true + + Enable/Disable aliases serving from jetty + + + + + fs.permissions.umask-mode + 022 + + The umask used when creating files and directories. + Can be in octal or in symbolic. Examples are: + "022" (octal for u=rwx,g=r-x,o=r-x in symbolic), + or "u=rwx,g=rwx,o=" (symbolic for 007 in octal). + + + + + + + ha.health-monitor.connect-retry-interval.ms + 1000 + + How often to retry connecting to the service. + + + + + ha.health-monitor.check-interval.ms + 1000 + + How often to check the service. + + + + + ha.health-monitor.sleep-after-disconnect.ms + 1000 + + How long to sleep after an unexpected RPC error. + + + + + ha.health-monitor.rpc-timeout.ms + 45000 + + Timeout for the actual monitorHealth() calls. + + + + + ha.failover-controller.new-active.rpc-timeout.ms + 60000 + + Timeout that the FC waits for the new active to become active + + + + + ha.failover-controller.graceful-fence.rpc-timeout.ms + 5000 + + Timeout that the FC waits for the old active to go to standby + + + + + ha.failover-controller.graceful-fence.connection.retries + 1 + + FC connection retries for graceful fencing + + + + + ha.failover-controller.cli-check.rpc-timeout.ms + 20000 + + Timeout that the CLI (manual) FC waits for monitorHealth, getServiceState + + + + + ipc.client.fallback-to-simple-auth-allowed + false + + When a client is configured to attempt a secure connection, but attempts to + connect to an insecure server, that server may instruct the client to + switch to SASL SIMPLE (unsecure) authentication. This setting controls + whether or not the client will accept this instruction from the server. + When false (the default), the client will not allow the fallback to SIMPLE + authentication, and will abort the connection. + + + + + fs.client.resolve.remote.symlinks + true + + Whether to resolve symlinks when accessing a remote Hadoop filesystem. + Setting this to false causes an exception to be thrown upon encountering + a symlink. This setting does not apply to local filesystems, which + automatically resolve local symlinks. + + + + + nfs.exports.allowed.hosts + * rw + + By default, the export can be mounted by any client. The value string + contains machine name and access privilege, separated by whitespace + characters. The machine name format can be a single host, a Java regular + expression, or an IPv4 address. The access privilege uses rw or ro to + specify read/write or read-only access of the machines to exports. If the + access privilege is not provided, the default is read-only. Entries are separated by ";". + For example: "192.168.0.0/22 rw ; host.*\.example\.com ; host1.test.org ro;". + Only the NFS gateway needs to restart after this property is updated. + + + + + hadoop.user.group.static.mapping.overrides + dr.who=; + + Static mapping of user to groups. This will override the groups if + available in the system for the specified user. In otherwords, groups + look-up will not happen for these users, instead groups mapped in this + configuration will be used. + Mapping should be in this format. + user1=group1,group2;user2=;user3=group2; + Default, "dr.who=;" will consider "dr.who" as user without groups. + + + + + rpc.metrics.quantile.enable + false + + Setting this property to true and rpc.metrics.percentiles.intervals + to a comma-separated list of the granularity in seconds, the + 50/75/90/95/99th percentile latency for rpc queue/processing time in + milliseconds are added to rpc metrics. + + + + + rpc.metrics.percentiles.intervals + + + A comma-separated list of the granularity in seconds for the metrics which + describe the 50/75/90/95/99th percentile latency for rpc queue/processing + time. The metrics are outputted if rpc.metrics.quantile.enable is set to + true. + + + + + hadoop.security.crypto.codec.classes.EXAMPLECIPHERSUITE + + + The prefix for a given crypto codec, contains a comma-separated + list of implementation classes for a given crypto codec (eg EXAMPLECIPHERSUITE). + The first implementation will be used if available, others are fallbacks. + + + + + hadoop.security.crypto.codec.classes.aes.ctr.nopadding + org.apache.hadoop.crypto.OpensslAesCtrCryptoCodec, org.apache.hadoop.crypto.JceAesCtrCryptoCodec + + Comma-separated list of crypto codec implementations for AES/CTR/NoPadding. + The first implementation will be used if available, others are fallbacks. + + + + + hadoop.security.crypto.cipher.suite + AES/CTR/NoPadding + + Cipher suite for crypto codec. + + + + + hadoop.security.crypto.jce.provider + + + The JCE provider name used in CryptoCodec. + + + + + hadoop.security.crypto.buffer.size + 8192 + + The buffer size used by CryptoInputStream and CryptoOutputStream. + + + + + hadoop.security.java.secure.random.algorithm + SHA1PRNG + + The java secure random algorithm. + + + + + hadoop.security.secure.random.impl + + + Implementation of secure random. + + + + + hadoop.security.random.device.file.path + /dev/urandom + + OS security random device file path. + + + + + hadoop.security.key.provider.path + + The KeyProvider to use when managing zone keys, and interacting with + encryption keys when reading and writing to an encryption zone. + For hdfs clients, the provider path will be same as namenode's + provider path. + + + + + fs.har.impl.disable.cache + true + Don't cache 'har' filesystem instances. + + + + + hadoop.security.kms.client.authentication.retry-count + 1 + + Number of time to retry connecting to KMS on authentication failure + + + + hadoop.security.kms.client.encrypted.key.cache.size + 500 + + Size of the EncryptedKeyVersion cache Queue for each key + + + + hadoop.security.kms.client.encrypted.key.cache.low-watermark + 0.3f + + If size of the EncryptedKeyVersion cache Queue falls below the + low watermark, this cache queue will be scheduled for a refill + + + + hadoop.security.kms.client.encrypted.key.cache.num.refill.threads + 2 + + Number of threads to use for refilling depleted EncryptedKeyVersion + cache Queues + + + + hadoop.security.kms.client.encrypted.key.cache.expiry + 43200000 + + Cache expiry time for a Key, after which the cache Queue for this + key will be dropped. Default = 12hrs + + + + + ipc.server.max.connections + 0 + The maximum number of concurrent connections a server is allowed + to accept. If this limit is exceeded, incoming connections will first fill + the listen queue and then may go to an OS-specific listen overflow queue. + The client may fail or timeout, but the server can avoid running out of file + descriptors using this feature. 0 means no limit. + + + + + + + + + Is the registry enabled in the YARN Resource Manager? + + If true, the YARN RM will, as needed. + create the user and system paths, and purge + service records when containers, application attempts + and applications complete. + + If false, the paths must be created by other means, + and no automatic cleanup of service records will take place. + + hadoop.registry.rm.enabled + false + + + + + The root zookeeper node for the registry + + hadoop.registry.zk.root + /registry + + + + + Zookeeper session timeout in milliseconds + + hadoop.registry.zk.session.timeout.ms + 60000 + + + + + Zookeeper connection timeout in milliseconds + + hadoop.registry.zk.connection.timeout.ms + 15000 + + + + + Zookeeper connection retry count before failing + + hadoop.registry.zk.retry.times + 5 + + + + + + hadoop.registry.zk.retry.interval.ms + 1000 + + + + + Zookeeper retry limit in milliseconds, during + exponential backoff. + + This places a limit even + if the retry times and interval limit, combined + with the backoff policy, result in a long retry + period + + hadoop.registry.zk.retry.ceiling.ms + 60000 + + + + + List of hostname:port pairs defining the + zookeeper quorum binding for the registry + + hadoop.registry.zk.quorum + localhost:2181 + + + + + Key to set if the registry is secure. Turning it on + changes the permissions policy from "open access" + to restrictions on kerberos with the option of + a user adding one or more auth key pairs down their + own tree. + + hadoop.registry.secure + false + + + + + A comma separated list of Zookeeper ACL identifiers with + system access to the registry in a secure cluster. + + These are given full access to all entries. + + If there is an "@" at the end of a SASL entry it + instructs the registry client to append the default kerberos domain. + + hadoop.registry.system.acls + sasl:yarn@, sasl:mapred@, sasl:hdfs@ + + + + + The kerberos realm: used to set the realm of + system principals which do not declare their realm, + and any other accounts that need the value. + + If empty, the default realm of the running process + is used. + + If neither are known and the realm is needed, then the registry + service/client will fail. + + hadoop.registry.kerberos.realm + + + + + + Key to define the JAAS context. Used in secure + mode + + hadoop.registry.jaas.context + Client + + + + + Enable hdfs shell commands to display warnings if (fs.defaultFS) property + is not set. + + hadoop.shell.missing.defaultFs.warning + false + + + + hadoop.shell.safely.delete.limit.num.files + 100 + Used by -safely option of hadoop fs shell -rm command to avoid + accidental deletion of large directories. When enabled, the -rm command + requires confirmation if the number of files to be deleted is greater than + this limit. The default limit is 100 files. The warning is disabled if + the limit is 0 or the -safely is not specified in -rm command. + + + + + fs.client.htrace.sampler.classes + + The class names of the HTrace Samplers to use for Hadoop + filesystem clients. + + + + + hadoop.htrace.span.receiver.classes + + The class names of the Span Receivers to use for Hadoop. + + + + + + + fs.adl.impl + org.apache.hadoop.fs.adl.AdlFileSystem + + + + fs.AbstractFileSystem.adl.impl + org.apache.hadoop.fs.adl.Adl + + + + adl.feature.ownerandgroup.enableupn + false + + When true : User and Group in FileStatus/AclStatus response is + represented as user friendly name as per Azure AD profile. + + When false (default) : User and Group in FileStatus/AclStatus + response is represented by the unique identifier from Azure AD + profile (Object ID as GUID). + + For optimal performance, false is recommended. + + + + + fs.adl.oauth2.access.token.provider.type + ClientCredential + + Defines Azure Active Directory OAuth2 access token provider type. + Supported types are ClientCredential, RefreshToken, and Custom. + The ClientCredential type requires property fs.adl.oauth2.client.id, + fs.adl.oauth2.credential, and fs.adl.oauth2.refresh.url. + The RefreshToken type requires property fs.adl.oauth2.client.id and + fs.adl.oauth2.refresh.token. + The Custom type requires property fs.adl.oauth2.access.token.provider. + + + + + fs.adl.oauth2.client.id + + The OAuth2 client id. + + + + fs.adl.oauth2.credential + + The OAuth2 access key. + + + + fs.adl.oauth2.refresh.url + + The OAuth2 token endpoint. + + + + fs.adl.oauth2.refresh.token + + The OAuth2 refresh token. + + + + fs.adl.oauth2.access.token.provider + + + The class name of the OAuth2 access token provider. + + + + + + + hadoop.caller.context.enabled + false + When the feature is enabled, additional fields are written into + name-node audit log records for auditing coarse granularity operations. + + + + hadoop.caller.context.max.size + 128 + The maximum bytes a caller context string can have. If the + passed caller context is longer than this maximum bytes, client will + truncate it before sending to server. Note that the server may have a + different maximum size, and will truncate the caller context to the + maximum size it allows. + + + + hadoop.caller.context.signature.max.size + 40 + + The caller's signature (optional) is for offline validation. If the + signature exceeds the maximum allowed bytes in server, the caller context + will be abandoned, in which case the caller context will not be recorded + in audit logs. + + + + diff --git a/sahara/plugins/vanilla/v2_8_2/resources/create_hive_db.sql b/sahara/plugins/vanilla/v2_8_2/resources/create_hive_db.sql new file mode 100644 index 0000000..e9fce08 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/create_hive_db.sql @@ -0,0 +1,9 @@ +CREATE DATABASE metastore; +USE metastore; +SOURCE /opt/hive/scripts/metastore/upgrade/mysql/hive-schema-2.3.0.mysql.sql; +CREATE USER 'hive'@'localhost' IDENTIFIED BY '{{password}}'; +REVOKE ALL PRIVILEGES, GRANT OPTION FROM 'hive'@'localhost'; +GRANT ALL PRIVILEGES ON metastore.* TO 'hive'@'localhost' IDENTIFIED BY '{{password}}'; +GRANT ALL PRIVILEGES ON metastore.* TO 'hive'@'%' IDENTIFIED BY '{{password}}'; +FLUSH PRIVILEGES; +exit diff --git a/sahara/plugins/vanilla/v2_8_2/resources/hdfs-default.xml b/sahara/plugins/vanilla/v2_8_2/resources/hdfs-default.xml new file mode 100644 index 0000000..97d8717 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/hdfs-default.xml @@ -0,0 +1,3138 @@ + + + + + + + + + + + + + hadoop.hdfs.configuration.version + 1 + version of this configuration file + + + + dfs.namenode.rpc-address + + + RPC address that handles all clients requests. In the case of HA/Federation where multiple namenodes exist, + the name service id is added to the name e.g. dfs.namenode.rpc-address.ns1 + dfs.namenode.rpc-address.EXAMPLENAMESERVICE + The value of this property will take the form of nn-host1:rpc-port. + + + + + dfs.namenode.rpc-bind-host + + + The actual address the RPC server will bind to. If this optional address is + set, it overrides only the hostname portion of dfs.namenode.rpc-address. + It can also be specified per name node or name service for HA/Federation. + This is useful for making the name node listen on all interfaces by + setting it to 0.0.0.0. + + + + + dfs.namenode.servicerpc-address + + + RPC address for HDFS Services communication. BackupNode, Datanodes and all other services should be + connecting to this address if it is configured. In the case of HA/Federation where multiple namenodes exist, + the name service id is added to the name e.g. dfs.namenode.servicerpc-address.ns1 + dfs.namenode.rpc-address.EXAMPLENAMESERVICE + The value of this property will take the form of nn-host1:rpc-port. + If the value of this property is unset the value of dfs.namenode.rpc-address will be used as the default. + + + + + dfs.namenode.servicerpc-bind-host + + + The actual address the service RPC server will bind to. If this optional address is + set, it overrides only the hostname portion of dfs.namenode.servicerpc-address. + It can also be specified per name node or name service for HA/Federation. + This is useful for making the name node listen on all interfaces by + setting it to 0.0.0.0. + + + + + dfs.namenode.lifeline.rpc-address + + + NameNode RPC lifeline address. This is an optional separate RPC address + that can be used to isolate health checks and liveness to protect against + resource exhaustion in the main RPC handler pool. In the case of + HA/Federation where multiple NameNodes exist, the name service ID is added + to the name e.g. dfs.namenode.lifeline.rpc-address.ns1. The value of this + property will take the form of nn-host1:rpc-port. If this property is not + defined, then the NameNode will not start a lifeline RPC server. By + default, the property is not defined. + + + + + dfs.namenode.lifeline.rpc-bind-host + + + The actual address the lifeline RPC server will bind to. If this optional + address is set, it overrides only the hostname portion of + dfs.namenode.lifeline.rpc-address. It can also be specified per name node + or name service for HA/Federation. This is useful for making the name node + listen on all interfaces by setting it to 0.0.0.0. + + + + + dfs.namenode.secondary.http-address + 0.0.0.0:50090 + + The secondary namenode http server address and port. + + + + + dfs.namenode.secondary.https-address + 0.0.0.0:50091 + + The secondary namenode HTTPS server address and port. + + + + + dfs.datanode.address + 0.0.0.0:50010 + + The datanode server address and port for data transfer. + + + + + dfs.datanode.http.address + 0.0.0.0:50075 + + The datanode http server address and port. + + + + + dfs.datanode.ipc.address + 0.0.0.0:50020 + + The datanode ipc server address and port. + + + + + dfs.datanode.handler.count + 10 + The number of server threads for the datanode. + + + + dfs.namenode.http-address + 0.0.0.0:50070 + + The address and the base port where the dfs namenode web ui will listen on. + + + + + dfs.namenode.http-bind-host + + + The actual adress the HTTP server will bind to. If this optional address + is set, it overrides only the hostname portion of dfs.namenode.http-address. + It can also be specified per name node or name service for HA/Federation. + This is useful for making the name node HTTP server listen on all + interfaces by setting it to 0.0.0.0. + + + + + dfs.namenode.heartbeat.recheck-interval + 300000 + + This time decides the interval to check for expired datanodes. + With this value and dfs.heartbeat.interval, the interval of + deciding the datanode is stale or not is also calculated. + The unit of this configuration is millisecond. + + + + + dfs.http.policy + HTTP_ONLY + Decide if HTTPS(SSL) is supported on HDFS + This configures the HTTP endpoint for HDFS daemons: + The following values are supported: + - HTTP_ONLY : Service is provided only on http + - HTTPS_ONLY : Service is provided only on https + - HTTP_AND_HTTPS : Service is provided both on http and https + + + + + dfs.client.https.need-auth + false + Whether SSL client certificate authentication is required + + + + + dfs.client.cached.conn.retry + 3 + The number of times the HDFS client will pull a socket from the + cache. Once this number is exceeded, the client will try to create a new + socket. + + + + + + dfs.https.server.keystore.resource + ssl-server.xml + Resource file from which ssl server keystore + information will be extracted + + + + + dfs.client.https.keystore.resource + ssl-client.xml + Resource file from which ssl client keystore + information will be extracted + + + + + dfs.datanode.https.address + 0.0.0.0:50475 + The datanode secure http server address and port. + + + + dfs.namenode.https-address + 0.0.0.0:50470 + The namenode secure http server address and port. + + + + dfs.namenode.https-bind-host + + + The actual adress the HTTPS server will bind to. If this optional address + is set, it overrides only the hostname portion of dfs.namenode.https-address. + It can also be specified per name node or name service for HA/Federation. + This is useful for making the name node HTTPS server listen on all + interfaces by setting it to 0.0.0.0. + + + + + dfs.datanode.dns.interface + default + + The name of the Network Interface from which a data node should + report its IP address. e.g. eth2. This setting may be required for some + multi-homed nodes where the DataNodes are assigned multiple hostnames + and it is desirable for the DataNodes to use a non-default hostname. + + Prefer using hadoop.security.dns.interface over + dfs.datanode.dns.interface. + + + + + dfs.datanode.dns.nameserver + default + + The host name or IP address of the name server (DNS) which a DataNode + should use to determine its own host name. + + Prefer using hadoop.security.dns.nameserver over + dfs.datanode.dns.nameserver. + + + + + dfs.namenode.backup.address + 0.0.0.0:50100 + + The backup node server address and port. + If the port is 0 then the server will start on a free port. + + + + + dfs.namenode.backup.http-address + 0.0.0.0:50105 + + The backup node http server address and port. + If the port is 0 then the server will start on a free port. + + + + + dfs.namenode.replication.considerLoad + true + Decide if chooseTarget considers the target's load or not + + + + + dfs.namenode.replication.considerLoad.factor + 2.0 + The factor by which a node's load can exceed the average + before being rejected for writes, only if considerLoad is true. + + + + + dfs.default.chunk.view.size + 32768 + The number of bytes to view for a file on the browser. + + + + + dfs.datanode.du.reserved + 0 + Reserved space in bytes per volume. Always leave this much space free for non dfs use. + Specific storage type based reservation is also supported. The property can be followed with + corresponding storage types ([ssd]/[disk]/[archive]/[ram_disk]) for cluster with heterogeneous storage. + For example, reserved space for RAM_DISK storage can be configured using property + 'dfs.datanode.du.reserved.ram_disk'. If specific storage type reservation is not configured + then dfs.datanode.du.reserved will be used. + + + + + dfs.namenode.name.dir + file://${hadoop.tmp.dir}/dfs/name + Determines where on the local filesystem the DFS name node + should store the name table(fsimage). If this is a comma-delimited list + of directories then the name table is replicated in all of the + directories, for redundancy. + + + + dfs.namenode.name.dir.restore + false + Set to true to enable NameNode to attempt recovering a + previously failed dfs.namenode.name.dir. When enabled, a recovery of any + failed directory is attempted during checkpoint. + + + + dfs.namenode.fs-limits.max-component-length + 255 + Defines the maximum number of bytes in UTF-8 encoding in each + component of a path. A value of 0 will disable the check. + + + + dfs.namenode.fs-limits.max-directory-items + 1048576 + Defines the maximum number of items that a directory may + contain. Cannot set the property to a value less than 1 or more than + 6400000. + + + + dfs.namenode.fs-limits.min-block-size + 1048576 + Minimum block size in bytes, enforced by the Namenode at create + time. This prevents the accidental creation of files with tiny block + sizes (and thus many blocks), which can degrade + performance. + + + + dfs.namenode.fs-limits.max-blocks-per-file + 1048576 + Maximum number of blocks per file, enforced by the Namenode on + write. This prevents the creation of extremely large files which can + degrade performance. + + + + dfs.namenode.edits.dir + ${dfs.namenode.name.dir} + Determines where on the local filesystem the DFS name node + should store the transaction (edits) file. If this is a comma-delimited list + of directories then the transaction file is replicated in all of the + directories, for redundancy. Default value is same as dfs.namenode.name.dir + + + + + dfs.namenode.edits.dir.required + + This should be a subset of dfs.namenode.edits.dir, + to ensure that the transaction (edits) file + in these places is always up-to-date. + + + + + dfs.namenode.shared.edits.dir + + A directory on shared storage between the multiple namenodes + in an HA cluster. This directory will be written by the active and read + by the standby in order to keep the namespaces synchronized. This directory + does not need to be listed in dfs.namenode.edits.dir above. It should be + left empty in a non-HA cluster. + + + + + dfs.namenode.edits.journal-plugin.qjournal + org.apache.hadoop.hdfs.qjournal.client.QuorumJournalManager + + + + dfs.permissions.enabled + true + + If "true", enable permission checking in HDFS. + If "false", permission checking is turned off, + but all other behavior is unchanged. + Switching from one parameter value to the other does not change the mode, + owner or group of files or directories. + + + + + dfs.permissions.superusergroup + supergroup + The name of the group of super-users. + The value should be a single group name. + + + + + dfs.cluster.administrators + + ACL for the admins, this configuration is used to control + who can access the default servlets in the namenode, etc. The value + should be a comma separated list of users and groups. The user list + comes first and is separated by a space followed by the group list, + e.g. "user1,user2 group1,group2". Both users and groups are optional, + so "user1", " group1", "", "user1 group1", "user1,user2 group1,group2" + are all valid (note the leading space in " group1"). '*' grants access + to all users and groups, e.g. '*', '* ' and ' *' are all valid. + + + + + dfs.namenode.acls.enabled + false + + Set to true to enable support for HDFS ACLs (Access Control Lists). By + default, ACLs are disabled. When ACLs are disabled, the NameNode rejects + all RPCs related to setting or getting ACLs. + + + + + dfs.namenode.lazypersist.file.scrub.interval.sec + 300 + + The NameNode periodically scans the namespace for LazyPersist files with + missing blocks and unlinks them from the namespace. This configuration key + controls the interval between successive scans. Set it to a negative value + to disable this behavior. + + + + dfs.block.access.token.enable + false + + If "true", access tokens are used as capabilities for accessing datanodes. + If "false", no access tokens are checked on accessing datanodes. + + + + + dfs.block.access.key.update.interval + 600 + + Interval in minutes at which namenode updates its access keys. + + + + + dfs.block.access.token.lifetime + 600 + The lifetime of access tokens in minutes. + + + + dfs.datanode.data.dir + file://${hadoop.tmp.dir}/dfs/data + Determines where on the local filesystem an DFS data node + should store its blocks. If this is a comma-delimited + list of directories, then data will be stored in all named + directories, typically on different devices. The directories should be tagged + with corresponding storage types ([SSD]/[DISK]/[ARCHIVE]/[RAM_DISK]) for HDFS + storage policies. The default storage type will be DISK if the directory does + not have a storage type tagged explicitly. Directories that do not exist will + be created if local filesystem permission allows. + + + + + dfs.datanode.data.dir.perm + 700 + Permissions for the directories on on the local filesystem where + the DFS data node store its blocks. The permissions can either be octal or + symbolic. + + + + dfs.replication + 3 + Default block replication. + The actual number of replications can be specified when the file is created. + The default is used if replication is not specified in create time. + + + + + dfs.replication.max + 512 + Maximal block replication. + + + + + dfs.namenode.replication.min + 1 + Minimal block replication. + + + + + dfs.namenode.safemode.replication.min + + + a separate minimum replication factor for calculating safe block count. + This is an expert level setting. + Setting this lower than the dfs.namenode.replication.min + is not recommend and/or dangerous for production setups. + When it's not set it takes value from dfs.namenode.replication.min + + + + + dfs.blocksize + 134217728 + + The default block size for new files, in bytes. + You can use the following suffix (case insensitive): + k(kilo), m(mega), g(giga), t(tera), p(peta), e(exa) to specify the size (such as 128k, 512m, 1g, etc.), + Or provide complete size in bytes (such as 134217728 for 128 MB). + + + + + dfs.client.block.write.retries + 3 + The number of retries for writing blocks to the data nodes, + before we signal failure to the application. + + + + + dfs.client.block.write.replace-datanode-on-failure.enable + true + + If there is a datanode/network failure in the write pipeline, + DFSClient will try to remove the failed datanode from the pipeline + and then continue writing with the remaining datanodes. As a result, + the number of datanodes in the pipeline is decreased. The feature is + to add new datanodes to the pipeline. + + This is a site-wide property to enable/disable the feature. + + When the cluster size is extremely small, e.g. 3 nodes or less, cluster + administrators may want to set the policy to NEVER in the default + configuration file or disable this feature. Otherwise, users may + experience an unusually high rate of pipeline failures since it is + impossible to find new datanodes for replacement. + + See also dfs.client.block.write.replace-datanode-on-failure.policy + + + + + dfs.client.block.write.replace-datanode-on-failure.policy + DEFAULT + + This property is used only if the value of + dfs.client.block.write.replace-datanode-on-failure.enable is true. + + ALWAYS: always add a new datanode when an existing datanode is removed. + + NEVER: never add a new datanode. + + DEFAULT: + Let r be the replication number. + Let n be the number of existing datanodes. + Add a new datanode only if r is greater than or equal to 3 and either + (1) floor(r/2) is greater than or equal to n; or + (2) r is greater than n and the block is hflushed/appended. + + + + + dfs.client.block.write.replace-datanode-on-failure.best-effort + false + + This property is used only if the value of + dfs.client.block.write.replace-datanode-on-failure.enable is true. + + Best effort means that the client will try to replace a failed datanode + in write pipeline (provided that the policy is satisfied), however, it + continues the write operation in case that the datanode replacement also + fails. + + Suppose the datanode replacement fails. + false: An exception should be thrown so that the write will fail. + true : The write should be resumed with the remaining datandoes. + + Note that setting this property to true allows writing to a pipeline + with a smaller number of datanodes. As a result, it increases the + probability of data loss. + + + + + dfs.blockreport.intervalMsec + 21600000 + Determines block reporting interval in milliseconds. + + + + dfs.blockreport.initialDelay 0 + Delay for first block report in seconds. + + + + dfs.blockreport.split.threshold + 1000000 + If the number of blocks on the DataNode is below this + threshold then it will send block reports for all Storage Directories + in a single message. + + If the number of blocks exceeds this threshold then the DataNode will + send block reports for each Storage Directory in separate messages. + + Set to zero to always split. + + + + + dfs.namenode.max.full.block.report.leases + 6 + The maximum number of leases for full block reports that the + NameNode will issue at any given time. This prevents the NameNode from + being flooded with full block reports that use up all the RPC handler + threads. This number should never be more than the number of RPC handler + threads or less than 1. + + + + + dfs.namenode.full.block.report.lease.length.ms + 300000 + + The number of milliseconds that the NameNode will wait before invalidating + a full block report lease. This prevents a crashed DataNode from + permanently using up a full block report lease. + + + + + dfs.datanode.directoryscan.interval + 21600 + Interval in seconds for Datanode to scan data directories and + reconcile the difference between blocks in memory and on the disk. + + + + + dfs.datanode.directoryscan.threads + 1 + How many threads should the threadpool used to compile reports + for volumes in parallel have. + + + + + dfs.datanode.directoryscan.throttle.limit.ms.per.sec + 1000 + The report compilation threads are limited to only running for + a given number of milliseconds per second, as configured by the + property. The limit is taken per thread, not in aggregate, e.g. setting + a limit of 100ms for 4 compiler threads will result in each thread being + limited to 100ms, not 25ms. + + Note that the throttle does not interrupt the report compiler threads, so the + actual running time of the threads per second will typically be somewhat + higher than the throttle limit, usually by no more than 20%. + + Setting this limit to 1000 disables compiler thread throttling. Only + values between 1 and 1000 are valid. Setting an invalid value will result + in the throttle being disbled and an error message being logged. 1000 is + the default setting. + + + + + dfs.heartbeat.interval + 3 + Determines datanode heartbeat interval in seconds. + + + + dfs.datanode.lifeline.interval.seconds + + + Sets the interval in seconds between sending DataNode Lifeline Protocol + messages from the DataNode to the NameNode. The value must be greater than + the value of dfs.heartbeat.interval. If this property is not defined, then + the default behavior is to calculate the interval as 3x the value of + dfs.heartbeat.interval. Note that normal heartbeat processing may cause the + DataNode to postpone sending lifeline messages if they are not required. + Under normal operations with speedy heartbeat processing, it is possible + that no lifeline messages will need to be sent at all. This property has no + effect if dfs.namenode.lifeline.rpc-address is not defined. + + + + + dfs.namenode.handler.count + 10 + The number of Namenode RPC server threads that listen to + requests from clients. + If dfs.namenode.servicerpc-address is not configured then + Namenode RPC server threads listen to requests from all nodes. + + + + + dfs.namenode.service.handler.count + 10 + The number of Namenode RPC server threads that listen to + requests from DataNodes and from all other non-client nodes. + dfs.namenode.service.handler.count will be valid only if + dfs.namenode.servicerpc-address is configured. + + + + + dfs.namenode.lifeline.handler.ratio + 0.10 + + A ratio applied to the value of dfs.namenode.handler.count, which then + provides the number of RPC server threads the NameNode runs for handling the + lifeline RPC server. For example, if dfs.namenode.handler.count is 100, and + dfs.namenode.lifeline.handler.factor is 0.10, then the NameNode starts + 100 * 0.10 = 10 threads for handling the lifeline RPC server. It is common + to tune the value of dfs.namenode.handler.count as a function of the number + of DataNodes in a cluster. Using this property allows for the lifeline RPC + server handler threads to be tuned automatically without needing to touch a + separate property. Lifeline message processing is lightweight, so it is + expected to require many fewer threads than the main NameNode RPC server. + This property is not used if dfs.namenode.lifeline.handler.count is defined, + which sets an absolute thread count. This property has no effect if + dfs.namenode.lifeline.rpc-address is not defined. + + + + + dfs.namenode.lifeline.handler.count + + + Sets an absolute number of RPC server threads the NameNode runs for handling + the DataNode Lifeline Protocol and HA health check requests from ZKFC. If + this property is defined, then it overrides the behavior of + dfs.namenode.lifeline.handler.ratio. By default, it is not defined. This + property has no effect if dfs.namenode.lifeline.rpc-address is not defined. + + + + + dfs.namenode.safemode.threshold-pct + 0.999f + + Specifies the percentage of blocks that should satisfy + the minimal replication requirement defined by dfs.namenode.replication.min. + Values less than or equal to 0 mean not to wait for any particular + percentage of blocks before exiting safemode. + Values greater than 1 will make safe mode permanent. + + + + + dfs.namenode.safemode.min.datanodes + 0 + + Specifies the number of datanodes that must be considered alive + before the name node exits safemode. + Values less than or equal to 0 mean not to take the number of live + datanodes into account when deciding whether to remain in safe mode + during startup. + Values greater than the number of datanodes in the cluster + will make safe mode permanent. + + + + + dfs.namenode.safemode.extension + 30000 + + Determines extension of safe mode in milliseconds + after the threshold level is reached. + + + + + dfs.namenode.resource.check.interval + 5000 + + The interval in milliseconds at which the NameNode resource checker runs. + The checker calculates the number of the NameNode storage volumes whose + available spaces are more than dfs.namenode.resource.du.reserved, and + enters safemode if the number becomes lower than the minimum value + specified by dfs.namenode.resource.checked.volumes.minimum. + + + + + dfs.namenode.resource.du.reserved + 104857600 + + The amount of space to reserve/require for a NameNode storage directory + in bytes. The default is 100MB. + + + + + dfs.namenode.resource.checked.volumes + + + A list of local directories for the NameNode resource checker to check in + addition to the local edits directories. + + + + + dfs.namenode.resource.checked.volumes.minimum + 1 + + The minimum number of redundant NameNode storage volumes required. + + + + + dfs.datanode.balance.bandwidthPerSec + 10m + + Specifies the maximum amount of bandwidth that each datanode + can utilize for the balancing purpose in term of + the number of bytes per second. You can use the following + suffix (case insensitive): + k(kilo), m(mega), g(giga), t(tera), p(peta), e(exa)to specify the size + (such as 128k, 512m, 1g, etc.). + Or provide complete size in bytes (such as 134217728 for 128 MB). + + + + + dfs.mover.max-no-move-interval + 60000 + + If this specified amount of time has elapsed and no block has been moved + out of a source DataNode, on more effort will be made to move blocks out of + this DataNode in the current Mover iteration. + + + + + dfs.hosts + + Names a file that contains a list of hosts that are + permitted to connect to the namenode. The full pathname of the file + must be specified. If the value is empty, all hosts are + permitted. + + + + dfs.hosts.exclude + + Names a file that contains a list of hosts that are + not permitted to connect to the namenode. The full pathname of the + file must be specified. If the value is empty, no hosts are + excluded. + + + + dfs.namenode.max.objects + 0 + The maximum number of files, directories and blocks + dfs supports. A value of zero indicates no limit to the number + of objects that dfs supports. + + + + + dfs.namenode.datanode.registration.ip-hostname-check + true + + If true (the default), then the namenode requires that a connecting + datanode's address must be resolved to a hostname. If necessary, a reverse + DNS lookup is performed. All attempts to register a datanode from an + unresolvable address are rejected. + + It is recommended that this setting be left on to prevent accidental + registration of datanodes listed by hostname in the excludes file during a + DNS outage. Only set this to false in environments where there is no + infrastructure to support reverse DNS lookup. + + + + + dfs.namenode.decommission.interval + 30 + Namenode periodicity in seconds to check if decommission is + complete. + + + + dfs.namenode.decommission.blocks.per.interval + 500000 + The approximate number of blocks to process per + decommission interval, as defined in dfs.namenode.decommission.interval. + + + + + dfs.namenode.decommission.max.concurrent.tracked.nodes + 100 + + The maximum number of decommission-in-progress datanodes nodes that will be + tracked at one time by the namenode. Tracking a decommission-in-progress + datanode consumes additional NN memory proportional to the number of blocks + on the datnode. Having a conservative limit reduces the potential impact + of decomissioning a large number of nodes at once. + + A value of 0 means no limit will be enforced. + + + + + dfs.namenode.replication.interval + 3 + The periodicity in seconds with which the namenode computes + replication work for datanodes. + + + + dfs.namenode.accesstime.precision + 3600000 + The access time for HDFS file is precise upto this value. + The default value is 1 hour. Setting a value of 0 disables + access times for HDFS. + + + + + dfs.datanode.plugins + + Comma-separated list of datanode plug-ins to be activated. + + + + + dfs.namenode.plugins + + Comma-separated list of namenode plug-ins to be activated. + + + + + dfs.namenode.block-placement-policy.default.prefer-local-node + true + Controls how the default block placement policy places + the first replica of a block. When true, it will prefer the node where + the client is running. When false, it will prefer a node in the same rack + as the client. Setting to false avoids situations where entire copies of + large files end up on a single node, thus creating hotspots. + + + + + + dfs.stream-buffer-size + 4096 + The size of buffer to stream files. + The size of this buffer should probably be a multiple of hardware + page size (4096 on Intel x86), and it determines how much data is + buffered during read and write operations. + + + + dfs.bytes-per-checksum + 512 + The number of bytes per checksum. Must not be larger than + dfs.stream-buffer-size + + + + dfs.client-write-packet-size + 65536 + Packet size for clients to write + + + + dfs.client.write.exclude.nodes.cache.expiry.interval.millis + 600000 + The maximum period to keep a DN in the excluded nodes list + at a client. After this period, in milliseconds, the previously excluded node(s) will + be removed automatically from the cache and will be considered good for block allocations + again. Useful to lower or raise in situations where you keep a file open for very long + periods (such as a Write-Ahead-Log (WAL) file) to make the writer tolerant to cluster maintenance + restarts. Defaults to 10 minutes. + + + + dfs.namenode.checkpoint.dir + file://${hadoop.tmp.dir}/dfs/namesecondary + Determines where on the local filesystem the DFS secondary + name node should store the temporary images to merge. + If this is a comma-delimited list of directories then the image is + replicated in all of the directories for redundancy. + + + + + dfs.namenode.checkpoint.edits.dir + ${dfs.namenode.checkpoint.dir} + Determines where on the local filesystem the DFS secondary + name node should store the temporary edits to merge. + If this is a comma-delimited list of directories then the edits is + replicated in all of the directories for redundancy. + Default value is same as dfs.namenode.checkpoint.dir + + + + + dfs.namenode.checkpoint.period + 3600 + The number of seconds between two periodic checkpoints. + + + + + dfs.namenode.checkpoint.txns + 1000000 + The Secondary NameNode or CheckpointNode will create a checkpoint + of the namespace every 'dfs.namenode.checkpoint.txns' transactions, regardless + of whether 'dfs.namenode.checkpoint.period' has expired. + + + + + dfs.namenode.checkpoint.check.period + 60 + The SecondaryNameNode and CheckpointNode will poll the NameNode + every 'dfs.namenode.checkpoint.check.period' seconds to query the number + of uncheckpointed transactions. + + + + + dfs.namenode.checkpoint.max-retries + 3 + The SecondaryNameNode retries failed checkpointing. If the + failure occurs while loading fsimage or replaying edits, the number of + retries is limited by this variable. + + + + + dfs.namenode.num.checkpoints.retained + 2 + The number of image checkpoint files (fsimage_*) that will be retained by + the NameNode and Secondary NameNode in their storage directories. All edit + logs (stored on edits_* files) necessary to recover an up-to-date namespace from the oldest retained + checkpoint will also be retained. + + + + + dfs.namenode.num.extra.edits.retained + 1000000 + The number of extra transactions which should be retained + beyond what is minimally necessary for a NN restart. + It does not translate directly to file's age, or the number of files kept, + but to the number of transactions (here "edits" means transactions). + One edit file may contain several transactions (edits). + During checkpoint, NameNode will identify the total number of edits to retain as extra by + checking the latest checkpoint transaction value, subtracted by the value of this property. + Then, it scans edits files to identify the older ones that don't include the computed range of + retained transactions that are to be kept around, and purges them subsequently. + The retainment can be useful for audit purposes or for an HA setup where a remote Standby Node may have + been offline for some time and need to have a longer backlog of retained + edits in order to start again. + Typically each edit is on the order of a few hundred bytes, so the default + of 1 million edits should be on the order of hundreds of MBs or low GBs. + + NOTE: Fewer extra edits may be retained than value specified for this setting + if doing so would mean that more segments would be retained than the number + configured by dfs.namenode.max.extra.edits.segments.retained. + + + + + dfs.namenode.max.extra.edits.segments.retained + 10000 + The maximum number of extra edit log segments which should be retained + beyond what is minimally necessary for a NN restart. When used in conjunction with + dfs.namenode.num.extra.edits.retained, this configuration property serves to cap + the number of extra edits files to a reasonable value. + + + + + dfs.namenode.delegation.key.update-interval + 86400000 + The update interval for master key for delegation tokens + in the namenode in milliseconds. + + + + + dfs.namenode.delegation.token.max-lifetime + 604800000 + The maximum lifetime in milliseconds for which a delegation + token is valid. + + + + + dfs.namenode.delegation.token.renew-interval + 86400000 + The renewal interval for delegation token in milliseconds. + + + + + dfs.datanode.failed.volumes.tolerated + 0 + The number of volumes that are allowed to + fail before a datanode stops offering service. By default + any volume failure will cause a datanode to shutdown. + + + + + dfs.image.compress + false + Should the dfs image be compressed? + + + + + dfs.image.compression.codec + org.apache.hadoop.io.compress.DefaultCodec + If the dfs image is compressed, how should they be compressed? + This has to be a codec defined in io.compression.codecs. + + + + + dfs.image.transfer.timeout + 60000 + + Socket timeout for image transfer in milliseconds. This timeout and the related + dfs.image.transfer.bandwidthPerSec parameter should be configured such + that normal image transfer can complete successfully. + This timeout prevents client hangs when the sender fails during + image transfer. This is socket timeout during image transfer. + + + + + dfs.image.transfer.bandwidthPerSec + 0 + + Maximum bandwidth used for regular image transfers (instead of + bootstrapping the standby namenode), in bytes per second. + This can help keep normal namenode operations responsive during + checkpointing. The maximum bandwidth and timeout in + dfs.image.transfer.timeout should be set such that normal image + transfers can complete successfully. + A default value of 0 indicates that throttling is disabled. + The maximum bandwidth used for bootstrapping standby namenode is + configured with dfs.image.transfer-bootstrap-standby.bandwidthPerSec. + + + + + dfs.image.transfer-bootstrap-standby.bandwidthPerSec + 0 + + Maximum bandwidth used for transferring image to bootstrap standby + namenode, in bytes per second. + A default value of 0 indicates that throttling is disabled. This default + value should be used in most cases, to ensure timely HA operations. + The maximum bandwidth used for regular image transfers is configured + with dfs.image.transfer.bandwidthPerSec. + + + + + dfs.image.transfer.chunksize + 65536 + + Chunksize in bytes to upload the checkpoint. + Chunked streaming is used to avoid internal buffering of contents + of image file of huge size. + + + + + dfs.namenode.support.allow.format + true + Does HDFS namenode allow itself to be formatted? + You may consider setting this to false for any production + cluster, to avoid any possibility of formatting a running DFS. + + + + + dfs.datanode.max.transfer.threads + 4096 + + Specifies the maximum number of threads to use for transferring data + in and out of the DN. + + + + + dfs.datanode.scan.period.hours + 504 + + If this is positive, the DataNode will not scan any + individual block more than once in the specified scan period. + If this is negative, the block scanner is disabled. + If this is set to zero, then the default value of 504 hours + or 3 weeks is used. Prior versions of HDFS incorrectly documented + that setting this key to zero will disable the block scanner. + + + + + dfs.block.scanner.volume.bytes.per.second + 1048576 + + If this is 0, the DataNode's block scanner will be disabled. If this + is positive, this is the number of bytes per second that the DataNode's + block scanner will try to scan from each volume. + + + + + dfs.datanode.readahead.bytes + 4194304 + + While reading block files, if the Hadoop native libraries are available, + the datanode can use the posix_fadvise system call to explicitly + page data into the operating system buffer cache ahead of the current + reader's position. This can improve performance especially when + disks are highly contended. + + This configuration specifies the number of bytes ahead of the current + read position which the datanode will attempt to read ahead. This + feature may be disabled by configuring this property to 0. + + If the native libraries are not available, this configuration has no + effect. + + + + + dfs.datanode.drop.cache.behind.reads + false + + In some workloads, the data read from HDFS is known to be significantly + large enough that it is unlikely to be useful to cache it in the + operating system buffer cache. In this case, the DataNode may be + configured to automatically purge all data from the buffer cache + after it is delivered to the client. This behavior is automatically + disabled for workloads which read only short sections of a block + (e.g HBase random-IO workloads). + + This may improve performance for some workloads by freeing buffer + cache space usage for more cacheable data. + + If the Hadoop native libraries are not available, this configuration + has no effect. + + + + + dfs.datanode.drop.cache.behind.writes + false + + In some workloads, the data written to HDFS is known to be significantly + large enough that it is unlikely to be useful to cache it in the + operating system buffer cache. In this case, the DataNode may be + configured to automatically purge all data from the buffer cache + after it is written to disk. + + This may improve performance for some workloads by freeing buffer + cache space usage for more cacheable data. + + If the Hadoop native libraries are not available, this configuration + has no effect. + + + + + dfs.datanode.sync.behind.writes + false + + If this configuration is enabled, the datanode will instruct the + operating system to enqueue all written data to the disk immediately + after it is written. This differs from the usual OS policy which + may wait for up to 30 seconds before triggering writeback. + + This may improve performance for some workloads by smoothing the + IO profile for data written to disk. + + If the Hadoop native libraries are not available, this configuration + has no effect. + + + + + dfs.client.failover.max.attempts + 15 + + Expert only. The number of client failover attempts that should be + made before the failover is considered failed. + + + + + dfs.client.failover.sleep.base.millis + 500 + + Expert only. The time to wait, in milliseconds, between failover + attempts increases exponentially as a function of the number of + attempts made so far, with a random factor of +/- 50%. This option + specifies the base value used in the failover calculation. The + first failover will retry immediately. The 2nd failover attempt + will delay at least dfs.client.failover.sleep.base.millis + milliseconds. And so on. + + + + + dfs.client.failover.sleep.max.millis + 15000 + + Expert only. The time to wait, in milliseconds, between failover + attempts increases exponentially as a function of the number of + attempts made so far, with a random factor of +/- 50%. This option + specifies the maximum value to wait between failovers. + Specifically, the time between two failover attempts will not + exceed +/- 50% of dfs.client.failover.sleep.max.millis + milliseconds. + + + + + dfs.client.failover.connection.retries + 0 + + Expert only. Indicates the number of retries a failover IPC client + will make to establish a server connection. + + + + + dfs.client.failover.connection.retries.on.timeouts + 0 + + Expert only. The number of retry attempts a failover IPC client + will make on socket timeout when establishing a server connection. + + + + + dfs.client.datanode-restart.timeout + 30 + + Expert only. The time to wait, in seconds, from reception of an + datanode shutdown notification for quick restart, until declaring + the datanode dead and invoking the normal recovery mechanisms. + The notification is sent by a datanode when it is being shutdown + using the shutdownDatanode admin command with the upgrade option. + + + + + dfs.nameservices + + + Comma-separated list of nameservices. + + + + + dfs.nameservice.id + + + The ID of this nameservice. If the nameservice ID is not + configured or more than one nameservice is configured for + dfs.nameservices it is determined automatically by + matching the local node's address with the configured address. + + + + + dfs.internal.nameservices + + + Comma-separated list of nameservices that belong to this cluster. + Datanode will report to all the nameservices in this list. By default + this is set to the value of dfs.nameservices. + + + + + dfs.ha.namenodes.EXAMPLENAMESERVICE + + + The prefix for a given nameservice, contains a comma-separated + list of namenodes for a given nameservice (eg EXAMPLENAMESERVICE). + + + + + dfs.ha.namenode.id + + + The ID of this namenode. If the namenode ID is not configured it + is determined automatically by matching the local node's address + with the configured address. + + + + + dfs.ha.log-roll.period + 120 + + How often, in seconds, the StandbyNode should ask the active to + roll edit logs. Since the StandbyNode only reads from finalized + log segments, the StandbyNode will only be as up-to-date as how + often the logs are rolled. Note that failover triggers a log roll + so the StandbyNode will be up to date before it becomes active. + + + + + dfs.ha.tail-edits.period + 60 + + How often, in seconds, the StandbyNode should check for new + finalized log segments in the shared edits log. + + + + + dfs.ha.automatic-failover.enabled + false + + Whether automatic failover is enabled. See the HDFS High + Availability documentation for details on automatic HA + configuration. + + + + + dfs.client.use.datanode.hostname + false + Whether clients should use datanode hostnames when + connecting to datanodes. + + + + + dfs.datanode.use.datanode.hostname + false + Whether datanodes should use datanode hostnames when + connecting to other datanodes for data transfer. + + + + + dfs.client.local.interfaces + + A comma separated list of network interface names to use + for data transfer between the client and datanodes. When creating + a connection to read from or write to a datanode, the client + chooses one of the specified interfaces at random and binds its + socket to the IP of that interface. Individual names may be + specified as either an interface name (eg "eth0"), a subinterface + name (eg "eth0:0"), or an IP address (which may be specified using + CIDR notation to match a range of IPs). + + + + + dfs.datanode.shared.file.descriptor.paths + /dev/shm,/tmp + + A comma-separated list of paths to use when creating file descriptors that + will be shared between the DataNode and the DFSClient. Typically we use + /dev/shm, so that the file descriptors will not be written to disk. + Systems that don't have /dev/shm will fall back to /tmp by default. + + + + + dfs.short.circuit.shared.memory.watcher.interrupt.check.ms + 60000 + + The length of time in milliseconds that the short-circuit shared memory + watcher will go between checking for java interruptions sent from other + threads. This is provided mainly for unit tests. + + + + + dfs.namenode.kerberos.principal + + + The NameNode service principal. This is typically set to + nn/_HOST@REALM.TLD. Each NameNode will substitute _HOST with its + own fully qualified hostname at startup. The _HOST placeholder + allows using the same configuration setting on both NameNodes + in an HA setup. + + + + + dfs.namenode.keytab.file + + + The keytab file used by each NameNode daemon to login as its + service principal. The principal name is configured with + dfs.namenode.kerberos.principal. + + + + + dfs.datanode.kerberos.principal + + + The DataNode service principal. This is typically set to + dn/_HOST@REALM.TLD. Each DataNode will substitute _HOST with its + own fully qualified hostname at startup. The _HOST placeholder + allows using the same configuration setting on all DataNodes. + + + + + dfs.datanode.keytab.file + + + The keytab file used by each DataNode daemon to login as its + service principal. The principal name is configured with + dfs.datanode.kerberos.principal. + + + + + dfs.journalnode.kerberos.principal + + + The JournalNode service principal. This is typically set to + jn/_HOST@REALM.TLD. Each JournalNode will substitute _HOST with its + own fully qualified hostname at startup. The _HOST placeholder + allows using the same configuration setting on all JournalNodes. + + + + + dfs.journalnode.keytab.file + + + The keytab file used by each JournalNode daemon to login as its + service principal. The principal name is configured with + dfs.journalnode.kerberos.principal. + + + + + dfs.namenode.kerberos.internal.spnego.principal + ${dfs.web.authentication.kerberos.principal} + + The server principal used by the NameNode for web UI SPNEGO + authentication when Kerberos security is enabled. This is + typically set to HTTP/_HOST@REALM.TLD The SPNEGO server principal + begins with the prefix HTTP/ by convention. + + If the value is '*', the web server will attempt to login with + every principal specified in the keytab file + dfs.web.authentication.kerberos.keytab. + + + + + dfs.journalnode.kerberos.internal.spnego.principal + + + The server principal used by the JournalNode HTTP Server for + SPNEGO authentication when Kerberos security is enabled. This is + typically set to HTTP/_HOST@REALM.TLD. The SPNEGO server principal + begins with the prefix HTTP/ by convention. + + If the value is '*', the web server will attempt to login with + every principal specified in the keytab file + dfs.web.authentication.kerberos.keytab. + + For most deployments this can be set to ${dfs.web.authentication.kerberos.principal} + i.e use the value of dfs.web.authentication.kerberos.principal. + + + + + dfs.secondary.namenode.kerberos.internal.spnego.principal + ${dfs.web.authentication.kerberos.principal} + + The server principal used by the Secondary NameNode for web UI SPNEGO + authentication when Kerberos security is enabled. Like all other + Secondary NameNode settings, it is ignored in an HA setup. + + If the value is '*', the web server will attempt to login with + every principal specified in the keytab file + dfs.web.authentication.kerberos.keytab. + + + + + dfs.web.authentication.kerberos.principal + + + The server principal used by the NameNode for WebHDFS SPNEGO + authentication. + + Required when WebHDFS and security are enabled. In most secure clusters this + setting is also used to specify the values for + dfs.namenode.kerberos.internal.spnego.principal and + dfs.journalnode.kerberos.internal.spnego.principal. + + + + + dfs.web.authentication.kerberos.keytab + + + The keytab file for the principal corresponding to + dfs.web.authentication.kerberos.principal. + + + + + dfs.namenode.kerberos.principal.pattern + * + + A client-side RegEx that can be configured to control + allowed realms to authenticate with (useful in cross-realm env.) + + + + + dfs.namenode.avoid.read.stale.datanode + false + + Indicate whether or not to avoid reading from "stale" datanodes whose + heartbeat messages have not been received by the namenode + for more than a specified time interval. Stale datanodes will be + moved to the end of the node list returned for reading. See + dfs.namenode.avoid.write.stale.datanode for a similar setting for writes. + + + + + dfs.namenode.avoid.write.stale.datanode + false + + Indicate whether or not to avoid writing to "stale" datanodes whose + heartbeat messages have not been received by the namenode + for more than a specified time interval. Writes will avoid using + stale datanodes unless more than a configured ratio + (dfs.namenode.write.stale.datanode.ratio) of datanodes are marked as + stale. See dfs.namenode.avoid.read.stale.datanode for a similar setting + for reads. + + + + + dfs.namenode.stale.datanode.interval + 30000 + + Default time interval in milliseconds for marking a datanode as "stale", + i.e., if the namenode has not received heartbeat msg from a datanode for + more than this time interval, the datanode will be marked and treated + as "stale" by default. The stale interval cannot be too small since + otherwise this may cause too frequent change of stale states. + We thus set a minimum stale interval value (the default value is 3 times + of heartbeat interval) and guarantee that the stale interval cannot be less + than the minimum value. A stale data node is avoided during lease/block + recovery. It can be conditionally avoided for reads (see + dfs.namenode.avoid.read.stale.datanode) and for writes (see + dfs.namenode.avoid.write.stale.datanode). + + + + + dfs.namenode.write.stale.datanode.ratio + 0.5f + + When the ratio of number stale datanodes to total datanodes marked + is greater than this ratio, stop avoiding writing to stale nodes so + as to prevent causing hotspots. + + + + + dfs.namenode.invalidate.work.pct.per.iteration + 0.32f + + *Note*: Advanced property. Change with caution. + This determines the percentage amount of block + invalidations (deletes) to do over a single DN heartbeat + deletion command. The final deletion count is determined by applying this + percentage to the number of live nodes in the system. + The resultant number is the number of blocks from the deletion list + chosen for proper invalidation over a single heartbeat of a single DN. + Value should be a positive, non-zero percentage in float notation (X.Yf), + with 1.0f meaning 100%. + + + + + dfs.namenode.replication.work.multiplier.per.iteration + 2 + + *Note*: Advanced property. Change with caution. + This determines the total amount of block transfers to begin in + parallel at a DN, for replication, when such a command list is being + sent over a DN heartbeat by the NN. The actual number is obtained by + multiplying this multiplier with the total number of live nodes in the + cluster. The result number is the number of blocks to begin transfers + immediately for, per DN heartbeat. This number can be any positive, + non-zero integer. + + + + + nfs.server.port + 2049 + + Specify the port number used by Hadoop NFS. + + + + + nfs.mountd.port + 4242 + + Specify the port number used by Hadoop mount daemon. + + + + + nfs.dump.dir + /tmp/.hdfs-nfs + + This directory is used to temporarily save out-of-order writes before + writing to HDFS. For each file, the out-of-order writes are dumped after + they are accumulated to exceed certain threshold (e.g., 1MB) in memory. + One needs to make sure the directory has enough space. + + + + + nfs.rtmax + 1048576 + This is the maximum size in bytes of a READ request + supported by the NFS gateway. If you change this, make sure you + also update the nfs mount's rsize(add rsize= # of bytes to the + mount directive). + + + + + nfs.wtmax + 1048576 + This is the maximum size in bytes of a WRITE request + supported by the NFS gateway. If you change this, make sure you + also update the nfs mount's wsize(add wsize= # of bytes to the + mount directive). + + + + + nfs.keytab.file + + + *Note*: Advanced property. Change with caution. + This is the path to the keytab file for the hdfs-nfs gateway. + This is required when the cluster is kerberized. + + + + + nfs.kerberos.principal + + + *Note*: Advanced property. Change with caution. + This is the name of the kerberos principal. This is required when + the cluster is kerberized.It must be of this format: + nfs-gateway-user/nfs-gateway-host@kerberos-realm + + + + + nfs.allow.insecure.ports + true + + When set to false, client connections originating from unprivileged ports + (those above 1023) will be rejected. This is to ensure that clients + connecting to this NFS Gateway must have had root privilege on the machine + where they're connecting from. + + + + + dfs.webhdfs.enabled + true + + Enable WebHDFS (REST API) in Namenodes and Datanodes. + + + + + hadoop.fuse.connection.timeout + 300 + + The minimum number of seconds that we'll cache libhdfs connection objects + in fuse_dfs. Lower values will result in lower memory consumption; higher + values may speed up access by avoiding the overhead of creating new + connection objects. + + + + + hadoop.fuse.timer.period + 5 + + The number of seconds between cache expiry checks in fuse_dfs. Lower values + will result in fuse_dfs noticing changes to Kerberos ticket caches more + quickly. + + + + + dfs.namenode.metrics.logger.period.seconds + 600 + + This setting controls how frequently the NameNode logs its metrics. The + logging configuration must also define one or more appenders for + NameNodeMetricsLog for the metrics to be logged. + NameNode metrics logging is disabled if this value is set to zero or + less than zero. + + + + + dfs.datanode.metrics.logger.period.seconds + 600 + + This setting controls how frequently the DataNode logs its metrics. The + logging configuration must also define one or more appenders for + DataNodeMetricsLog for the metrics to be logged. + DataNode metrics logging is disabled if this value is set to zero or + less than zero. + + + + + dfs.metrics.percentiles.intervals + + + Comma-delimited set of integers denoting the desired rollover intervals + (in seconds) for percentile latency metrics on the Namenode and Datanode. + By default, percentile latency metrics are disabled. + + + + + hadoop.user.group.metrics.percentiles.intervals + + + A comma-separated list of the granularity in seconds for the metrics + which describe the 50/75/90/95/99th percentile latency for group resolution + in milliseconds. + By default, percentile latency metrics are disabled. + + + + + dfs.encrypt.data.transfer + false + + Whether or not actual block data that is read/written from/to HDFS should + be encrypted on the wire. This only needs to be set on the NN and DNs, + clients will deduce this automatically. It is possible to override this setting + per connection by specifying custom logic via dfs.trustedchannel.resolver.class. + + + + + dfs.encrypt.data.transfer.algorithm + + + This value may be set to either "3des" or "rc4". If nothing is set, then + the configured JCE default on the system is used (usually 3DES.) It is + widely believed that 3DES is more cryptographically secure, but RC4 is + substantially faster. + + Note that if AES is supported by both the client and server then this + encryption algorithm will only be used to initially transfer keys for AES. + (See dfs.encrypt.data.transfer.cipher.suites.) + + + + + dfs.encrypt.data.transfer.cipher.suites + + + This value may be either undefined or AES/CTR/NoPadding. If defined, then + dfs.encrypt.data.transfer uses the specified cipher suite for data + encryption. If not defined, then only the algorithm specified in + dfs.encrypt.data.transfer.algorithm is used. By default, the property is + not defined. + + + + + dfs.encrypt.data.transfer.cipher.key.bitlength + 128 + + The key bitlength negotiated by dfsclient and datanode for encryption. + This value may be set to either 128, 192 or 256. + + + + + dfs.trustedchannel.resolver.class + + + TrustedChannelResolver is used to determine whether a channel + is trusted for plain data transfer. The TrustedChannelResolver is + invoked on both client and server side. If the resolver indicates + that the channel is trusted, then the data transfer will not be + encrypted even if dfs.encrypt.data.transfer is set to true. The + default implementation returns false indicating that the channel + is not trusted. + + + + + dfs.data.transfer.protection + + + A comma-separated list of SASL protection values used for secured + connections to the DataNode when reading or writing block data. Possible + values are authentication, integrity and privacy. authentication means + authentication only and no integrity or privacy; integrity implies + authentication and integrity are enabled; and privacy implies all of + authentication, integrity and privacy are enabled. If + dfs.encrypt.data.transfer is set to true, then it supersedes the setting for + dfs.data.transfer.protection and enforces that all connections must use a + specialized encrypted SASL handshake. This property is ignored for + connections to a DataNode listening on a privileged port. In this case, it + is assumed that the use of a privileged port establishes sufficient trust. + + + + + dfs.data.transfer.saslproperties.resolver.class + + + SaslPropertiesResolver used to resolve the QOP used for a connection to the + DataNode when reading or writing block data. If not specified, the value of + hadoop.security.saslproperties.resolver.class is used as the default value. + + + + + dfs.datanode.hdfs-blocks-metadata.enabled + false + + Boolean which enables backend datanode-side support for the experimental DistributedFileSystem#getFileVBlockStorageLocations API. + + + + + dfs.client.file-block-storage-locations.num-threads + 10 + + Number of threads used for making parallel RPCs in DistributedFileSystem#getFileBlockStorageLocations(). + + + + + dfs.client.file-block-storage-locations.timeout.millis + 1000 + + Timeout (in milliseconds) for the parallel RPCs made in DistributedFileSystem#getFileBlockStorageLocations(). + + + + + dfs.journalnode.rpc-address + 0.0.0.0:8485 + + The JournalNode RPC server address and port. + + + + + dfs.journalnode.http-address + 0.0.0.0:8480 + + The address and port the JournalNode HTTP server listens on. + If the port is 0 then the server will start on a free port. + + + + + dfs.journalnode.https-address + 0.0.0.0:8481 + + The address and port the JournalNode HTTPS server listens on. + If the port is 0 then the server will start on a free port. + + + + + dfs.namenode.audit.loggers + default + + List of classes implementing audit loggers that will receive audit events. + These should be implementations of org.apache.hadoop.hdfs.server.namenode.AuditLogger. + The special value "default" can be used to reference the default audit + logger, which uses the configured log system. Installing custom audit loggers + may affect the performance and stability of the NameNode. Refer to the custom + logger's documentation for more details. + + + + + dfs.datanode.available-space-volume-choosing-policy.balanced-space-threshold + 10737418240 + + Only used when the dfs.datanode.fsdataset.volume.choosing.policy is set to + org.apache.hadoop.hdfs.server.datanode.fsdataset.AvailableSpaceVolumeChoosingPolicy. + This setting controls how much DN volumes are allowed to differ in terms of + bytes of free disk space before they are considered imbalanced. If the free + space of all the volumes are within this range of each other, the volumes + will be considered balanced and block assignments will be done on a pure + round robin basis. + + + + + dfs.datanode.available-space-volume-choosing-policy.balanced-space-preference-fraction + 0.75f + + Only used when the dfs.datanode.fsdataset.volume.choosing.policy is set to + org.apache.hadoop.hdfs.server.datanode.fsdataset.AvailableSpaceVolumeChoosingPolicy. + This setting controls what percentage of new block allocations will be sent + to volumes with more available disk space than others. This setting should + be in the range 0.0 - 1.0, though in practice 0.5 - 1.0, since there should + be no reason to prefer that volumes with less available disk space receive + more block allocations. + + + + + dfs.namenode.edits.noeditlogchannelflush + false + + Specifies whether to flush edit log file channel. When set, expensive + FileChannel#force calls are skipped and synchronous disk writes are + enabled instead by opening the edit log file with RandomAccessFile("rws") + flags. This can significantly improve the performance of edit log writes + on the Windows platform. + Note that the behavior of the "rws" flags is platform and hardware specific + and might not provide the same level of guarantees as FileChannel#force. + For example, the write will skip the disk-cache on SAS and SCSI devices + while it might not on SATA devices. This is an expert level setting, + change with caution. + + + + + dfs.client.cache.drop.behind.writes + + + Just like dfs.datanode.drop.cache.behind.writes, this setting causes the + page cache to be dropped behind HDFS writes, potentially freeing up more + memory for other uses. Unlike dfs.datanode.drop.cache.behind.writes, this + is a client-side setting rather than a setting for the entire datanode. + If present, this setting will override the DataNode default. + + If the native libraries are not available to the DataNode, this + configuration has no effect. + + + + + dfs.client.cache.drop.behind.reads + + + Just like dfs.datanode.drop.cache.behind.reads, this setting causes the + page cache to be dropped behind HDFS reads, potentially freeing up more + memory for other uses. Unlike dfs.datanode.drop.cache.behind.reads, this + is a client-side setting rather than a setting for the entire datanode. If + present, this setting will override the DataNode default. + + If the native libraries are not available to the DataNode, this + configuration has no effect. + + + + + dfs.client.cache.readahead + + + When using remote reads, this setting causes the datanode to + read ahead in the block file using posix_fadvise, potentially decreasing + I/O wait times. Unlike dfs.datanode.readahead.bytes, this is a client-side + setting rather than a setting for the entire datanode. If present, this + setting will override the DataNode default. + + When using local reads, this setting determines how much readahead we do in + BlockReaderLocal. + + If the native libraries are not available to the DataNode, this + configuration has no effect. + + + + + dfs.namenode.enable.retrycache + true + + This enables the retry cache on the namenode. Namenode tracks for + non-idempotent requests the corresponding response. If a client retries the + request, the response from the retry cache is sent. Such operations + are tagged with annotation @AtMostOnce in namenode protocols. It is + recommended that this flag be set to true. Setting it to false, will result + in clients getting failure responses to retried request. This flag must + be enabled in HA setup for transparent fail-overs. + + The entries in the cache have expiration time configurable + using dfs.namenode.retrycache.expirytime.millis. + + + + + dfs.namenode.retrycache.expirytime.millis + 600000 + + The time for which retry cache entries are retained. + + + + + dfs.namenode.retrycache.heap.percent + 0.03f + + This parameter configures the heap size allocated for retry cache + (excluding the response cached). This corresponds to approximately + 4096 entries for every 64MB of namenode process java heap size. + Assuming retry cache entry expiration time (configured using + dfs.namenode.retrycache.expirytime.millis) of 10 minutes, this + enables retry cache to support 7 operations per second sustained + for 10 minutes. As the heap size is increased, the operation rate + linearly increases. + + + + + dfs.client.mmap.enabled + true + + If this is set to false, the client won't attempt to perform memory-mapped reads. + + + + + dfs.client.mmap.cache.size + 256 + + When zero-copy reads are used, the DFSClient keeps a cache of recently used + memory mapped regions. This parameter controls the maximum number of + entries that we will keep in that cache. + + The larger this number is, the more file descriptors we will potentially + use for memory-mapped files. mmaped files also use virtual address space. + You may need to increase your ulimit virtual address space limits before + increasing the client mmap cache size. + + Note that you can still do zero-copy reads when this size is set to 0. + + + + + dfs.client.mmap.cache.timeout.ms + 3600000 + + The minimum length of time that we will keep an mmap entry in the cache + between uses. If an entry is in the cache longer than this, and nobody + uses it, it will be removed by a background thread. + + + + + dfs.client.mmap.retry.timeout.ms + 300000 + + The minimum amount of time that we will wait before retrying a failed mmap + operation. + + + + + dfs.client.short.circuit.replica.stale.threshold.ms + 1800000 + + The maximum amount of time that we will consider a short-circuit replica to + be valid, if there is no communication from the DataNode. After this time + has elapsed, we will re-fetch the short-circuit replica even if it is in + the cache. + + + + + dfs.namenode.path.based.cache.block.map.allocation.percent + 0.25 + + The percentage of the Java heap which we will allocate to the cached blocks + map. The cached blocks map is a hash map which uses chained hashing. + Smaller maps may be accessed more slowly if the number of cached blocks is + large; larger maps will consume more memory. + + + + + dfs.datanode.max.locked.memory + 0 + + The amount of memory in bytes to use for caching of block replicas in + memory on the datanode. The datanode's maximum locked memory soft ulimit + (RLIMIT_MEMLOCK) must be set to at least this value, else the datanode + will abort on startup. + + By default, this parameter is set to 0, which disables in-memory caching. + + If the native libraries are not available to the DataNode, this + configuration has no effect. + + + + + dfs.namenode.list.cache.directives.num.responses + 100 + + This value controls the number of cache directives that the NameNode will + send over the wire in response to a listDirectives RPC. + + + + + dfs.namenode.list.cache.pools.num.responses + 100 + + This value controls the number of cache pools that the NameNode will + send over the wire in response to a listPools RPC. + + + + + dfs.namenode.path.based.cache.refresh.interval.ms + 30000 + + The amount of milliseconds between subsequent path cache rescans. Path + cache rescans are when we calculate which blocks should be cached, and on + what datanodes. + + By default, this parameter is set to 30 seconds. + + + + + dfs.namenode.path.based.cache.retry.interval.ms + 30000 + + When the NameNode needs to uncache something that is cached, or cache + something that is not cached, it must direct the DataNodes to do so by + sending a DNA_CACHE or DNA_UNCACHE command in response to a DataNode + heartbeat. This parameter controls how frequently the NameNode will + resend these commands. + + + + + dfs.datanode.fsdatasetcache.max.threads.per.volume + 4 + + The maximum number of threads per volume to use for caching new data + on the datanode. These threads consume both I/O and CPU. This can affect + normal datanode operations. + + + + + dfs.cachereport.intervalMsec + 10000 + + Determines cache reporting interval in milliseconds. After this amount of + time, the DataNode sends a full report of its cache state to the NameNode. + The NameNode uses the cache report to update its map of cached blocks to + DataNode locations. + + This configuration has no effect if in-memory caching has been disabled by + setting dfs.datanode.max.locked.memory to 0 (which is the default). + + If the native libraries are not available to the DataNode, this + configuration has no effect. + + + + + dfs.namenode.edit.log.autoroll.multiplier.threshold + 2.0 + + Determines when an active namenode will roll its own edit log. + The actual threshold (in number of edits) is determined by multiplying + this value by dfs.namenode.checkpoint.txns. + + This prevents extremely large edit files from accumulating on the active + namenode, which can cause timeouts during namenode startup and pose an + administrative hassle. This behavior is intended as a failsafe for when + the standby or secondary namenode fail to roll the edit log by the normal + checkpoint threshold. + + + + + dfs.namenode.edit.log.autoroll.check.interval.ms + 300000 + + How often an active namenode will check if it needs to roll its edit log, + in milliseconds. + + + + + dfs.webhdfs.user.provider.user.pattern + ^[A-Za-z_][A-Za-z0-9._-]*[$]?$ + + Valid pattern for user and group names for webhdfs, it must be a valid java regex. + + + + + dfs.webhdfs.socket.connect-timeout + 60s + + Socket timeout for connecting to WebHDFS servers. This prevents a + WebHDFS client from hanging if the server hostname is + misconfigured, or the server does not response before the timeout + expires. Value is followed by a unit specifier: ns, us, ms, s, m, + h, d for nanoseconds, microseconds, milliseconds, seconds, + minutes, hours, days respectively. Values should provide units, + but milliseconds are assumed. + + + + + dfs.webhdfs.socket.read-timeout + 60s + + Socket timeout for reading data from WebHDFS servers. This + prevents a WebHDFS client from hanging if the server stops sending + data. Value is followed by a unit specifier: ns, us, ms, s, m, h, + d for nanoseconds, microseconds, milliseconds, seconds, minutes, + hours, days respectively. Values should provide units, + but milliseconds are assumed. + + + + + dfs.client.context + default + + The name of the DFSClient context that we should use. Clients that share + a context share a socket cache and short-circuit cache, among other things. + You should only change this if you don't want to share with another set of + threads. + + + + + dfs.client.read.shortcircuit + false + + This configuration parameter turns on short-circuit local reads. + + + + + dfs.client.socket.send.buffer.size + 0 + + Socket send buffer size for a write pipeline in DFSClient side. + This may affect TCP connection throughput. + If it is set to zero or negative value, + no buffer size will be set explicitly, + thus enable tcp auto-tuning on some system. + The default value is 0. + + + + + dfs.domain.socket.path + + + Optional. This is a path to a UNIX domain socket that will be used for + communication between the DataNode and local HDFS clients. + If the string "_PORT" is present in this path, it will be replaced by the + TCP port of the DataNode. + + + + + dfs.client.read.shortcircuit.skip.checksum + false + + If this configuration parameter is set, + short-circuit local reads will skip checksums. + This is normally not recommended, + but it may be useful for special setups. + You might consider using this + if you are doing your own checksumming outside of HDFS. + + + + + dfs.client.read.shortcircuit.streams.cache.size + 256 + + The DFSClient maintains a cache of recently opened file descriptors. + This parameter controls the maximum number of file descriptors in the cache. + Setting this higher will use more file descriptors, + but potentially provide better performance on workloads + involving lots of seeks. + + + + + dfs.client.read.shortcircuit.streams.cache.expiry.ms + 300000 + + This controls the minimum amount of time + file descriptors need to sit in the client cache context + before they can be closed for being inactive for too long. + + + + + dfs.datanode.shared.file.descriptor.paths + /dev/shm,/tmp + + Comma separated paths to the directory on which + shared memory segments are created. + The client and the DataNode exchange information via + this shared memory segment. + It tries paths in order until creation of shared memory segment succeeds. + + + + + dfs.namenode.audit.log.debug.cmdlist + + + A comma separated list of NameNode commands that are written to the HDFS + namenode audit log only if the audit log level is debug. + + + + + dfs.client.use.legacy.blockreader.local + false + + Legacy short-circuit reader implementation based on HDFS-2246 is used + if this configuration parameter is true. + This is for the platforms other than Linux + where the new implementation based on HDFS-347 is not available. + + + + + dfs.block.local-path-access.user + + + Comma separated list of the users allowd to open block files + on legacy short-circuit local read. + + + + + dfs.client.domain.socket.data.traffic + false + + This control whether we will try to pass normal data traffic + over UNIX domain socket rather than over TCP socket + on node-local data transfer. + This is currently experimental and turned off by default. + + + + + dfs.namenode.reject-unresolved-dn-topology-mapping + false + + If the value is set to true, then namenode will reject datanode + registration if the topology mapping for a datanode is not resolved and + NULL is returned (script defined by net.topology.script.file.name fails + to execute). Otherwise, datanode will be registered and the default rack + will be assigned as the topology path. Topology paths are important for + data resiliency, since they define fault domains. Thus it may be unwanted + behavior to allow datanode registration with the default rack if the + resolving topology failed. + + + + + dfs.client.slow.io.warning.threshold.ms + 30000 + The threshold in milliseconds at which we will log a slow + io warning in a dfsclient. By default, this parameter is set to 30000 + milliseconds (30 seconds). + + + + + dfs.datanode.slow.io.warning.threshold.ms + 300 + The threshold in milliseconds at which we will log a slow + io warning in a datanode. By default, this parameter is set to 300 + milliseconds. + + + + + dfs.namenode.xattrs.enabled + true + + Whether support for extended attributes is enabled on the NameNode. + + + + + dfs.namenode.fs-limits.max-xattrs-per-inode + 32 + + Maximum number of extended attributes per inode. + + + + + dfs.namenode.fs-limits.max-xattr-size + 16384 + + The maximum combined size of the name and value of an extended attribute + in bytes. It should be larger than 0, and less than or equal to maximum + size hard limit which is 32768. + + + + + dfs.namenode.lease-recheck-interval-ms + 2000 + During the release of lease a lock is hold that make any + operations on the namenode stuck. In order to not block them during + a too long duration we stop releasing lease after this max lock limit. + + + + + dfs.namenode.max-lock-hold-to-release-lease-ms + 25 + During the release of lease a lock is hold that make any + operations on the namenode stuck. In order to not block them during + a too long duration we stop releasing lease after this max lock limit. + + + + + dfs.namenode.write-lock-reporting-threshold-ms + 5000 + When a write lock is held on the namenode for a long time, + this will be logged as the lock is released. This sets how long the + lock must be held for logging to occur. + + + + + dfs.namenode.read-lock-reporting-threshold-ms + 5000 + When a read lock is held on the namenode for a long time, + this will be logged as the lock is released. This sets how long the + lock must be held for logging to occur. + + + + + dfs.namenode.lock.detailed-metrics.enabled + false + If true, the namenode will keep track of how long various + operations hold the Namesystem lock for and emit this as metrics. These + metrics have names of the form FSN(Read|Write)LockNanosOperationName, + where OperationName denotes the name of the operation that initiated the + lock hold (this will be OTHER for certain uncategorized operations) and + they export the hold time values in nanoseconds. + + + + + dfs.namenode.fslock.fair + true + If this is true, the FS Namesystem lock will be used in Fair mode, + which will help to prevent writer threads from being starved, but can provide + lower lock throughput. See java.util.concurrent.locks.ReentrantReadWriteLock + for more information on fair/non-fair locks. + + + + + dfs.namenode.startup.delay.block.deletion.sec + 0 + The delay in seconds at which we will pause the blocks deletion + after Namenode startup. By default it's disabled. + In the case a directory has large number of directories and files are + deleted, suggested delay is one hour to give the administrator enough time + to notice large number of pending deletion blocks and take corrective + action. + + + + + dfs.namenode.list.encryption.zones.num.responses + 100 + When listing encryption zones, the maximum number of zones + that will be returned in a batch. Fetching the list incrementally in + batches improves namenode performance. + + + + + dfs.namenode.edekcacheloader.interval.ms + 1000 + When KeyProvider is configured, the interval time of warming + up edek cache on NN starts up / becomes active. All edeks will be loaded + from KMS into provider cache. The edek cache loader will try to warm up the + cache until succeed or NN leaves active state. + + + + + dfs.namenode.edekcacheloader.initial.delay.ms + 3000 + When KeyProvider is configured, the time delayed until the first + attempt to warm up edek cache on NN start up / become active. + + + + + dfs.namenode.inotify.max.events.per.rpc + 1000 + Maximum number of events that will be sent to an inotify client + in a single RPC response. The default value attempts to amortize away + the overhead for this RPC while avoiding huge memory requirements for the + client and NameNode (1000 events should consume no more than 1 MB.) + + + + + dfs.user.home.dir.prefix + /user + The directory to prepend to user name to get the user's + home direcotry. + + + + + dfs.datanode.cache.revocation.timeout.ms + 900000 + When the DFSClient reads from a block file which the DataNode is + caching, the DFSClient can skip verifying checksums. The DataNode will + keep the block file in cache until the client is done. If the client takes + an unusually long time, though, the DataNode may need to evict the block + file from the cache anyway. This value controls how long the DataNode will + wait for the client to release a replica that it is reading without + checksums. + + + + + dfs.datanode.cache.revocation.polling.ms + 500 + How often the DataNode should poll to see if the clients have + stopped using a replica that the DataNode wants to uncache. + + + + + dfs.datanode.block.id.layout.upgrade.threads + 12 + The number of threads to use when creating hard links from + current to previous blocks during upgrade of a DataNode to block ID-based + block layout (see HDFS-6482 for details on the layout). + + + + dfs.storage.policy.enabled + true + + Allow users to change the storage policy on files and directories. + + + + + dfs.namenode.legacy-oiv-image.dir + + Determines where to save the namespace in the old fsimage format + during checkpointing by standby NameNode or SecondaryNameNode. Users can + dump the contents of the old format fsimage by oiv_legacy command. If + the value is not specified, old format fsimage will not be saved in + checkpoint. + + + + + dfs.namenode.top.enabled + true + Enable nntop: reporting top users on namenode + + + + + dfs.namenode.top.window.num.buckets + 10 + Number of buckets in the rolling window implementation of nntop + + + + + dfs.namenode.top.num.users + 10 + Number of top users returned by the top tool + + + + + dfs.namenode.top.windows.minutes + 1,5,25 + comma separated list of nntop reporting periods in minutes + + + + + dfs.webhdfs.ugi.expire.after.access + 600000 + How long in milliseconds after the last access + the cached UGI will expire. With 0, never expire. + + + + + dfs.namenode.blocks.per.postponedblocks.rescan + 10000 + Number of blocks to rescan for each iteration of + postponedMisreplicatedBlocks. + + + + + dfs.datanode.block-pinning.enabled + false + Whether pin blocks on favored DataNode. + + + + dfs.client.block.write.locateFollowingBlock.initial.delay.ms + 400 + The initial delay (unit is ms) for locateFollowingBlock, + the delay time will increase exponentially(double) for each retry. + + + + + dfs.ha.zkfc.nn.http.timeout.ms + 20000 + + The HTTP connection and read timeout value (unit is ms ) when DFS ZKFC + tries to get local NN thread dump after local NN becomes + SERVICE_NOT_RESPONDING or SERVICE_UNHEALTHY. + If it is set to zero, DFS ZKFC won't get local NN thread dump. + + + + + dfs.namenode.quota.init-threads + 4 + + The number of concurrent threads to be used in quota initialization. The + speed of quota initialization also affects the namenode fail-over latency. + If the size of name space is big, try increasing this. + + + + + dfs.datanode.transfer.socket.send.buffer.size + 0 + + Socket send buffer size for DataXceiver (mirroring packets to downstream + in pipeline). This may affect TCP connection throughput. + If it is set to zero or negative value, no buffer size will be set + explicitly, thus enable tcp auto-tuning on some system. + The default value is 0. + + + + + dfs.datanode.transfer.socket.recv.buffer.size + 0 + + Socket receive buffer size for DataXceiver (receiving packets from client + during block writing). This may affect TCP connection throughput. + If it is set to zero or negative value, no buffer size will be set + explicitly, thus enable tcp auto-tuning on some system. + The default value is 0. + + + + + dfs.namenode.upgrade.domain.factor + ${dfs.replication} + + This is valid only when block placement policy is set to + BlockPlacementPolicyWithUpgradeDomain. It defines the number of + unique upgrade domains any block's replicas should have. + When the number of replicas is less or equal to this value, the policy + ensures each replica has an unique upgrade domain. When the number of + replicas is greater than this value, the policy ensures the number of + unique domains is at least this value. + + + + + dfs.datanode.bp-ready.timeout + 20 + + The maximum wait time for datanode to be ready before failing the + received request. Setting this to 0 fails requests right away if the + datanode is not yet registered with the namenode. This wait time + reduces initial request failures after datanode restart. + + + + + dfs.webhdfs.rest-csrf.enabled + false + + If true, then enables WebHDFS protection against cross-site request forgery + (CSRF). The WebHDFS client also uses this property to determine whether or + not it needs to send the custom CSRF prevention header in its HTTP requests. + + + + + dfs.webhdfs.rest-csrf.custom-header + X-XSRF-HEADER + + The name of a custom header that HTTP requests must send when protection + against cross-site request forgery (CSRF) is enabled for WebHDFS by setting + dfs.webhdfs.rest-csrf.enabled to true. The WebHDFS client also uses this + property to determine whether or not it needs to send the custom CSRF + prevention header in its HTTP requests. + + + + + dfs.webhdfs.rest-csrf.methods-to-ignore + GET,OPTIONS,HEAD,TRACE + + A comma-separated list of HTTP methods that do not require HTTP requests to + include a custom header when protection against cross-site request forgery + (CSRF) is enabled for WebHDFS by setting dfs.webhdfs.rest-csrf.enabled to + true. The WebHDFS client also uses this property to determine whether or + not it needs to send the custom CSRF prevention header in its HTTP requests. + + + + + dfs.webhdfs.rest-csrf.browser-useragents-regex + ^Mozilla.*,^Opera.* + + A comma-separated list of regular expressions used to match against an HTTP + request's User-Agent header when protection against cross-site request + forgery (CSRF) is enabled for WebHDFS by setting + dfs.webhdfs.reset-csrf.enabled to true. If the incoming User-Agent matches + any of these regular expressions, then the request is considered to be sent + by a browser, and therefore CSRF prevention is enforced. If the request's + User-Agent does not match any of these regular expressions, then the request + is considered to be sent by something other than a browser, such as scripted + automation. In this case, CSRF is not a potential attack vector, so + the prevention is not enforced. This helps achieve backwards-compatibility + with existing automation that has not been updated to send the CSRF + prevention header. + + + + + dfs.xframe.enabled + true + + If true, then enables protection against clickjacking by returning + X_FRAME_OPTIONS header value set to SAMEORIGIN. + Clickjacking protection prevents an attacker from using transparent or + opaque layers to trick a user into clicking on a button + or link on another page. + + + + + dfs.xframe.value + SAMEORIGIN + + This configration value allows user to specify the value for the + X-FRAME-OPTIONS. The possible values for this field are + DENY, SAMEORIGIN and ALLOW-FROM. Any other value will throw an + exception when namenode and datanodes are starting up. + + + + + + dfs.http.client.retry.policy.enabled + false + + If "true", enable the retry policy of WebHDFS client. + If "false", retry policy is turned off. + Enabling the retry policy can be quite useful while using WebHDFS to + copy large files between clusters that could timeout, or + copy files between HA clusters that could failover during the copy. + + + + + dfs.http.client.retry.policy.spec + 10000,6,60000,10 + + Specify a policy of multiple linear random retry for WebHDFS client, + e.g. given pairs of number of retries and sleep time (n0, t0), (n1, t1), + ..., the first n0 retries sleep t0 milliseconds on average, + the following n1 retries sleep t1 milliseconds on average, and so on. + + + + + dfs.http.client.failover.max.attempts + 15 + + Specify the max number of failover attempts for WebHDFS client + in case of network exception. + + + + + dfs.http.client.retry.max.attempts + 10 + + Specify the max number of retry attempts for WebHDFS client, + if the difference between retried attempts and failovered attempts is + larger than the max number of retry attempts, there will be no more + retries. + + + + + dfs.http.client.failover.sleep.base.millis + 500 + + Specify the base amount of time in milliseconds upon which the + exponentially increased sleep time between retries or failovers + is calculated for WebHDFS client. + + + + + dfs.http.client.failover.sleep.max.millis + 15000 + + Specify the upper bound of sleep time in milliseconds between + retries or failovers for WebHDFS client. + + + + dfs.balancer.keytab.enabled + false + + Set to true to enable login using a keytab for Kerberized Hadoop. + + + + + dfs.balancer.address + 0.0.0.0:0 + + The hostname used for a keytab based Kerberos login. Keytab based login + can be enabled with dfs.balancer.keytab.enabled. + + + + + dfs.balancer.keytab.file + + + The keytab file used by the Balancer to login as its + service principal. The principal name is configured with + dfs.balancer.kerberos.principal. Keytab based login can be + enabled with dfs.balancer.keytab.enabled. + + + + + dfs.balancer.kerberos.principal + + + The Balancer principal. This is typically set to + balancer/_HOST@REALM.TLD. The Balancer will substitute _HOST with its + own fully qualified hostname at startup. The _HOST placeholder + allows using the same configuration setting on different servers. + Keytab based login can be enabled with dfs.balancer.keytab.enabled. + + + + + dfs.balancer.block-move.timeout + 0 + + Maximum amount of time in milliseconds for a block to move. If this is set + greater than 0, Balancer will stop waiting for a block move completion + after this time. In typical clusters, a 3 to 5 minute timeout is reasonable. + If timeout happens to a large proportion of block moves, this needs to be + increased. It could also be that too much work is dispatched and many nodes + are constantly exceeding the bandwidth limit as a result. In that case, + other balancer parameters might need to be adjusted. + It is disabled (0) by default. + + + + + dfs.balancer.max-no-move-interval + 60000 + + If this specified amount of time has elapsed and no block has been moved + out of a source DataNode, on more effort will be made to move blocks out of + this DataNode in the current Balancer iteration. + + + + + dfs.lock.suppress.warning.interval + 10s + Instrumentation reporting long critical sections will suppress + consecutive warnings within this interval. + + + + dfs.webhdfs.use.ipc.callq + true + Enables routing of webhdfs calls through rpc + call queue + + + + httpfs.buffer.size + 4096 + + The size buffer to be used when creating or opening httpfs filesystem IO stream. + + + + + dfs.namenode.hosts.provider.classname + org.apache.hadoop.hdfs.server.blockmanagement.HostFileManager + + The class that provides access for host files. + org.apache.hadoop.hdfs.server.blockmanagement.HostFileManager is used + by default which loads files specified by dfs.hosts and dfs.hosts.exclude. + If org.apache.hadoop.hdfs.server.blockmanagement.CombinedHostFileManager is + used, it will load the JSON file defined in dfs.hosts. + To change class name, nn restart is required. "dfsadmin -refreshNodes" only + refreshes the configuration files used by the class. + + + + diff --git a/sahara/plugins/vanilla/v2_8_2/resources/hive-default.xml b/sahara/plugins/vanilla/v2_8_2/resources/hive-default.xml new file mode 100644 index 0000000..97b9b07 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/hive-default.xml @@ -0,0 +1,5959 @@ + + + + + + + + hive.exec.script.wrapper + + + + + hive.exec.plan + + + + + hive.exec.stagingdir + .hive-staging + Directory name that will be created inside table locations in order to support HDFS encryption. This is replaces ${hive.exec.scratchdir} for query results with the exception of read-only tables. In all cases ${hive.exec.scratchdir} is still used for other temporary files, such as job plans. + + + hive.exec.scratchdir + /tmp/hive + HDFS root scratch dir for Hive jobs which gets created with write all (733) permission. For each connecting user, an HDFS scratch dir: ${hive.exec.scratchdir}/<username> is created, with ${hive.scratch.dir.permission}. + + + hive.repl.rootdir + /user/hive/repl/ + HDFS root dir for all replication dumps. + + + hive.repl.cm.enabled + false + Turn on ChangeManager, so delete files will go to cmrootdir. + + + hive.repl.cmrootdir + /user/hive/cmroot/ + Root dir for ChangeManager, used for deleted files. + + + hive.repl.cm.retain + 24h + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is hour if not specified. + Time to retain removed files in cmrootdir. + + + + hive.repl.cm.interval + 3600s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Inteval for cmroot cleanup thread. + + + + hive.exec.local.scratchdir + ${system:java.io.tmpdir}/${system:user.name} + Local scratch space for Hive jobs + + + hive.downloaded.resources.dir + ${system:java.io.tmpdir}/${hive.session.id}_resources + Temporary local directory for added resources in the remote file system. + + + hive.scratch.dir.permission + 700 + The permission for the user specific scratch directories that get created. + + + hive.exec.submitviachild + false + + + + hive.exec.submit.local.task.via.child + true + + Determines whether local tasks (typically mapjoin hashtable generation phase) runs in + separate JVM (true recommended) or not. + Avoids the overhead of spawning new JVM, but can lead to out-of-memory issues. + + + + hive.exec.script.maxerrsize + 100000 + + Maximum number of bytes a script is allowed to emit to standard error (per map-reduce task). + This prevents runaway scripts from filling logs partitions to capacity + + + + hive.exec.script.allow.partial.consumption + false + + When enabled, this option allows a user script to exit successfully without consuming + all the data from the standard input. + + + + stream.stderr.reporter.prefix + reporter: + Streaming jobs that log to standard error with this prefix can log counter or status information. + + + stream.stderr.reporter.enabled + true + Enable consumption of status and counter messages for streaming jobs. + + + hive.exec.compress.output + false + + This controls whether the final outputs of a query (to a local/HDFS file or a Hive table) is compressed. + The compression codec and other options are determined from Hadoop config variables mapred.output.compress* + + + + hive.exec.compress.intermediate + false + + This controls whether intermediate files produced by Hive between multiple map-reduce jobs are compressed. + The compression codec and other options are determined from Hadoop config variables mapred.output.compress* + + + + hive.intermediate.compression.codec + + + + + hive.intermediate.compression.type + + + + + hive.exec.reducers.bytes.per.reducer + 256000000 + size per reducer.The default is 256Mb, i.e if the input size is 1G, it will use 4 reducers. + + + hive.exec.reducers.max + 1009 + + max number of reducers will be used. If the one specified in the configuration parameter mapred.reduce.tasks is + negative, Hive will use this one as the max number of reducers when automatically determine number of reducers. + + + + hive.exec.pre.hooks + + + Comma-separated list of pre-execution hooks to be invoked for each statement. + A pre-execution hook is specified as the name of a Java class which implements the + org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface. + + + + hive.exec.post.hooks + + + Comma-separated list of post-execution hooks to be invoked for each statement. + A post-execution hook is specified as the name of a Java class which implements the + org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface. + + + + hive.exec.failure.hooks + + + Comma-separated list of on-failure hooks to be invoked for each statement. + An on-failure hook is specified as the name of Java class which implements the + org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface. + + + + hive.exec.query.redactor.hooks + + + Comma-separated list of hooks to be invoked for each query which can + tranform the query before it's placed in the job.xml file. Must be a Java class which + extends from the org.apache.hadoop.hive.ql.hooks.Redactor abstract class. + + + + hive.client.stats.publishers + + + Comma-separated list of statistics publishers to be invoked on counters on each job. + A client stats publisher is specified as the name of a Java class which implements the + org.apache.hadoop.hive.ql.stats.ClientStatsPublisher interface. + + + + hive.ats.hook.queue.capacity + 64 + + Queue size for the ATS Hook executor. If the number of outstanding submissions + to the ATS executor exceed this amount, the Hive ATS Hook will not try to log queries to ATS. + + + + hive.exec.parallel + false + Whether to execute jobs in parallel + + + hive.exec.parallel.thread.number + 8 + How many jobs at most can be executed in parallel + + + hive.mapred.reduce.tasks.speculative.execution + true + Whether speculative execution for reducers should be turned on. + + + hive.exec.counters.pull.interval + 1000 + + The interval with which to poll the JobTracker for the counters the running job. + The smaller it is the more load there will be on the jobtracker, the higher it is the less granular the caught will be. + + + + hive.exec.dynamic.partition + true + Whether or not to allow dynamic partitions in DML/DDL. + + + hive.exec.dynamic.partition.mode + strict + + In strict mode, the user must specify at least one static partition + in case the user accidentally overwrites all partitions. + In nonstrict mode all partitions are allowed to be dynamic. + + + + hive.exec.max.dynamic.partitions + 1000 + Maximum number of dynamic partitions allowed to be created in total. + + + hive.exec.max.dynamic.partitions.pernode + 100 + Maximum number of dynamic partitions allowed to be created in each mapper/reducer node. + + + hive.exec.max.created.files + 100000 + Maximum number of HDFS files created by all mappers/reducers in a MapReduce job. + + + hive.exec.default.partition.name + __HIVE_DEFAULT_PARTITION__ + + The default partition name in case the dynamic partition column value is null/empty string or any other values that cannot be escaped. + This value must not contain any special character used in HDFS URI (e.g., ':', '%', '/' etc). + The user has to be aware that the dynamic partition value should not contain this value to avoid confusions. + + + + hive.lockmgr.zookeeper.default.partition.name + __HIVE_DEFAULT_ZOOKEEPER_PARTITION__ + + + + hive.exec.show.job.failure.debug.info + true + + If a job fails, whether to provide a link in the CLI to the task with the + most failures, along with debugging hints if applicable. + + + + hive.exec.job.debug.capture.stacktraces + true + + Whether or not stack traces parsed from the task logs of a sampled failed task + for each failed job should be stored in the SessionState + + + + hive.exec.job.debug.timeout + 30000 + + + + hive.exec.tasklog.debug.timeout + 20000 + + + + hive.output.file.extension + + + String used as a file extension for output files. + If not set, defaults to the codec extension for text files (e.g. ".gz"), or no extension otherwise. + + + + hive.exec.mode.local.auto + false + Let Hive determine whether to run in local mode automatically + + + hive.exec.mode.local.auto.inputbytes.max + 134217728 + When hive.exec.mode.local.auto is true, input bytes should less than this for local mode. + + + hive.exec.mode.local.auto.input.files.max + 4 + When hive.exec.mode.local.auto is true, the number of tasks should less than this for local mode. + + + hive.exec.drop.ignorenonexistent + true + Do not report an error if DROP TABLE/VIEW/Index/Function specifies a non-existent table/view/index/function + + + hive.ignore.mapjoin.hint + true + Ignore the mapjoin hint + + + hive.file.max.footer + 100 + maximum number of lines for footer user can define for a table file + + + hive.resultset.use.unique.column.names + true + + Make column names unique in the result set by qualifying column names with table alias if needed. + Table alias will be added to column names for queries of type "select *" or + if query explicitly uses table alias "select r1.x..". + + + + fs.har.impl + org.apache.hadoop.hive.shims.HiveHarFileSystem + The implementation for accessing Hadoop Archives. Note that this won't be applicable to Hadoop versions less than 0.20 + + + hive.metastore.warehouse.dir + /user/hive/warehouse + location of default database for the warehouse + + + hive.metastore.uris + + Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore. + + + hive.metastore.client.capability.check + true + Whether to check client capabilities for potentially breaking API usage. + + + hive.metastore.fastpath + false + Used to avoid all of the proxies and object copies in the metastore. Note, if this is set, you MUST use a local metastore (hive.metastore.uris must be empty) otherwise undefined and most likely undesired behavior will result + + + hive.metastore.fshandler.threads + 15 + Number of threads to be allocated for metastore handler for fs operations. + + + hive.metastore.hbase.catalog.cache.size + 50000 + Maximum number of objects we will place in the hbase metastore catalog cache. The objects will be divided up by types that we need to cache. + + + hive.metastore.hbase.aggregate.stats.cache.size + 10000 + Maximum number of aggregate stats nodes that we will place in the hbase metastore aggregate stats cache. + + + hive.metastore.hbase.aggregate.stats.max.partitions + 10000 + Maximum number of partitions that are aggregated per cache node. + + + hive.metastore.hbase.aggregate.stats.false.positive.probability + 0.01 + Maximum false positive probability for the Bloom Filter used in each aggregate stats cache node (default 1%). + + + hive.metastore.hbase.aggregate.stats.max.variance + 0.1 + Maximum tolerable variance in number of partitions between a cached node and our request (default 10%). + + + hive.metastore.hbase.cache.ttl + 600s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds for a cached node to be active in the cache before they become stale. + + + + hive.metastore.hbase.cache.max.writer.wait + 5000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Number of milliseconds a writer will wait to acquire the writelock before giving up. + + + + hive.metastore.hbase.cache.max.reader.wait + 1000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Number of milliseconds a reader will wait to acquire the readlock before giving up. + + + + hive.metastore.hbase.cache.max.full + 0.9 + Maximum cache full % after which the cache cleaner thread kicks in. + + + hive.metastore.hbase.cache.clean.until + 0.8 + The cleaner thread cleans until cache reaches this % full size. + + + hive.metastore.hbase.connection.class + org.apache.hadoop.hive.metastore.hbase.VanillaHBaseConnection + Class used to connection to HBase + + + hive.metastore.hbase.aggr.stats.cache.entries + 10000 + How many in stats objects to cache in memory + + + hive.metastore.hbase.aggr.stats.memory.ttl + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds stats objects live in memory after they are read from HBase. + + + + hive.metastore.hbase.aggr.stats.invalidator.frequency + 5s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + How often the stats cache scans its HBase entries and looks for expired entries + + + + hive.metastore.hbase.aggr.stats.hbase.ttl + 604800s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds stats entries live in HBase cache after they are created. They may be invalided by updates or partition drops before this. Default is one week. + + + + hive.metastore.hbase.file.metadata.threads + 1 + Number of threads to use to read file metadata in background to cache it. + + + hive.metastore.connect.retries + 3 + Number of retries while opening a connection to metastore + + + hive.metastore.failure.retries + 1 + Number of retries upon failure of Thrift metastore calls + + + hive.metastore.port + 9083 + Hive metastore listener port + + + hive.metastore.client.connect.retry.delay + 1s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds for the client to wait between consecutive connection attempts + + + + hive.metastore.client.socket.timeout + 600s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + MetaStore Client socket timeout in seconds + + + + hive.metastore.client.socket.lifetime + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + MetaStore Client socket lifetime in seconds. After this time is exceeded, client + reconnects on the next MetaStore operation. A value of 0s means the connection + has an infinite lifetime. + + + + javax.jdo.option.ConnectionPassword + mine + password to use against metastore database + + + hive.metastore.ds.connection.url.hook + + Name of the hook to use for retrieving the JDO connection URL. If empty, the value in javax.jdo.option.ConnectionURL is used + + + javax.jdo.option.Multithreaded + true + Set this to true if multiple threads access metastore through JDO concurrently. + + + javax.jdo.option.ConnectionURL + jdbc:derby:;databaseName=metastore_db;create=true + + JDBC connect string for a JDBC metastore. + To use SSL to encrypt/authenticate the connection, provide database-specific SSL flag in the connection URL. + For example, jdbc:postgresql://myhost/db?ssl=true for postgres database. + + + + hive.metastore.dbaccess.ssl.properties + + + Comma-separated SSL properties for metastore to access database when JDO connection URL + enables SSL access. e.g. javax.net.ssl.trustStore=/tmp/truststore,javax.net.ssl.trustStorePassword=pwd. + + + + hive.hmshandler.retry.attempts + 10 + The number of times to retry a HMSHandler call if there were a connection error. + + + hive.hmshandler.retry.interval + 2000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The time between HMSHandler retry attempts on failure. + + + + hive.hmshandler.force.reload.conf + false + + Whether to force reloading of the HMSHandler configuration (including + the connection URL, before the next metastore query that accesses the + datastore. Once reloaded, this value is reset to false. Used for + testing only. + + + + hive.metastore.server.max.message.size + 104857600 + Maximum message size in bytes a HMS will accept. + + + hive.metastore.server.min.threads + 200 + Minimum number of worker threads in the Thrift server's pool. + + + hive.metastore.server.max.threads + 1000 + Maximum number of worker threads in the Thrift server's pool. + + + hive.metastore.server.tcp.keepalive + true + Whether to enable TCP keepalive for the metastore server. Keepalive will prevent accumulation of half-open connections. + + + hive.metastore.archive.intermediate.original + _INTERMEDIATE_ORIGINAL + + Intermediate dir suffixes used for archiving. Not important what they + are, as long as collisions are avoided + + + + hive.metastore.archive.intermediate.archived + _INTERMEDIATE_ARCHIVED + + + + hive.metastore.archive.intermediate.extracted + _INTERMEDIATE_EXTRACTED + + + + hive.metastore.kerberos.keytab.file + + The path to the Kerberos Keytab file containing the metastore Thrift server's service principal. + + + hive.metastore.kerberos.principal + hive-metastore/_HOST@EXAMPLE.COM + + The service principal for the metastore Thrift server. + The special string _HOST will be replaced automatically with the correct host name. + + + + hive.metastore.sasl.enabled + false + If true, the metastore Thrift interface will be secured with SASL. Clients must authenticate with Kerberos. + + + hive.metastore.thrift.framed.transport.enabled + false + If true, the metastore Thrift interface will use TFramedTransport. When false (default) a standard TTransport is used. + + + hive.metastore.thrift.compact.protocol.enabled + false + + If true, the metastore Thrift interface will use TCompactProtocol. When false (default) TBinaryProtocol will be used. + Setting it to true will break compatibility with older clients running TBinaryProtocol. + + + + hive.metastore.token.signature + + The delegation token service name to match when selecting a token from the current user's tokens. + + + hive.cluster.delegation.token.store.class + org.apache.hadoop.hive.thrift.MemoryTokenStore + The delegation token store implementation. Set to org.apache.hadoop.hive.thrift.ZooKeeperTokenStore for load-balanced cluster. + + + hive.cluster.delegation.token.store.zookeeper.connectString + + + The ZooKeeper token store connect string. You can re-use the configuration value + set in hive.zookeeper.quorum, by leaving this parameter unset. + + + + hive.cluster.delegation.token.store.zookeeper.znode + /hivedelegation + + The root path for token store data. Note that this is used by both HiveServer2 and + MetaStore to store delegation Token. One directory gets created for each of them. + The final directory names would have the servername appended to it (HIVESERVER2, + METASTORE). + + + + hive.cluster.delegation.token.store.zookeeper.acl + + + ACL for token store entries. Comma separated list of ACL entries. For example: + sasl:hive/host1@MY.DOMAIN:cdrwa,sasl:hive/host2@MY.DOMAIN:cdrwa + Defaults to all permissions for the hiveserver2/metastore process user. + + + + hive.metastore.cache.pinobjtypes + Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order + List of comma separated metastore object types that should be pinned in the cache + + + datanucleus.connectionPoolingType + BONECP + + Expects one of [bonecp, dbcp, hikaricp, none]. + Specify connection pool library for datanucleus + + + + datanucleus.connectionPool.maxPoolSize + 10 + + Specify the maximum number of connections in the connection pool. Note: The configured size will be used by + 2 connection pools (TxnHandler and ObjectStore). When configuring the max connection pool size, it is + recommended to take into account the number of metastore instances and the number of HiveServer2 instances + configured with embedded metastore. To get optimal performance, set config to meet the following condition + (2 * pool_size * metastore_instances + 2 * pool_size * HS2_instances_with_embedded_metastore) = + (2 * physical_core_count + hard_disk_count). + + + + datanucleus.rdbms.initializeColumnInfo + NONE + initializeColumnInfo setting for DataNucleus; set to NONE at least on Postgres. + + + datanucleus.schema.validateTables + false + validates existing schema against code. turn this on if you want to verify existing schema + + + datanucleus.schema.validateColumns + false + validates existing schema against code. turn this on if you want to verify existing schema + + + datanucleus.schema.validateConstraints + false + validates existing schema against code. turn this on if you want to verify existing schema + + + datanucleus.storeManagerType + rdbms + metadata store type + + + datanucleus.schema.autoCreateAll + false + Auto creates necessary schema on a startup if one doesn't exist. Set this to false, after creating it once.To enable auto create also set hive.metastore.schema.verification=false. Auto creation is not recommended for production use cases, run schematool command instead. + + + hive.metastore.schema.verification + true + + Enforce metastore schema version consistency. + True: Verify that version information stored in is compatible with one from Hive jars. Also disable automatic + schema migration attempt. Users are required to manually migrate schema after Hive upgrade which ensures + proper metastore schema migration. (Default) + False: Warn if the version information stored in metastore doesn't match with one from in Hive jars. + + + + hive.metastore.schema.verification.record.version + false + + When true the current MS version is recorded in the VERSION table. If this is disabled and verification is + enabled the MS will be unusable. + + + + datanucleus.transactionIsolation + read-committed + Default transaction isolation level for identity generation. + + + datanucleus.cache.level2 + false + Use a level 2 cache. Turn this off if metadata is changed independently of Hive metastore server + + + datanucleus.cache.level2.type + none + + + + datanucleus.identifierFactory + datanucleus1 + + Name of the identifier factory to use when generating table/column names etc. + 'datanucleus1' is used for backward compatibility with DataNucleus v1 + + + + datanucleus.rdbms.useLegacyNativeValueStrategy + true + + + + datanucleus.plugin.pluginRegistryBundleCheck + LOG + Defines what happens when plugin bundles are found and are duplicated [EXCEPTION|LOG|NONE] + + + hive.metastore.batch.retrieve.max + 300 + + Maximum number of objects (tables/partitions) can be retrieved from metastore in one batch. + The higher the number, the less the number of round trips is needed to the Hive metastore server, + but it may also cause higher memory requirement at the client side. + + + + hive.metastore.batch.retrieve.table.partition.max + 1000 + Maximum number of objects that metastore internally retrieves in one batch. + + + hive.metastore.init.hooks + + + A comma separated list of hooks to be invoked at the beginning of HMSHandler initialization. + An init hook is specified as the name of Java class which extends org.apache.hadoop.hive.metastore.MetaStoreInitListener. + + + + hive.metastore.pre.event.listeners + + List of comma separated listeners for metastore events. + + + hive.metastore.event.listeners + + A comma separated list of Java classes that implement the org.apache.hadoop.hive.metastore.MetaStoreEventListener interface. The metastore event and corresponding listener method will be invoked in separate JDO transactions. Alternatively, configure hive.metastore.transactional.event.listeners to ensure both are invoked in same JDO transaction. + + + hive.metastore.transactional.event.listeners + + A comma separated list of Java classes that implement the org.apache.hadoop.hive.metastore.MetaStoreEventListener interface. Both the metastore event and corresponding listener method will be invoked in the same JDO transaction. + + + hive.metastore.event.db.listener.timetolive + 86400s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + time after which events will be removed from the database listener queue + + + + hive.metastore.authorization.storage.checks + false + + Should the metastore do authorization checks against the underlying storage (usually hdfs) + for operations like drop-partition (disallow the drop-partition if the user in + question doesn't have permissions to delete the corresponding directory + on the storage). + + + + hive.metastore.authorization.storage.check.externaltable.drop + true + + Should StorageBasedAuthorization check permission of the storage before dropping external table. + StorageBasedAuthorization already does this check for managed table. For external table however, + anyone who has read permission of the directory could drop external table, which is surprising. + The flag is set to false by default to maintain backward compatibility. + + + + hive.metastore.event.clean.freq + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Frequency at which timer task runs to purge expired events in metastore. + + + + hive.metastore.event.expiry.duration + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Duration after which events expire from events table + + + + hive.metastore.event.message.factory + org.apache.hadoop.hive.metastore.messaging.json.JSONMessageFactory + Factory class for making encoding and decoding messages in the events generated. + + + hive.metastore.execute.setugi + true + + In unsecure mode, setting this property to true will cause the metastore to execute DFS operations using + the client's reported user and group permissions. Note that this property must be set on + both the client and server sides. Further note that its best effort. + If client sets its to true and server sets it to false, client setting will be ignored. + + + + hive.metastore.partition.name.whitelist.pattern + + Partition names will be checked against this regex pattern and rejected if not matched. + + + hive.metastore.integral.jdo.pushdown + false + + Allow JDO query pushdown for integral partition columns in metastore. Off by default. This + improves metastore perf for integral columns, especially if there's a large number of partitions. + However, it doesn't work correctly with integral values that are not normalized (e.g. have + leading zeroes, like 0012). If metastore direct SQL is enabled and works, this optimization + is also irrelevant. + + + + hive.metastore.try.direct.sql + true + + Whether the Hive metastore should try to use direct SQL queries instead of the + DataNucleus for certain read paths. This can improve metastore performance when + fetching many partitions or column statistics by orders of magnitude; however, it + is not guaranteed to work on all RDBMS-es and all versions. In case of SQL failures, + the metastore will fall back to the DataNucleus, so it's safe even if SQL doesn't + work for all queries on your datastore. If all SQL queries fail (for example, your + metastore is backed by MongoDB), you might want to disable this to save the + try-and-fall-back cost. + + + + hive.metastore.direct.sql.batch.size + 0 + + Batch size for partition and other object retrieval from the underlying DB in direct + SQL. For some DBs like Oracle and MSSQL, there are hardcoded or perf-based limitations + that necessitate this. For DBs that can handle the queries, this isn't necessary and + may impede performance. -1 means no batching, 0 means automatic batching. + + + + hive.metastore.try.direct.sql.ddl + true + + Same as hive.metastore.try.direct.sql, for read statements within a transaction that + modifies metastore data. Due to non-standard behavior in Postgres, if a direct SQL + select query has incorrect syntax or something similar inside a transaction, the + entire transaction will fail and fall-back to DataNucleus will not be possible. You + should disable the usage of direct SQL inside transactions if that happens in your case. + + + + hive.direct.sql.max.query.length + 100 + + The maximum + size of a query string (in KB). + + + + hive.direct.sql.max.elements.in.clause + 1000 + + The maximum number of values in a IN clause. Once exceeded, it will be broken into + multiple OR separated IN clauses. + + + + hive.direct.sql.max.elements.values.clause + 1000 + The maximum number of values in a VALUES clause for INSERT statement. + + + hive.metastore.orm.retrieveMapNullsAsEmptyStrings + false + Thrift does not support nulls in maps, so any nulls present in maps retrieved from ORM must either be pruned or converted to empty strings. Some backing dbs such as Oracle persist empty strings as nulls, so we should set this parameter if we wish to reverse that behaviour. For others, pruning is the correct behaviour + + + hive.metastore.disallow.incompatible.col.type.changes + true + + If true (default is false), ALTER TABLE operations which change the type of a + column (say STRING) to an incompatible type (say MAP) are disallowed. + RCFile default SerDe (ColumnarSerDe) serializes the values in such a way that the + datatypes can be converted from string to any type. The map is also serialized as + a string, which can be read as a string as well. However, with any binary + serialization, this is not true. Blocking the ALTER TABLE prevents ClassCastExceptions + when subsequently trying to access old partitions. + + Primitive types like INT, STRING, BIGINT, etc., are compatible with each other and are + not blocked. + + See HIVE-4409 for more details. + + + + hive.metastore.limit.partition.request + -1 + + This limits the number of partitions that can be requested from the metastore for a given table. + The default value "-1" means no limit. + + + + hive.table.parameters.default + + Default property values for newly created tables + + + hive.ddl.createtablelike.properties.whitelist + + Table Properties to copy over when executing a Create Table Like. + + + hive.metastore.rawstore.impl + org.apache.hadoop.hive.metastore.ObjectStore + + Name of the class that implements org.apache.hadoop.hive.metastore.rawstore interface. + This class is used to store and retrieval of raw metadata objects such as table, database + + + + hive.metastore.txn.store.impl + org.apache.hadoop.hive.metastore.txn.CompactionTxnHandler + Name of class that implements org.apache.hadoop.hive.metastore.txn.TxnStore. This class is used to store and retrieve transactions and locks + + + javax.jdo.option.ConnectionDriverName + org.apache.derby.jdbc.EmbeddedDriver + Driver class name for a JDBC metastore + + + javax.jdo.PersistenceManagerFactoryClass + org.datanucleus.api.jdo.JDOPersistenceManagerFactory + class implementing the jdo persistence + + + hive.metastore.expression.proxy + org.apache.hadoop.hive.ql.optimizer.ppr.PartitionExpressionForMetastore + + + + javax.jdo.option.DetachAllOnCommit + true + Detaches all objects from session so that they can be used after transaction is committed + + + javax.jdo.option.NonTransactionalRead + true + Reads outside of transactions + + + javax.jdo.option.ConnectionUserName + APP + Username to use against metastore database + + + hive.metastore.end.function.listeners + + List of comma separated listeners for the end of metastore functions. + + + hive.metastore.partition.inherit.table.properties + + + List of comma separated keys occurring in table properties which will get inherited to newly created partitions. + * implies all the keys will get inherited. + + + + hive.metastore.filter.hook + org.apache.hadoop.hive.metastore.DefaultMetaStoreFilterHookImpl + Metastore hook class for filtering the metadata read results. If hive.security.authorization.manageris set to instance of HiveAuthorizerFactory, then this value is ignored. + + + hive.metastore.dml.events + false + If true, the metastore will be asked to fire events for DML operations + + + hive.metastore.client.drop.partitions.using.expressions + true + Choose whether dropping partitions with HCatClient pushes the partition-predicate to the metastore, or drops partitions iteratively + + + hive.metastore.aggregate.stats.cache.enabled + true + Whether aggregate stats caching is enabled or not. + + + hive.metastore.aggregate.stats.cache.size + 10000 + Maximum number of aggregate stats nodes that we will place in the metastore aggregate stats cache. + + + hive.metastore.aggregate.stats.cache.max.partitions + 10000 + Maximum number of partitions that are aggregated per cache node. + + + hive.metastore.aggregate.stats.cache.fpp + 0.01 + Maximum false positive probability for the Bloom Filter used in each aggregate stats cache node (default 1%). + + + hive.metastore.aggregate.stats.cache.max.variance + 0.01 + Maximum tolerable variance in number of partitions between a cached node and our request (default 1%). + + + hive.metastore.aggregate.stats.cache.ttl + 600s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds for a cached node to be active in the cache before they become stale. + + + + hive.metastore.aggregate.stats.cache.max.writer.wait + 5000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Number of milliseconds a writer will wait to acquire the writelock before giving up. + + + + hive.metastore.aggregate.stats.cache.max.reader.wait + 1000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Number of milliseconds a reader will wait to acquire the readlock before giving up. + + + + hive.metastore.aggregate.stats.cache.max.full + 0.9 + Maximum cache full % after which the cache cleaner thread kicks in. + + + hive.metastore.aggregate.stats.cache.clean.until + 0.8 + The cleaner thread cleans until cache reaches this % full size. + + + hive.metastore.metrics.enabled + false + Enable metrics on the metastore. + + + hive.metastore.initial.metadata.count.enabled + true + Enable a metadata count at metastore startup for metrics. + + + hive.metastore.use.SSL + false + Set this to true for using SSL encryption in HMS server. + + + hive.metastore.keystore.path + + Metastore SSL certificate keystore location. + + + hive.metastore.keystore.password + + Metastore SSL certificate keystore password. + + + hive.metastore.truststore.path + + Metastore SSL certificate truststore location. + + + hive.metastore.truststore.password + + Metastore SSL certificate truststore password. + + + hive.metadata.export.location + + + When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, + it is the location to which the metadata will be exported. The default is an empty string, which results in the + metadata being exported to the current user's home directory on HDFS. + + + + hive.metadata.move.exported.metadata.to.trash + true + + When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, + this setting determines if the metadata that is exported will subsequently be moved to the user's trash directory + alongside the dropped table data. This ensures that the metadata will be cleaned up along with the dropped table data. + + + + hive.cli.errors.ignore + false + + + + hive.cli.print.current.db + false + Whether to include the current database in the Hive prompt. + + + hive.cli.prompt + hive + + Command line prompt configuration value. Other hiveconf can be used in this configuration value. + Variable substitution will only be invoked at the Hive CLI startup. + + + + hive.cli.pretty.output.num.cols + -1 + + The number of columns to use when formatting output generated by the DESCRIBE PRETTY table_name command. + If the value of this property is -1, then Hive will use the auto-detected terminal width. + + + + hive.metastore.fs.handler.class + org.apache.hadoop.hive.metastore.HiveMetaStoreFsImpl + + + + hive.session.id + + + + + hive.session.silent + false + + + + hive.session.history.enabled + false + Whether to log Hive query, query plan, runtime statistics etc. + + + hive.query.string + + Query being executed (might be multiple per a session) + + + hive.query.id + + ID for query being executed (might be multiple per a session) + + + hive.jobname.length + 50 + max jobname length + + + hive.jar.path + + The location of hive_cli.jar that is used when submitting jobs in a separate jvm. + + + hive.aux.jars.path + + The location of the plugin jars that contain implementations of user defined functions and serdes. + + + hive.reloadable.aux.jars.path + + + The locations of the plugin jars, which can be a comma-separated folders or jars. Jars can be renewed + by executing reload command. And these jars can be used as the auxiliary classes like creating a UDF or SerDe. + + + + hive.added.files.path + + This an internal parameter. + + + hive.added.jars.path + + This an internal parameter. + + + hive.added.archives.path + + This an internal parameter. + + + hive.auto.progress.timeout + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + How long to run autoprogressor for the script/UDTF operators. + Set to 0 for forever. + + + + hive.script.auto.progress + false + + Whether Hive Transform/Map/Reduce Clause should automatically send progress information to TaskTracker + to avoid the task getting killed because of inactivity. Hive sends progress information when the script is + outputting to stderr. This option removes the need of periodically producing stderr messages, + but users should be cautious because this may prevent infinite loops in the scripts to be killed by TaskTracker. + + + + hive.script.operator.id.env.var + HIVE_SCRIPT_OPERATOR_ID + + Name of the environment variable that holds the unique script operator ID in the user's + transform function (the custom mapper/reducer that the user has specified in the query) + + + + hive.script.operator.truncate.env + false + Truncate each environment variable for external script in scripts operator to 20KB (to fit system limits) + + + hive.script.operator.env.blacklist + hive.txn.valid.txns,hive.script.operator.env.blacklist + Comma separated list of keys from the configuration file not to convert to environment variables when envoking the script operator + + + hive.strict.checks.large.query + false + + Enabling strict large query checks disallows the following: + Orderby without limit. + No partition being picked up for a query against partitioned table. + Note that these checks currently do not consider data size, only the query pattern. + + + + hive.strict.checks.type.safety + true + + Enabling strict type safety checks disallows the following: + Comparing bigints and strings. + Comparing bigints and doubles. + + + + hive.strict.checks.cartesian.product + true + + Enabling strict Cartesian join checks disallows the following: + Cartesian product (cross join). + + + + hive.strict.checks.bucketing + true + + Enabling strict bucketing checks disallows the following: + Load into bucketed tables. + + + + hive.mapred.mode + + Deprecated; use hive.strict.checks.* settings instead. + + + hive.alias + + + + + hive.map.aggr + true + Whether to use map-side aggregation in Hive Group By queries + + + hive.groupby.skewindata + false + Whether there is skew in data to optimize group by queries + + + hive.join.emit.interval + 1000 + How many rows in the right-most join operand Hive should buffer before emitting the join result. + + + hive.join.cache.size + 25000 + How many rows in the joining tables (except the streaming table) should be cached in memory. + + + hive.cbo.enable + true + Flag to control enabling Cost Based Optimizations using Calcite framework. + + + hive.cbo.cnf.maxnodes + -1 + When converting to conjunctive normal form (CNF), fail ifthe expression exceeds this threshold; the threshold is expressed in terms of number of nodes (leaves andinterior nodes). -1 to not set up a threshold. + + + hive.cbo.returnpath.hiveop + false + Flag to control calcite plan to hive operator conversion + + + hive.cbo.costmodel.extended + false + Flag to control enabling the extended cost model based onCPU, IO and cardinality. Otherwise, the cost model is based on cardinality. + + + hive.cbo.costmodel.cpu + 0.000001 + Default cost of a comparison + + + hive.cbo.costmodel.network + 150.0 + Default cost of a transfering a byte over network; expressed as multiple of CPU cost + + + hive.cbo.costmodel.local.fs.write + 4.0 + Default cost of writing a byte to local FS; expressed as multiple of NETWORK cost + + + hive.cbo.costmodel.local.fs.read + 4.0 + Default cost of reading a byte from local FS; expressed as multiple of NETWORK cost + + + hive.cbo.costmodel.hdfs.write + 10.0 + Default cost of writing a byte to HDFS; expressed as multiple of Local FS write cost + + + hive.cbo.costmodel.hdfs.read + 1.5 + Default cost of reading a byte from HDFS; expressed as multiple of Local FS read cost + + + hive.cbo.show.warnings + true + Toggle display of CBO warnings like missing column stats + + + hive.transpose.aggr.join + false + push aggregates through join + + + hive.optimize.semijoin.conversion + true + convert group by followed by inner equi join into semijoin + + + hive.order.columnalignment + true + Flag to control whether we want to try to aligncolumns in operators such as Aggregate or Join so that we try to reduce the number of shuffling stages + + + hive.materializedview.rewriting + false + Whether to try to rewrite queries using the materialized views enabled for rewriting + + + hive.materializedview.fileformat + ORC + + Expects one of [none, textfile, sequencefile, rcfile, orc]. + Default file format for CREATE MATERIALIZED VIEW statement + + + + hive.materializedview.serde + org.apache.hadoop.hive.ql.io.orc.OrcSerde + Default SerDe used for materialized views + + + hive.mapjoin.bucket.cache.size + 100 + + + + hive.mapjoin.optimized.hashtable + true + + Whether Hive should use memory-optimized hash table for MapJoin. + Only works on Tez and Spark, because memory-optimized hashtable cannot be serialized. + + + + hive.mapjoin.optimized.hashtable.probe.percent + 0.5 + Probing space percentage of the optimized hashtable + + + hive.mapjoin.hybridgrace.hashtable + true + Whether to use hybridgrace hash join as the join method for mapjoin. Tez only. + + + hive.mapjoin.hybridgrace.memcheckfrequency + 1024 + For hybrid grace hash join, how often (how many rows apart) we check if memory is full. This number should be power of 2. + + + hive.mapjoin.hybridgrace.minwbsize + 524288 + For hybrid graceHash join, the minimum write buffer size used by optimized hashtable. Default is 512 KB. + + + hive.mapjoin.hybridgrace.minnumpartitions + 16 + ForHybrid grace hash join, the minimum number of partitions to create. + + + hive.mapjoin.optimized.hashtable.wbsize + 8388608 + + Optimized hashtable (see hive.mapjoin.optimized.hashtable) uses a chain of buffers to + store data. This is one buffer size. HT may be slightly faster if this is larger, but for small + joins unnecessary memory will be allocated and then trimmed. + + + + hive.mapjoin.hybridgrace.bloomfilter + true + Whether to use BloomFilter in Hybrid grace hash join to minimize unnecessary spilling. + + + hive.smbjoin.cache.rows + 10000 + How many rows with the same key value should be cached in memory per smb joined table. + + + hive.groupby.mapaggr.checkinterval + 100000 + Number of rows after which size of the grouping keys/aggregation classes is performed + + + hive.map.aggr.hash.percentmemory + 0.5 + Portion of total memory to be used by map-side group aggregation hash table + + + hive.mapjoin.followby.map.aggr.hash.percentmemory + 0.3 + Portion of total memory to be used by map-side group aggregation hash table, when this group by is followed by map join + + + hive.map.aggr.hash.force.flush.memory.threshold + 0.9 + + The max memory to be used by map-side group aggregation hash table. + If the memory usage is higher than this number, force to flush data + + + + hive.map.aggr.hash.min.reduction + 0.5 + + Hash aggregation will be turned off if the ratio between hash table size and input rows is bigger than this number. + Set to 1 to make sure hash aggregation is never turned off. + + + + hive.multigroupby.singlereducer + true + + Whether to optimize multi group by query to generate single M/R job plan. If the multi group by query has + common group by keys, it will be optimized to generate single M/R job. + + + + hive.map.groupby.sorted + true + + If the bucketing/sorting properties of the table exactly match the grouping key, whether to perform + the group by in the mapper by using BucketizedHiveInputFormat. The only downside to this + is that it limits the number of mappers to the number of files. + + + + hive.groupby.position.alias + false + Whether to enable using Column Position Alias in Group By + + + hive.orderby.position.alias + true + Whether to enable using Column Position Alias in Order By + + + hive.groupby.orderby.position.alias + false + + Whether to enable using Column Position Alias in Group By or Order By (deprecated). + Use hive.orderby.position.alias or hive.groupby.position.alias instead + + + + hive.new.job.grouping.set.cardinality + 30 + + Whether a new map-reduce job should be launched for grouping sets/rollups/cubes. + For a query like: select a, b, c, count(1) from T group by a, b, c with rollup; + 4 rows are created per row: (a, b, c), (a, b, null), (a, null, null), (null, null, null). + This can lead to explosion across map-reduce boundary if the cardinality of T is very high, + and map-side aggregation does not do a very good job. + + This parameter decides if Hive should add an additional map-reduce job. If the grouping set + cardinality (4 in the example above), is more than this value, a new MR job is added under the + assumption that the original group by will reduce the data size. + + + + hive.groupby.limit.extrastep + true + + This parameter decides if Hive should + create new MR job for sorting final output + + + + hive.exec.copyfile.maxnumfiles + 1 + Maximum number of files Hive uses to do sequential HDFS copies between directories.Distributed copies (distcp) will be used instead for larger numbers of files so that copies can be done faster. + + + hive.exec.copyfile.maxsize + 33554432 + Maximum file size (in bytes) that Hive uses to do single HDFS copies between directories.Distributed copies (distcp) will be used instead for bigger files so that copies can be done faster. + + + hive.udtf.auto.progress + false + + Whether Hive should automatically send progress information to TaskTracker + when using UDTF's to prevent the task getting killed because of inactivity. Users should be cautious + because this may prevent TaskTracker from killing tasks with infinite loops. + + + + hive.default.fileformat + TextFile + + Expects one of [textfile, sequencefile, rcfile, orc, parquet]. + Default file format for CREATE TABLE statement. Users can explicitly override it by CREATE TABLE ... STORED AS [FORMAT] + + + + hive.default.fileformat.managed + none + + Expects one of [none, textfile, sequencefile, rcfile, orc, parquet]. + Default file format for CREATE TABLE statement applied to managed tables only. External tables will be + created with format specified by hive.default.fileformat. Leaving this null will result in using hive.default.fileformat + for all tables. + + + + hive.query.result.fileformat + SequenceFile + + Expects one of [textfile, sequencefile, rcfile, llap]. + Default file format for storing result of the query. + + + + hive.fileformat.check + true + Whether to check file format or not when loading data files + + + hive.default.rcfile.serde + org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe + The default SerDe Hive will use for the RCFile format + + + hive.default.serde + org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + The default SerDe Hive will use for storage formats that do not specify a SerDe. + + + hive.serdes.using.metastore.for.schema + org.apache.hadoop.hive.ql.io.orc.OrcSerde,org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe,org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe,org.apache.hadoop.hive.serde2.dynamic_type.DynamicSerDe,org.apache.hadoop.hive.serde2.MetadataTypedColumnsetSerDe,org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe,org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe,org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + SerDes retrieving schema from metastore. This is an internal parameter. + + + hive.querylog.location + ${system:java.io.tmpdir}/${system:user.name} + Location of Hive run time structured log file + + + hive.querylog.enable.plan.progress + true + + Whether to log the plan's progress every time a job's progress is checked. + These logs are written to the location specified by hive.querylog.location + + + + hive.querylog.plan.progress.interval + 60000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The interval to wait between logging the plan's progress. + If there is a whole number percentage change in the progress of the mappers or the reducers, + the progress is logged regardless of this value. + The actual interval will be the ceiling of (this value divided by the value of + hive.exec.counters.pull.interval) multiplied by the value of hive.exec.counters.pull.interval + I.e. if it is not divide evenly by the value of hive.exec.counters.pull.interval it will be + logged less frequently than specified. + This only has an effect if hive.querylog.enable.plan.progress is set to true. + + + + hive.script.serde + org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + The default SerDe for transmitting input data to and reading output data from the user scripts. + + + hive.script.recordreader + org.apache.hadoop.hive.ql.exec.TextRecordReader + The default record reader for reading data from the user scripts. + + + hive.script.recordwriter + org.apache.hadoop.hive.ql.exec.TextRecordWriter + The default record writer for writing data to the user scripts. + + + hive.transform.escape.input + false + + This adds an option to escape special chars (newlines, carriage returns and + tabs) when they are passed to the user script. This is useful if the Hive tables + can contain data that contains special characters. + + + + hive.binary.record.max.length + 1000 + + Read from a binary stream and treat each hive.binary.record.max.length bytes as a record. + The last record before the end of stream can have less than hive.binary.record.max.length bytes + + + + hive.mapred.local.mem + 0 + mapper/reducer memory in local mode + + + hive.mapjoin.smalltable.filesize + 25000000 + + The threshold for the input file size of the small tables; if the file size is smaller + than this threshold, it will try to convert the common join into map join + + + + hive.exec.schema.evolution + true + Use schema evolution to convert self-describing file format's data to the schema desired by the reader. + + + hive.transactional.events.mem + 10000000 + + Vectorized ACID readers can often load all the delete events from all the delete deltas + into memory to optimize for performance. To prevent out-of-memory errors, this is a rough heuristic + that limits the total number of delete events that can be loaded into memory at once. + Roughly it has been set to 10 million delete events per bucket (~160 MB). + + + + hive.sample.seednumber + 0 + A number used to percentage sampling. By changing this number, user will change the subsets of data sampled. + + + hive.test.mode + false + Whether Hive is running in test mode. If yes, it turns on sampling and prefixes the output tablename. + + + hive.test.mode.prefix + test_ + In test mode, specfies prefixes for the output table + + + hive.test.mode.samplefreq + 32 + + In test mode, specfies sampling frequency for table, which is not bucketed, + For example, the following query: + INSERT OVERWRITE TABLE dest SELECT col1 from src + would be converted to + INSERT OVERWRITE TABLE test_dest + SELECT col1 from src TABLESAMPLE (BUCKET 1 out of 32 on rand(1)) + + + + hive.test.mode.nosamplelist + + In test mode, specifies comma separated table names which would not apply sampling + + + hive.test.dummystats.aggregator + + internal variable for test + + + hive.test.dummystats.publisher + + internal variable for test + + + hive.test.currenttimestamp + + current timestamp for test + + + hive.test.rollbacktxn + false + For testing only. Will mark every ACID transaction aborted + + + hive.test.fail.compaction + false + For testing only. Will cause CompactorMR to fail. + + + hive.test.fail.heartbeater + false + For testing only. Will cause Heartbeater to fail. + + + hive.merge.mapfiles + true + Merge small files at the end of a map-only job + + + hive.merge.mapredfiles + false + Merge small files at the end of a map-reduce job + + + hive.merge.tezfiles + false + Merge small files at the end of a Tez DAG + + + hive.merge.sparkfiles + false + Merge small files at the end of a Spark DAG Transformation + + + hive.merge.size.per.task + 256000000 + Size of merged files at the end of the job + + + hive.merge.smallfiles.avgsize + 16000000 + + When the average output file size of a job is less than this number, Hive will start an additional + map-reduce job to merge the output files into bigger files. This is only done for map-only jobs + if hive.merge.mapfiles is true, and for map-reduce jobs if hive.merge.mapredfiles is true. + + + + hive.merge.rcfile.block.level + true + + + + hive.merge.orcfile.stripe.level + true + + When hive.merge.mapfiles, hive.merge.mapredfiles or hive.merge.tezfiles is enabled + while writing a table with ORC file format, enabling this config will do stripe-level + fast merge for small ORC files. Note that enabling this config will not honor the + padding tolerance config (hive.exec.orc.block.padding.tolerance). + + + + hive.exec.rcfile.use.explicit.header + true + + If this is set the header for RCFiles will simply be RCF. If this is not + set the header will be that borrowed from sequence files, e.g. SEQ- followed + by the input and output RCFile formats. + + + + hive.exec.rcfile.use.sync.cache + true + + + + hive.io.rcfile.record.interval + 2147483647 + + + + hive.io.rcfile.column.number.conf + 0 + + + + hive.io.rcfile.tolerate.corruptions + false + + + + hive.io.rcfile.record.buffer.size + 4194304 + + + + parquet.memory.pool.ratio + 0.5 + + Maximum fraction of heap that can be used by Parquet file writers in one task. + It is for avoiding OutOfMemory error in tasks. Work with Parquet 1.6.0 and above. + This config parameter is defined in Parquet, so that it does not start with 'hive.'. + + + + hive.parquet.timestamp.skip.conversion + true + Current Hive implementation of parquet stores timestamps to UTC, this flag allows skipping of the conversionon reading parquet files from other tools + + + hive.int.timestamp.conversion.in.seconds + false + + Boolean/tinyint/smallint/int/bigint value is interpreted as milliseconds during the timestamp conversion. + Set this flag to true to interpret the value as seconds to be consistent with float/double. + + + + hive.exec.orc.base.delta.ratio + 8 + + The ratio of base writer and + delta writer in terms of STRIPE_SIZE and BUFFER_SIZE. + + + + hive.exec.orc.split.strategy + HYBRID + + Expects one of [hybrid, bi, etl]. + This is not a user level config. BI strategy is used when the requirement is to spend less time in split generation as opposed to query execution (split generation does not read or cache file footers). ETL strategy is used when spending little more time in split generation is acceptable (split generation reads and caches file footers). HYBRID chooses between the above strategies based on heuristics. + + + + hive.orc.splits.ms.footer.cache.enabled + false + Whether to enable using file metadata cache in metastore for ORC file footers. + + + hive.orc.splits.ms.footer.cache.ppd.enabled + true + + Whether to enable file footer cache PPD (hive.orc.splits.ms.footer.cache.enabled + must also be set to true for this to work). + + + + hive.orc.splits.include.file.footer + false + + If turned on splits generated by orc will include metadata about the stripes in the file. This + data is read remotely (from the client or HS2 machine) and sent to all the tasks. + + + + hive.orc.splits.directory.batch.ms + 0 + + How long, in ms, to wait to batch input directories for processing during ORC split + generation. 0 means process directories individually. This can increase the number of + metastore calls if metastore metadata cache is used. + + + + hive.orc.splits.include.fileid + true + Include file ID in splits on file systems that support it. + + + hive.orc.splits.allow.synthetic.fileid + true + Allow synthetic file ID in splits on file systems that don't have a native one. + + + hive.orc.cache.stripe.details.mem.size + 256Mb + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + Maximum size of orc splits cached in the client. + + + + hive.orc.compute.splits.num.threads + 10 + How many threads orc should use to create splits in parallel. + + + hive.orc.cache.use.soft.references + false + + By default, the cache that ORC input format uses to store orc file footer use hard + references for the cached object. Setting this to true can help avoid out of memory + issues under memory pressure (in some cases) at the cost of slight unpredictability in + overall query performance. + + + + hive.io.sarg.cache.max.weight.mb + 10 + The max weight allowed for the SearchArgument Cache. By default, the cache allows a max-weight of 10MB, after which entries will be evicted. + + + hive.lazysimple.extended_boolean_literal + false + + LazySimpleSerde uses this property to determine if it treats 'T', 't', 'F', 'f', + '1', and '0' as extened, legal boolean literal, in addition to 'TRUE' and 'FALSE'. + The default is false, which means only 'TRUE' and 'FALSE' are treated as legal + boolean literal. + + + + hive.optimize.skewjoin + false + + Whether to enable skew join optimization. + The algorithm is as follows: At runtime, detect the keys with a large skew. Instead of + processing those keys, store them temporarily in an HDFS directory. In a follow-up map-reduce + job, process those skewed keys. The same key need not be skewed for all the tables, and so, + the follow-up map-reduce job (for the skewed keys) would be much faster, since it would be a + map-join. + + + + hive.optimize.dynamic.partition.hashjoin + false + + Whether to enable dynamically partitioned hash join optimization. + This setting is also dependent on enabling hive.auto.convert.join + + + + hive.auto.convert.join + true + Whether Hive enables the optimization about converting common join into mapjoin based on the input file size + + + hive.auto.convert.join.noconditionaltask + true + + Whether Hive enables the optimization about converting common join into mapjoin based on the input file size. + If this parameter is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than the + specified size, the join is directly converted to a mapjoin (there is no conditional task). + + + + hive.auto.convert.join.noconditionaltask.size + 10000000 + + If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect. + However, if it is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than this size, + the join is directly converted to a mapjoin(there is no conditional task). The default is 10MB + + + + hive.auto.convert.join.use.nonstaged + false + + For conditional joins, if input stream from a small alias can be directly applied to join operator without + filtering or projection, the alias need not to be pre-staged in distributed cache via mapred local task. + Currently, this is not working with vectorization or tez execution engine. + + + + hive.skewjoin.key + 100000 + + Determine if we get a skew key in join. If we see more than the specified number of rows with the same key in join operator, + we think the key as a skew join key. + + + + hive.skewjoin.mapjoin.map.tasks + 10000 + + Determine the number of map task used in the follow up map join job for a skew join. + It should be used together with hive.skewjoin.mapjoin.min.split to perform a fine grained control. + + + + hive.skewjoin.mapjoin.min.split + 33554432 + + Determine the number of map task at most used in the follow up map join job for a skew join by specifying + the minimum split size. It should be used together with hive.skewjoin.mapjoin.map.tasks to perform a fine grained control. + + + + hive.heartbeat.interval + 1000 + Send a heartbeat after this interval - used by mapjoin and filter operators + + + hive.limit.row.max.size + 100000 + When trying a smaller subset of data for simple LIMIT, how much size we need to guarantee each row to have at least. + + + hive.limit.optimize.limit.file + 10 + When trying a smaller subset of data for simple LIMIT, maximum number of files we can sample. + + + hive.limit.optimize.enable + false + Whether to enable to optimization to trying a smaller subset of data for simple LIMIT first. + + + hive.limit.optimize.fetch.max + 50000 + + Maximum number of rows allowed for a smaller subset of data for simple LIMIT, if it is a fetch query. + Insert queries are not restricted by this limit. + + + + hive.limit.pushdown.memory.usage + 0.1 + + Expects value between 0.0f and 1.0f. + The fraction of available memory to be used for buffering rows in Reducesink operator for limit pushdown optimization. + + + + hive.limit.query.max.table.partition + -1 + + This controls how many partitions can be scanned for each partitioned table. + The default value "-1" means no limit. (DEPRECATED: Please use hive.metastore.limit.partition.request in the metastore instead.) + + + + hive.auto.convert.join.hashtable.max.entries + 40000000 + + If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect. + However, if it is on, and the predicated number of entries in hashtable for a given join + input is larger than this number, the join will not be converted to a mapjoin. + The value "-1" means no limit. + + + + hive.hashtable.key.count.adjustment + 1.0 + Adjustment to mapjoin hashtable size derived from table and column statistics; the estimate of the number of keys is divided by this value. If the value is 0, statistics are not usedand hive.hashtable.initialCapacity is used instead. + + + hive.hashtable.initialCapacity + 100000 + Initial capacity of mapjoin hashtable if statistics are absent, or if hive.hashtable.key.count.adjustment is set to 0 + + + hive.hashtable.loadfactor + 0.75 + + + + hive.mapjoin.followby.gby.localtask.max.memory.usage + 0.55 + + This number means how much memory the local task can take to hold the key/value into an in-memory hash table + when this map join is followed by a group by. If the local task's memory usage is more than this number, + the local task will abort by itself. It means the data of the small table is too large to be held in memory. + + + + hive.mapjoin.localtask.max.memory.usage + 0.9 + + This number means how much memory the local task can take to hold the key/value into an in-memory hash table. + If the local task's memory usage is more than this number, the local task will abort by itself. + It means the data of the small table is too large to be held in memory. + + + + hive.mapjoin.check.memory.rows + 100000 + The number means after how many rows processed it needs to check the memory usage + + + hive.debug.localtask + false + + + + hive.input.format + org.apache.hadoop.hive.ql.io.CombineHiveInputFormat + The default input format. Set this to HiveInputFormat if you encounter problems with CombineHiveInputFormat. + + + hive.tez.input.format + org.apache.hadoop.hive.ql.io.HiveInputFormat + The default input format for tez. Tez groups splits in the AM. + + + hive.tez.container.size + -1 + By default Tez will spawn containers of the size of a mapper. This can be used to overwrite. + + + hive.tez.cpu.vcores + -1 + + By default Tez will ask for however many cpus map-reduce is configured to use per container. + This can be used to overwrite. + + + + hive.tez.java.opts + + By default Tez will use the Java options from map tasks. This can be used to overwrite. + + + hive.tez.log.level + INFO + + The log level to use for tasks executing as part of the DAG. + Used only if hive.tez.java.opts is used to configure Java options. + + + + hive.tez.hs2.user.access + true + Whether to grant access to the hs2/hive user for queries + + + hive.query.name + + + This named is used by Tez to set the dag name. This name in turn will appear on + the Tez UI representing the work that was done. + + + + hive.optimize.bucketingsorting + true + + Don't create a reducer for enforcing + bucketing/sorting for queries of the form: + insert overwrite table T2 select * from T1; + where T1 and T2 are bucketed/sorted by the same keys into the same number of buckets. + + + + hive.mapred.partitioner + org.apache.hadoop.hive.ql.io.DefaultHivePartitioner + + + + hive.enforce.sortmergebucketmapjoin + false + If the user asked for sort-merge bucketed map-side join, and it cannot be performed, should the query fail or not ? + + + hive.enforce.bucketmapjoin + false + + If the user asked for bucketed map-side join, and it cannot be performed, + should the query fail or not ? For example, if the buckets in the tables being joined are + not a multiple of each other, bucketed map-side join cannot be performed, and the + query will fail if hive.enforce.bucketmapjoin is set to true. + + + + hive.auto.convert.sortmerge.join + false + Will the join be automatically converted to a sort-merge join, if the joined tables pass the criteria for sort-merge join. + + + hive.auto.convert.sortmerge.join.reduce.side + true + Whether hive.auto.convert.sortmerge.join (if enabled) should be applied to reduce side. + + + hive.auto.convert.sortmerge.join.bigtable.selection.policy + org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ + + The policy to choose the big table for automatic conversion to sort-merge join. + By default, the table with the largest partitions is assigned the big table. All policies are: + . based on position of the table - the leftmost table is selected + org.apache.hadoop.hive.ql.optimizer.LeftmostBigTableSMJ. + . based on total size (all the partitions selected in the query) of the table + org.apache.hadoop.hive.ql.optimizer.TableSizeBasedBigTableSelectorForAutoSMJ. + . based on average size (all the partitions selected in the query) of the table + org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ. + New policies can be added in future. + + + + hive.auto.convert.sortmerge.join.to.mapjoin + false + + If hive.auto.convert.sortmerge.join is set to true, and a join was converted to a sort-merge join, + this parameter decides whether each table should be tried as a big table, and effectively a map-join should be + tried. That would create a conditional task with n+1 children for a n-way join (1 child for each table as the + big table), and the backup task will be the sort-merge join. In some cases, a map-join would be faster than a + sort-merge join, if there is no advantage of having the output bucketed and sorted. For example, if a very big sorted + and bucketed table with few files (say 10 files) are being joined with a very small sorter and bucketed table + with few files (10 files), the sort-merge join will only use 10 mappers, and a simple map-only join might be faster + if the complete small table can fit in memory, and a map-join can be performed. + + + + hive.exec.script.trust + false + + + + hive.exec.rowoffset + false + Whether to provide the row offset virtual column + + + hive.optimize.index.filter + false + Whether to enable automatic use of indexes + + + hive.optimize.index.autoupdate + false + Whether to update stale indexes automatically + + + hive.optimize.ppd + true + Whether to enable predicate pushdown + + + hive.optimize.ppd.windowing + true + Whether to enable predicate pushdown through windowing + + + hive.ppd.recognizetransivity + true + Whether to transitively replicate predicate filters over equijoin conditions. + + + hive.ppd.remove.duplicatefilters + true + + During query optimization, filters may be pushed down in the operator tree. + If this config is true only pushed down filters remain in the operator tree, + and the original filter is removed. If this config is false, the original filter + is also left in the operator tree at the original place. + + + + hive.optimize.point.lookup + true + Whether to transform OR clauses in Filter operators into IN clauses + + + hive.optimize.point.lookup.min + 31 + Minimum number of OR clauses needed to transform into IN clauses + + + hive.optimize.partition.columns.separate + true + Extract partition columns from IN clauses + + + hive.optimize.constant.propagation + true + Whether to enable constant propagation optimizer + + + hive.optimize.remove.identity.project + true + Removes identity project from operator tree + + + hive.optimize.metadataonly + false + + Whether to eliminate scans of the tables from which no columns are selected. Note + that, when selecting from empty tables with data files, this can produce incorrect + results, so it's disabled by default. It works correctly for normal tables. + + + + hive.optimize.null.scan + true + Dont scan relations which are guaranteed to not generate any rows + + + hive.optimize.ppd.storage + true + Whether to push predicates down to storage handlers + + + hive.optimize.groupby + true + Whether to enable the bucketed group by from bucketed partitions/tables. + + + hive.optimize.bucketmapjoin + false + Whether to try bucket mapjoin + + + hive.optimize.bucketmapjoin.sortedmerge + false + Whether to try sorted bucket merge map join + + + hive.optimize.reducededuplication + true + + Remove extra map-reduce jobs if the data is already clustered by the same key which needs to be used again. + This should always be set to true. Since it is a new feature, it has been made configurable. + + + + hive.optimize.reducededuplication.min.reducer + 4 + + Reduce deduplication merges two RSs by moving key/parts/reducer-num of the child RS to parent RS. + That means if reducer-num of the child RS is fixed (order by or forced bucketing) and small, it can make very slow, single MR. + The optimization will be automatically disabled if number of reducers would be less than specified value. + + + + hive.optimize.sort.dynamic.partition + false + + When enabled dynamic partitioning column will be globally sorted. + This way we can keep only one record writer open for each partition value + in the reducer thereby reducing the memory pressure on reducers. + + + + hive.optimize.sampling.orderby + false + Uses sampling on order-by clause for parallel execution. + + + hive.optimize.sampling.orderby.number + 1000 + Total number of samples to be obtained. + + + hive.optimize.sampling.orderby.percent + 0.1 + + Expects value between 0.0f and 1.0f. + Probability with which a row will be chosen. + + + + hive.optimize.distinct.rewrite + true + When applicable this optimization rewrites distinct aggregates from a single stage to multi-stage aggregation. This may not be optimal in all cases. Ideally, whether to trigger it or not should be cost based decision. Until Hive formalizes cost model for this, this is config driven. + + + hive.optimize.union.remove + false + + Whether to remove the union and push the operators between union and the filesink above union. + This avoids an extra scan of the output by union. This is independently useful for union + queries, and specially useful when hive.optimize.skewjoin.compiletime is set to true, since an + extra union is inserted. + + The merge is triggered if either of hive.merge.mapfiles or hive.merge.mapredfiles is set to true. + If the user has set hive.merge.mapfiles to true and hive.merge.mapredfiles to false, the idea was the + number of reducers are few, so the number of files anyway are small. However, with this optimization, + we are increasing the number of files possibly by a big margin. So, we merge aggressively. + + + + hive.optimize.correlation + false + exploit intra-query correlations. + + + hive.optimize.limittranspose + false + + Whether to push a limit through left/right outer join or union. If the value is true and the size of the outer + input is reduced enough (as specified in hive.optimize.limittranspose.reduction), the limit is pushed + to the outer input or union; to remain semantically correct, the limit is kept on top of the join or the union too. + + + + hive.optimize.limittranspose.reductionpercentage + 1.0 + + When hive.optimize.limittranspose is true, this variable specifies the minimal reduction of the + size of the outer input of the join or input of the union that we should get in order to apply the rule. + + + + hive.optimize.limittranspose.reductiontuples + 0 + + When hive.optimize.limittranspose is true, this variable specifies the minimal reduction in the + number of tuples of the outer input of the join or the input of the union that you should get in order to apply the rule. + + + + hive.optimize.filter.stats.reduction + false + + Whether to simplify comparison + expressions in filter operators using column stats + + + + hive.optimize.skewjoin.compiletime + false + + Whether to create a separate plan for skewed keys for the tables in the join. + This is based on the skewed keys stored in the metadata. At compile time, the plan is broken + into different joins: one for the skewed keys, and the other for the remaining keys. And then, + a union is performed for the 2 joins generated above. So unless the same skewed key is present + in both the joined tables, the join for the skewed key will be performed as a map-side join. + + The main difference between this parameter and hive.optimize.skewjoin is that this parameter + uses the skew information stored in the metastore to optimize the plan at compile time itself. + If there is no skew information in the metadata, this parameter will not have any affect. + Both hive.optimize.skewjoin.compiletime and hive.optimize.skewjoin should be set to true. + Ideally, hive.optimize.skewjoin should be renamed as hive.optimize.skewjoin.runtime, but not doing + so for backward compatibility. + + If the skew information is correctly stored in the metadata, hive.optimize.skewjoin.compiletime + would change the query plan to take care of it, and hive.optimize.skewjoin will be a no-op. + + + + hive.optimize.cte.materialize.threshold + -1 + + If the number of references to a CTE clause exceeds this threshold, Hive will materialize it + before executing the main query block. -1 will disable this feature. + + + + hive.optimize.index.filter.compact.minsize + 5368709120 + Minimum size (in bytes) of the inputs on which a compact index is automatically used. + + + hive.optimize.index.filter.compact.maxsize + -1 + Maximum size (in bytes) of the inputs on which a compact index is automatically used. A negative number is equivalent to infinity. + + + hive.index.compact.query.max.entries + 10000000 + The maximum number of index entries to read during a query that uses the compact index. Negative value is equivalent to infinity. + + + hive.index.compact.query.max.size + 10737418240 + The maximum number of bytes that a query using the compact index can read. Negative value is equivalent to infinity. + + + hive.index.compact.binary.search + true + Whether or not to use a binary search to find the entries in an index table that match the filter, where possible + + + hive.stats.autogather + true + A flag to gather statistics (only basic) automatically during the INSERT OVERWRITE command. + + + hive.stats.column.autogather + false + A flag to gather column statistics automatically. + + + hive.stats.dbclass + fs + + Expects one of the pattern in [custom, fs]. + The storage that stores temporary Hive statistics. In filesystem based statistics collection ('fs'), + each task writes statistics it has collected in a file on the filesystem, which will be aggregated + after the job has finished. Supported values are fs (filesystem) and custom as defined in StatsSetupConst.java. + + + + hive.stats.default.publisher + + The Java class (implementing the StatsPublisher interface) that is used by default if hive.stats.dbclass is custom type. + + + hive.stats.default.aggregator + + The Java class (implementing the StatsAggregator interface) that is used by default if hive.stats.dbclass is custom type. + + + hive.stats.atomic + false + whether to update metastore stats only if all stats are available + + + hive.client.stats.counters + + + Subset of counters that should be of interest for hive.client.stats.publishers (when one wants to limit their publishing). + Non-display names should be used + + + + hive.stats.reliable + false + + Whether queries will fail because stats cannot be collected completely accurately. + If this is set to true, reading/writing from/into a partition may fail because the stats + could not be computed accurately. + + + + hive.analyze.stmt.collect.partlevel.stats + true + analyze table T compute statistics for columns. Queries like these should compute partitionlevel stats for partitioned table even when no part spec is specified. + + + hive.stats.gather.num.threads + 10 + + Number of threads used by partialscan/noscan analyze command for partitioned tables. + This is applicable only for file formats that implement StatsProvidingRecordReader (like ORC). + + + + hive.stats.collect.tablekeys + false + + Whether join and group by keys on tables are derived and maintained in the QueryPlan. + This is useful to identify how tables are accessed and to determine if they should be bucketed. + + + + hive.stats.collect.scancols + false + + Whether column accesses are tracked in the QueryPlan. + This is useful to identify how tables are accessed and to determine if there are wasted columns that can be trimmed. + + + + hive.stats.ndv.error + 20.0 + + Standard error expressed in percentage. Provides a tradeoff between accuracy and compute cost. + A lower value for error indicates higher accuracy and a higher compute cost. + + + + hive.metastore.stats.ndv.tuner + 0.0 + + Provides a tunable parameter between the lower bound and the higher bound of ndv for aggregate ndv across all the partitions. + The lower bound is equal to the maximum of ndv of all the partitions. The higher bound is equal to the sum of ndv of all the partitions. + Its value should be between 0.0 (i.e., choose lower bound) and 1.0 (i.e., choose higher bound) + + + + hive.metastore.stats.ndv.densityfunction + false + Whether to use density function to estimate the NDV for the whole table based on the NDV of partitions + + + hive.stats.max.variable.length + 100 + + To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), + average row size is multiplied with the total number of rows coming out of each operator. + Average row size is computed from average column size of all columns in the row. In the absence + of column statistics, for variable length columns (like string, bytes etc.), this value will be + used. For fixed length columns their corresponding Java equivalent sizes are used + (float - 4 bytes, double - 8 bytes etc.). + + + + hive.stats.list.num.entries + 10 + + To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), + average row size is multiplied with the total number of rows coming out of each operator. + Average row size is computed from average column size of all columns in the row. In the absence + of column statistics and for variable length complex columns like list, the average number of + entries/values can be specified using this config. + + + + hive.stats.map.num.entries + 10 + + To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), + average row size is multiplied with the total number of rows coming out of each operator. + Average row size is computed from average column size of all columns in the row. In the absence + of column statistics and for variable length complex columns like map, the average number of + entries/values can be specified using this config. + + + + hive.stats.fetch.partition.stats + true + + Annotation of operator tree with statistics information requires partition level basic + statistics like number of rows, data size and file size. Partition statistics are fetched from + metastore. Fetching partition statistics for each needed partition can be expensive when the + number of partitions is high. This flag can be used to disable fetching of partition statistics + from metastore. When this flag is disabled, Hive will make calls to filesystem to get file sizes + and will estimate the number of rows from row schema. + + + + hive.stats.fetch.column.stats + false + + Annotation of operator tree with statistics information requires column statistics. + Column statistics are fetched from metastore. Fetching column statistics for each needed column + can be expensive when the number of columns is high. This flag can be used to disable fetching + of column statistics from metastore. + + + + hive.stats.join.factor + 1.1 + + Hive/Tez optimizer estimates the data size flowing through each of the operators. JOIN operator + uses column statistics to estimate the number of rows flowing out of it and hence the data size. + In the absence of column statistics, this factor determines the amount of rows that flows out + of JOIN operator. + + + + hive.stats.deserialization.factor + 1.0 + + Hive/Tez optimizer estimates the data size flowing through each of the operators. In the absence + of basic statistics like number of rows and data size, file size is used to estimate the number + of rows and data size. Since files in tables/partitions are serialized (and optionally + compressed) the estimates of number of rows and data size cannot be reliably determined. + This factor is multiplied with the file size to account for serialization and compression. + + + + hive.stats.filter.in.factor + 1.0 + + Currently column distribution is assumed to be uniform. This can lead to overestimation/underestimation + in the number of rows filtered by a certain operator, which in turn might lead to overprovision or + underprovision of resources. This factor is applied to the cardinality estimation of IN clauses in + filter operators. + + + + hive.support.concurrency + false + + Whether Hive supports concurrency control or not. + A ZooKeeper instance must be up and running when using zookeeper Hive lock manager + + + + hive.lock.manager + org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager + + + + hive.lock.numretries + 100 + The number of times you want to try to get all the locks + + + hive.unlock.numretries + 10 + The number of times you want to retry to do one unlock + + + hive.lock.sleep.between.retries + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + The time should be in between 0 sec (exclusive) and 9223372036854775807 sec (exclusive). + The maximum sleep time between various retries + + + + hive.lock.mapred.only.operation + false + + This param is to control whether or not only do lock on queries + that need to execute at least one mapred job. + + + + hive.zookeeper.quorum + + + List of ZooKeeper servers to talk to. This is needed for: + 1. Read/write locks - when hive.lock.manager is set to + org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager, + 2. When HiveServer2 supports service discovery via Zookeeper. + 3. For delegation token storage if zookeeper store is used, if + hive.cluster.delegation.token.store.zookeeper.connectString is not set + 4. LLAP daemon registry service + + + + hive.zookeeper.client.port + 2181 + + The port of ZooKeeper servers to talk to. + If the list of Zookeeper servers specified in hive.zookeeper.quorum + does not contain port numbers, this value is used. + + + + hive.zookeeper.session.timeout + 1200000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + ZooKeeper client's session timeout (in milliseconds). The client is disconnected, and as a result, all locks released, + if a heartbeat is not sent in the timeout. + + + + hive.zookeeper.namespace + hive_zookeeper_namespace + The parent node under which all ZooKeeper nodes are created. + + + hive.zookeeper.clean.extra.nodes + false + Clean extra nodes at the end of the session. + + + hive.zookeeper.connection.max.retries + 3 + Max number of times to retry when connecting to the ZooKeeper server. + + + hive.zookeeper.connection.basesleeptime + 1000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Initial amount of time (in milliseconds) to wait between retries + when connecting to the ZooKeeper server when using ExponentialBackoffRetry policy. + + + + hive.txn.manager + org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager + + Set to org.apache.hadoop.hive.ql.lockmgr.DbTxnManager as part of turning on Hive + transactions, which also requires appropriate settings for hive.compactor.initiator.on, + hive.compactor.worker.threads, hive.support.concurrency (true), + and hive.exec.dynamic.partition.mode (nonstrict). + The default DummyTxnManager replicates pre-Hive-0.13 behavior and provides + no transactions. + + + + hive.txn.strict.locking.mode + true + + In strict mode non-ACID + resources use standard R/W lock semantics, e.g. INSERT will acquire exclusive lock. + In nonstrict mode, for non-ACID resources, INSERT will only acquire shared lock, which + allows two concurrent writes to the same partition but still lets lock manager prevent + DROP TABLE etc. when the table is being written to + + + + hive.txn.timeout + 300s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + time after which transactions are declared aborted if the client has not sent a heartbeat. + + + + hive.txn.heartbeat.threadpool.size + 5 + The number of threads to use for heartbeating. For Hive CLI, 1 is enough. For HiveServer2, we need a few + + + hive.txn.manager.dump.lock.state.on.acquire.timeout + false + Set this to true so that when attempt to acquire a lock on resource times out, the current state of the lock manager is dumped to log file. This is for debugging. See also hive.lock.numretries and hive.lock.sleep.between.retries. + + + hive.txn.operational.properties + 0 + + Sets the operational properties that control the appropriate behavior for various + versions of the Hive ACID subsystem. Setting it to zero will turn on the legacy mode + for ACID, while setting it to one will enable a split-update feature found in the newer + version of Hive ACID subsystem. Mostly it is intended to be used as an internal property + for future versions of ACID. (See HIVE-14035 for details.) + + + + hive.max.open.txns + 100000 + + Maximum number of open transactions. If + current open transactions reach this limit, future open transaction requests will be + rejected, until this number goes below the limit. + + + + hive.count.open.txns.interval + 1s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Time in seconds between checks to count open transactions. + + + + hive.txn.max.open.batch + 1000 + + Maximum number of transactions that can be fetched in one call to open_txns(). + This controls how many transactions streaming agents such as Flume or Storm open + simultaneously. The streaming agent then writes that number of entries into a single + file (per Flume agent or Storm bolt). Thus increasing this value decreases the number + of delta files created by streaming agents. But it also increases the number of open + transactions that Hive has to track at any given time, which may negatively affect + read performance. + + + + hive.txn.retryable.sqlex.regex + + + Comma separated list + of regular expression patterns for SQL state, error code, and error message of + retryable SQLExceptions, that's suitable for the metastore DB. + For example: Can't serialize.*,40001$,^Deadlock,.*ORA-08176.* + The string that the regex will be matched against is of the following form, where ex is a SQLException: + ex.getMessage() + " (SQLState=" + ex.getSQLState() + ", ErrorCode=" + ex.getErrorCode() + ")" + + + + hive.compactor.initiator.on + false + + Whether to run the initiator and cleaner threads on this metastore instance or not. + Set this to true on one instance of the Thrift metastore service as part of turning + on Hive transactions. For a complete list of parameters required for turning on + transactions, see hive.txn.manager. + + + + hive.compactor.worker.threads + 0 + + How many compactor worker threads to run on this metastore instance. Set this to a + positive number on one or more instances of the Thrift metastore service as part of + turning on Hive transactions. For a complete list of parameters required for turning + on transactions, see hive.txn.manager. + Worker threads spawn MapReduce jobs to do compactions. They do not do the compactions + themselves. Increasing the number of worker threads will decrease the time it takes + tables or partitions to be compacted once they are determined to need compaction. + It will also increase the background load on the Hadoop cluster as more MapReduce jobs + will be running in the background. + + + + hive.compactor.worker.timeout + 86400s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Time in seconds after which a compaction job will be declared failed and the + compaction re-queued. + + + + hive.compactor.check.interval + 300s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Time in seconds between checks to see if any tables or partitions need to be + compacted. This should be kept high because each check for compaction requires + many calls against the NameNode. + Decreasing this value will reduce the time it takes for compaction to be started + for a table or partition that requires compaction. However, checking if compaction + is needed requires several calls to the NameNode for each table or partition that + has had a transaction done on it since the last major compaction. So decreasing this + value will increase the load on the NameNode. + + + + hive.compactor.delta.num.threshold + 10 + + Number of delta directories in a table or partition that will trigger a minor + compaction. + + + + hive.compactor.delta.pct.threshold + 0.1 + + Percentage (fractional) size of the delta files relative to the base that will trigger + a major compaction. (1.0 = 100%, so the default 0.1 = 10%.) + + + + hive.compactor.max.num.delta + 500 + Maximum number of delta files that the compactor will attempt to handle in a single job. + + + hive.compactor.abortedtxn.threshold + 1000 + + Number of aborted transactions involving a given table or partition that will trigger + a major compaction. + + + + hive.compactor.initiator.failed.compacts.threshold + 2 + + Expects value between 1 and 20. + Number of consecutive compaction failures (per table/partition) after which automatic compactions will not be scheduled any more. Note that this must be less than hive.compactor.history.retention.failed. + + + + hive.compactor.cleaner.run.interval + 5000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Time between runs of the cleaner thread + + + + hive.compactor.job.queue + + + Used to specify name of Hadoop queue to which + Compaction jobs will be submitted. Set to empty string to let Hadoop choose the queue. + + + + hive.compactor.history.retention.succeeded + 3 + + Expects value between 0 and 100. + Determines how many successful compaction records will be retained in compaction history for a given table/partition. + + + + hive.compactor.history.retention.failed + 3 + + Expects value between 0 and 100. + Determines how many failed compaction records will be retained in compaction history for a given table/partition. + + + + hive.compactor.history.retention.attempted + 2 + + Expects value between 0 and 100. + Determines how many attempted compaction records will be retained in compaction history for a given table/partition. + + + + hive.compactor.history.reaper.interval + 2m + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Determines how often compaction history reaper runs + + + + hive.timedout.txn.reaper.start + 100s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Time delay of 1st reaper run after metastore start + + + + hive.timedout.txn.reaper.interval + 180s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Time interval describing how often the reaper runs + + + + hive.writeset.reaper.interval + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Frequency of WriteSet reaper runs + + + + hive.merge.cardinality.check + true + + Set to true to ensure that each SQL Merge statement ensures that for each row in the target + table there is at most 1 matching row in the source table per SQL Specification. + + + + hive.druid.indexer.segments.granularity + DAY + + Expects one of the pattern in [YEAR, MONTH, WEEK, DAY, HOUR, MINUTE, SECOND]. + Granularity for the segments created by the Druid storage handler + + + + hive.druid.indexer.partition.size.max + 5000000 + Maximum number of records per segment partition + + + hive.druid.indexer.memory.rownum.max + 75000 + Maximum number of records in memory while storing data in Druid + + + hive.druid.broker.address.default + localhost:8082 + + Address of the Druid broker. If we are querying Druid from Hive, this address needs to be + declared + + + + hive.druid.coordinator.address.default + localhost:8081 + Address of the Druid coordinator. It is used to check the load status of newly created segments + + + hive.druid.select.distribute + true + + If it is set to true, we distribute the execution of Druid Select queries. Concretely, we retrieve + the result for Select queries directly from the Druid nodes containing the segments data. + In particular, first we contact the Druid broker node to obtain the nodes containing the segments + for the given query, and then we contact those nodes to retrieve the results for the query. + If it is set to false, we do not execute the Select queries in a distributed fashion. Instead, results + for those queries are returned by the Druid broker node. + + + + hive.druid.select.threshold + 10000 + + Takes only effect when hive.druid.select.distribute is set to false. + When we can split a Select query, this is the maximum number of rows that we try to retrieve + per query. In order to do that, we obtain the estimated size for the complete result. If the + number of records of the query results is larger than this threshold, we split the query in + total number of rows/threshold parts across the time dimension. Note that we assume the + records to be split uniformly across the time dimension. + + + + hive.druid.http.numConnection + 20 + + Number of connections used by + the HTTP client. + + + + hive.druid.http.read.timeout + PT1M + + Read timeout period for the HTTP + client in ISO8601 format (for example P2W, P3M, PT1H30M, PT0.750S), default is period of 1 minute. + + + + hive.druid.sleep.time + PT10S + Sleep time between retries in ISO8601 format (for example P2W, P3M, PT1H30M, PT0.750S), default is period of 10 seconds. + + + hive.druid.basePersistDirectory + + Local temporary directory used to persist intermediate indexing state, will default to JVM system property java.io.tmpdir. + + + hive.druid.storage.storageDirectory + /druid/segments + druid deep storage location. + + + hive.druid.metadata.base + druid + Default prefix for metadata tables + + + hive.druid.metadata.db.type + mysql + + Expects one of the pattern in [mysql, postgresql]. + Type of the metadata database. + + + + hive.druid.metadata.username + + Username to connect to Type of the metadata DB. + + + hive.druid.metadata.password + + Password to connect to Type of the metadata DB. + + + hive.druid.metadata.uri + + URI to connect to the database (for example jdbc:mysql://hostname:port/DBName). + + + hive.druid.working.directory + /tmp/workingDirectory + Default hdfs working directory used to store some intermediate metadata + + + hive.druid.maxTries + 5 + Maximum number of retries before giving up + + + hive.druid.passiveWaitTimeMs + 30000 + Wait time in ms default to 30 seconds. + + + hive.hbase.wal.enabled + true + + Whether writes to HBase should be forced to the write-ahead log. + Disabling this improves HBase write performance at the risk of lost writes in case of a crash. + + + + hive.hbase.generatehfiles + false + True when HBaseStorageHandler should generate hfiles instead of operate against the online table. + + + hive.hbase.snapshot.name + + The HBase table snapshot name to use. + + + hive.hbase.snapshot.restoredir + /tmp + The directory in which to restore the HBase table snapshot. + + + hive.archive.enabled + false + Whether archiving operations are permitted + + + hive.optimize.index.groupby + false + Whether to enable optimization of group-by queries using Aggregate indexes. + + + hive.fetch.task.conversion + more + + Expects one of [none, minimal, more]. + Some select queries can be converted to single FETCH task minimizing latency. + Currently the query should be single sourced not having any subquery and should not have + any aggregations or distincts (which incurs RS), lateral views and joins. + 0. none : disable hive.fetch.task.conversion + 1. minimal : SELECT STAR, FILTER on partition columns, LIMIT only + 2. more : SELECT, FILTER, LIMIT only (support TABLESAMPLE and virtual columns) + + + + hive.fetch.task.conversion.threshold + 1073741824 + + Input threshold for applying hive.fetch.task.conversion. If target table is native, input length + is calculated by summation of file lengths. If it's not native, storage handler for the table + can optionally implement org.apache.hadoop.hive.ql.metadata.InputEstimator interface. + + + + hive.fetch.task.aggr + false + + Aggregation queries with no group-by clause (for example, select count(*) from src) execute + final aggregations in single reduce task. If this is set true, Hive delegates final aggregation + stage to fetch task, possibly decreasing the query time. + + + + hive.compute.query.using.stats + true + + When set to true Hive will answer a few queries like count(1) purely using stats + stored in metastore. For basic stats collection turn on the config hive.stats.autogather to true. + For more advanced stats collection need to run analyze table queries. + + + + hive.fetch.output.serde + org.apache.hadoop.hive.serde2.DelimitedJSONSerDe + The SerDe used by FetchTask to serialize the fetch output. + + + hive.cache.expr.evaluation + true + + If true, the evaluation result of a deterministic expression referenced twice or more + will be cached. + For example, in a filter condition like '.. where key + 10 = 100 or key + 10 = 0' + the expression 'key + 10' will be evaluated/cached once and reused for the following + expression ('key + 10 = 0'). Currently, this is applied only to expressions in select + or filter operators. + + + + hive.variable.substitute + true + This enables substitution using syntax like ${var} ${system:var} and ${env:var}. + + + hive.variable.substitute.depth + 40 + The maximum replacements the substitution engine will do. + + + hive.conf.validation + true + Enables type checking for registered Hive configurations + + + hive.semantic.analyzer.hook + + + + + hive.security.authorization.enabled + false + enable or disable the Hive client authorization + + + hive.security.authorization.manager + org.apache.hadoop.hive.ql.security.authorization.plugin.sqlstd.SQLStdHiveAuthorizerFactory + + The Hive client authorization manager class name. The user defined authorization class should implement + interface org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider. + + + + hive.security.authenticator.manager + org.apache.hadoop.hive.ql.security.HadoopDefaultAuthenticator + + hive client authenticator manager class name. The user defined authenticator should implement + interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider. + + + + hive.security.metastore.authorization.manager + org.apache.hadoop.hive.ql.security.authorization.DefaultHiveMetastoreAuthorizationProvider + + Names of authorization manager classes (comma separated) to be used in the metastore + for authorization. The user defined authorization class should implement interface + org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider. + All authorization manager classes have to successfully authorize the metastore API + call for the command execution to be allowed. + + + + hive.security.metastore.authorization.auth.reads + true + If this is true, metastore authorizer authorizes read actions on database, table + + + hive.security.metastore.authenticator.manager + org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator + + authenticator manager class name to be used in the metastore for authentication. + The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider. + + + + hive.security.authorization.createtable.user.grants + + + the privileges automatically granted to some users whenever a table gets created. + An example like "userX,userY:select;userZ:create" will grant select privilege to userX and userY, + and grant create privilege to userZ whenever a new table created. + + + + hive.security.authorization.createtable.group.grants + + + the privileges automatically granted to some groups whenever a table gets created. + An example like "groupX,groupY:select;groupZ:create" will grant select privilege to groupX and groupY, + and grant create privilege to groupZ whenever a new table created. + + + + hive.security.authorization.createtable.role.grants + + + the privileges automatically granted to some roles whenever a table gets created. + An example like "roleX,roleY:select;roleZ:create" will grant select privilege to roleX and roleY, + and grant create privilege to roleZ whenever a new table created. + + + + hive.security.authorization.createtable.owner.grants + + + The privileges automatically granted to the owner whenever a table gets created. + An example like "select,drop" will grant select and drop privilege to the owner + of the table. Note that the default gives the creator of a table no access to the + table (but see HIVE-8067). + + + + hive.security.authorization.task.factory + org.apache.hadoop.hive.ql.parse.authorization.HiveAuthorizationTaskFactoryImpl + Authorization DDL task factory implementation + + + hive.security.authorization.sqlstd.confwhitelist + + + List of comma separated Java regexes. Configurations parameters that match these + regexes can be modified by user when SQL standard authorization is enabled. + To get the default value, use the 'set <param>' command. + Note that the hive.conf.restricted.list checks are still enforced after the white list + check + + + + hive.security.authorization.sqlstd.confwhitelist.append + + + List of comma separated Java regexes, to be appended to list set in + hive.security.authorization.sqlstd.confwhitelist. Using this list instead + of updating the original list means that you can append to the defaults + set by SQL standard authorization instead of replacing it entirely. + + + + hive.cli.print.header + false + Whether to print the names of the columns in query output. + + + hive.cli.tez.session.async + true + + Whether to start Tez + session in background when running CLI with Tez, allowing CLI to be available earlier. + + + + hive.error.on.empty.partition + false + Whether to throw an exception if dynamic partition insert generates empty results. + + + hive.index.compact.file + + internal variable + + + hive.index.blockfilter.file + + internal variable + + + hive.index.compact.file.ignore.hdfs + false + + When true the HDFS location stored in the index file will be ignored at runtime. + If the data got moved or the name of the cluster got changed, the index data should still be usable. + + + + hive.exim.uri.scheme.whitelist + hdfs,pfile,file,s3,s3a + A comma separated list of acceptable URI schemes for import and export. + + + hive.exim.strict.repl.tables + true + + Parameter that determines if 'regular' (non-replication) export dumps can be + imported on to tables that are the target of replication. If this parameter is + set, regular imports will check if the destination table(if it exists) has a 'repl.last.id' set on it. If so, it will fail. + + + + hive.repl.task.factory + org.apache.hive.hcatalog.api.repl.exim.EximReplicationTaskFactory + + Parameter that can be used to override which ReplicationTaskFactory will be + used to instantiate ReplicationTask events. Override for third party repl plugins + + + + hive.mapper.cannot.span.multiple.partitions + false + + + + hive.rework.mapredwork + false + + should rework the mapred work or not. + This is first introduced by SymlinkTextInputFormat to replace symlink files with real paths at compile time. + + + + hive.exec.concatenate.check.index + true + + If this is set to true, Hive will throw error when doing + 'alter table tbl_name [partSpec] concatenate' on a table/partition + that has indexes on it. The reason the user want to set this to true + is because it can help user to avoid handling all index drop, recreation, + rebuild work. This is very helpful for tables with thousands of partitions. + + + + hive.io.exception.handlers + + + A list of io exception handler class names. This is used + to construct a list exception handlers to handle exceptions thrown + by record readers + + + + hive.log4j.file + + + Hive log4j configuration file. + If the property is not set, then logging will be initialized using hive-log4j2.properties found on the classpath. + If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.xml"), + which you can then extract a URL from and pass to PropertyConfigurator.configure(URL). + + + + hive.exec.log4j.file + + + Hive log4j configuration file for execution mode(sub command). + If the property is not set, then logging will be initialized using hive-exec-log4j2.properties found on the classpath. + If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.xml"), + which you can then extract a URL from and pass to PropertyConfigurator.configure(URL). + + + + hive.async.log.enabled + true + + Whether to enable Log4j2's asynchronous logging. Asynchronous logging can give + significant performance improvement as logging will be handled in separate thread + that uses LMAX disruptor queue for buffering log messages. + Refer https://logging.apache.org/log4j/2.x/manual/async.html for benefits and + drawbacks. + + + + hive.log.explain.output + false + + Whether to log explain output for every query. + When enabled, will log EXPLAIN EXTENDED output for the query at INFO log4j log level. + + + + hive.explain.user + true + + Whether to show explain result at user level. + When enabled, will log EXPLAIN output for the query at user level. + + + + hive.autogen.columnalias.prefix.label + _c + + String used as a prefix when auto generating column alias. + By default the prefix label will be appended with a column position number to form the column alias. + Auto generation would happen if an aggregate function is used in a select clause without an explicit alias. + + + + hive.autogen.columnalias.prefix.includefuncname + false + Whether to include function name in the column alias auto generated by Hive. + + + hive.service.metrics.class + org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics + + Expects one of [org.apache.hadoop.hive.common.metrics.metrics2.codahalemetrics, org.apache.hadoop.hive.common.metrics.legacymetrics]. + Hive metrics subsystem implementation class. + + + + hive.service.metrics.reporter + JSON_FILE, JMX + Reporter type for metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics, comma separated list of JMX, CONSOLE, JSON_FILE, HADOOP2 + + + hive.service.metrics.file.location + /tmp/report.json + For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics JSON_FILE reporter, the location of local JSON metrics file. This file will get overwritten at every interval. + + + hive.service.metrics.file.frequency + 5s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics JSON_FILE reporter, the frequency of updating JSON metrics file. + + + + hive.service.metrics.hadoop2.frequency + 30s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics HADOOP2 reporter, the frequency of updating the HADOOP2 metrics system. + + + + hive.service.metrics.hadoop2.component + hive + Component name to provide to Hadoop2 Metrics system. Ideally 'hivemetastore' for the MetaStore and and 'hiveserver2' for HiveServer2. + + + hive.exec.perf.logger + org.apache.hadoop.hive.ql.log.PerfLogger + + The class responsible for logging client side performance metrics. + Must be a subclass of org.apache.hadoop.hive.ql.log.PerfLogger + + + + hive.start.cleanup.scratchdir + false + To cleanup the Hive scratchdir when starting the Hive Server + + + hive.scratchdir.lock + false + To hold a lock file in scratchdir to prevent to be removed by cleardanglingscratchdir + + + hive.insert.into.multilevel.dirs + false + + Where to insert into multilevel directories like + "insert directory '/HIVEFT25686/chinna/' from table" + + + + hive.warehouse.subdir.inherit.perms + true + + Set this to false if the table directories should be created + with the permissions derived from dfs umask instead of + inheriting the permission of the warehouse or database directory. + + + + hive.insert.into.external.tables + true + whether insert into external tables is allowed + + + hive.exec.temporary.table.storage + default + + Expects one of [memory, ssd, default]. + Define the storage policy for temporary tables.Choices between memory, ssd and default + + + + hive.query.lifetime.hooks + + A comma separated list of hooks which implement QueryLifeTimeHook. These will be triggered before/after query compilation and before/after query execution, in the order specified + + + hive.exec.driver.run.hooks + + A comma separated list of hooks which implement HiveDriverRunHook. Will be run at the beginning and end of Driver.run, these will be run in the order specified. + + + hive.ddl.output.format + + + The data format to use for DDL output. One of "text" (for human + readable text) or "json" (for a json object). + + + + hive.entity.separator + @ + Separator used to construct names of tables and partitions. For example, dbname@tablename@partitionname + + + hive.entity.capture.transform + false + Compiler to capture transform URI referred in the query + + + hive.display.partition.cols.separately + true + + In older Hive version (0.10 and earlier) no distinction was made between + partition columns or non-partition columns while displaying columns in describe + table. From 0.12 onwards, they are displayed separately. This flag will let you + get old behavior, if desired. See, test-case in patch for HIVE-6689. + + + + hive.ssl.protocol.blacklist + SSLv2,SSLv3 + SSL Versions to disable for all Hive Servers + + + hive.server2.clear.dangling.scratchdir + false + Clear dangling scratch dir periodically in HS2 + + + hive.server2.clear.dangling.scratchdir.interval + 1800s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Interval to clear dangling scratch dir periodically in HS2 + + + + hive.server2.sleep.interval.between.start.attempts + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The time should be in between 0 msec (inclusive) and 9223372036854775807 msec (inclusive). + Amount of time to sleep between HiveServer2 start attempts. Primarily meant for tests + + + + hive.server2.max.start.attempts + 30 + + Expects value bigger than 0. + Number of times HiveServer2 will attempt to start before exiting. The sleep interval between retries is determined by hive.server2.sleep.interval.between.start.attempts + The default of 30 will keep trying for 30 minutes. + + + + hive.server2.support.dynamic.service.discovery + false + Whether HiveServer2 supports dynamic service discovery for its clients. To support this, each instance of HiveServer2 currently uses ZooKeeper to register itself, when it is brought up. JDBC/ODBC clients should use the ZooKeeper ensemble: hive.zookeeper.quorum in their connection string. + + + hive.server2.zookeeper.namespace + hiveserver2 + The parent node in ZooKeeper used by HiveServer2 when supporting dynamic service discovery. + + + hive.server2.zookeeper.publish.configs + true + Whether we should publish HiveServer2's configs to ZooKeeper. + + + hive.server2.global.init.file.location + ${env:HIVE_CONF_DIR} + + Either the location of a HS2 global init file or a directory containing a .hiverc file. If the + property is set, the value must be a valid path to an init file or directory where the init file is located. + + + + hive.server2.transport.mode + binary + + Expects one of [binary, http]. + Transport mode of HiveServer2. + + + + hive.server2.thrift.bind.host + + Bind host on which to run the HiveServer2 Thrift service. + + + hive.driver.parallel.compilation + false + + Whether to + enable parallel compilation of the queries between sessions and within the same session on HiveServer2. The default is false. + + + + hive.server2.compile.lock.timeout + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds a request will wait to acquire the compile lock before giving up. Setting it to 0s disables the timeout. + + + + hive.server2.parallel.ops.in.session + true + Whether to allow several parallel operations (such as SQL statements) in one session. + + + hive.server2.webui.host + 0.0.0.0 + The host address the HiveServer2 WebUI will listen on + + + hive.server2.webui.port + 10002 + The port the HiveServer2 WebUI will listen on. This can beset to 0 or a negative integer to disable the web UI + + + hive.server2.webui.max.threads + 50 + The max HiveServer2 WebUI threads + + + hive.server2.webui.use.ssl + false + Set this to true for using SSL encryption for HiveServer2 WebUI. + + + hive.server2.webui.keystore.path + + SSL certificate keystore location for HiveServer2 WebUI. + + + hive.server2.webui.keystore.password + + SSL certificate keystore password for HiveServer2 WebUI. + + + hive.server2.webui.use.spnego + false + If true, the HiveServer2 WebUI will be secured with SPNEGO. Clients must authenticate with Kerberos. + + + hive.server2.webui.spnego.keytab + + The path to the Kerberos Keytab file containing the HiveServer2 WebUI SPNEGO service principal. + + + hive.server2.webui.spnego.principal + HTTP/_HOST@EXAMPLE.COM + + The HiveServer2 WebUI SPNEGO service principal. + The special string _HOST will be replaced automatically with + the value of hive.server2.webui.host or the correct host name. + + + + hive.server2.webui.max.historic.queries + 25 + The maximum number of past queries to show in HiverSever2 WebUI. + + + hive.server2.tez.default.queues + + + A list of comma separated values corresponding to YARN queues of the same name. + When HiveServer2 is launched in Tez mode, this configuration needs to be set + for multiple Tez sessions to run in parallel on the cluster. + + + + hive.server2.tez.sessions.per.default.queue + 1 + + A positive integer that determines the number of Tez sessions that should be + launched on each of the queues specified by "hive.server2.tez.default.queues". + Determines the parallelism on each queue. + + + + hive.server2.tez.initialize.default.sessions + false + + This flag is used in HiveServer2 to enable a user to use HiveServer2 without + turning on Tez for HiveServer2. The user could potentially want to run queries + over Tez without the pool of sessions. + + + + hive.server2.tez.session.lifetime + 162h + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is hour if not specified. + The lifetime of the Tez sessions launched by HS2 when default sessions are enabled. + Set to 0 to disable session expiration. + + + + hive.server2.tez.session.lifetime.jitter + 3h + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is hour if not specified. + The jitter for Tez session lifetime; prevents all the sessions from restarting at once. + + + + hive.server2.tez.sessions.init.threads + 16 + + If hive.server2.tez.initialize.default.sessions is enabled, the maximum number of + threads to use to initialize the default sessions. + + + + hive.server2.tez.sessions.restricted.configs + + + The configuration settings that cannot be set when submitting jobs to HiveServer2. If + any of these are set to values different from those in the server configuration, an + exception will be thrown. + + + + hive.server2.tez.sessions.custom.queue.allowed + true + + Expects one of [true, false, ignore]. + Whether Tez session pool should allow submitting queries to custom queues. The options + are true, false (error out), ignore (accept the query but ignore the queue setting). + + + + hive.server2.logging.operation.enabled + true + When true, HS2 will save operation logs and make them available for clients + + + hive.server2.logging.operation.log.location + ${system:java.io.tmpdir}/${system:user.name}/operation_logs + Top level directory where operation logs are stored if logging functionality is enabled + + + hive.server2.logging.operation.level + EXECUTION + + Expects one of [none, execution, performance, verbose]. + HS2 operation logging mode available to clients to be set at session level. + For this to work, hive.server2.logging.operation.enabled should be set to true. + NONE: Ignore any logging + EXECUTION: Log completion of tasks + PERFORMANCE: Execution + Performance logs + VERBOSE: All logs + + + + hive.server2.metrics.enabled + false + Enable metrics on the HiveServer2. + + + hive.server2.thrift.http.port + 10001 + Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'http'. + + + hive.server2.thrift.http.path + cliservice + Path component of URL endpoint when in HTTP mode. + + + hive.server2.thrift.max.message.size + 104857600 + Maximum message size in bytes a HS2 server will accept. + + + hive.server2.thrift.http.max.idle.time + 1800s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Maximum idle time for a connection on the server when in HTTP mode. + + + + hive.server2.thrift.http.worker.keepalive.time + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Keepalive time for an idle http worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval. + + + + hive.server2.thrift.http.request.header.size + 6144 + Request header size in bytes, when using HTTP transport mode. Jetty defaults used. + + + hive.server2.thrift.http.response.header.size + 6144 + Response header size in bytes, when using HTTP transport mode. Jetty defaults used. + + + hive.server2.thrift.http.cookie.auth.enabled + true + When true, HiveServer2 in HTTP transport mode, will use cookie based authentication mechanism. + + + hive.server2.thrift.http.cookie.max.age + 86400s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Maximum age in seconds for server side cookie used by HS2 in HTTP mode. + + + + hive.server2.thrift.http.cookie.domain + + Domain for the HS2 generated cookies + + + hive.server2.thrift.http.cookie.path + + Path for the HS2 generated cookies + + + hive.server2.thrift.http.cookie.is.secure + true + Deprecated: Secure attribute of the HS2 generated cookie (this is automatically enabled for SSL enabled HiveServer2). + + + hive.server2.thrift.http.cookie.is.httponly + true + HttpOnly attribute of the HS2 generated cookie. + + + hive.server2.thrift.port + 10000 + Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'binary'. + + + hive.server2.thrift.sasl.qop + auth + + Expects one of [auth, auth-int, auth-conf]. + Sasl QOP value; set it to one of following values to enable higher levels of + protection for HiveServer2 communication with clients. + Setting hadoop.rpc.protection to a higher level than HiveServer2 does not + make sense in most situations. HiveServer2 ignores hadoop.rpc.protection in favor + of hive.server2.thrift.sasl.qop. + "auth" - authentication only (default) + "auth-int" - authentication plus integrity protection + "auth-conf" - authentication plus integrity and confidentiality protection + This is applicable only if HiveServer2 is configured to use Kerberos authentication. + + + + hive.server2.thrift.min.worker.threads + 5 + Minimum number of Thrift worker threads + + + hive.server2.thrift.max.worker.threads + 500 + Maximum number of Thrift worker threads + + + hive.server2.thrift.exponential.backoff.slot.length + 100ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Binary exponential backoff slot time for Thrift clients during login to HiveServer2, + for retries until hitting Thrift client timeout + + + + hive.server2.thrift.login.timeout + 20s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Timeout for Thrift clients during login to HiveServer2 + + + + hive.server2.thrift.worker.keepalive.time + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Keepalive time (in seconds) for an idle worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval. + + + + hive.server2.async.exec.threads + 100 + Number of threads in the async thread pool for HiveServer2 + + + hive.server2.async.exec.shutdown.timeout + 10s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + How long HiveServer2 shutdown will wait for async threads to terminate. + + + + hive.server2.async.exec.wait.queue.size + 100 + + Size of the wait queue for async thread pool in HiveServer2. + After hitting this limit, the async thread pool will reject new requests. + + + + hive.server2.async.exec.keepalive.time + 10s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Time that an idle HiveServer2 async thread (from the thread pool) will wait for a new task + to arrive before terminating + + + + hive.server2.async.exec.async.compile + false + Whether to enable compiling async query asynchronously. If enabled, it is unknown if the query will have any resultset before compilation completed. + + + hive.server2.long.polling.timeout + 5000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Time that HiveServer2 will wait before responding to asynchronous calls that use long polling + + + + hive.session.impl.classname + + Classname for custom implementation of hive session + + + hive.session.impl.withugi.classname + + Classname for custom implementation of hive session with UGI + + + hive.server2.authentication + NONE + + Expects one of [nosasl, none, ldap, kerberos, pam, custom]. + Client authentication types. + NONE: no authentication check + LDAP: LDAP/AD based authentication + KERBEROS: Kerberos/GSSAPI authentication + CUSTOM: Custom authentication provider + (Use with property hive.server2.custom.authentication.class) + PAM: Pluggable authentication module + NOSASL: Raw transport + + + + hive.server2.allow.user.substitution + true + Allow alternate user to be specified as part of HiveServer2 open connection request. + + + hive.server2.authentication.kerberos.keytab + + Kerberos keytab file for server principal + + + hive.server2.authentication.kerberos.principal + + Kerberos server principal + + + hive.server2.authentication.spnego.keytab + + + keytab file for SPNego principal, optional, + typical value would look like /etc/security/keytabs/spnego.service.keytab, + This keytab would be used by HiveServer2 when Kerberos security is enabled and + HTTP transport mode is used. + This needs to be set only if SPNEGO is to be used in authentication. + SPNego authentication would be honored only if valid + hive.server2.authentication.spnego.principal + and + hive.server2.authentication.spnego.keytab + are specified. + + + + hive.server2.authentication.spnego.principal + + + SPNego service principal, optional, + typical value would look like HTTP/_HOST@EXAMPLE.COM + SPNego service principal would be used by HiveServer2 when Kerberos security is enabled + and HTTP transport mode is used. + This needs to be set only if SPNEGO is to be used in authentication. + + + + hive.server2.authentication.ldap.url + + + LDAP connection URL(s), + this value could contain URLs to mutiple LDAP servers instances for HA, + each LDAP URL is separated by a SPACE character. URLs are used in the + order specified until a connection is successful. + + + + hive.server2.authentication.ldap.baseDN + + LDAP base DN + + + hive.server2.authentication.ldap.Domain + + + + + hive.server2.authentication.ldap.groupDNPattern + + + COLON-separated list of patterns to use to find DNs for group entities in this directory. + Use %s where the actual group name is to be substituted for. + For example: CN=%s,CN=Groups,DC=subdomain,DC=domain,DC=com. + + + + hive.server2.authentication.ldap.groupFilter + + + COMMA-separated list of LDAP Group names (short name not full DNs). + For example: HiveAdmins,HadoopAdmins,Administrators + + + + hive.server2.authentication.ldap.userDNPattern + + + COLON-separated list of patterns to use to find DNs for users in this directory. + Use %s where the actual group name is to be substituted for. + For example: CN=%s,CN=Users,DC=subdomain,DC=domain,DC=com. + + + + hive.server2.authentication.ldap.userFilter + + + COMMA-separated list of LDAP usernames (just short names, not full DNs). + For example: hiveuser,impalauser,hiveadmin,hadoopadmin + + + + hive.server2.authentication.ldap.guidKey + uid + + LDAP attribute name whose values are unique in this LDAP server. + For example: uid or CN. + + + + hive.server2.authentication.ldap.groupMembershipKey + member + + LDAP attribute name on the group object that contains the list of distinguished names + for the user, group, and contact objects that are members of the group. + For example: member, uniqueMember or memberUid + + + + hive.server2.authentication.ldap.userMembershipKey + + + LDAP attribute name on the user object that contains groups of which the user is + a direct member, except for the primary group, which is represented by the + primaryGroupId. + For example: memberOf + + + + hive.server2.authentication.ldap.groupClassKey + groupOfNames + + LDAP attribute name on the group entry that is to be used in LDAP group searches. + For example: group, groupOfNames or groupOfUniqueNames. + + + + hive.server2.authentication.ldap.customLDAPQuery + + + A full LDAP query that LDAP Atn provider uses to execute against LDAP Server. + If this query returns a null resultset, the LDAP Provider fails the Authentication + request, succeeds if the user is part of the resultset.For example: (&(objectClass=group)(objectClass=top)(instanceType=4)(cn=Domain*)) + (&(objectClass=person)(|(sAMAccountName=admin)(|(memberOf=CN=Domain Admins,CN=Users,DC=domain,DC=com)(memberOf=CN=Administrators,CN=Builtin,DC=domain,DC=com)))) + + + + hive.server2.custom.authentication.class + + + Custom authentication class. Used when property + 'hive.server2.authentication' is set to 'CUSTOM'. Provided class + must be a proper implementation of the interface + org.apache.hive.service.auth.PasswdAuthenticationProvider. HiveServer2 + will call its Authenticate(user, passed) method to authenticate requests. + The implementation may optionally implement Hadoop's + org.apache.hadoop.conf.Configurable class to grab Hive's Configuration object. + + + + hive.server2.authentication.pam.services + + + List of the underlying pam services that should be used when auth type is PAM + A file with the same name must exist in /etc/pam.d + + + + hive.server2.enable.doAs + true + + Setting this property to true will have HiveServer2 execute + Hive operations as the user making the calls to it. + + + + hive.server2.table.type.mapping + CLASSIC + + Expects one of [classic, hive]. + This setting reflects how HiveServer2 will report the table types for JDBC and other + client implementations that retrieve the available tables and supported table types + HIVE : Exposes Hive's native table types like MANAGED_TABLE, EXTERNAL_TABLE, VIRTUAL_VIEW + CLASSIC : More generic types like TABLE and VIEW + + + + hive.server2.session.hook + + + + + hive.server2.use.SSL + false + Set this to true for using SSL encryption in HiveServer2. + + + hive.server2.keystore.path + + SSL certificate keystore location. + + + hive.server2.keystore.password + + SSL certificate keystore password. + + + hive.server2.map.fair.scheduler.queue + true + + If the YARN fair scheduler is configured and HiveServer2 is running in non-impersonation mode, + this setting determines the user for fair scheduler queue mapping. + If set to true (default), the logged-in user determines the fair scheduler queue + for submitted jobs, so that map reduce resource usage can be tracked by user. + If set to false, all Hive jobs go to the 'hive' user's queue. + + + + hive.server2.builtin.udf.whitelist + + + Comma separated list of builtin udf names allowed in queries. + An empty whitelist allows all builtin udfs to be executed. The udf black list takes precedence over udf white list + + + + hive.server2.builtin.udf.blacklist + + Comma separated list of udfs names. These udfs will not be allowed in queries. The udf black list takes precedence over udf white list + + + hive.allow.udf.load.on.demand + false + + Whether enable loading UDFs from metastore on demand; this is mostly relevant for + HS2 and was the default behavior before Hive 1.2. Off by default. + + + + hive.server2.session.check.interval + 6h + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The time should be bigger than or equal to 3000 msec. + The check interval for session/operation timeout, which can be disabled by setting to zero or negative value. + + + + hive.server2.close.session.on.disconnect + true + Session will be closed when connection is closed. Set this to false to have session outlive its parent connection. + + + hive.server2.idle.session.timeout + 7d + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Session will be closed when it's not accessed for this duration, which can be disabled by setting to zero or negative value. + + + + hive.server2.idle.operation.timeout + 5d + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Operation will be closed when it's not accessed for this duration of time, which can be disabled by setting to zero value. + With positive value, it's checked for operations in terminal state only (FINISHED, CANCELED, CLOSED, ERROR). + With negative value, it's checked for all of the operations regardless of state. + + + + hive.server2.idle.session.check.operation + true + + Session will be considered to be idle only if there is no activity, and there is no pending operation. + This setting takes effect only if session idle timeout (hive.server2.idle.session.timeout) and checking + (hive.server2.session.check.interval) are enabled. + + + + hive.server2.thrift.client.retry.limit + 1 + Number of retries upon failure of Thrift HiveServer2 calls + + + hive.server2.thrift.client.connect.retry.limit + 1 + Number of retries while opening a connection to HiveServe2 + + + hive.server2.thrift.client.retry.delay.seconds + 1s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds for the HiveServer2 thrift client to wait between consecutive connection attempts. Also specifies the time to wait between retrying thrift calls upon failures + + + + hive.server2.thrift.client.user + anonymous + Username to use against thrift client + + + hive.server2.thrift.client.password + anonymous + Password to use against thrift client + + + hive.server2.thrift.resultset.serialize.in.tasks + false + + Whether we should serialize the Thrift structures used in JDBC ResultSet RPC in task nodes. + We use SequenceFile and ThriftJDBCBinarySerDe to read and write the final results if this is true. + + + + hive.server2.thrift.resultset.max.fetch.size + 10000 + Max number of rows sent in one Fetch RPC call by the server to the client. + + + hive.server2.thrift.resultset.default.fetch.size + 1000 + + The number of rows sent in one Fetch RPC call by the server to the client, if not + specified by the client. + + + + hive.server2.xsrf.filter.enabled + false + If enabled, HiveServer2 will block any requests made to it over http if an X-XSRF-HEADER header is not present + + + hive.security.command.whitelist + set,reset,dfs,add,list,delete,reload,compile + Comma separated list of non-SQL Hive commands users are authorized to execute + + + hive.server2.job.credential.provider.path + + If set, this configuration property should provide a comma-separated list of URLs that indicates the type and location of providers to be used by hadoop credential provider API. It provides HiveServer2 the ability to provide job-specific credential providers for jobs run using MR and Spark execution engines. This functionality has not been tested against Tez. + + + hive.mv.files.thread + 15 + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + The size should be in between 0Pb (inclusive) and 1Kb (inclusive). + Number of threads used to move files in move task. Set it to 0 to disable multi-threaded file moves. This parameter is also used by MSCK to check tables. + + + + hive.load.dynamic.partitions.thread + 15 + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + The size should be in between 1 bytes (inclusive) and 1Kb (inclusive). + Number of threads used to load dynamic partitions. + + + + hive.multi.insert.move.tasks.share.dependencies + false + + If this is set all move tasks for tables/partitions (not directories) at the end of a + multi-insert query will only begin once the dependencies for all these move tasks have been + met. + Advantages: If concurrency is enabled, the locks will only be released once the query has + finished, so with this config enabled, the time when the table/partition is + generated will be much closer to when the lock on it is released. + Disadvantages: If concurrency is not enabled, with this disabled, the tables/partitions which + are produced by this query and finish earlier will be available for querying + much earlier. Since the locks are only released once the query finishes, this + does not apply if concurrency is enabled. + + + + hive.exec.infer.bucket.sort + false + + If this is set, when writing partitions, the metadata will include the bucketing/sorting + properties with which the data was written if any (this will not overwrite the metadata + inherited from the table if the table is bucketed/sorted) + + + + hive.exec.infer.bucket.sort.num.buckets.power.two + false + + If this is set, when setting the number of reducers for the map reduce task which writes the + final output files, it will choose a number which is a power of two, unless the user specifies + the number of reducers to use using mapred.reduce.tasks. The number of reducers + may be set to a power of two, only to be followed by a merge task meaning preventing + anything from being inferred. + With hive.exec.infer.bucket.sort set to true: + Advantages: If this is not set, the number of buckets for partitions will seem arbitrary, + which means that the number of mappers used for optimized joins, for example, will + be very low. With this set, since the number of buckets used for any partition is + a power of two, the number of mappers used for optimized joins will be the least + number of buckets used by any partition being joined. + Disadvantages: This may mean a much larger or much smaller number of reducers being used in the + final map reduce job, e.g. if a job was originally going to take 257 reducers, + it will now take 512 reducers, similarly if the max number of reducers is 511, + and a job was going to use this many, it will now use 256 reducers. + + + + hive.optimize.listbucketing + false + Enable list bucketing optimizer. Default value is false so that we disable it by default. + + + hive.server.read.socket.timeout + 10s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Timeout for the HiveServer to close the connection if no response from the client. By default, 10 seconds. + + + + hive.server.tcp.keepalive + true + Whether to enable TCP keepalive for the Hive Server. Keepalive will prevent accumulation of half-open connections. + + + hive.decode.partition.name + false + Whether to show the unquoted partition names in query results. + + + hive.execution.engine + mr + + Expects one of [mr, tez, spark]. + Chooses execution engine. Options are: mr (Map reduce, default), tez, spark. While MR + remains the default engine for historical reasons, it is itself a historical engine + and is deprecated in Hive 2 line. It may be removed without further warning. + + + + hive.execution.mode + container + + Expects one of [container, llap]. + Chooses whether query fragments will run in container or in llap + + + + hive.jar.directory + + + This is the location hive in tez mode will look for to find a site wide + installed hive instance. + + + + hive.user.install.directory + /user/ + + If hive (in tez mode only) cannot find a usable hive jar in "hive.jar.directory", + it will upload the hive jar to "hive.user.install.directory/user.name" + and use it to run queries. + + + + hive.vectorized.execution.enabled + false + + This flag should be set to true to enable vectorized mode of query execution. + The default value is false. + + + + hive.vectorized.execution.reduce.enabled + true + + This flag should be set to true to enable vectorized mode of the reduce-side of query execution. + The default value is true. + + + + hive.vectorized.execution.reduce.groupby.enabled + true + + This flag should be set to true to enable vectorized mode of the reduce-side GROUP BY query execution. + The default value is true. + + + + hive.vectorized.execution.mapjoin.native.enabled + true + + This flag should be set to true to enable native (i.e. non-pass through) vectorization + of queries using MapJoin. + The default value is true. + + + + hive.vectorized.execution.mapjoin.native.multikey.only.enabled + false + + This flag should be set to true to restrict use of native vector map join hash tables to + the MultiKey in queries using MapJoin. + The default value is false. + + + + hive.vectorized.execution.mapjoin.minmax.enabled + false + + This flag should be set to true to enable vector map join hash tables to + use max / max filtering for integer join queries using MapJoin. + The default value is false. + + + + hive.vectorized.execution.mapjoin.overflow.repeated.threshold + -1 + + The number of small table rows for a match in vector map join hash tables + where we use the repeated field optimization in overflow vectorized row batch for join queries using MapJoin. + A value of -1 means do use the join result optimization. Otherwise, threshold value can be 0 to maximum integer. + + + + hive.vectorized.execution.mapjoin.native.fast.hashtable.enabled + false + + This flag should be set to true to enable use of native fast vector map join hash tables in + queries using MapJoin. + The default value is false. + + + + hive.vectorized.groupby.checkinterval + 100000 + Number of entries added to the group by aggregation hash before a recomputation of average entry size is performed. + + + hive.vectorized.groupby.maxentries + 1000000 + + Max number of entries in the vector group by aggregation hashtables. + Exceeding this will trigger a flush irrelevant of memory pressure condition. + + + + hive.vectorized.groupby.flush.percent + 0.1 + Percent of entries in the group by aggregation hash flushed when the memory threshold is exceeded. + + + hive.vectorized.execution.reducesink.new.enabled + true + + This flag should be set to true to enable the new vectorization + of queries using ReduceSink. + iThe default value is true. + + + + hive.vectorized.use.vectorized.input.format + true + + This flag should be set to true to enable vectorizing with vectorized input file format capable SerDe. + The default value is true. + + + + hive.vectorized.use.vector.serde.deserialize + true + + This flag should be set to true to enable vectorizing rows using vector deserialize. + The default value is true. + + + + hive.vectorized.use.row.serde.deserialize + false + + This flag should be set to true to enable vectorizing using row deserialize. + The default value is false. + + + + hive.vectorized.adaptor.usage.mode + all + + Expects one of [none, chosen, all]. + Specifies the extent to which the VectorUDFAdaptor will be used for UDFs that do not have a cooresponding vectorized class. + 0. none : disable any usage of VectorUDFAdaptor + 1. chosen : use VectorUDFAdaptor for a small set of UDFs that were choosen for good performance + 2. all : use VectorUDFAdaptor for all UDFs + + + + hive.typecheck.on.insert + true + This property has been extended to control whether to check, convert, and normalize partition value to conform to its column type in partition operations including but not limited to insert, such as alter, describe etc. + + + hive.hadoop.classpath + + + For Windows OS, we need to pass HIVE_HADOOP_CLASSPATH Java parameter while starting HiveServer2 + using "-hiveconf hive.hadoop.classpath=%HIVE_LIB%". + + + + hive.rpc.query.plan + false + Whether to send the query plan via local resource or RPC + + + hive.compute.splits.in.am + true + Whether to generate the splits locally or in the AM (tez only) + + + hive.tez.input.generate.consistent.splits + true + Whether to generate consistent split locations when generating splits in the AM + + + hive.prewarm.enabled + false + Enables container prewarm for Tez/Spark (Hadoop 2 only) + + + hive.prewarm.numcontainers + 10 + Controls the number of containers to prewarm for Tez/Spark (Hadoop 2 only) + + + hive.stageid.rearrange + none + + Expects one of [none, idonly, traverse, execution]. + + + + hive.explain.dependency.append.tasktype + false + + + + hive.counters.group.name + HIVE + The name of counter group for internal Hive variables (CREATED_FILE, FATAL_ERROR, etc.) + + + hive.support.quoted.identifiers + column + + Expects one of [none, column]. + Whether to use quoted identifier. 'none' or 'column' can be used. + none: default(past) behavior. Implies only alphaNumeric and underscore are valid characters in identifiers. + column: implies column names can contain any character. + + + + hive.support.special.characters.tablename + true + + This flag should be set to true to enable support for special characters in table names. + When it is set to false, only [a-zA-Z_0-9]+ are supported. + The only supported special character right now is '/'. This flag applies only to quoted table names. + The default value is true. + + + + hive.users.in.admin.role + + + Comma separated list of users who are in admin role for bootstrapping. + More users can be added in ADMIN role later. + + + + hive.compat + 0.12 + + Enable (configurable) deprecated behaviors by setting desired level of backward compatibility. + Setting to 0.12: + Maintains division behavior: int / int = double + + + + hive.convert.join.bucket.mapjoin.tez + false + + Whether joins can be automatically converted to bucket map joins in hive + when tez is used as the execution engine. + + + + hive.exec.check.crossproducts + true + Check if a plan contains a Cross Product. If there is one, output a warning to the Session's console. + + + hive.localize.resource.wait.interval + 5000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Time to wait for another thread to localize the same resource for hive-tez. + + + + hive.localize.resource.num.wait.attempts + 5 + The number of attempts waiting for localizing a resource in hive-tez. + + + hive.tez.auto.reducer.parallelism + false + + Turn on Tez' auto reducer parallelism feature. When enabled, Hive will still estimate data sizes + and set parallelism estimates. Tez will sample source vertices' output sizes and adjust the estimates at runtime as + necessary. + + + + hive.tez.max.partition.factor + 2.0 + When auto reducer parallelism is enabled this factor will be used to over-partition data in shuffle edges. + + + hive.tez.min.partition.factor + 0.25 + + When auto reducer parallelism is enabled this factor will be used to put a lower limit to the number + of reducers that tez specifies. + + + + hive.tez.bucket.pruning + false + + When pruning is enabled, filters on bucket columns will be processed by + filtering the splits against a bitset of included buckets. This needs predicates + produced by hive.optimize.ppd and hive.optimize.index.filters. + + + + hive.tez.bucket.pruning.compat + true + + When pruning is enabled, handle possibly broken inserts due to negative hashcodes. + This occasionally doubles the data scan cost, but is default enabled for safety + + + + hive.tez.dynamic.partition.pruning + true + + When dynamic pruning is enabled, joins on partition keys will be processed by sending + events from the processing vertices to the Tez application master. These events will be + used to prune unnecessary partitions. + + + + hive.tez.dynamic.partition.pruning.max.event.size + 1048576 + Maximum size of events sent by processors in dynamic pruning. If this size is crossed no pruning will take place. + + + hive.tez.dynamic.partition.pruning.max.data.size + 104857600 + Maximum total data size of events in dynamic pruning. + + + hive.tez.dynamic.semijoin.reduction + true + When dynamic semijoin is enabled, shuffle joins will perform a leaky semijoin before shuffle. This requires hive.tez.dynamic.partition.pruning to be enabled. + + + hive.tez.min.bloom.filter.entries + 1000000 + Bloom filter should be of at min certain size to be effective + + + hive.tez.max.bloom.filter.entries + 100000000 + Bloom filter should be of at max certain size to be effective + + + hive.tez.bloom.filter.factor + 2.0 + Bloom filter should be a multiple of this factor with nDV + + + hive.tez.bigtable.minsize.semijoin.reduction + 1000000 + Big table for runtime filteting should be of atleast this size + + + hive.tez.dynamic.semijoin.reduction.threshold + 0.5 + Only perform semijoin optimization if the estimated benefit at or above this fraction of the target table + + + hive.tez.smb.number.waves + 0.5 + The number of waves in which to run the SMB join. Account for cluster being occupied. Ideally should be 1 wave. + + + hive.tez.exec.print.summary + false + Display breakdown of execution steps, for every query executed by the shell. + + + hive.tez.exec.inplace.progress + true + Updates tez job execution progress in-place in the terminal when hive-cli is used. + + + hive.server2.in.place.progress + true + Allows hive server 2 to send progress bar update information. This is currently available only if the execution engine is tez. + + + hive.spark.exec.inplace.progress + true + Updates spark job execution progress in-place in the terminal. + + + hive.tez.container.max.java.heap.fraction + 0.8 + This is to override the tez setting with the same name + + + hive.tez.task.scale.memory.reserve-fraction.min + 0.3 + This is to override the tez setting tez.task.scale.memory.reserve-fraction + + + hive.tez.task.scale.memory.reserve.fraction.max + 0.5 + The maximum fraction of JVM memory which Tez will reserve for the processor + + + hive.tez.task.scale.memory.reserve.fraction + -1.0 + The customized fraction of JVM memory which Tez will reserve for the processor + + + hive.llap.io.enabled + + Whether the LLAP IO layer is enabled. + + + hive.llap.io.nonvector.wrapper.enabled + true + + Whether the LLAP IO layer is enabled for non-vectorized queries that read inputs + that can be vectorized + + + + hive.llap.io.memory.mode + cache + + Expects one of [cache, none]. + LLAP IO memory usage; 'cache' (the default) uses data and metadata cache with a + custom off-heap allocator, 'none' doesn't use either (this mode may result in + significant performance degradation) + + + + hive.llap.io.allocator.alloc.min + 256Kb + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + Minimum allocation possible from LLAP buddy allocator. Allocations below that are + padded to minimum allocation. For ORC, should generally be the same as the expected + compression buffer size, or next lowest power of 2. Must be a power of 2. + + + + hive.llap.io.allocator.alloc.max + 16Mb + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + Maximum allocation possible from LLAP buddy allocator. For ORC, should be as large as + the largest expected ORC compression buffer size. Must be a power of 2. + + + + hive.llap.io.metadata.fraction + 0.1 + + Temporary setting for on-heap metadata cache fraction of xmx, set to avoid potential + heap problems on very large datasets when on-heap metadata cache takes over + everything. -1 managed metadata and data together (which is more flexible). This + setting will be removed (in effect become -1) once ORC metadata cache is moved off-heap. + + + + hive.llap.io.allocator.arena.count + 8 + + Arena count for LLAP low-level cache; cache will be allocated in the steps of + (size/arena_count) bytes. This size must be <= 1Gb and >= max allocation; if it is + not the case, an adjusted size will be used. Using powers of 2 is recommended. + + + + hive.llap.io.memory.size + 1Gb + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + Maximum size for IO allocator or ORC low-level cache. + + + + hive.llap.io.allocator.direct + true + Whether ORC low-level cache should use direct allocation. + + + hive.llap.io.allocator.mmap + false + + Whether ORC low-level cache should use memory mapped allocation (direct I/O). + This is recommended to be used along-side NVDIMM (DAX) or NVMe flash storage. + + + + hive.llap.io.allocator.mmap.path + /tmp + + Expects a writable directory on the local filesystem. + The directory location for mapping NVDIMM/NVMe flash storage into the ORC low-level cache. + + + + hive.llap.io.use.lrfu + true + Whether ORC low-level cache should use LRFU cache policy instead of default (FIFO). + + + hive.llap.io.lrfu.lambda + 0.01 + + Lambda for ORC low-level cache LRFU cache policy. Must be in [0, 1]. 0 makes LRFU + behave like LFU, 1 makes it behave like LRU, values in between balance accordingly. + + + + hive.llap.cache.allow.synthetic.fileid + false + + Whether LLAP cache should use synthetic file ID if real one is not available. Systems + like HDFS, Isilon, etc. provide a unique file/inode ID. On other FSes (e.g. local + FS), the cache would not work by default because LLAP is unable to uniquely track the + files; enabling this setting allows LLAP to generate file ID from the path, size and + modification time, which is almost certain to identify file uniquely. However, if you + use a FS without file IDs and rewrite files a lot (or are paranoid), you might want + to avoid this setting. + + + + hive.llap.orc.gap.cache + true + + Whether LLAP cache for ORC should remember gaps in ORC compression buffer read + estimates, to avoid re-reading the data that was read once and discarded because it + is unneeded. This is only necessary for ORC files written before HIVE-9660. + + + + hive.llap.io.use.fileid.path + true + + Whether LLAP should use fileId (inode)-based path to ensure better consistency for the + cases of file overwrites. This is supported on HDFS. + + + + hive.llap.io.encode.enabled + true + + Whether LLAP should try to re-encode and cache data for non-ORC formats. This is used + on LLAP Server side to determine if the infrastructure for that is initialized. + + + + hive.llap.io.encode.formats + org.apache.hadoop.mapred.TextInputFormat, + + The table input formats for which LLAP IO should re-encode and cache data. + Comma-separated list. + + + + hive.llap.io.encode.alloc.size + 256Kb + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + Allocation size for the buffers used to cache encoded data from non-ORC files. Must + be a power of two between hive.llap.io.allocator.alloc.min and + hive.llap.io.allocator.alloc.max. + + + + hive.llap.io.encode.vector.serde.enabled + true + Whether LLAP should use vectorized SerDe reader to read text data when re-encoding. + + + hive.llap.io.encode.vector.serde.async.enabled + true + Whether LLAP should use async mode in vectorized SerDe reader to read text data. + + + hive.llap.io.encode.slice.row.count + 100000 + + Row count to use to separate cache slices when reading encoded data from row-based + inputs into LLAP cache, if this feature is enabled. + + + + hive.llap.io.encode.slice.lrr + true + + Whether to separate cache slices when reading encoded data from text inputs via MR + MR LineRecordRedader into LLAP cache, if this feature is enabled. Safety flag. + + + + hive.llap.io.orc.time.counters + true + Whether to enable time counters for LLAP IO layer (time spent in HDFS, etc.) + + + hive.llap.auto.allow.uber + false + Whether or not to allow the planner to run vertices in the AM. + + + hive.llap.auto.enforce.tree + true + Enforce that all parents are in llap, before considering vertex + + + hive.llap.auto.enforce.vectorized + true + Enforce that inputs are vectorized, before considering vertex + + + hive.llap.auto.enforce.stats + true + Enforce that col stats are available, before considering vertex + + + hive.llap.auto.max.input.size + 10737418240 + Check input size, before considering vertex (-1 disables check) + + + hive.llap.auto.max.output.size + 1073741824 + Check output size, before considering vertex (-1 disables check) + + + hive.llap.skip.compile.udf.check + false + + Whether to skip the compile-time check for non-built-in UDFs when deciding whether to + execute tasks in LLAP. Skipping the check allows executing UDFs from pre-localized + jars in LLAP; if the jars are not pre-localized, the UDFs will simply fail to load. + + + + hive.llap.allow.permanent.fns + true + Whether LLAP decider should allow permanent UDFs. + + + hive.llap.execution.mode + none + + Expects one of [auto, none, all, map, only]. + Chooses whether query fragments will run in container or in llap + + + + hive.llap.object.cache.enabled + true + Cache objects (plans, hashtables, etc) in llap + + + hive.llap.io.decoding.metrics.percentiles.intervals + 30 + + Comma-delimited set of integers denoting the desired rollover intervals (in seconds) + for percentile latency metrics on the LLAP daemon IO decoding time. + hive.llap.queue.metrics.percentiles.intervals + + + + hive.llap.io.threadpool.size + 10 + Specify the number of threads to use for low-level IO thread pool. + + + hive.llap.daemon.service.principal + + The name of the LLAP daemon's service principal. + + + hive.llap.daemon.keytab.file + + The path to the Kerberos Keytab file containing the LLAP daemon's service principal. + + + hive.llap.zk.sm.principal + + The name of the principal to use to talk to ZooKeeper for ZooKeeper SecretManager. + + + hive.llap.zk.sm.keytab.file + + + The path to the Kerberos Keytab file containing the principal to use to talk to + ZooKeeper for ZooKeeper SecretManager. + + + + hive.llap.webui.spnego.keytab + + + The path to the Kerberos Keytab file containing the LLAP WebUI SPNEGO principal. + Typical value would look like /etc/security/keytabs/spnego.service.keytab. + + + + hive.llap.webui.spnego.principal + + + The LLAP WebUI SPNEGO service principal. Configured similarly to + hive.server2.webui.spnego.principal + + + + hive.llap.task.principal + + + The name of the principal to use to run tasks. By default, the clients are required + to provide tokens to access HDFS/etc. + + + + hive.llap.task.keytab.file + + + The path to the Kerberos Keytab file containing the principal to use to run tasks. + By default, the clients are required to provide tokens to access HDFS/etc. + + + + hive.llap.zk.sm.connectionString + + ZooKeeper connection string for ZooKeeper SecretManager. + + + hive.llap.zk.registry.user + + + In the LLAP ZooKeeper-based registry, specifies the username in the Zookeeper path. + This should be the hive user or whichever user is running the LLAP daemon. + + + + hive.llap.zk.registry.namespace + + + In the LLAP ZooKeeper-based registry, overrides the ZK path namespace. Note that + using this makes the path management (e.g. setting correct ACLs) your responsibility. + + + + hive.llap.daemon.acl + * + The ACL for LLAP daemon. + + + hive.llap.daemon.acl.blocked + + The deny ACL for LLAP daemon. + + + hive.llap.management.acl + * + The ACL for LLAP daemon management. + + + hive.llap.management.acl.blocked + + The deny ACL for LLAP daemon management. + + + hive.llap.remote.token.requires.signing + true + + Expects one of [false, except_llap_owner, true]. + Whether the token returned from LLAP management API should require fragment signing. + True by default; can be disabled to allow CLI to get tokens from LLAP in a secure + cluster by setting it to true or 'except_llap_owner' (the latter returns such tokens + to everyone except the user LLAP cluster is authenticating under). + + + + hive.llap.daemon.delegation.token.lifetime + 14d + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + LLAP delegation token lifetime, in seconds if specified without a unit. + + + + hive.llap.management.rpc.port + 15004 + RPC port for LLAP daemon management service. + + + hive.llap.auto.auth + false + Whether or not to set Hadoop configs to enable auth in LLAP web app. + + + hive.llap.daemon.rpc.num.handlers + 5 + Number of RPC handlers for LLAP daemon. + + + hive.llap.daemon.work.dirs + + + Working directories for the daemon. This should not be set if running as a YARN + application via Slider. It must be set when not running via Slider on YARN. If the value + is set when running as a Slider YARN application, the specified value will be used. + + + + hive.llap.daemon.yarn.shuffle.port + 15551 + YARN shuffle port for LLAP-daemon-hosted shuffle. + + + hive.llap.daemon.yarn.container.mb + -1 + llap server yarn container size in MB. Used in LlapServiceDriver and package.py + + + hive.llap.daemon.queue.name + + Queue name within which the llap slider application will run. Used in LlapServiceDriver and package.py + + + hive.llap.daemon.container.id + + ContainerId of a running LlapDaemon. Used to publish to the registry + + + hive.llap.daemon.nm.address + + + NM Address host:rpcPort for the NodeManager on which the instance of the daemon is running. + Published to the llap registry. Should never be set by users + + + + hive.llap.daemon.shuffle.dir.watcher.enabled + false + TODO doc + + + hive.llap.daemon.am.liveness.heartbeat.interval.ms + 10000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Tez AM-LLAP heartbeat interval (milliseconds). This needs to be below the task timeout + interval, but otherwise as high as possible to avoid unnecessary traffic. + + + + hive.llap.am.liveness.connection.timeout.ms + 10000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Amount of time to wait on connection failures to the AM from an LLAP daemon before + considering the AM to be dead. + + + + hive.llap.am.use.fqdn + false + Whether to use FQDN of the AM machine when submitting work to LLAP. + + + hive.llap.am.liveness.connection.sleep.between.retries.ms + 2000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Sleep duration while waiting to retry connection failures to the AM from the daemon for + the general keep-alive thread (milliseconds). + + + + hive.llap.task.scheduler.timeout.seconds + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Amount of time to wait before failing the query when there are no llap daemons running + (alive) in the cluster. + + + + hive.llap.daemon.num.executors + 4 + + Number of executors to use in LLAP daemon; essentially, the number of tasks that can be + executed in parallel. + + + + hive.llap.daemon.am-reporter.max.threads + 4 + + Maximum number of threads to be used for AM reporter. If this is lower than number of + executors in llap daemon, it would be set to number of executors at runtime. + + + + hive.llap.daemon.rpc.port + 0 + The LLAP daemon RPC port. + + + hive.llap.daemon.memory.per.instance.mb + 4096 + The total amount of memory to use for the executors inside LLAP (in megabytes). + + + hive.llap.daemon.xmx.headroom + 5% + + The total amount of heap memory set aside by LLAP and not used by the executors. Can + be specified as size (e.g. '512Mb'), or percentage (e.g. '5%'). Note that the latter is + derived from the total daemon XMX, which can be different from the total executor + memory if the cache is on-heap; although that's not the default configuration. + + + + hive.llap.daemon.vcpus.per.instance + 4 + The total number of vcpus to use for the executors inside LLAP. + + + hive.llap.daemon.num.file.cleaner.threads + 1 + Number of file cleaner threads in LLAP. + + + hive.llap.file.cleanup.delay.seconds + 300s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + How long to delay before cleaning up query files in LLAP (in seconds, for debugging). + + + + hive.llap.daemon.service.hosts + + + Explicitly specified hosts to use for LLAP scheduling. Useful for testing. By default, + YARN registry is used. + + + + hive.llap.daemon.service.refresh.interval.sec + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + LLAP YARN registry service list refresh delay, in seconds. + + + + hive.llap.daemon.communicator.num.threads + 10 + Number of threads to use in LLAP task communicator in Tez AM. + + + hive.llap.daemon.download.permanent.fns + false + Whether LLAP daemon should localize the resources for permanent UDFs. + + + hive.llap.task.scheduler.node.reenable.min.timeout.ms + 200ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Minimum time after which a previously disabled node will be re-enabled for scheduling, + in milliseconds. This may be modified by an exponential back-off if failures persist. + + + + hive.llap.task.scheduler.node.reenable.max.timeout.ms + 10000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Maximum time after which a previously disabled node will be re-enabled for scheduling, + in milliseconds. This may be modified by an exponential back-off if failures persist. + + + + hive.llap.task.scheduler.node.disable.backoff.factor + 1.5 + + Backoff factor on successive blacklists of a node due to some failures. Blacklist times + start at the min timeout and go up to the max timeout based on this backoff factor. + + + + hive.llap.task.scheduler.num.schedulable.tasks.per.node + 0 + + The number of tasks the AM TaskScheduler will try allocating per node. 0 indicates that + this should be picked up from the Registry. -1 indicates unlimited capacity; positive + values indicate a specific bound. + + + + hive.llap.task.scheduler.locality.delay + 0ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The time should be in between -1 msec (inclusive) and 9223372036854775807 msec (inclusive). + Amount of time to wait before allocating a request which contains location information, to a location other than the ones requested. Set to -1 for an infinite delay, 0for no delay. + + + + hive.llap.daemon.task.preemption.metrics.intervals + 30,60,300 + + Comma-delimited set of integers denoting the desired rollover intervals (in seconds) + for percentile latency metrics. Used by LLAP daemon task scheduler metrics for + time taken to kill task (due to pre-emption) and useful time wasted by the task that + is about to be preempted. + + + + hive.llap.daemon.task.scheduler.wait.queue.size + 10 + LLAP scheduler maximum queue size. + + + hive.llap.daemon.wait.queue.comparator.class.name + org.apache.hadoop.hive.llap.daemon.impl.comparator.ShortestJobFirstComparator + + The priority comparator to use for LLAP scheduler prioroty queue. The built-in options + are org.apache.hadoop.hive.llap.daemon.impl.comparator.ShortestJobFirstComparator and + .....FirstInFirstOutComparator + + + + hive.llap.daemon.task.scheduler.enable.preemption + true + + Whether non-finishable running tasks (e.g. a reducer waiting for inputs) should be + preempted by finishable tasks inside LLAP scheduler. + + + + hive.llap.task.communicator.connection.timeout.ms + 16000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Connection timeout (in milliseconds) before a failure to an LLAP daemon from Tez AM. + + + + hive.llap.task.communicator.listener.thread-count + 30 + The number of task communicator listener threads. + + + hive.llap.task.communicator.connection.sleep.between.retries.ms + 2000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Sleep duration (in milliseconds) to wait before retrying on error when obtaining a + connection to LLAP daemon from Tez AM. + + + + hive.llap.daemon.web.port + 15002 + LLAP daemon web UI port. + + + hive.llap.daemon.web.ssl + false + Whether LLAP daemon web UI should use SSL. + + + hive.llap.client.consistent.splits + false + Whether to setup split locations to match nodes on which llap daemons are running, instead of using the locations provided by the split itself. If there is no llap daemon running, fall back to locations provided by the split. This is effective only if hive.execution.mode is llap + + + hive.llap.validate.acls + true + + Whether LLAP should reject permissive ACLs in some cases (e.g. its own management + protocol or ZK paths), similar to how ssh refuses a key with bad access permissions. + + + + hive.llap.daemon.output.service.port + 15003 + LLAP daemon output service port + + + hive.llap.daemon.output.stream.timeout + 120s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + The timeout for the client to connect to LLAP output service and start the fragment + output after sending the fragment. The fragment will fail if its output is not claimed. + + + + hive.llap.daemon.output.service.send.buffer.size + 131072 + Send buffer size to be used by LLAP daemon output service + + + hive.llap.daemon.output.service.max.pending.writes + 8 + + Maximum number of queued writes allowed per connection when sending data + via the LLAP output service to external clients. + + + + hive.llap.enable.grace.join.in.llap + false + Override if grace join should be allowed to run in llap. + + + hive.llap.hs2.coordinator.enabled + true + + Whether to create the LLAP coordinator; since execution engine and container vs llap + settings are both coming from job configs, we don't know at start whether this should + be created. Default true. + + + + hive.llap.daemon.logger + query-routing + + Expects one of [query-routing, rfa, console]. + logger used for llap-daemons. + + + + hive.spark.use.op.stats + true + Whether to use operator stats to determine reducer parallelism for Hive on Spark. If this is false, Hive will use source table stats to determine reducer parallelism for all first level reduce tasks, and the maximum reducer parallelism from all parents for all the rest (second level and onward) reducer tasks. + + + hive.spark.use.file.size.for.mapjoin + false + If this is set to true, mapjoin optimization in Hive/Spark will use source file sizes associated with TableScan operator on the root of operator tree, instead of using operator statistics. + + + hive.spark.client.future.timeout + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Timeout for requests from Hive client to remote Spark driver. + + + + hive.spark.job.monitor.timeout + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Timeout for job monitor to get Spark job state. + + + + hive.spark.client.connect.timeout + 1000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Timeout for remote Spark driver in connecting back to Hive client. + + + + hive.spark.client.server.connect.timeout + 90000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Timeout for handshake between Hive client and remote Spark driver. Checked by both processes. + + + + hive.spark.client.secret.bits + 256 + Number of bits of randomness in the generated secret for communication between Hive client and remote Spark driver. Rounded down to the nearest multiple of 8. + + + hive.spark.client.rpc.threads + 8 + Maximum number of threads for remote Spark driver's RPC event loop. + + + hive.spark.client.rpc.max.size + 52428800 + Maximum message size in bytes for communication between Hive client and remote Spark driver. Default is 50MB. + + + hive.spark.client.channel.log.level + + Channel logging level for remote Spark driver. One of {DEBUG, ERROR, INFO, TRACE, WARN}. + + + hive.spark.client.rpc.sasl.mechanisms + DIGEST-MD5 + Name of the SASL mechanism to use for authentication. + + + hive.spark.client.rpc.server.address + + The server address of HiverServer2 host to be used for communication between Hive client and remote Spark driver. Default is empty, which means the address will be determined in the same way as for hive.server2.thrift.bind.host.This is only necessary if the host has mutiple network addresses and if a different network address other than hive.server2.thrift.bind.host is to be used. + + + hive.spark.client.rpc.server.port + + A list of port ranges which can be used by RPC server with the format of 49152-49222,49228 and a random one is selected from the list. Default is empty, which randomly selects one port from all available ones. + + + hive.spark.dynamic.partition.pruning + false + + When dynamic pruning is enabled, joins on partition keys will be processed by writing + to a temporary HDFS file, and read later for removing unnecessary partitions. + + + + hive.spark.dynamic.partition.pruning.max.data.size + 104857600 + Maximum total data size in dynamic pruning. + + + hive.spark.use.groupby.shuffle + true + Spark groupByKey transformation has better performance but uses unbounded memory.Turn this off when there is a memory issue. + + + hive.reorder.nway.joins + true + Runs reordering of tables within single n-way join (i.e.: picks streamtable) + + + hive.merge.nway.joins + true + Merge adjacent joins into a single n-way join + + + hive.log.every.n.records + 0 + + Expects value bigger than 0. + If value is greater than 0 logs in fixed intervals of size n rather than exponentially. + + + + hive.msck.path.validation + throw + + Expects one of [throw, skip, ignore]. + The approach msck should take with HDFS directories that are partition-like but contain unsupported characters. 'throw' (an exception) is the default; 'skip' will skip the invalid directories and still repair the others; 'ignore' will skip the validation (legacy behavior, causes bugs in many cases) + + + + hive.msck.repair.batch.size + 0 + Batch size for the msck repair command. If the value is greater than zero, it will execute batch wise with the configured batch size. The default value is zero. Zero means it will execute directly (Not batch wise) + + + hive.server2.llap.concurrent.queries + -1 + The number of queries allowed in parallel via llap. Negative number implies 'infinite'. + + + hive.tez.enable.memory.manager + true + Enable memory manager for tez + + + hive.hash.table.inflation.factor + 2.0 + Expected inflation factor between disk/in memory representation of hash tables + + + hive.log.trace.id + + Log tracing id that can be used by upstream clients for tracking respective logs. Truncated to 64 characters. Defaults to use auto-generated session id. + + + hive.conf.restricted.list + hive.security.authenticator.manager,hive.security.authorization.manager,hive.security.metastore.authorization.manager,hive.security.metastore.authenticator.manager,hive.users.in.admin.role,hive.server2.xsrf.filter.enabled,hive.security.authorization.enabled,hive.server2.authentication.ldap.baseDN,hive.server2.authentication.ldap.url,hive.server2.authentication.ldap.Domain,hive.server2.authentication.ldap.groupDNPattern,hive.server2.authentication.ldap.groupFilter,hive.server2.authentication.ldap.userDNPattern,hive.server2.authentication.ldap.userFilter,hive.server2.authentication.ldap.groupMembershipKey,hive.server2.authentication.ldap.userMembershipKey,hive.server2.authentication.ldap.groupClassKey,hive.server2.authentication.ldap.customLDAPQuery + Comma separated list of configuration options which are immutable at runtime + + + hive.conf.hidden.list + javax.jdo.option.ConnectionPassword,hive.server2.keystore.password,fs.s3.awsAccessKeyId,fs.s3.awsSecretAccessKey,fs.s3n.awsAccessKeyId,fs.s3n.awsSecretAccessKey,fs.s3a.access.key,fs.s3a.secret.key,fs.s3a.proxy.password + Comma separated list of configuration options which should not be read by normal user like passwords + + + hive.conf.internal.variable.list + hive.added.files.path,hive.added.jars.path,hive.added.archives.path + Comma separated list of variables which are used internally and should not be configurable. + + + hive.query.timeout.seconds + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Timeout for Running Query in seconds. A nonpositive value means infinite. If the query timeout is also set by thrift API call, the smaller one will be taken. + + + + hive.exec.input.listing.max.threads + 0 + + Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb). + The size should be in between 0Pb (inclusive) and 1Kb (inclusive). + Maximum number of threads that Hive uses to list file information from file systems (recommended > 1 for blobstore). + + + + hive.blobstore.supported.schemes + s3,s3a,s3n + Comma-separated list of supported blobstore schemes. + + + hive.blobstore.use.blobstore.as.scratchdir + false + Enable the use of scratch directories directly on blob storage systems (it may cause performance penalties). + + + hive.blobstore.optimizations.enabled + true + + This parameter enables a number of optimizations when running on blobstores: + (1) If hive.blobstore.use.blobstore.as.scratchdir is false, force the last Hive job to write to the blobstore. + This is a performance optimization that forces the final FileSinkOperator to write to the blobstore. + See HIVE-15121 for details. + + + diff --git a/sahara/plugins/vanilla/v2_8_2/resources/mapred-default.xml b/sahara/plugins/vanilla/v2_8_2/resources/mapred-default.xml new file mode 100644 index 0000000..a0a969f --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/mapred-default.xml @@ -0,0 +1,1892 @@ + + + + + + + + + + + + mapreduce.job.committer.setup.cleanup.needed + true + true, if job needs job-setup and job-cleanup. + false, otherwise + + + + + + mapreduce.task.io.sort.factor + 10 + The number of streams to merge at once while sorting + files. This determines the number of open file handles. + + + + mapreduce.task.io.sort.mb + 100 + The total amount of buffer memory to use while sorting + files, in megabytes. By default, gives each merge stream 1MB, which + should minimize seeks. + + + + mapreduce.map.sort.spill.percent + 0.80 + The soft limit in the serialization buffer. Once reached, a + thread will begin to spill the contents to disk in the background. Note that + collection will not block if this threshold is exceeded while a spill is + already in progress, so spills may be larger than this threshold when it is + set to less than .5 + + + + mapreduce.jobtracker.address + local + The host and port that the MapReduce job tracker runs + at. If "local", then jobs are run in-process as a single map + and reduce task. + + + + + mapreduce.local.clientfactory.class.name + org.apache.hadoop.mapred.LocalClientFactory + This the client factory that is responsible for + creating local job runner client + + + + mapreduce.jobtracker.system.dir + ${hadoop.tmp.dir}/mapred/system + The directory where MapReduce stores control files. + + + + + mapreduce.jobtracker.staging.root.dir + ${hadoop.tmp.dir}/mapred/staging + The root of the staging area for users' job files + In practice, this should be the directory where users' home + directories are located (usually /user) + + + + + mapreduce.cluster.temp.dir + ${hadoop.tmp.dir}/mapred/temp + A shared directory for temporary files. + + + + + mapreduce.job.maps + 2 + The default number of map tasks per job. + Ignored when mapreduce.framework.name is "local". + + + + + mapreduce.job.reduces + 1 + The default number of reduce tasks per job. Typically set to 99% + of the cluster's reduce capacity, so that if a node fails the reduces can + still be executed in a single wave. + Ignored when mapreduce.framework.name is "local". + + + + + mapreduce.job.running.map.limit + 0 + The maximum number of simultaneous map tasks per job. + There is no limit if this value is 0 or negative. + + + + + mapreduce.job.running.reduce.limit + 0 + The maximum number of simultaneous reduce tasks per job. + There is no limit if this value is 0 or negative. + + + + + mapreduce.job.reducer.preempt.delay.sec + 0 + The threshold (in seconds) after which an unsatisfied + mapper request triggers reducer preemption when there is no anticipated + headroom. If set to 0 or a negative value, the reducer is preempted as + soon as lack of headroom is detected. Default is 0. + + + + + mapreduce.job.reducer.unconditional-preempt.delay.sec + 300 + The threshold (in seconds) after which an unsatisfied + mapper request triggers a forced reducer preemption irrespective of the + anticipated headroom. By default, it is set to 5 mins. Setting it to 0 + leads to immediate reducer preemption. Setting to -1 disables this + preemption altogether. + + + + + mapreduce.job.max.split.locations + 10 + The max number of block locations to store for each split for + locality calculation. + + + + + mapreduce.job.split.metainfo.maxsize + 10000000 + The maximum permissible size of the split metainfo file. + The MapReduce ApplicationMaster won't attempt to read submitted split metainfo + files bigger than this configured value. + No limits if set to -1. + + + + + mapreduce.map.maxattempts + 4 + Expert: The maximum number of attempts per map task. + In other words, framework will try to execute a map task these many number + of times before giving up on it. + + + + + mapreduce.reduce.maxattempts + 4 + Expert: The maximum number of attempts per reduce task. + In other words, framework will try to execute a reduce task these many number + of times before giving up on it. + + + + + mapreduce.reduce.shuffle.fetch.retry.enabled + ${yarn.nodemanager.recovery.enabled} + Set to enable fetch retry during host restart. + + + + mapreduce.reduce.shuffle.fetch.retry.interval-ms + 1000 + Time of interval that fetcher retry to fetch again when some + non-fatal failure happens because of some events like NM restart. + + + + + mapreduce.reduce.shuffle.fetch.retry.timeout-ms + 30000 + Timeout value for fetcher to retry to fetch again when some + non-fatal failure happens because of some events like NM restart. + + + + mapreduce.reduce.shuffle.retry-delay.max.ms + 60000 + The maximum number of ms the reducer will delay before retrying + to download map data. + + + + + mapreduce.reduce.shuffle.parallelcopies + 5 + The default number of parallel transfers run by reduce + during the copy(shuffle) phase. + + + + + mapreduce.reduce.shuffle.connect.timeout + 180000 + Expert: The maximum amount of time (in milli seconds) reduce + task spends in trying to connect to a remote node for getting map output. + + + + + mapreduce.reduce.shuffle.read.timeout + 180000 + Expert: The maximum amount of time (in milli seconds) reduce + task waits for map output data to be available for reading after obtaining + connection. + + + + + mapreduce.shuffle.listen.queue.size + 128 + The length of the shuffle server listen queue. + + + + mapreduce.shuffle.connection-keep-alive.enable + false + set to true to support keep-alive connections. + + + + mapreduce.shuffle.connection-keep-alive.timeout + 5 + The number of seconds a shuffle client attempts to retain + http connection. Refer "Keep-Alive: timeout=" header in + Http specification + + + + + mapreduce.task.timeout + 600000 + The number of milliseconds before a task will be + terminated if it neither reads an input, writes an output, nor + updates its status string. A value of 0 disables the timeout. + + + + + mapreduce.map.memory.mb + 1024 + The amount of memory to request from the scheduler for each + map task. + + + + + mapreduce.map.cpu.vcores + 1 + The number of virtual cores to request from the scheduler for + each map task. + + + + + mapreduce.reduce.memory.mb + 1024 + The amount of memory to request from the scheduler for each + reduce task. + + + + + mapreduce.reduce.cpu.vcores + 1 + The number of virtual cores to request from the scheduler for + each reduce task. + + + + + mapred.child.java.opts + -Xmx200m + Java opts for the task processes. + The following symbol, if present, will be interpolated: @taskid@ is replaced + by current TaskID. Any other occurrences of '@' will go unchanged. + For example, to enable verbose gc logging to a file named for the taskid in + /tmp and to set the heap maximum to be a gigabyte, pass a 'value' of: + -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc + + Usage of -Djava.library.path can cause programs to no longer function if + hadoop native libraries are used. These values should instead be set as part + of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and + mapreduce.reduce.env config settings. + + + + + + + + + mapred.child.env + + User added environment variables for the task processes. + Example : + 1) A=foo This will set the env variable A to foo + 2) B=$B:c This is inherit nodemanager's B env variable on Unix. + 3) B=%B%;c This is inherit nodemanager's B env variable on Windows. + + + + + + + + + mapreduce.admin.user.env + + + Expert: Additional execution environment entries for + map and reduce task processes. This is not an additive property. + You must preserve the original value if you want your map and + reduce tasks to have access to native libraries (compression, etc). + When this value is empty, the command to set execution + envrionment will be OS dependent: + For linux, use LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native. + For windows, use PATH = %PATH%;%HADOOP_COMMON_HOME%\\bin. + + + + + yarn.app.mapreduce.am.log.level + INFO + The logging level for the MR ApplicationMaster. The allowed + levels are: OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL. + The setting here could be overriden if "mapreduce.job.log4j-properties-file" + is set. + + + + + mapreduce.map.log.level + INFO + The logging level for the map task. The allowed levels are: + OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL. + The setting here could be overridden if "mapreduce.job.log4j-properties-file" + is set. + + + + + mapreduce.reduce.log.level + INFO + The logging level for the reduce task. The allowed levels are: + OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL. + The setting here could be overridden if "mapreduce.job.log4j-properties-file" + is set. + + + + + mapreduce.map.cpu.vcores + 1 + + The number of virtual cores required for each map task. + + + + + mapreduce.reduce.cpu.vcores + 1 + + The number of virtual cores required for each reduce task. + + + + + mapreduce.reduce.merge.inmem.threshold + 1000 + The threshold, in terms of the number of files + for the in-memory merge process. When we accumulate threshold number of files + we initiate the in-memory merge and spill to disk. A value of 0 or less than + 0 indicates we want to DON'T have any threshold and instead depend only on + the ramfs's memory consumption to trigger the merge. + + + + + mapreduce.reduce.shuffle.merge.percent + 0.66 + The usage threshold at which an in-memory merge will be + initiated, expressed as a percentage of the total memory allocated to + storing in-memory map outputs, as defined by + mapreduce.reduce.shuffle.input.buffer.percent. + + + + + mapreduce.reduce.shuffle.input.buffer.percent + 0.70 + The percentage of memory to be allocated from the maximum heap + size to storing map outputs during the shuffle. + + + + + mapreduce.reduce.input.buffer.percent + 0.0 + The percentage of memory- relative to the maximum heap size- to + retain map outputs during the reduce. When the shuffle is concluded, any + remaining map outputs in memory must consume less than this threshold before + the reduce can begin. + + + + + mapreduce.reduce.shuffle.memory.limit.percent + 0.25 + Expert: Maximum percentage of the in-memory limit that a + single shuffle can consume + + + + mapreduce.shuffle.ssl.enabled + false + + Whether to use SSL for for the Shuffle HTTP endpoints. + + + + + mapreduce.shuffle.ssl.file.buffer.size + 65536 + Buffer size for reading spills from file when using SSL. + + + + + mapreduce.shuffle.max.connections + 0 + Max allowed connections for the shuffle. Set to 0 (zero) + to indicate no limit on the number of connections. + + + + + mapreduce.shuffle.max.threads + 0 + Max allowed threads for serving shuffle connections. Set to zero + to indicate the default of 2 times the number of available + processors (as reported by Runtime.availableProcessors()). Netty is used to + serve requests, so a thread is not needed for each connection. + + + + + mapreduce.shuffle.transferTo.allowed + + This option can enable/disable using nio transferTo method in + the shuffle phase. NIO transferTo does not perform well on windows in the + shuffle phase. Thus, with this configuration property it is possible to + disable it, in which case custom transfer method will be used. Recommended + value is false when running Hadoop on Windows. For Linux, it is recommended + to set it to true. If nothing is set then the default value is false for + Windows, and true for Linux. + + + + + mapreduce.shuffle.transfer.buffer.size + 131072 + This property is used only if + mapreduce.shuffle.transferTo.allowed is set to false. In that case, + this property defines the size of the buffer used in the buffer copy code + for the shuffle phase. The size of this buffer determines the size of the IO + requests. + + + + + mapreduce.reduce.markreset.buffer.percent + 0.0 + The percentage of memory -relative to the maximum heap size- to + be used for caching values when using the mark-reset functionality. + + + + + mapreduce.map.speculative + true + If true, then multiple instances of some map tasks + may be executed in parallel. + + + + mapreduce.reduce.speculative + true + If true, then multiple instances of some reduce tasks + may be executed in parallel. + + + + mapreduce.job.speculative.speculative-cap-running-tasks + 0.1 + The max percent (0-1) of running tasks that + can be speculatively re-executed at any time. + + + + mapreduce.job.speculative.speculative-cap-total-tasks + 0.01 + The max percent (0-1) of all tasks that + can be speculatively re-executed at any time. + + + + mapreduce.job.speculative.minimum-allowed-tasks + 10 + The minimum allowed tasks that + can be speculatively re-executed at any time. + + + + mapreduce.job.speculative.retry-after-no-speculate + 1000 + The waiting time(ms) to do next round of speculation + if there is no task speculated in this round. + + + + mapreduce.job.speculative.retry-after-speculate + 15000 + The waiting time(ms) to do next round of speculation + if there are tasks speculated in this round. + + + + mapreduce.job.map.output.collector.class + org.apache.hadoop.mapred.MapTask$MapOutputBuffer + + The MapOutputCollector implementation(s) to use. This may be a comma-separated + list of class names, in which case the map task will try to initialize each + of the collectors in turn. The first to successfully initialize will be used. + + + + + mapreduce.job.speculative.slowtaskthreshold + 1.0 + The number of standard deviations by which a task's + ave progress-rates must be lower than the average of all running tasks' + for the task to be considered too slow. + + + + + mapreduce.job.ubertask.enable + false + Whether to enable the small-jobs "ubertask" optimization, + which runs "sufficiently small" jobs sequentially within a single JVM. + "Small" is defined by the following maxmaps, maxreduces, and maxbytes + settings. Note that configurations for application masters also affect + the "Small" definition - yarn.app.mapreduce.am.resource.mb must be + larger than both mapreduce.map.memory.mb and mapreduce.reduce.memory.mb, + and yarn.app.mapreduce.am.resource.cpu-vcores must be larger than + both mapreduce.map.cpu.vcores and mapreduce.reduce.cpu.vcores to enable + ubertask. Users may override this value. + + + + + mapreduce.job.ubertask.maxmaps + 9 + Threshold for number of maps, beyond which job is considered + too big for the ubertasking optimization. Users may override this value, + but only downward. + + + + + mapreduce.job.ubertask.maxreduces + 1 + Threshold for number of reduces, beyond which job is considered + too big for the ubertasking optimization. CURRENTLY THE CODE CANNOT SUPPORT + MORE THAN ONE REDUCE and will ignore larger values. (Zero is a valid max, + however.) Users may override this value, but only downward. + + + + + mapreduce.job.ubertask.maxbytes + + Threshold for number of input bytes, beyond which job is + considered too big for the ubertasking optimization. If no value is + specified, dfs.block.size is used as a default. Be sure to specify a + default value in mapred-site.xml if the underlying filesystem is not HDFS. + Users may override this value, but only downward. + + + + + mapreduce.job.emit-timeline-data + false + Specifies if the Application Master should emit timeline data + to the timeline server. Individual jobs can override this value. + + + + + mapreduce.input.fileinputformat.split.minsize + 0 + The minimum size chunk that map input should be split + into. Note that some file formats may have minimum split sizes that + take priority over this setting. + + + + mapreduce.input.fileinputformat.list-status.num-threads + 1 + The number of threads to use to list and fetch block locations + for the specified input paths. Note: multiple threads should not be used + if a custom non thread-safe path filter is used. + + + + + mapreduce.input.lineinputformat.linespermap + 1 + When using NLineInputFormat, the number of lines of input data + to include in each split. + + + + + mapreduce.client.submit.file.replication + 10 + The replication level for submitted job files. This + should be around the square root of the number of nodes. + + + + + mapreduce.task.files.preserve.failedtasks + false + Should the files for failed tasks be kept. This should only be + used on jobs that are failing, because the storage is never + reclaimed. It also prevents the map outputs from being erased + from the reduce directory as they are consumed. + + + + + + + mapreduce.output.fileoutputformat.compress + false + Should the job outputs be compressed? + + + + + mapreduce.output.fileoutputformat.compress.type + RECORD + If the job outputs are to compressed as SequenceFiles, how should + they be compressed? Should be one of NONE, RECORD or BLOCK. + + + + + mapreduce.output.fileoutputformat.compress.codec + org.apache.hadoop.io.compress.DefaultCodec + If the job outputs are compressed, how should they be compressed? + + + + + mapreduce.map.output.compress + false + Should the outputs of the maps be compressed before being + sent across the network. Uses SequenceFile compression. + + + + + mapreduce.map.output.compress.codec + org.apache.hadoop.io.compress.DefaultCodec + If the map outputs are compressed, how should they be + compressed? + + + + + map.sort.class + org.apache.hadoop.util.QuickSort + The default sort class for sorting keys. + + + + + mapreduce.task.userlog.limit.kb + 0 + The maximum size of user-logs of each task in KB. 0 disables the cap. + + + + + yarn.app.mapreduce.am.container.log.limit.kb + 0 + The maximum size of the MRAppMaster attempt container logs in KB. + 0 disables the cap. + + + + + yarn.app.mapreduce.task.container.log.backups + 0 + Number of backup files for task logs when using + ContainerRollingLogAppender (CRLA). See + org.apache.log4j.RollingFileAppender.maxBackupIndex. By default, + ContainerLogAppender (CLA) is used, and container logs are not rolled. CRLA + is enabled for tasks when both mapreduce.task.userlog.limit.kb and + yarn.app.mapreduce.task.container.log.backups are greater than zero. + + + + + yarn.app.mapreduce.am.container.log.backups + 0 + Number of backup files for the ApplicationMaster logs when using + ContainerRollingLogAppender (CRLA). See + org.apache.log4j.RollingFileAppender.maxBackupIndex. By default, + ContainerLogAppender (CLA) is used, and container logs are not rolled. CRLA + is enabled for the ApplicationMaster when both + yarn.app.mapreduce.am.container.log.limit.kb and + yarn.app.mapreduce.am.container.log.backups are greater than zero. + + + + + yarn.app.mapreduce.shuffle.log.separate + true + If enabled ('true') logging generated by the client-side shuffle + classes in a reducer will be written in a dedicated log file + 'syslog.shuffle' instead of 'syslog'. + + + + + yarn.app.mapreduce.shuffle.log.limit.kb + 0 + Maximum size of the syslog.shuffle file in kilobytes + (0 for no limit). + + + + + yarn.app.mapreduce.shuffle.log.backups + 0 + If yarn.app.mapreduce.shuffle.log.limit.kb and + yarn.app.mapreduce.shuffle.log.backups are greater than zero + then a ContainerRollngLogAppender is used instead of ContainerLogAppender + for syslog.shuffle. See + org.apache.log4j.RollingFileAppender.maxBackupIndex + + + + + mapreduce.job.maxtaskfailures.per.tracker + 3 + The number of task-failures on a node manager of a given job + after which new tasks of that job aren't assigned to it. It + MUST be less than mapreduce.map.maxattempts and + mapreduce.reduce.maxattempts otherwise the failed task will + never be tried on a different node. + + + + + mapreduce.client.output.filter + FAILED + The filter for controlling the output of the task's userlogs sent + to the console of the JobClient. + The permissible options are: NONE, KILLED, FAILED, SUCCEEDED and + ALL. + + + + + mapreduce.client.completion.pollinterval + 5000 + The interval (in milliseconds) between which the JobClient + polls the MapReduce ApplicationMaster for updates about job status. You may want to + set this to a lower value to make tests run faster on a single node system. Adjusting + this value in production may lead to unwanted client-server traffic. + + + + + mapreduce.client.progressmonitor.pollinterval + 1000 + The interval (in milliseconds) between which the JobClient + reports status to the console and checks for job completion. You may want to set this + to a lower value to make tests run faster on a single node system. Adjusting + this value in production may lead to unwanted client-server traffic. + + + + + + mapreduce.task.profile + false + To set whether the system should collect profiler + information for some of the tasks in this job? The information is stored + in the user log directory. The value is "true" if task profiling + is enabled. + + + + mapreduce.task.profile.maps + 0-2 + To set the ranges of map tasks to profile. + mapreduce.task.profile has to be set to true for the value to be accounted. + + + + + mapreduce.task.profile.reduces + 0-2 + To set the ranges of reduce tasks to profile. + mapreduce.task.profile has to be set to true for the value to be accounted. + + + + + mapreduce.task.profile.params + -agentlib:hprof=cpu=samples,heap=sites,force=n,thread=y,verbose=n,file=%s + JVM profiler parameters used to profile map and reduce task + attempts. This string may contain a single format specifier %s that will + be replaced by the path to profile.out in the task attempt log directory. + To specify different profiling options for map tasks and reduce tasks, + more specific parameters mapreduce.task.profile.map.params and + mapreduce.task.profile.reduce.params should be used. + + + + mapreduce.task.profile.map.params + ${mapreduce.task.profile.params} + Map-task-specific JVM profiler parameters. See + mapreduce.task.profile.params + + + + mapreduce.task.profile.reduce.params + ${mapreduce.task.profile.params} + Reduce-task-specific JVM profiler parameters. See + mapreduce.task.profile.params + + + + mapreduce.task.skip.start.attempts + 2 + The number of Task attempts AFTER which skip mode + will be kicked off. When skip mode is kicked off, the + tasks reports the range of records which it will process + next, to the MR ApplicationMaster. So that on failures, the MR AM + knows which ones are possibly the bad records. On further executions, + those are skipped. + + + + + mapreduce.map.skip.proc-count.auto-incr + true + The flag which if set to true, + SkipBadRecords.COUNTER_MAP_PROCESSED_RECORDS is incremented + by MapRunner after invoking the map function. This value must be set to + false for applications which process the records asynchronously + or buffer the input records. For example streaming. + In such cases applications should increment this counter on their own. + + + + + mapreduce.reduce.skip.proc-count.auto-incr + true + The flag which if set to true, + SkipBadRecords.COUNTER_REDUCE_PROCESSED_GROUPS is incremented + by framework after invoking the reduce function. This value must be set to + false for applications which process the records asynchronously + or buffer the input records. For example streaming. + In such cases applications should increment this counter on their own. + + + + + mapreduce.job.skip.outdir + + If no value is specified here, the skipped records are + written to the output directory at _logs/skip. + User can stop writing skipped records by giving the value "none". + + + + + mapreduce.map.skip.maxrecords + 0 + The number of acceptable skip records surrounding the bad + record PER bad record in mapper. The number includes the bad record as well. + To turn the feature of detection/skipping of bad records off, set the + value to 0. + The framework tries to narrow down the skipped range by retrying + until this threshold is met OR all attempts get exhausted for this task. + Set the value to Long.MAX_VALUE to indicate that framework need not try to + narrow down. Whatever records(depends on application) get skipped are + acceptable. + + + + + mapreduce.reduce.skip.maxgroups + 0 + The number of acceptable skip groups surrounding the bad + group PER bad group in reducer. The number includes the bad group as well. + To turn the feature of detection/skipping of bad groups off, set the + value to 0. + The framework tries to narrow down the skipped range by retrying + until this threshold is met OR all attempts get exhausted for this task. + Set the value to Long.MAX_VALUE to indicate that framework need not try to + narrow down. Whatever groups(depends on application) get skipped are + acceptable. + + + + + mapreduce.ifile.readahead + true + Configuration key to enable/disable IFile readahead. + + + + + mapreduce.ifile.readahead.bytes + 4194304 + Configuration key to set the IFile readahead length in bytes. + + + + + + mapreduce.job.queuename + default + Queue to which a job is submitted. This must match one of the + queues defined in mapred-queues.xml for the system. Also, the ACL setup + for the queue must allow the current user to submit a job to the queue. + Before specifying a queue, ensure that the system is configured with + the queue, and access is allowed for submitting jobs to the queue. + + + + + mapreduce.job.tags + + Tags for the job that will be passed to YARN at submission + time. Queries to YARN for applications can filter on these tags. + + + + + mapreduce.cluster.local.dir + ${hadoop.tmp.dir}/mapred/local + + The local directory where MapReduce stores intermediate + data files. May be a comma-separated list of + directories on different devices in order to spread disk i/o. + Directories that do not exist are ignored. + + + + + mapreduce.cluster.acls.enabled + false + Specifies whether ACLs should be checked + for authorization of users for doing various queue and job level operations. + ACLs are disabled by default. If enabled, access control checks are made by + MapReduce ApplicationMaster when requests are made by users for queue + operations like submit job to a queue and kill a job in the queue and job + operations like viewing the job-details (See mapreduce.job.acl-view-job) + or for modifying the job (See mapreduce.job.acl-modify-job) using + Map/Reduce APIs, RPCs or via the console and web user interfaces. + For enabling this flag, set to true in mapred-site.xml file of all + MapReduce clients (MR job submitting nodes). + + + + + mapreduce.job.acl-modify-job + + Job specific access-control list for 'modifying' the job. It + is only used if authorization is enabled in Map/Reduce by setting the + configuration property mapreduce.cluster.acls.enabled to true. + This specifies the list of users and/or groups who can do modification + operations on the job. For specifying a list of users and groups the + format to use is "user1,user2 group1,group". If set to '*', it allows all + users/groups to modify this job. If set to ' '(i.e. space), it allows + none. This configuration is used to guard all the modifications with respect + to this job and takes care of all the following operations: + o killing this job + o killing a task of this job, failing a task of this job + o setting the priority of this job + Each of these operations are also protected by the per-queue level ACL + "acl-administer-jobs" configured via mapred-queues.xml. So a caller should + have the authorization to satisfy either the queue-level ACL or the + job-level ACL. + + Irrespective of this ACL configuration, (a) job-owner, (b) the user who + started the cluster, (c) members of an admin configured supergroup + configured via mapreduce.cluster.permissions.supergroup and (d) queue + administrators of the queue to which this job was submitted to configured + via acl-administer-jobs for the specific queue in mapred-queues.xml can + do all the modification operations on a job. + + By default, nobody else besides job-owner, the user who started the cluster, + members of supergroup and queue administrators can perform modification + operations on a job. + + + + + mapreduce.job.acl-view-job + + Job specific access-control list for 'viewing' the job. It is + only used if authorization is enabled in Map/Reduce by setting the + configuration property mapreduce.cluster.acls.enabled to true. + This specifies the list of users and/or groups who can view private details + about the job. For specifying a list of users and groups the + format to use is "user1,user2 group1,group". If set to '*', it allows all + users/groups to modify this job. If set to ' '(i.e. space), it allows + none. This configuration is used to guard some of the job-views and at + present only protects APIs that can return possibly sensitive information + of the job-owner like + o job-level counters + o task-level counters + o tasks' diagnostic information + o task-logs displayed on the HistoryServer's web-UI and + o job.xml showed by the HistoryServer's web-UI + Every other piece of information of jobs is still accessible by any other + user, for e.g., JobStatus, JobProfile, list of jobs in the queue, etc. + + Irrespective of this ACL configuration, (a) job-owner, (b) the user who + started the cluster, (c) members of an admin configured supergroup + configured via mapreduce.cluster.permissions.supergroup and (d) queue + administrators of the queue to which this job was submitted to configured + via acl-administer-jobs for the specific queue in mapred-queues.xml can + do all the view operations on a job. + + By default, nobody else besides job-owner, the user who started the + cluster, memebers of supergroup and queue administrators can perform + view operations on a job. + + + + + mapreduce.job.finish-when-all-reducers-done + false + Specifies whether the job should complete once all reducers + have finished, regardless of whether there are still running mappers. + + + + + mapreduce.job.token.tracking.ids.enabled + false + Whether to write tracking ids of tokens to + job-conf. When true, the configuration property + "mapreduce.job.token.tracking.ids" is set to the token-tracking-ids of + the job + + + + mapreduce.job.token.tracking.ids + + When mapreduce.job.token.tracking.ids.enabled is + set to true, this is set by the framework to the + token-tracking-ids used by the job. + + + + mapreduce.task.merge.progress.records + 10000 + The number of records to process during merge before + sending a progress notification to the MR ApplicationMaster. + + + + + mapreduce.task.combine.progress.records + 10000 + The number of records to process during combine output collection + before sending a progress notification. + + + + + mapreduce.job.reduce.slowstart.completedmaps + 0.05 + Fraction of the number of maps in the job which should be + complete before reduces are scheduled for the job. + + + + +mapreduce.job.complete.cancel.delegation.tokens + true + if false - do not unregister/cancel delegation tokens from + renewal, because same tokens may be used by spawned jobs + + + + + mapreduce.shuffle.port + 13562 + Default port that the ShuffleHandler will run on. ShuffleHandler + is a service run at the NodeManager to facilitate transfers of intermediate + Map outputs to requesting Reducers. + + + + + mapreduce.job.reduce.shuffle.consumer.plugin.class + org.apache.hadoop.mapreduce.task.reduce.Shuffle + + Name of the class whose instance will be used + to send shuffle requests by reducetasks of this job. + The class must be an instance of org.apache.hadoop.mapred.ShuffleConsumerPlugin. + + + + + + + mapreduce.job.node-label-expression + All the containers of the Map Reduce job will be run with this + node label expression. If the node-label-expression for job is not set, then + it will use queue's default-node-label-expression for all job's containers. + + + + + mapreduce.job.am.node-label-expression + This is node-label configuration for Map Reduce Application Master + container. If not configured it will make use of + mapreduce.job.node-label-expression and if job's node-label expression is not + configured then it will use queue's default-node-label-expression. + + + + + mapreduce.map.node-label-expression + This is node-label configuration for Map task containers. If not + configured it will use mapreduce.job.node-label-expression and if job's + node-label expression is not configured then it will use queue's + default-node-label-expression. + + + + + mapreduce.reduce.node-label-expression + This is node-label configuration for Reduce task containers. If + not configured it will use mapreduce.job.node-label-expression and if job's + node-label expression is not configured then it will use queue's + default-node-label-expression. + + + + + mapreduce.job.counters.limit + 120 + Limit on the number of user counters allowed per job. + + + + + mapreduce.framework.name + local + The runtime framework for executing MapReduce jobs. + Can be one of local, classic or yarn. + + + + + yarn.app.mapreduce.am.staging-dir + /tmp/hadoop-yarn/staging + The staging dir used while submitting jobs. + + + + + mapreduce.am.max-attempts + 2 + The maximum number of application attempts. It is a + application-specific setting. It should not be larger than the global number + set by resourcemanager. Otherwise, it will be override. The default number is + set to 2, to allow at least one retry for AM. + + + + + mapreduce.job.end-notification.url + + Indicates url which will be called on completion of job to inform + end status of job. + User can give at most 2 variables with URI : $jobId and $jobStatus. + If they are present in URI, then they will be replaced by their + respective values. + + + + + mapreduce.job.end-notification.retry.attempts + 0 + The number of times the submitter of the job wants to retry job + end notification if it fails. This is capped by + mapreduce.job.end-notification.max.attempts + + + + mapreduce.job.end-notification.retry.interval + 1000 + The number of milliseconds the submitter of the job wants to + wait before job end notification is retried if it fails. This is capped by + mapreduce.job.end-notification.max.retry.interval + + + + mapreduce.job.end-notification.max.attempts + 5 + true + The maximum number of times a URL will be read for providing job + end notification. Cluster administrators can set this to limit how long + after end of a job, the Application Master waits before exiting. Must be + marked as final to prevent users from overriding this. + + + + + mapreduce.job.log4j-properties-file + + Used to override the default settings of log4j in container-log4j.properties + for NodeManager. Like container-log4j.properties, it requires certain + framework appenders properly defined in this overriden file. The file on the + path will be added to distributed cache and classpath. If no-scheme is given + in the path, it defaults to point to a log4j file on the local FS. + + + + + mapreduce.job.end-notification.max.retry.interval + 5000 + true + The maximum amount of time (in milliseconds) to wait before + retrying job end notification. Cluster administrators can set this to + limit how long the Application Master waits before exiting. Must be marked + as final to prevent users from overriding this. + + + + yarn.app.mapreduce.am.env + + User added environment variables for the MR App Master + processes. Example : + 1) A=foo This will set the env variable A to foo + 2) B=$B:c This is inherit tasktracker's B env variable. + + + + + yarn.app.mapreduce.am.admin.user.env + + Environment variables for the MR App Master + processes for admin purposes. These values are set first and can be + overridden by the user env (yarn.app.mapreduce.am.env) Example : + 1) A=foo This will set the env variable A to foo + 2) B=$B:c This is inherit app master's B env variable. + + + + + yarn.app.mapreduce.am.command-opts + -Xmx1024m + Java opts for the MR App Master processes. + The following symbol, if present, will be interpolated: @taskid@ is replaced + by current TaskID. Any other occurrences of '@' will go unchanged. + For example, to enable verbose gc logging to a file named for the taskid in + /tmp and to set the heap maximum to be a gigabyte, pass a 'value' of: + -Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc + + Usage of -Djava.library.path can cause programs to no longer function if + hadoop native libraries are used. These values should instead be set as part + of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and + mapreduce.reduce.env config settings. + + + + + yarn.app.mapreduce.am.admin-command-opts + + Java opts for the MR App Master processes for admin purposes. + It will appears before the opts set by yarn.app.mapreduce.am.command-opts and + thus its options can be overridden user. + + Usage of -Djava.library.path can cause programs to no longer function if + hadoop native libraries are used. These values should instead be set as part + of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and + mapreduce.reduce.env config settings. + + + + + yarn.app.mapreduce.am.job.task.listener.thread-count + 30 + The number of threads used to handle RPC calls in the + MR AppMaster from remote tasks + + + + yarn.app.mapreduce.am.job.client.port-range + + Range of ports that the MapReduce AM can use when binding. + Leave blank if you want all possible ports. + For example 50000-50050,50100-50200 + + + + yarn.app.mapreduce.am.job.committer.cancel-timeout + 60000 + The amount of time in milliseconds to wait for the output + committer to cancel an operation if the job is killed + + + + yarn.app.mapreduce.am.job.committer.commit-window + 10000 + Defines a time window in milliseconds for output commit + operations. If contact with the RM has occurred within this window then + commits are allowed, otherwise the AM will not allow output commits until + contact with the RM has been re-established. + + + + mapreduce.fileoutputcommitter.algorithm.version + 1 + The file output committer algorithm version + valid algorithm version number: 1 or 2 + default to 1, which is the original algorithm + + In algorithm version 1, + + 1. commitTask will rename directory + $joboutput/_temporary/$appAttemptID/_temporary/$taskAttemptID/ + to + $joboutput/_temporary/$appAttemptID/$taskID/ + + 2. recoverTask will also do a rename + $joboutput/_temporary/$appAttemptID/$taskID/ + to + $joboutput/_temporary/($appAttemptID + 1)/$taskID/ + + 3. commitJob will merge every task output file in + $joboutput/_temporary/$appAttemptID/$taskID/ + to + $joboutput/, then it will delete $joboutput/_temporary/ + and write $joboutput/_SUCCESS + + It has a performance regression, which is discussed in MAPREDUCE-4815. + If a job generates many files to commit then the commitJob + method call at the end of the job can take minutes. + the commit is single-threaded and waits until all + tasks have completed before commencing. + + algorithm version 2 will change the behavior of commitTask, + recoverTask, and commitJob. + + 1. commitTask will rename all files in + $joboutput/_temporary/$appAttemptID/_temporary/$taskAttemptID/ + to $joboutput/ + + 2. recoverTask actually doesn't require to do anything, but for + upgrade from version 1 to version 2 case, it will check if there + are any files in + $joboutput/_temporary/($appAttemptID - 1)/$taskID/ + and rename them to $joboutput/ + + 3. commitJob can simply delete $joboutput/_temporary and write + $joboutput/_SUCCESS + + This algorithm will reduce the output commit time for + large jobs by having the tasks commit directly to the final + output directory as they were completing and commitJob had + very little to do. + + + + + yarn.app.mapreduce.am.scheduler.heartbeat.interval-ms + 1000 + The interval in ms at which the MR AppMaster should send + heartbeats to the ResourceManager + + + + yarn.app.mapreduce.client-am.ipc.max-retries + 3 + The number of client retries to the AM - before reconnecting + to the RM to fetch Application Status. + + + + yarn.app.mapreduce.client-am.ipc.max-retries-on-timeouts + 3 + The number of client retries on socket timeouts to the AM - before + reconnecting to the RM to fetch Application Status. + + + + yarn.app.mapreduce.client.max-retries + 3 + The number of client retries to the RM/HS before + throwing exception. This is a layer above the ipc. + + + + yarn.app.mapreduce.am.resource.mb + 1536 + The amount of memory the MR AppMaster needs. + + + + yarn.app.mapreduce.am.resource.cpu-vcores + 1 + + The number of virtual CPU cores the MR AppMaster needs. + + + + + yarn.app.mapreduce.am.hard-kill-timeout-ms + 10000 + + Number of milliseconds to wait before the job client kills the application. + + + + + yarn.app.mapreduce.client.job.max-retries + 0 + The number of retries the client will make for getJob and + dependent calls. The default is 0 as this is generally only needed for + non-HDFS DFS where additional, high level retries are required to avoid + spurious failures during the getJob call. 30 is a good value for + WASB + + + + yarn.app.mapreduce.client.job.retry-interval + 2000 + The delay between getJob retries in ms for retries configured + with yarn.app.mapreduce.client.job.max-retries. + + + + CLASSPATH for MR applications. A comma-separated list + of CLASSPATH entries. If mapreduce.application.framework is set then this + must specify the appropriate classpath for that archive, and the name of + the archive must be present in the classpath. + If mapreduce.app-submission.cross-platform is false, platform-specific + environment vairable expansion syntax would be used to construct the default + CLASSPATH entries. + For Linux: + $HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*, + $HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*. + For Windows: + %HADOOP_MAPRED_HOME%/share/hadoop/mapreduce/*, + %HADOOP_MAPRED_HOME%/share/hadoop/mapreduce/lib/*. + + If mapreduce.app-submission.cross-platform is true, platform-agnostic default + CLASSPATH for MR applications would be used: + {{HADOOP_MAPRED_HOME}}/share/hadoop/mapreduce/*, + {{HADOOP_MAPRED_HOME}}/share/hadoop/mapreduce/lib/* + Parameter expansion marker will be replaced by NodeManager on container + launch based on the underlying OS accordingly. + + mapreduce.application.classpath + + + + + If enabled, user can submit an application cross-platform + i.e. submit an application from a Windows client to a Linux/Unix server or + vice versa. + + mapreduce.app-submission.cross-platform + false + + + + Path to the MapReduce framework archive. If set, the framework + archive will automatically be distributed along with the job, and this + path would normally reside in a public location in an HDFS filesystem. As + with distributed cache files, this can be a URL with a fragment specifying + the alias to use for the archive name. For example, + hdfs:/mapred/framework/hadoop-mapreduce-2.1.1.tar.gz#mrframework would + alias the localized archive as "mrframework". + + Note that mapreduce.application.classpath must include the appropriate + classpath for the specified framework. The base name of the archive, or + alias of the archive if an alias is used, must appear in the specified + classpath. + + mapreduce.application.framework.path + + + + + mapreduce.job.classloader + false + Whether to use a separate (isolated) classloader for + user classes in the task JVM. + + + + mapreduce.job.classloader.system.classes + + Used to override the default definition of the system classes for + the job classloader. The system classes are a comma-separated list of + patterns that indicate whether to load a class from the system classpath, + instead from the user-supplied JARs, when mapreduce.job.classloader is + enabled. + + A positive pattern is defined as: + 1. A single class name 'C' that matches 'C' and transitively all nested + classes 'C$*' defined in C; + 2. A package name ending with a '.' (e.g., "com.example.") that matches + all classes from that package. + A negative pattern is defined by a '-' in front of a positive pattern + (e.g., "-com.example."). + + A class is considered a system class if and only if it matches one of the + positive patterns and none of the negative ones. More formally: + A class is a member of the inclusion set I if it matches one of the positive + patterns. A class is a member of the exclusion set E if it matches one of + the negative patterns. The set of system classes S = I \ E. + + + + + mapreduce.jvm.system-properties-to-log + os.name,os.version,java.home,java.runtime.version,java.vendor,java.version,java.vm.name,java.class.path,java.io.tmpdir,user.dir,user.name + Comma-delimited list of system properties to log on mapreduce JVM start + + + + + + mapreduce.jobhistory.address + 0.0.0.0:10020 + MapReduce JobHistory Server IPC host:port + + + + mapreduce.jobhistory.webapp.address + 0.0.0.0:19888 + MapReduce JobHistory Server Web UI host:port + + + + mapreduce.jobhistory.webapp.https.address + 0.0.0.0:19890 + + The https address the MapReduce JobHistory Server WebApp is on. + + + + + mapreduce.jobhistory.keytab + + Location of the kerberos keytab file for the MapReduce + JobHistory Server. + + /etc/security/keytab/jhs.service.keytab + + + + mapreduce.jobhistory.principal + + Kerberos principal name for the MapReduce JobHistory Server. + + jhs/_HOST@REALM.TLD + + + + mapreduce.jobhistory.intermediate-done-dir + ${yarn.app.mapreduce.am.staging-dir}/history/done_intermediate + + + + + mapreduce.jobhistory.done-dir + ${yarn.app.mapreduce.am.staging-dir}/history/done + + + + + mapreduce.jobhistory.cleaner.enable + true + + + + + mapreduce.jobhistory.cleaner.interval-ms + 86400000 + How often the job history cleaner checks for files to delete, + in milliseconds. Defaults to 86400000 (one day). Files are only deleted if + they are older than mapreduce.jobhistory.max-age-ms. + + + + + mapreduce.jobhistory.max-age-ms + 604800000 + Job history files older than this many milliseconds will + be deleted when the history cleaner runs. Defaults to 604800000 (1 week). + + + + + mapreduce.jobhistory.client.thread-count + 10 + The number of threads to handle client API requests + + + + mapreduce.jobhistory.datestring.cache.size + 200000 + Size of the date string cache. Effects the number of directories + which will be scanned to find a job. + + + + mapreduce.jobhistory.joblist.cache.size + 20000 + Size of the job list cache + + + + mapreduce.jobhistory.loadedjobs.cache.size + 5 + Size of the loaded job cache. This property is ignored if + the property mapreduce.jobhistory.loadedtasks.cache.size is set to a + positive value. + + + + + mapreduce.jobhistory.loadedtasks.cache.size + + Change the job history cache limit to be set in terms + of total task count. If the total number of tasks loaded exceeds + this value, then the job cache will be shrunk down until it is + under this limit (minimum 1 job in cache). If this value is empty + or nonpositive then the cache reverts to using the property + mapreduce.jobhistory.loadedjobs.cache.size as a job cache size. + + Two recommendations for the mapreduce.jobhistory.loadedtasks.cache.size + property: + 1) For every 100k of cache size, set the heap size of the Job History + Server to 1.2GB. For example, + mapreduce.jobhistory.loadedtasks.cache.size=500000, heap size=6GB. + 2) Make sure that the cache size is larger than the number of tasks + required for the largest job run on the cluster. It might be a good + idea to set the value slightly higher (say, 20%) in order to allow + for job size growth. + + + + + mapreduce.jobhistory.move.interval-ms + 180000 + Scan for history files to more from intermediate done dir to done + dir at this frequency. + + + + + mapreduce.jobhistory.move.thread-count + 3 + The number of threads used to move files. + + + + mapreduce.jobhistory.store.class + + The HistoryStorage class to use to cache history data. + + + + mapreduce.jobhistory.minicluster.fixed.ports + false + Whether to use fixed ports with the minicluster + + + + mapreduce.jobhistory.admin.address + 0.0.0.0:10033 + The address of the History server admin interface. + + + + mapreduce.jobhistory.admin.acl + * + ACL of who can be admin of the History server. + + + + mapreduce.jobhistory.recovery.enable + false + Enable the history server to store server state and recover + server state upon startup. If enabled then + mapreduce.jobhistory.recovery.store.class must be specified. + + + + mapreduce.jobhistory.recovery.store.class + org.apache.hadoop.mapreduce.v2.hs.HistoryServerFileSystemStateStoreService + The HistoryServerStateStoreService class to store history server + state for recovery. + + + + mapreduce.jobhistory.recovery.store.fs.uri + ${hadoop.tmp.dir}/mapred/history/recoverystore + + The URI where history server state will be stored if + HistoryServerFileSystemStateStoreService is configured as the recovery + storage class. + + + + mapreduce.jobhistory.recovery.store.leveldb.path + ${hadoop.tmp.dir}/mapred/history/recoverystore + The URI where history server state will be stored if + HistoryServerLeveldbSystemStateStoreService is configured as the recovery + storage class. + + + + mapreduce.jobhistory.http.policy + HTTP_ONLY + + This configures the HTTP endpoint for JobHistoryServer web UI. + The following values are supported: + - HTTP_ONLY : Service is provided only on http + - HTTPS_ONLY : Service is provided only on https + + + + + mapreduce.jobhistory.jobname.limit + 50 + + Number of characters allowed for job name in Job History Server web page. + + + + + + File format the AM will use when generating the .jhist file. Valid + values are "json" for text output and "binary" for faster parsing. + + mapreduce.jobhistory.jhist.format + json + + + + yarn.app.mapreduce.am.containerlauncher.threadpool-initial-size + 10 + The initial size of thread pool to launch containers in the + app master. + + + + + mapreduce.task.exit.timeout + 60000 + The number of milliseconds before a task will be + terminated if it stays in finishing state for too long. + After a task attempt completes from TaskUmbilicalProtocol's point of view, + it will be transitioned to finishing state. That will give a chance for the + task to exit by itself. + + + + + mapreduce.task.exit.timeout.check-interval-ms + 20000 + The interval in milliseconds between which the MR framework + checks if task attempts stay in finishing state for too long. + + + + + mapreduce.task.local-fs.write-limit.bytes + -1 + Limit on the byte written to the local file system by each task. + This limit only applies to writes that go through the Hadoop filesystem APIs + within the task process (i.e.: writes that will update the local filesystem's + BYTES_WRITTEN counter). It does not cover other writes such as logging, + sideband writes from subprocesses (e.g.: streaming jobs), etc. + Negative values disable the limit. + default is -1 + + + + + The list of job configuration properties whose value will be redacted. + + mapreduce.job.redacted-properties + + + diff --git a/sahara/plugins/vanilla/v2_8_2/resources/oozie-default.xml b/sahara/plugins/vanilla/v2_8_2/resources/oozie-default.xml new file mode 100644 index 0000000..b61f163 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/oozie-default.xml @@ -0,0 +1,2843 @@ + + + + + + + + + + + + oozie.output.compression.codec + gz + + The name of the compression codec to use. + The implementation class for the codec needs to be specified through another property oozie.compression.codecs. + You can specify a comma separated list of 'Codec_name'='Codec_class' for oozie.compression.codecs + where codec class implements the interface org.apache.oozie.compression.CompressionCodec. + If oozie.compression.codecs is not specified, gz codec implementation is used by default. + + + + + oozie.external_monitoring.enable + false + + If the oozie functional metrics needs to be exposed to the metrics-server backend, set it to true + If set to true, the following properties has to be specified : oozie.metrics.server.name, + oozie.metrics.host, oozie.metrics.prefix, oozie.metrics.report.interval.sec, oozie.metrics.port + + + + + oozie.external_monitoring.type + graphite + + The name of the server to which we want to send the metrics, would be graphite or ganglia. + + + + + oozie.external_monitoring.address + http://localhost:2020 + + + + oozie.external_monitoring.metricPrefix + oozie + + + + oozie.external_monitoring.reporterIntervalSecs + 60 + + + + oozie.jmx_monitoring.enable + false + + If the oozie functional metrics needs to be exposed via JMX interface, set it to true. + + + + + oozie.action.mapreduce.uber.jar.enable + false + + If true, enables the oozie.mapreduce.uber.jar mapreduce workflow configuration property, which is used to specify an + uber jar in HDFS. Submitting a workflow with an uber jar requires at least Hadoop 2.2.0 or 1.2.0. If false, workflows + which specify the oozie.mapreduce.uber.jar configuration property will fail. + + + + + oozie.processing.timezone + UTC + + Oozie server timezone. Valid values are UTC and GMT(+/-)####, for example 'GMT+0530' would be India + timezone. All dates parsed and genered dates by Oozie Coordinator/Bundle will be done in the specified + timezone. The default value of 'UTC' should not be changed under normal circumtances. If for any reason + is changed, note that GMT(+/-)#### timezones do not observe DST changes. + + + + + + + oozie.base.url + http://localhost:8080/oozie + + Base Oozie URL. + + + + + + + oozie.system.id + oozie-${user.name} + + The Oozie system ID. + + + + + oozie.systemmode + NORMAL + + System mode for Oozie at startup. + + + + + oozie.delete.runtime.dir.on.shutdown + true + + If the runtime directory should be kept after Oozie shutdowns down. + + + + + oozie.services + + org.apache.oozie.service.SchedulerService, + org.apache.oozie.service.InstrumentationService, + org.apache.oozie.service.MemoryLocksService, + org.apache.oozie.service.UUIDService, + org.apache.oozie.service.ELService, + org.apache.oozie.service.AuthorizationService, + org.apache.oozie.service.UserGroupInformationService, + org.apache.oozie.service.HadoopAccessorService, + org.apache.oozie.service.JobsConcurrencyService, + org.apache.oozie.service.URIHandlerService, + org.apache.oozie.service.DagXLogInfoService, + org.apache.oozie.service.SchemaService, + org.apache.oozie.service.LiteWorkflowAppService, + org.apache.oozie.service.JPAService, + org.apache.oozie.service.StoreService, + org.apache.oozie.service.SLAStoreService, + org.apache.oozie.service.DBLiteWorkflowStoreService, + org.apache.oozie.service.CallbackService, + org.apache.oozie.service.ActionService, + org.apache.oozie.service.ShareLibService, + org.apache.oozie.service.CallableQueueService, + org.apache.oozie.service.ActionCheckerService, + org.apache.oozie.service.RecoveryService, + org.apache.oozie.service.PurgeService, + org.apache.oozie.service.CoordinatorEngineService, + org.apache.oozie.service.BundleEngineService, + org.apache.oozie.service.DagEngineService, + org.apache.oozie.service.CoordMaterializeTriggerService, + org.apache.oozie.service.StatusTransitService, + org.apache.oozie.service.PauseTransitService, + org.apache.oozie.service.GroupsService, + org.apache.oozie.service.ProxyUserService, + org.apache.oozie.service.XLogStreamingService, + org.apache.oozie.service.JvmPauseMonitorService, + org.apache.oozie.service.SparkConfigurationService + + + All services to be created and managed by Oozie Services singleton. + Class names must be separated by commas. + + + + + oozie.services.ext + + + To add/replace services defined in 'oozie.services' with custom implementations. + Class names must be separated by commas. + + + + + oozie.service.XLogStreamingService.buffer.len + 4096 + 4K buffer for streaming the logs progressively + + + + + oozie.service.HCatAccessorService.jmsconnections + + default=java.naming.factory.initial#org.apache.activemq.jndi.ActiveMQInitialContextFactory;java.naming.provider.url#tcp://localhost:61616;connectionFactoryNames#ConnectionFactory + + + Specify the map of endpoints to JMS configuration properties. In general, endpoint + identifies the HCatalog server URL. "default" is used if no endpoint is mentioned + in the query. If some JMS property is not defined, the system will use the property + defined jndi.properties. jndi.properties files is retrieved from the application classpath. + Mapping rules can also be provided for mapping Hcatalog servers to corresponding JMS providers. + hcat://${1}.${2}.server.com:8020=java.naming.factory.initial#Dummy.Factory;java.naming.provider.url#tcp://broker.${2}:61616 + + + + + + + oozie.service.JMSTopicService.topic.name + + default=${username} + + + Topic options are ${username} or ${jobId} or a fixed string which can be specified as default or for a + particular job type. + For e.g To have a fixed string topic for workflows, coordinators and bundles, + specify in the following comma-separated format: {jobtype1}={some_string1}, {jobtype2}={some_string2} + where job type can be WORKFLOW, COORDINATOR or BUNDLE. + e.g. Following defines topic for workflow job, workflow action, coordinator job, coordinator action, + bundle job and bundle action + WORKFLOW=workflow, + COORDINATOR=coordinator, + BUNDLE=bundle + For jobs with no defined topic, default topic will be ${username} + + + + + + oozie.jms.producer.connection.properties + java.naming.factory.initial#org.apache.activemq.jndi.ActiveMQInitialContextFactory;java.naming.provider.url#tcp://localhost:61616;connectionFactoryNames#ConnectionFactory + + + + + oozie.service.JMSAccessorService.connectioncontext.impl + + org.apache.oozie.jms.DefaultConnectionContext + + + Specifies the Connection Context implementation + + + + + + + + oozie.service.ConfigurationService.ignore.system.properties + + oozie.service.AuthorizationService.security.enabled + + + Specifies "oozie.*" properties to cannot be overriden via Java system properties. + Property names must be separted by commas. + + + + + oozie.service.ConfigurationService.verify.available.properties + true + + Specifies whether the available configurations check is enabled or not. + + + + + + + oozie.service.SchedulerService.threads + 10 + + The number of threads to be used by the SchedulerService to run deamon tasks. + If maxed out, scheduled daemon tasks will be queued up and delayed until threads become available. + + + + + + + oozie.service.AuthorizationService.authorization.enabled + false + + Specifies whether security (user name/admin role) is enabled or not. + If disabled any user can manage Oozie system and manage any job. + + + + + oozie.service.AuthorizationService.default.group.as.acl + false + + Enables old behavior where the User's default group is the job's ACL. + + + + + + + oozie.service.InstrumentationService.logging.interval + 60 + + Interval, in seconds, at which instrumentation should be logged by the InstrumentationService. + If set to 0 it will not log instrumentation data. + + + + + + oozie.service.PurgeService.older.than + 30 + + Completed workflow jobs older than this value, in days, will be purged by the PurgeService. + + + + + oozie.service.PurgeService.coord.older.than + 7 + + Completed coordinator jobs older than this value, in days, will be purged by the PurgeService. + + + + + oozie.service.PurgeService.bundle.older.than + 7 + + Completed bundle jobs older than this value, in days, will be purged by the PurgeService. + + + + + oozie.service.PurgeService.purge.old.coord.action + false + + Whether to purge completed workflows and their corresponding coordinator actions + of long running coordinator jobs if the completed workflow jobs are older than the value + specified in oozie.service.PurgeService.older.than. + + + + + oozie.service.PurgeService.purge.limit + 100 + + Completed Actions purge - limit each purge to this value + + + + + oozie.service.PurgeService.purge.interval + 3600 + + Interval at which the purge service will run, in seconds. + + + + + + + oozie.service.RecoveryService.wf.actions.older.than + 120 + + Age of the actions which are eligible to be queued for recovery, in seconds. + + + + + oozie.service.RecoveryService.wf.actions.created.time.interval + 7 + + Created time period of the actions which are eligible to be queued for recovery in days. + + + + + oozie.service.RecoveryService.callable.batch.size + 10 + + This value determines the number of callable which will be batched together + to be executed by a single thread. + + + + + oozie.service.RecoveryService.push.dependency.interval + 200 + + This value determines the delay for push missing dependency command queueing + in Recovery Service + + + + + oozie.service.RecoveryService.interval + 60 + + Interval at which the RecoverService will run, in seconds. + + + + + oozie.service.RecoveryService.coord.older.than + 600 + + Age of the Coordinator jobs or actions which are eligible to be queued for recovery, in seconds. + + + + + oozie.service.RecoveryService.bundle.older.than + 600 + + Age of the Bundle jobs which are eligible to be queued for recovery, in seconds. + + + + + + + oozie.service.CallableQueueService.queue.size + 10000 + Max callable queue size + + + + oozie.service.CallableQueueService.threads + 10 + Number of threads used for executing callables + + + + oozie.service.CallableQueueService.callable.concurrency + 3 + + Maximum concurrency for a given callable type. + Each command is a callable type (submit, start, run, signal, job, jobs, suspend,resume, etc). + Each action type is a callable type (Map-Reduce, Pig, SSH, FS, sub-workflow, etc). + All commands that use action executors (action-start, action-end, action-kill and action-check) use + the action type as the callable type. + + + + + oozie.service.CallableQueueService.callable.next.eligible + true + + If true, when a callable in the queue has already reached max concurrency, + Oozie continuously find next one which has not yet reach max concurrency. + + + + + oozie.service.CallableQueueService.InterruptMapMaxSize + 500 + + Maximum Size of the Interrupt Map, the interrupt element will not be inserted in the map if exceeded the size. + + + + + oozie.service.CallableQueueService.InterruptTypes + kill,resume,suspend,bundle_kill,bundle_resume,bundle_suspend,coord_kill,coord_change,coord_resume,coord_suspend + + Getting the types of XCommands that are considered to be of Interrupt type + + + + + + + oozie.service.CoordMaterializeTriggerService.lookup.interval + + 300 + Coordinator Job Lookup interval.(in seconds). + + + + + + + oozie.service.CoordMaterializeTriggerService.materialization.window + + 3600 + Coordinator Job Lookup command materialized each + job for this next "window" duration + + + + + oozie.service.CoordMaterializeTriggerService.callable.batch.size + 10 + + This value determines the number of callable which will be batched together + to be executed by a single thread. + + + + + oozie.service.CoordMaterializeTriggerService.materialization.system.limit + 50 + + This value determines the number of coordinator jobs to be materialized at a given time. + + + + + oozie.service.coord.normal.default.timeout + + 120 + Default timeout for a coordinator action input check (in minutes) for normal job. + -1 means infinite timeout + + + + oozie.service.coord.default.max.timeout + + 86400 + Default maximum timeout for a coordinator action input check (in minutes). 86400= 60days + + + + + oozie.service.coord.input.check.requeue.interval + + 60000 + Command re-queue interval for coordinator data input check (in millisecond). + + + + + oozie.service.coord.input.check.requeue.interval.additional.delay + 0 + This value (in seconds) will be added into oozie.service.coord.input.check.requeue.interval and resulting value +will be the requeue interval for the actions which are waiting for a long time without any input. + + + + + oozie.service.coord.push.check.requeue.interval + + 600000 + Command re-queue interval for push dependencies (in millisecond). + + + + + oozie.service.coord.default.concurrency + + 1 + Default concurrency for a coordinator job to determine how many maximum action should + be executed at the same time. -1 means infinite concurrency. + + + + oozie.service.coord.default.throttle + + 12 + Default throttle for a coordinator job to determine how many maximum action should + be in WAITING state at the same time. + + + + oozie.service.coord.materialization.throttling.factor + + 0.05 + Determine how many maximum actions should be in WAITING state for a single job at any time. The value is calculated by + this factor X the total queue size. + + + + oozie.service.coord.check.maximum.frequency + true + + When true, Oozie will reject any coordinators with a frequency faster than 5 minutes. It is not recommended to disable + this check or submit coordinators with frequencies faster than 5 minutes: doing so can cause unintended behavior and + additional system stress. + + + + + + + oozie.service.ELService.groups + job-submit,workflow,wf-sla-submit,coord-job-submit-freq,coord-job-submit-nofuncs,coord-job-submit-data,coord-job-submit-instances,coord-sla-submit,coord-action-create,coord-action-create-inst,coord-sla-create,coord-action-start,coord-job-wait-timeout,bundle-submit,coord-job-submit-initial-instance + List of groups for different ELServices + + + + oozie.service.ELService.constants.job-submit + + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.functions.job-submit + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.constants.job-submit + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions without having to include all the built in ones. + + + + + oozie.service.ELService.ext.functions.job-submit + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions without having to include all the built in ones. + + + + + + oozie.service.ELService.constants.workflow + + KB=org.apache.oozie.util.ELConstantsFunctions#KB, + MB=org.apache.oozie.util.ELConstantsFunctions#MB, + GB=org.apache.oozie.util.ELConstantsFunctions#GB, + TB=org.apache.oozie.util.ELConstantsFunctions#TB, + PB=org.apache.oozie.util.ELConstantsFunctions#PB, + RECORDS=org.apache.oozie.action.hadoop.HadoopELFunctions#RECORDS, + MAP_IN=org.apache.oozie.action.hadoop.HadoopELFunctions#MAP_IN, + MAP_OUT=org.apache.oozie.action.hadoop.HadoopELFunctions#MAP_OUT, + REDUCE_IN=org.apache.oozie.action.hadoop.HadoopELFunctions#REDUCE_IN, + REDUCE_OUT=org.apache.oozie.action.hadoop.HadoopELFunctions#REDUCE_OUT, + GROUPS=org.apache.oozie.action.hadoop.HadoopELFunctions#GROUPS + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.workflow + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.workflow + + firstNotNull=org.apache.oozie.util.ELConstantsFunctions#firstNotNull, + concat=org.apache.oozie.util.ELConstantsFunctions#concat, + replaceAll=org.apache.oozie.util.ELConstantsFunctions#replaceAll, + appendAll=org.apache.oozie.util.ELConstantsFunctions#appendAll, + trim=org.apache.oozie.util.ELConstantsFunctions#trim, + timestamp=org.apache.oozie.util.ELConstantsFunctions#timestamp, + urlEncode=org.apache.oozie.util.ELConstantsFunctions#urlEncode, + toJsonStr=org.apache.oozie.util.ELConstantsFunctions#toJsonStr, + toPropertiesStr=org.apache.oozie.util.ELConstantsFunctions#toPropertiesStr, + toConfigurationStr=org.apache.oozie.util.ELConstantsFunctions#toConfigurationStr, + wf:id=org.apache.oozie.DagELFunctions#wf_id, + wf:name=org.apache.oozie.DagELFunctions#wf_name, + wf:appPath=org.apache.oozie.DagELFunctions#wf_appPath, + wf:conf=org.apache.oozie.DagELFunctions#wf_conf, + wf:user=org.apache.oozie.DagELFunctions#wf_user, + wf:group=org.apache.oozie.DagELFunctions#wf_group, + wf:callback=org.apache.oozie.DagELFunctions#wf_callback, + wf:transition=org.apache.oozie.DagELFunctions#wf_transition, + wf:lastErrorNode=org.apache.oozie.DagELFunctions#wf_lastErrorNode, + wf:errorCode=org.apache.oozie.DagELFunctions#wf_errorCode, + wf:errorMessage=org.apache.oozie.DagELFunctions#wf_errorMessage, + wf:run=org.apache.oozie.DagELFunctions#wf_run, + wf:actionData=org.apache.oozie.DagELFunctions#wf_actionData, + wf:actionExternalId=org.apache.oozie.DagELFunctions#wf_actionExternalId, + wf:actionTrackerUri=org.apache.oozie.DagELFunctions#wf_actionTrackerUri, + wf:actionExternalStatus=org.apache.oozie.DagELFunctions#wf_actionExternalStatus, + hadoop:counters=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_counters, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf, + fs:exists=org.apache.oozie.action.hadoop.FsELFunctions#fs_exists, + fs:isDir=org.apache.oozie.action.hadoop.FsELFunctions#fs_isDir, + fs:dirSize=org.apache.oozie.action.hadoop.FsELFunctions#fs_dirSize, + fs:fileSize=org.apache.oozie.action.hadoop.FsELFunctions#fs_fileSize, + fs:blockSize=org.apache.oozie.action.hadoop.FsELFunctions#fs_blockSize, + hcat:exists=org.apache.oozie.coord.HCatELFunctions#hcat_exists + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.WorkflowAppService.WorkflowDefinitionMaxLength + 100000 + + The maximum length of the workflow definition in bytes + An error will be reported if the length exceeds the given maximum + + + + + oozie.service.ELService.ext.functions.workflow + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + oozie.service.ELService.constants.wf-sla-submit + + MINUTES=org.apache.oozie.util.ELConstantsFunctions#SUBMIT_MINUTES, + HOURS=org.apache.oozie.util.ELConstantsFunctions#SUBMIT_HOURS, + DAYS=org.apache.oozie.util.ELConstantsFunctions#SUBMIT_DAYS + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.wf-sla-submit + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.wf-sla-submit + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + oozie.service.ELService.ext.functions.wf-sla-submit + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + +l + + + + oozie.service.ELService.constants.coord-job-submit-freq + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-job-submit-freq + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-job-submit-freq + + coord:days=org.apache.oozie.coord.CoordELFunctions#ph1_coord_days, + coord:months=org.apache.oozie.coord.CoordELFunctions#ph1_coord_months, + coord:hours=org.apache.oozie.coord.CoordELFunctions#ph1_coord_hours, + coord:minutes=org.apache.oozie.coord.CoordELFunctions#ph1_coord_minutes, + coord:endOfDays=org.apache.oozie.coord.CoordELFunctions#ph1_coord_endOfDays, + coord:endOfMonths=org.apache.oozie.coord.CoordELFunctions#ph1_coord_endOfMonths, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.functions.coord-job-submit-initial-instance + + ${oozie.service.ELService.functions.coord-job-submit-nofuncs}, + coord:dateOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_dateOffset, + coord:dateTzOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_dateTzOffset + + + EL functions for coord job submit initial instance, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-job-submit-freq + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.constants.coord-job-wait-timeout + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.constants.coord-job-wait-timeout + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions without having to include all the built in ones. + + + + + oozie.service.ELService.functions.coord-job-wait-timeout + + coord:days=org.apache.oozie.coord.CoordELFunctions#ph1_coord_days, + coord:months=org.apache.oozie.coord.CoordELFunctions#ph1_coord_months, + coord:hours=org.apache.oozie.coord.CoordELFunctions#ph1_coord_hours, + coord:minutes=org.apache.oozie.coord.CoordELFunctions#ph1_coord_minutes, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-job-wait-timeout + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions without having to include all the built in ones. + + + + + + oozie.service.ELService.constants.coord-job-submit-nofuncs + + MINUTE=org.apache.oozie.coord.CoordELConstants#SUBMIT_MINUTE, + HOUR=org.apache.oozie.coord.CoordELConstants#SUBMIT_HOUR, + DAY=org.apache.oozie.coord.CoordELConstants#SUBMIT_DAY, + MONTH=org.apache.oozie.coord.CoordELConstants#SUBMIT_MONTH, + YEAR=org.apache.oozie.coord.CoordELConstants#SUBMIT_YEAR + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-job-submit-nofuncs + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-job-submit-nofuncs + + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-job-submit-nofuncs + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + oozie.service.ELService.constants.coord-job-submit-instances + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-job-submit-instances + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-job-submit-instances + + coord:hoursInDay=org.apache.oozie.coord.CoordELFunctions#ph1_coord_hoursInDay_echo, + coord:daysInMonth=org.apache.oozie.coord.CoordELFunctions#ph1_coord_daysInMonth_echo, + coord:tzOffset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_tzOffset_echo, + coord:current=org.apache.oozie.coord.CoordELFunctions#ph1_coord_current_echo, + coord:currentRange=org.apache.oozie.coord.CoordELFunctions#ph1_coord_currentRange_echo, + coord:offset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_offset_echo, + coord:latest=org.apache.oozie.coord.CoordELFunctions#ph1_coord_latest_echo, + coord:latestRange=org.apache.oozie.coord.CoordELFunctions#ph1_coord_latestRange_echo, + coord:future=org.apache.oozie.coord.CoordELFunctions#ph1_coord_future_echo, + coord:futureRange=org.apache.oozie.coord.CoordELFunctions#ph1_coord_futureRange_echo, + coord:formatTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_formatTime_echo, + coord:epochTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_epochTime_echo, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + coord:absolute=org.apache.oozie.coord.CoordELFunctions#ph1_coord_absolute_echo, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf, + coord:dateOffset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dateOffset_echo, + coord:dateTzOffset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dateTzOffset_echo + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-job-submit-instances + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + + oozie.service.ELService.constants.coord-job-submit-data + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-job-submit-data + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-job-submit-data + + coord:dataIn=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dataIn_echo, + coord:dataOut=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dataOut_echo, + coord:nominalTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_nominalTime_echo_wrap, + coord:actualTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_actualTime_echo_wrap, + coord:dateOffset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dateOffset_echo, + coord:dateTzOffset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dateTzOffset_echo, + coord:formatTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_formatTime_echo, + coord:epochTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_epochTime_echo, + coord:actionId=org.apache.oozie.coord.CoordELFunctions#ph1_coord_actionId_echo, + coord:name=org.apache.oozie.coord.CoordELFunctions#ph1_coord_name_echo, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + coord:databaseIn=org.apache.oozie.coord.HCatELFunctions#ph1_coord_databaseIn_echo, + coord:databaseOut=org.apache.oozie.coord.HCatELFunctions#ph1_coord_databaseOut_echo, + coord:tableIn=org.apache.oozie.coord.HCatELFunctions#ph1_coord_tableIn_echo, + coord:tableOut=org.apache.oozie.coord.HCatELFunctions#ph1_coord_tableOut_echo, + coord:dataInPartitionFilter=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataInPartitionFilter_echo, + coord:dataInPartitionMin=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataInPartitionMin_echo, + coord:dataInPartitionMax=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataInPartitionMax_echo, + coord:dataInPartitions=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataInPartitions_echo, + coord:dataOutPartitions=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataOutPartitions_echo, + coord:dataOutPartitionValue=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataOutPartitionValue_echo, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-job-submit-data + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + oozie.service.ELService.constants.coord-sla-submit + + MINUTES=org.apache.oozie.coord.CoordELConstants#SUBMIT_MINUTES, + HOURS=org.apache.oozie.coord.CoordELConstants#SUBMIT_HOURS, + DAYS=org.apache.oozie.coord.CoordELConstants#SUBMIT_DAYS + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-sla-submit + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.bundle-submit + bundle:conf=org.apache.oozie.bundle.BundleELFunctions#bundle_conf + + + + oozie.service.ELService.functions.coord-sla-submit + + coord:dataOut=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dataOut_echo, + coord:nominalTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_nominalTime_echo_fixed, + coord:actualTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_actualTime_echo_wrap, + coord:dateOffset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dateOffset_echo, + coord:dateTzOffset=org.apache.oozie.coord.CoordELFunctions#ph1_coord_dateTzOffset_echo, + coord:formatTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_formatTime_echo, + coord:epochTime=org.apache.oozie.coord.CoordELFunctions#ph1_coord_epochTime_echo, + coord:actionId=org.apache.oozie.coord.CoordELFunctions#ph1_coord_actionId_echo, + coord:name=org.apache.oozie.coord.CoordELFunctions#ph1_coord_name_echo, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + coord:databaseOut=org.apache.oozie.coord.HCatELFunctions#ph1_coord_databaseOut_echo, + coord:tableOut=org.apache.oozie.coord.HCatELFunctions#ph1_coord_tableOut_echo, + coord:dataOutPartitions=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataOutPartitions_echo, + coord:dataOutPartitionValue=org.apache.oozie.coord.HCatELFunctions#ph1_coord_dataOutPartitionValue_echo, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + oozie.service.ELService.ext.functions.coord-sla-submit + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + oozie.service.ELService.constants.coord-action-create + + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-action-create + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-action-create + + coord:hoursInDay=org.apache.oozie.coord.CoordELFunctions#ph2_coord_hoursInDay, + coord:daysInMonth=org.apache.oozie.coord.CoordELFunctions#ph2_coord_daysInMonth, + coord:tzOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_tzOffset, + coord:current=org.apache.oozie.coord.CoordELFunctions#ph2_coord_current, + coord:currentRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_currentRange, + coord:offset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_offset, + coord:latest=org.apache.oozie.coord.CoordELFunctions#ph2_coord_latest_echo, + coord:latestRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_latestRange_echo, + coord:future=org.apache.oozie.coord.CoordELFunctions#ph2_coord_future_echo, + coord:futureRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_futureRange_echo, + coord:actionId=org.apache.oozie.coord.CoordELFunctions#ph2_coord_actionId, + coord:name=org.apache.oozie.coord.CoordELFunctions#ph2_coord_name, + coord:formatTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_formatTime, + coord:epochTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_epochTime, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + coord:absolute=org.apache.oozie.coord.CoordELFunctions#ph2_coord_absolute_echo, + coord:absoluteRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_absolute_range, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-action-create + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + + oozie.service.ELService.constants.coord-action-create-inst + + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-action-create-inst + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-action-create-inst + + coord:hoursInDay=org.apache.oozie.coord.CoordELFunctions#ph2_coord_hoursInDay, + coord:daysInMonth=org.apache.oozie.coord.CoordELFunctions#ph2_coord_daysInMonth, + coord:tzOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_tzOffset, + coord:current=org.apache.oozie.coord.CoordELFunctions#ph2_coord_current_echo, + coord:currentRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_currentRange_echo, + coord:offset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_offset_echo, + coord:latest=org.apache.oozie.coord.CoordELFunctions#ph2_coord_latest_echo, + coord:latestRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_latestRange_echo, + coord:future=org.apache.oozie.coord.CoordELFunctions#ph2_coord_future_echo, + coord:futureRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_futureRange_echo, + coord:formatTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_formatTime, + coord:epochTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_epochTime, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + coord:absolute=org.apache.oozie.coord.CoordELFunctions#ph2_coord_absolute_echo, + coord:absoluteRange=org.apache.oozie.coord.CoordELFunctions#ph2_coord_absolute_range, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf, + coord:dateOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_dateOffset, + coord:dateTzOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_dateTzOffset + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-action-create-inst + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + oozie.service.ELService.constants.coord-sla-create + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-sla-create + + MINUTES=org.apache.oozie.coord.CoordELConstants#SUBMIT_MINUTES, + HOURS=org.apache.oozie.coord.CoordELConstants#SUBMIT_HOURS, + DAYS=org.apache.oozie.coord.CoordELConstants#SUBMIT_DAYS + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-sla-create + + coord:dataOut=org.apache.oozie.coord.CoordELFunctions#ph3_coord_dataOut, + coord:nominalTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_nominalTime, + coord:actualTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_actualTime, + coord:dateOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_dateOffset, + coord:dateTzOffset=org.apache.oozie.coord.CoordELFunctions#ph2_coord_dateTzOffset, + coord:formatTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_formatTime, + coord:epochTime=org.apache.oozie.coord.CoordELFunctions#ph2_coord_epochTime, + coord:actionId=org.apache.oozie.coord.CoordELFunctions#ph2_coord_actionId, + coord:name=org.apache.oozie.coord.CoordELFunctions#ph2_coord_name, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + coord:databaseOut=org.apache.oozie.coord.HCatELFunctions#ph3_coord_databaseOut, + coord:tableOut=org.apache.oozie.coord.HCatELFunctions#ph3_coord_tableOut, + coord:dataOutPartitions=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataOutPartitions, + coord:dataOutPartitionValue=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataOutPartitionValue, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + oozie.service.ELService.ext.functions.coord-sla-create + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + + oozie.service.ELService.constants.coord-action-start + + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + + + + + oozie.service.ELService.ext.constants.coord-action-start + + + EL constant declarations, separated by commas, format is [PREFIX:]NAME=CLASS#CONSTANT. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.functions.coord-action-start + + coord:hoursInDay=org.apache.oozie.coord.CoordELFunctions#ph3_coord_hoursInDay, + coord:daysInMonth=org.apache.oozie.coord.CoordELFunctions#ph3_coord_daysInMonth, + coord:tzOffset=org.apache.oozie.coord.CoordELFunctions#ph3_coord_tzOffset, + coord:latest=org.apache.oozie.coord.CoordELFunctions#ph3_coord_latest, + coord:latestRange=org.apache.oozie.coord.CoordELFunctions#ph3_coord_latestRange, + coord:future=org.apache.oozie.coord.CoordELFunctions#ph3_coord_future, + coord:futureRange=org.apache.oozie.coord.CoordELFunctions#ph3_coord_futureRange, + coord:dataIn=org.apache.oozie.coord.CoordELFunctions#ph3_coord_dataIn, + coord:dataOut=org.apache.oozie.coord.CoordELFunctions#ph3_coord_dataOut, + coord:nominalTime=org.apache.oozie.coord.CoordELFunctions#ph3_coord_nominalTime, + coord:actualTime=org.apache.oozie.coord.CoordELFunctions#ph3_coord_actualTime, + coord:dateOffset=org.apache.oozie.coord.CoordELFunctions#ph3_coord_dateOffset, + coord:dateTzOffset=org.apache.oozie.coord.CoordELFunctions#ph3_coord_dateTzOffset, + coord:formatTime=org.apache.oozie.coord.CoordELFunctions#ph3_coord_formatTime, + coord:epochTime=org.apache.oozie.coord.CoordELFunctions#ph3_coord_epochTime, + coord:actionId=org.apache.oozie.coord.CoordELFunctions#ph3_coord_actionId, + coord:name=org.apache.oozie.coord.CoordELFunctions#ph3_coord_name, + coord:conf=org.apache.oozie.coord.CoordELFunctions#coord_conf, + coord:user=org.apache.oozie.coord.CoordELFunctions#coord_user, + coord:databaseIn=org.apache.oozie.coord.HCatELFunctions#ph3_coord_databaseIn, + coord:databaseOut=org.apache.oozie.coord.HCatELFunctions#ph3_coord_databaseOut, + coord:tableIn=org.apache.oozie.coord.HCatELFunctions#ph3_coord_tableIn, + coord:tableOut=org.apache.oozie.coord.HCatELFunctions#ph3_coord_tableOut, + coord:dataInPartitionFilter=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataInPartitionFilter, + coord:dataInPartitionMin=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataInPartitionMin, + coord:dataInPartitionMax=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataInPartitionMax, + coord:dataInPartitions=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataInPartitions, + coord:dataOutPartitions=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataOutPartitions, + coord:dataOutPartitionValue=org.apache.oozie.coord.HCatELFunctions#ph3_coord_dataOutPartitionValue, + hadoop:conf=org.apache.oozie.action.hadoop.HadoopELFunctions#hadoop_conf + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + + + + + oozie.service.ELService.ext.functions.coord-action-start + + + + EL functions declarations, separated by commas, format is [PREFIX:]NAME=CLASS#METHOD. + This property is a convenience property to add extensions to the built in executors without having to + include all the built in ones. + + + + + oozie.service.ELService.latest-el.use-current-time + false + + Determine whether to use the current time to determine the latest dependency or the action creation time. + This is for backward compatibility with older oozie behaviour. + + + + + + + oozie.service.UUIDService.generator + counter + + random : generated UUIDs will be random strings. + counter: generated UUIDs generated will be a counter postfixed with the system startup time. + + + + + + + oozie.service.DBLiteWorkflowStoreService.status.metrics.collection.interval + 5 + Workflow Status metrics collection interval in minutes. + + + + oozie.service.DBLiteWorkflowStoreService.status.metrics.window + 3600 + + Workflow Status metrics collection window in seconds. Workflow status will be instrumented for the window. + + + + + + + oozie.db.schema.name + oozie + + Oozie DataBase Name + + + + + + + oozie.service.JPAService.create.db.schema + false + + Creates Oozie DB. + + If set to true, it creates the DB schema if it does not exist. If the DB schema exists is a NOP. + If set to false, it does not create the DB schema. If the DB schema does not exist it fails start up. + + + + + oozie.service.JPAService.validate.db.connection + true + + Validates DB connections from the DB connection pool. + If the 'oozie.service.JPAService.create.db.schema' property is set to true, this property is ignored. + + + + + oozie.service.JPAService.validate.db.connection.eviction.interval + 300000 + + Validates DB connections from the DB connection pool. + When validate db connection 'TestWhileIdle' is true, the number of milliseconds to sleep + between runs of the idle object evictor thread. + + + + + oozie.service.JPAService.validate.db.connection.eviction.num + 10 + + Validates DB connections from the DB connection pool. + When validate db connection 'TestWhileIdle' is true, the number of objects to examine during + each run of the idle object evictor thread. + + + + + + oozie.service.JPAService.connection.data.source + org.apache.commons.dbcp.BasicDataSource + + DataSource to be used for connection pooling. + + + + + oozie.service.JPAService.connection.properties + + + DataSource connection properties. + + + + + oozie.service.JPAService.jdbc.driver + org.apache.derby.jdbc.EmbeddedDriver + + JDBC driver class. + + + + + oozie.service.JPAService.jdbc.url + jdbc:derby:${oozie.data.dir}/${oozie.db.schema.name}-db;create=true + + JDBC URL. + + + + + oozie.service.JPAService.jdbc.username + sa + + DB user name. + + + + + oozie.service.JPAService.jdbc.password + + + DB user password. + + IMPORTANT: if password is emtpy leave a 1 space string, the service trims the value, + if empty Configuration assumes it is NULL. + + IMPORTANT: if the StoreServicePasswordService is active, it will reset this value with the value given in + the console. + + + + + oozie.service.JPAService.pool.max.active.conn + 10 + + Max number of connections. + + + + + oozie.service.JPAService.openjpa.BrokerImpl + non-finalizing + + The default OpenJPAEntityManager implementation automatically closes itself during instance finalization. + This guards against accidental resource leaks that may occur if a developer fails to explicitly close + EntityManagers when finished with them, but it also incurs a scalability bottleneck, since the JVM must + perform synchronization during instance creation, and since the finalizer thread will have more instances to monitor. + To avoid this overhead, set the openjpa.BrokerImpl configuration property to non-finalizing. + To use default implementation set it to empty space. + + + + + + + oozie.service.SchemaService.wf.schemas + + oozie-workflow-0.1.xsd,oozie-workflow-0.2.xsd,oozie-workflow-0.2.5.xsd,oozie-workflow-0.3.xsd,oozie-workflow-0.4.xsd, + oozie-workflow-0.4.5.xsd,oozie-workflow-0.5.xsd, + shell-action-0.1.xsd,shell-action-0.2.xsd,shell-action-0.3.xsd, + email-action-0.1.xsd,email-action-0.2.xsd, + hive-action-0.2.xsd,hive-action-0.3.xsd,hive-action-0.4.xsd,hive-action-0.5.xsd,hive-action-0.6.xsd, + sqoop-action-0.2.xsd,sqoop-action-0.3.xsd,sqoop-action-0.4.xsd, + ssh-action-0.1.xsd,ssh-action-0.2.xsd, + distcp-action-0.1.xsd,distcp-action-0.2.xsd, + oozie-sla-0.1.xsd,oozie-sla-0.2.xsd, + hive2-action-0.1.xsd, hive2-action-0.2.xsd, + spark-action-0.1.xsd,spark-action-0.2.xsd + + + List of schemas for workflows (separated by commas). + + + + + oozie.service.SchemaService.wf.ext.schemas + + + List of additional schemas for workflows (separated by commas). + + + + + oozie.service.SchemaService.coord.schemas + + oozie-coordinator-0.1.xsd,oozie-coordinator-0.2.xsd,oozie-coordinator-0.3.xsd,oozie-coordinator-0.4.xsd, + oozie-coordinator-0.5.xsd,oozie-sla-0.1.xsd,oozie-sla-0.2.xsd + + + List of schemas for coordinators (separated by commas). + + + + + oozie.service.SchemaService.coord.ext.schemas + + + List of additional schemas for coordinators (separated by commas). + + + + + oozie.service.SchemaService.bundle.schemas + + oozie-bundle-0.1.xsd,oozie-bundle-0.2.xsd + + + List of schemas for bundles (separated by commas). + + + + + oozie.service.SchemaService.bundle.ext.schemas + + + List of additional schemas for bundles (separated by commas). + + + + + oozie.service.SchemaService.sla.schemas + + gms-oozie-sla-0.1.xsd,oozie-sla-0.2.xsd + + + List of schemas for semantic validation for GMS SLA (separated by commas). + + + + + oozie.service.SchemaService.sla.ext.schemas + + + List of additional schemas for semantic validation for GMS SLA (separated by commas). + + + + + + + oozie.service.CallbackService.base.url + ${oozie.base.url}/callback + + Base callback URL used by ActionExecutors. + + + + + oozie.service.CallbackService.early.requeue.max.retries + 5 + + If Oozie receives a callback too early (while the action is in PREP state), it will requeue the command this many times + to give the action time to transition to RUNNING. + + + + + + + oozie.servlet.CallbackServlet.max.data.len + 2048 + + Max size in characters for the action completion data output. + + + + + + + oozie.external.stats.max.size + -1 + + Max size in bytes for action stats. -1 means infinite value. + + + + + + + oozie.JobCommand.job.console.url + ${oozie.base.url}?job= + + Base console URL for a workflow job. + + + + + + + + oozie.service.ActionService.executor.classes + + org.apache.oozie.action.decision.DecisionActionExecutor, + org.apache.oozie.action.hadoop.JavaActionExecutor, + org.apache.oozie.action.hadoop.FsActionExecutor, + org.apache.oozie.action.hadoop.MapReduceActionExecutor, + org.apache.oozie.action.hadoop.PigActionExecutor, + org.apache.oozie.action.hadoop.HiveActionExecutor, + org.apache.oozie.action.hadoop.ShellActionExecutor, + org.apache.oozie.action.hadoop.SqoopActionExecutor, + org.apache.oozie.action.hadoop.DistcpActionExecutor, + org.apache.oozie.action.hadoop.Hive2ActionExecutor, + org.apache.oozie.action.ssh.SshActionExecutor, + org.apache.oozie.action.oozie.SubWorkflowActionExecutor, + org.apache.oozie.action.email.EmailActionExecutor, + org.apache.oozie.action.hadoop.SparkActionExecutor + + + List of ActionExecutors classes (separated by commas). + Only action types with associated executors can be used in workflows. + + + + + oozie.service.ActionService.executor.ext.classes + + + List of ActionExecutors extension classes (separated by commas). Only action types with associated + executors can be used in workflows. This property is a convenience property to add extensions to the built + in executors without having to include all the built in ones. + + + + + + + oozie.service.ActionCheckerService.action.check.interval + 60 + + The frequency at which the ActionCheckService will run. + + + + + oozie.service.ActionCheckerService.action.check.delay + 600 + + The time, in seconds, between an ActionCheck for the same action. + + + + + oozie.service.ActionCheckerService.callable.batch.size + 10 + + This value determines the number of actions which will be batched together + to be executed by a single thread. + + + + + + oozie.service.StatusTransitService.statusTransit.interval + 60 + + The frequency in seconds at which the StatusTransitService will run. + + + + + oozie.service.StatusTransitService.backward.support.for.coord.status + false + + true, if coordinator job submits using 'uri:oozie:coordinator:0.1' and wants to keep Oozie 2.x status transit. + if set true, + 1. SUCCEEDED state in coordinator job means materialization done. + 2. No DONEWITHERROR state in coordinator job + 3. No PAUSED or PREPPAUSED state in coordinator job + 4. PREPSUSPENDED becomes SUSPENDED in coordinator job + + + + + oozie.service.StatusTransitService.backward.support.for.states.without.error + true + + true, if you want to keep Oozie 3.2 status transit. + Change it to false for Oozie 4.x releases. + if set true, + No states like RUNNINGWITHERROR, SUSPENDEDWITHERROR and PAUSEDWITHERROR + for coordinator and bundle + + + + + + oozie.service.PauseTransitService.PauseTransit.interval + 60 + + The frequency in seconds at which the PauseTransitService will run. + + + + + + oozie.action.max.output.data + 2048 + + Max size in characters for output data. + + + + + oozie.action.fs.glob.max + 50000 + + Maximum number of globbed files. + + + + + + + + oozie.action.launcher.am.restart.kill.childjobs + true + + Multiple instances of launcher jobs can happen due to RM non-work preserving recovery on RM restart, AM recovery + due to crashes or AM network connectivity loss. This could also lead to orphaned child jobs of the old AM attempts + leading to conflicting runs. This kills child jobs of previous attempts using YARN application tags. + + + + + oozie.action.launcher.mapreduce.job.ubertask.enable + true + + Enables Uber Mode for the launcher job in YARN/Hadoop 2 (no effect in Hadoop 1) for all action types by default. + This can be overridden on a per-action-type basis by setting + oozie.action.#action-type#.launcher.mapreduce.job.ubertask.enable in oozie-site.xml (where #action-type# is the action + type; for example, "pig"). And that can be overridden on a per-action basis by setting + oozie.launcher.mapreduce.job.ubertask.enable in an action's configuration section in a workflow. In summary, the + priority is this: + 1. action's configuration section in a workflow + 2. oozie.action.#action-type#.launcher.mapreduce.job.ubertask.enable in oozie-site + 3. oozie.action.launcher.mapreduce.job.ubertask.enable in oozie-site + + + + + oozie.action.shell.launcher.mapreduce.job.ubertask.enable + false + + The Shell action may have issues with the $PATH environment when using Uber Mode, and so Uber Mode is disabled by + default for it. See oozie.action.launcher.mapreduce.job.ubertask.enable + + + + + oozie.action.spark.setup.hadoop.conf.dir + false + + Oozie action.xml (oozie.action.conf.xml) contains all the hadoop configuration and user provided configurations. + This property will allow users to copy Oozie action.xml as hadoop *-site configurations files. The advantage is, + user need not to manage these files into spark sharelib. If user wants to manage the hadoop configurations + themselves, it should should disable it. + + + + + oozie.action.shell.setup.hadoop.conf.dir + false + + The Shell action is commonly used to run programs that rely on HADOOP_CONF_DIR (e.g. hive, beeline, sqoop, etc). With + YARN, HADOO_CONF_DIR is set to the NodeManager's copies of Hadoop's *-site.xml files, which can be problematic because + (a) they are for meant for the NM, not necessarily clients, and (b) they won't have any of the configs that Oozie, or + the user through Oozie, sets. When this property is set to true, The Shell action will prepare the *-site.xml files + based on the correct config and set HADOOP_CONF_DIR to point to it. Setting it to false will make Oozie leave + HADOOP_CONF_DIR alone. This can also be set at the Action level by putting it in the Shell Action's configuration + section, which also has priorty. That all said, it's recommended to use the appropriate action type when possible. + + + + + oozie.action.shell.setup.hadoop.conf.dir.write.log4j.properties + true + + Toggle to control if a log4j.properties file should be written into the configuration directory prepared when + oozie.action.shell.setup.hadoop.conf.dir is enabled. This is used to control logging behavior of log4j using commands + run within the shell action script, and to ensure logging does not impact output data capture if leaked to stdout. + Content of the written file is determined by the value of oozie.action.shell.setup.hadoop.conf.dir.log4j.content. + + + + + oozie.action.shell.setup.hadoop.conf.dir.log4j.content + + log4j.rootLogger=${hadoop.root.logger} + hadoop.root.logger=INFO,console + log4j.appender.console=org.apache.log4j.ConsoleAppender + log4j.appender.console.target=System.err + log4j.appender.console.layout=org.apache.log4j.PatternLayout + log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n + + + The value to write into a log4j.properties file under the config directory created when + oozie.action.shell.setup.hadoop.conf.dir and oozie.action.shell.setup.hadoop.conf.dir.write.log4j.properties + properties are both enabled. The values must be properly newline separated and in format expected by Log4J. + Trailing and preceding whitespaces will be trimmed when reading this property. + This is used to control logging behavior of log4j using commands run within the shell action script. + + + + + oozie.action.launcher.yarn.timeline-service.enabled + false + + Enables/disables getting delegation tokens for ATS for the launcher job in + YARN/Hadoop 2.6 (no effect in Hadoop 1) for all action types by default if tez-site.xml is present in + distributed cache. + This can be overridden on a per-action basis by setting + oozie.launcher.yarn.timeline-service.enabled in an action's configuration section in a workflow. + + + + + oozie.action.rootlogger.log.level + INFO + + Logging level for root logger + + + + + + + + oozie.action.retries.max + 3 + + The number of retries for executing an action in case of failure + + + + + oozie.action.retry.interval + 10 + + The interval between retries of an action in case of failure + + + + + oozie.action.retry.policy + periodic + + Retry policy of an action in case of failure. Possible values are periodic/exponential + + + + + + + oozie.action.ssh.delete.remote.tmp.dir + true + + If set to true, it will delete temporary directory at the end of execution of ssh action. + + + + + oozie.action.ssh.http.command + curl + + Command to use for callback to oozie, normally is 'curl' or 'wget'. + The command must available in PATH environment variable of the USER@HOST box shell. + + + + + oozie.action.ssh.http.command.post.options + --data-binary @#stdout --request POST --header "content-type:text/plain" + + The callback command POST options. + Used when the ouptut of the ssh action is captured. + + + + + oozie.action.ssh.allow.user.at.host + true + + Specifies whether the user specified by the ssh action is allowed or is to be replaced + by the Job user + + + + + + + oozie.action.subworkflow.max.depth + 50 + + The maximum depth for subworkflows. For example, if set to 3, then a workflow can start subwf1, which can start subwf2, + which can start subwf3; but if subwf3 tries to start subwf4, then the action will fail. This is helpful in preventing + errant workflows from starting infintely recursive subworkflows. + + + + + + + oozie.service.HadoopAccessorService.kerberos.enabled + false + + Indicates if Oozie is configured to use Kerberos. + + + + + local.realm + LOCALHOST + + Kerberos Realm used by Oozie and Hadoop. Using 'local.realm' to be aligned with Hadoop configuration + + + + + oozie.service.HadoopAccessorService.keytab.file + ${user.home}/oozie.keytab + + Location of the Oozie user keytab file. + + + + + oozie.service.HadoopAccessorService.kerberos.principal + ${user.name}/localhost@${local.realm} + + Kerberos principal for Oozie service. + + + + + oozie.service.HadoopAccessorService.jobTracker.whitelist + + + Whitelisted job tracker for Oozie service. + + + + + oozie.service.HadoopAccessorService.nameNode.whitelist + + + Whitelisted job tracker for Oozie service. + + + + + oozie.service.HadoopAccessorService.hadoop.configurations + *=hadoop-conf + + Comma separated AUTHORITY=HADOOP_CONF_DIR, where AUTHORITY is the HOST:PORT of + the Hadoop service (JobTracker, YARN, HDFS). The wildcard '*' configuration is + used when there is no exact match for an authority. The HADOOP_CONF_DIR contains + the relevant Hadoop *-site.xml files. If the path is relative is looked within + the Oozie configuration directory; though the path can be absolute (i.e. to point + to Hadoop client conf/ directories in the local filesystem. + + + + + + oozie.service.HadoopAccessorService.action.configurations + *=action-conf + + Comma separated AUTHORITY=ACTION_CONF_DIR, where AUTHORITY is the HOST:PORT of + the Hadoop MapReduce service (JobTracker, YARN). The wildcard '*' configuration is + used when there is no exact match for an authority. The ACTION_CONF_DIR may contain + ACTION.xml files where ACTION is the action type ('java', 'map-reduce', 'pig', + 'hive', 'sqoop', etc.). If the ACTION.xml file exists, its properties will be used + as defaults properties for the action. If the path is relative is looked within + the Oozie configuration directory; though the path can be absolute (i.e. to point + to Hadoop client conf/ directories in the local filesystem. + + + + + oozie.service.HadoopAccessorService.action.configurations.load.default.resources + true + + true means that default and site xml files of hadoop (core-default, core-site, + hdfs-default, hdfs-site, mapred-default, mapred-site, yarn-default, yarn-site) + are parsed into actionConf on Oozie server. false means that site xml files are + not loaded on server, instead loaded on launcher node. + This is only done for pig and hive actions which handle loading those files + automatically from the classpath on launcher task. It defaults to true. + + + + + + oozie.credentials.credentialclasses + + + A list of credential class mapping for CredentialsProvider + + + + oozie.credentials.skip + false + + This determines if Oozie should skip getting credentials from the credential providers. This can be overwritten at a + job-level or action-level. + + + + + oozie.actions.main.classnames + distcp=org.apache.hadoop.tools.DistCp + + A list of class name mapping for Action classes + + + + + oozie.service.WorkflowAppService.system.libpath + /user/${user.name}/share/lib + + System library path to use for workflow applications. + This path is added to workflow application if their job properties sets + the property 'oozie.use.system.libpath' to true. + + + + + oozie.command.default.lock.timeout + 5000 + + Default timeout (in milliseconds) for commands for acquiring an exclusive lock on an entity. + + + + + oozie.command.default.requeue.delay + 10000 + + Default time (in milliseconds) for commands that are requeued for delayed execution. + + + + + + + oozie.service.LiteWorkflowStoreService.user.retry.max + 3 + + Automatic retry max count for workflow action is 3 in default. + + + + + oozie.service.LiteWorkflowStoreService.user.retry.inteval + 10 + + Automatic retry interval for workflow action is in minutes and the default value is 10 minutes. + + + + + oozie.service.LiteWorkflowStoreService.user.retry.policy + periodic + + Automatic retry policy for workflow action. Possible values are periodic or exponential, periodic being the default. + + + + + oozie.service.LiteWorkflowStoreService.user.retry.error.code + JA008,JA009,JA017,JA018,JA019,FS009,FS008,FS014 + + Automatic retry interval for workflow action is handled for these specified error code: + FS009, FS008 is file exists error when using chmod in fs action. + FS014 is permission error in fs action + JA018 is output directory exists error in workflow map-reduce action. + JA019 is error while executing distcp action. + JA017 is job not exists error in action executor. + JA008 is FileNotFoundException in action executor. + JA009 is IOException in action executor. + ALL is the any kind of error in action executor. + + + + + oozie.service.LiteWorkflowStoreService.user.retry.error.code.ext + + + Automatic retry interval for workflow action is handled for these specified extra error code: + ALL is the any kind of error in action executor. + + + + + oozie.service.LiteWorkflowStoreService.node.def.version + _oozie_inst_v_2 + + NodeDef default version, _oozie_inst_v_0, _oozie_inst_v_1 or _oozie_inst_v_2 + + + + + + + oozie.authentication.type + simple + + Defines authentication used for Oozie HTTP endpoint. + Supported values are: simple | kerberos | #AUTHENTICATION_HANDLER_CLASSNAME# + + + + oozie.server.authentication.type + ${oozie.authentication.type} + + Defines authentication used for Oozie server communicating to other Oozie server over HTTP(s). + Supported values are: simple | kerberos | #AUTHENTICATOR_CLASSNAME# + + + + + oozie.authentication.token.validity + 36000 + + Indicates how long (in seconds) an authentication token is valid before it has + to be renewed. + + + + + oozie.authentication.cookie.domain + + + The domain to use for the HTTP cookie that stores the authentication token. + In order to authentiation to work correctly across multiple hosts + the domain must be correctly set. + + + + + oozie.authentication.simple.anonymous.allowed + true + + Indicates if anonymous requests are allowed when using 'simple' authentication. + + + + + oozie.authentication.kerberos.principal + HTTP/localhost@${local.realm} + + Indicates the Kerberos principal to be used for HTTP endpoint. + The principal MUST start with 'HTTP/' as per Kerberos HTTP SPNEGO specification. + + + + + oozie.authentication.kerberos.keytab + ${oozie.service.HadoopAccessorService.keytab.file} + + Location of the keytab file with the credentials for the principal. + Referring to the same keytab file Oozie uses for its Kerberos credentials for Hadoop. + + + + + oozie.authentication.kerberos.name.rules + DEFAULT + + The kerberos names rules is to resolve kerberos principal names, refer to Hadoop's + KerberosName for more details. + + + + + + oozie.coord.execution.none.tolerance + 1 + + Default time tolerance in minutes after action nominal time for an action to be skipped + when execution order is "NONE" + + + + + + oozie.coord.actions.default.length + 1000 + + Default number of coordinator actions to be retrieved by the info command + + + + + + oozie.validate.ForkJoin + true + + If true, fork and join should be validated at wf submission time. + + + + + oozie.workflow.parallel.fork.action.start + true + + Determines how Oozie processes starting of forked actions. If true, forked actions and their job submissions + are done in parallel which is best for performance. If false, they are submitted sequentially. + + + + + oozie.coord.action.get.all.attributes + false + + Setting to true is not recommended as coord job/action info will bring all columns of the action in memory. + Set it true only if backward compatibility for action/job info is required. + + + + + oozie.service.HadoopAccessorService.supported.filesystems + hdfs,hftp,webhdfs + + Enlist the different filesystems supported for federation. If wildcard "*" is specified, + then ALL file schemes will be allowed. + + + + + oozie.service.URIHandlerService.uri.handlers + org.apache.oozie.dependency.FSURIHandler + + Enlist the different uri handlers supported for data availability checks. + + + + + + oozie.notification.url.connection.timeout + 10000 + + Defines the timeout, in milliseconds, for Oozie HTTP notification callbacks. Oozie does + HTTP notifications for workflow jobs which set the 'oozie.wf.action.notification.url', + 'oozie.wf.worklfow.notification.url' and/or 'oozie.coord.action.notification.url' + properties in their job.properties. Refer to section '5 Oozie Notifications' in the + Workflow specification for details. + + + + + + + oozie.hadoop-2.0.2-alpha.workaround.for.distributed.cache + false + + Due to a bug in Hadoop 2.0.2-alpha, MAPREDUCE-4820, launcher jobs fail to set + the distributed cache for the action job because the local JARs are implicitly + included triggering a duplicate check. + This flag removes the distributed cache files for the action as they'll be + included from the local JARs of the JobClient (MRApps) submitting the action + job from the launcher. + + + + + oozie.service.EventHandlerService.filter.app.types + workflow_job, coordinator_action + + The app-types among workflow/coordinator/bundle job/action for which + for which events system is enabled. + + + + + oozie.service.EventHandlerService.event.queue + org.apache.oozie.event.MemoryEventQueue + + The implementation for EventQueue in use by the EventHandlerService. + + + + + oozie.service.EventHandlerService.event.listeners + org.apache.oozie.jms.JMSJobEventListener + + + + oozie.service.EventHandlerService.queue.size + 10000 + + Maximum number of events to be contained in the event queue. + + + + + oozie.service.EventHandlerService.worker.interval + 30 + + The default interval (seconds) at which the worker threads will be scheduled to run + and process events. + + + + + oozie.service.EventHandlerService.batch.size + 10 + + The batch size for batched draining per thread from the event queue. + + + + + oozie.service.EventHandlerService.worker.threads + 3 + + Number of worker threads to be scheduled to run and process events. + + + + + oozie.sla.service.SLAService.capacity + 5000 + + Maximum number of sla records to be contained in the memory structure. + + + + + oozie.sla.service.SLAService.alert.events + END_MISS + + Default types of SLA events for being alerted of. + + + + + oozie.sla.service.SLAService.calculator.impl + org.apache.oozie.sla.SLACalculatorMemory + + The implementation for SLACalculator in use by the SLAService. + + + + + oozie.sla.service.SLAService.job.event.latency + 90000 + + Time in milliseconds to account of latency of getting the job status event + to compare against and decide sla miss/met + + + + + oozie.sla.service.SLAService.check.interval + 30 + + Time interval, in seconds, at which SLA Worker will be scheduled to run + + + + + oozie.sla.disable.alerts.older.than + 48 + + Time threshold, in HOURS, for disabling SLA alerting for jobs whose + nominal time is older than this. + + + + + + oozie.zookeeper.connection.string + localhost:2181 + + Comma-separated values of host:port pairs of the ZooKeeper servers. + + + + + oozie.zookeeper.namespace + oozie + + The namespace to use. All of the Oozie Servers that are planning on talking to each other should have the same + namespace. + + + + + oozie.zookeeper.connection.timeout + 180 + + Default ZK connection timeout (in sec). + + + + oozie.zookeeper.session.timeout + 300 + + Default ZK session timeout (in sec). If connection is lost even after retry, then Oozie server will shutdown + itself if oozie.zookeeper.server.shutdown.ontimeout is true. + + + + oozie.zookeeper.max.retries + 10 + + Maximum number of times to retry. + + + + + oozie.zookeeper.server.shutdown.ontimeout + true + + If true, Oozie server will shutdown itself on ZK + connection timeout. + + + + + oozie.http.hostname + localhost + + Oozie server host name. + + + + + oozie.http.port + 11000 + + Oozie server port. + + + + + oozie.https.port + 11443 + + Oozie ssl server port. + + + + + oozie.instance.id + ${oozie.http.hostname} + + Each Oozie server should have its own unique instance id. The default is system property + =${OOZIE_HTTP_HOSTNAME}= (i.e. the hostname). + + + + + + oozie.service.ShareLibService.mapping.file + + + Sharelib mapping files contains list of key=value, + where key will be the sharelib name for the action and value is a comma separated list of + DFS directories or jar files. + Example. + oozie.pig_10=hdfs:///share/lib/pig/pig-0.10.1/lib/ + oozie.pig=hdfs:///share/lib/pig/pig-0.11.1/lib/ + oozie.distcp=hdfs:///share/lib/hadoop-2.2.0/share/hadoop/tools/lib/hadoop-distcp-2.2.0.jar + + + + + oozie.service.ShareLibService.fail.fast.on.startup + false + + Fails server starup if sharelib initilzation fails. + + + + + oozie.service.ShareLibService.purge.interval + 1 + + How often, in days, Oozie should check for old ShareLibs and LauncherLibs to purge from HDFS. + + + + + oozie.service.ShareLibService.temp.sharelib.retention.days + 7 + + ShareLib retention time in days. + + + + + oozie.action.ship.launcher.jar + false + + Specifies whether launcher jar is shipped or not. + + + + + oozie.action.jobinfo.enable + false + + JobInfo will contain information of bundle, coordinator, workflow and actions. If enabled, hadoop job will have + property(oozie.job.info) which value is multiple key/value pair separated by ",". This information can be used for + analytics like how many oozie jobs are submitted for a particular period, what is the total number of failed pig jobs, + etc from mapreduce job history logs and configuration. + User can also add custom workflow property to jobinfo by adding property which prefix with "oozie.job.info." + Eg. + oozie.job.info="bundle.id=,bundle.name=,coord.name=,coord.nominal.time=,coord.name=,wf.id=, + wf.name=,action.name=,action.type=,launcher=true" + + + + + oozie.service.XLogStreamingService.max.log.scan.duration + -1 + + Max log scan duration in hours. If log scan request end_date - start_date > value, + then exception is thrown to reduce the scan duration. -1 indicate no limit. + + + + + oozie.service.XLogStreamingService.actionlist.max.log.scan.duration + -1 + + Max log scan duration in hours for coordinator job when list of actions are specified. + If log streaming request end_date - start_date > value, then exception is thrown to reduce the scan duration. + -1 indicate no limit. + This setting is separate from max.log.scan.duration as we want to allow higher durations when actions are specified. + + + + + + oozie.service.JvmPauseMonitorService.warn-threshold.ms + 10000 + + The JvmPauseMonitorService runs a thread that repeatedly tries to detect when the JVM pauses, which could indicate + that the JVM or host machine is overloaded or other problems. This thread sleeps for 500ms; if it sleeps for + significantly longer, then there is likely a problem. This property specifies the threadshold for when Oozie should log + a WARN level message; there is also a counter named "jvm.pause.warn-threshold". + + + + + oozie.service.JvmPauseMonitorService.info-threshold.ms + 1000 + + The JvmPauseMonitorService runs a thread that repeatedly tries to detect when the JVM pauses, which could indicate + that the JVM or host machine is overloaded or other problems. This thread sleeps for 500ms; if it sleeps for + significantly longer, then there is likely a problem. This property specifies the threadshold for when Oozie should log + an INFO level message; there is also a counter named "jvm.pause.info-threshold". + + + + + oozie.service.ZKLocksService.locks.reaper.threshold + 300 + + The frequency at which the ChildReaper will run. + Duration should be in sec. Default is 5 min. + + + + + oozie.service.ZKLocksService.locks.reaper.threads + 2 + + Number of fixed threads used by ChildReaper to + delete empty locks. + + + + + oozie.service.AbandonedCoordCheckerService.check.interval + + 1440 + + Interval, in minutes, at which AbandonedCoordCheckerService should run. + + + + + oozie.service.AbandonedCoordCheckerService.check.delay + + 60 + + Delay, in minutes, at which AbandonedCoordCheckerService should run. + + + + + oozie.service.AbandonedCoordCheckerService.failure.limit + + 25 + + Failure limit. A job is considered to be abandoned/faulty if total number of actions in + failed/timedout/suspended >= "Failure limit" and there are no succeeded action. + + + + + oozie.service.AbandonedCoordCheckerService.kill.jobs + + false + + If true, AbandonedCoordCheckerService will kill abandoned coords. + + + + + oozie.service.AbandonedCoordCheckerService.job.older.than + 2880 + + In minutes, job will be considered as abandoned/faulty if job is older than this value. + + + + + oozie.notification.proxy + + + System level proxy setting for job notifications. + + + + + oozie.wf.rerun.disablechild + false + + By setting this option, workflow rerun will be disabled if parent workflow or coordinator exist and + it will only rerun through parent. + + + + + oozie.use.system.libpath + false + + Default value of oozie.use.system.libpath. If user haven't specified =oozie.use.system.libpath= + in the job.properties and this value is true and Oozie will include sharelib jars for workflow. + + + + + oozie.service.PauseTransitService.callable.batch.size + + 10 + + This value determines the number of callable which will be batched together + to be executed by a single thread. + + + + + + oozie.configuration.substitute.depth + 20 + + This value determines the depth of substitution in configurations. + If set -1, No limitation on substitution. + + + + + oozie.service.SparkConfigurationService.spark.configurations + *=spark-conf + + Comma separated AUTHORITY=SPARK_CONF_DIR, where AUTHORITY is the HOST:PORT of + the ResourceManager of a YARN cluster. The wildcard '*' configuration is + used when there is no exact match for an authority. The SPARK_CONF_DIR contains + the relevant spark-defaults.conf properties file. If the path is relative is looked within + the Oozie configuration directory; though the path can be absolute. This is only used + when the Spark master is set to either "yarn-client" or "yarn-cluster". + + + + + oozie.service.SparkConfigurationService.spark.configurations.ignore.spark.yarn.jar + true + + If true, Oozie will ignore the "spark.yarn.jar" property from any Spark configurations specified in + oozie.service.SparkConfigurationService.spark.configurations. If false, Oozie will not ignore it. It is recommended + to leave this as true because it can interfere with the jars in the Spark sharelib. + + + + + oozie.email.attachment.enabled + true + + This value determines whether to support email attachment of a file on HDFS. + Set it false if there is any security concern. + + + + + oozie.email.smtp.host + localhost + + The host where the email action may find the SMTP server. + + + + + oozie.email.smtp.port + 25 + + The port to connect to for the SMTP server, for email actions. + + + + + oozie.email.smtp.auth + false + + Boolean property that toggles if authentication is to be done or not when using email actions. + + + + + oozie.email.smtp.username + + + If authentication is enabled for email actions, the username to login as (to the SMTP server). + + + + + oozie.email.smtp.password + + + If authentication is enabled for email actions, the password to login with (to the SMTP server). + + + + + oozie.email.from.address + oozie@localhost + + The from address to be used for mailing all emails done via the email action. + + + + + oozie.email.smtp.socket.timeout.ms + 10000 + + The timeout to apply over all SMTP server socket operations done during the email action. + + + + + oozie.actions.default.name-node + + + The default value to use for the <name-node> element in applicable action types. This value will be used when + neither the action itself nor the global section specifies a <name-node>. As expected, it should be of the form + "hdfs://HOST:PORT". + + + + + oozie.actions.default.job-tracker + + + The default value to use for the <job-tracker> element in applicable action types. This value will be used when + neither the action itself nor the global section specifies a <job-tracker>. As expected, it should be of the form + "HOST:PORT". + + + + diff --git a/sahara/plugins/vanilla/v2_8_2/resources/yarn-default.xml b/sahara/plugins/vanilla/v2_8_2/resources/yarn-default.xml new file mode 100644 index 0000000..7f2ac51 --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/resources/yarn-default.xml @@ -0,0 +1,2635 @@ + + + + + + + + + + + + + + + Factory to create client IPC classes. + yarn.ipc.client.factory.class + + + + Factory to create server IPC classes. + yarn.ipc.server.factory.class + + + + Factory to create serializeable records. + yarn.ipc.record.factory.class + + + + RPC class implementation + yarn.ipc.rpc.class + org.apache.hadoop.yarn.ipc.HadoopYarnProtoRPC + + + + + + The hostname of the RM. + yarn.resourcemanager.hostname + 0.0.0.0 + + + + The address of the applications manager interface in the RM. + yarn.resourcemanager.address + ${yarn.resourcemanager.hostname}:8032 + + + + + The actual address the server will bind to. If this optional address is + set, the RPC and webapp servers will bind to this address and the port specified in + yarn.resourcemanager.address and yarn.resourcemanager.webapp.address, respectively. This + is most useful for making RM listen to all interfaces by setting to 0.0.0.0. + + yarn.resourcemanager.bind-host + + + + + The number of threads used to handle applications manager requests. + yarn.resourcemanager.client.thread-count + 50 + + + + Number of threads used to launch/cleanup AM. + yarn.resourcemanager.amlauncher.thread-count + 50 + + + + Retry times to connect with NM. + yarn.resourcemanager.nodemanager-connect-retries + 10 + + + + Timeout in milliseconds when YARN dispatcher tries to drain the + events. Typically, this happens when service is stopping. e.g. RM drains + the ATS events dispatcher when stopping. + + yarn.dispatcher.drain-events.timeout + 300000 + + + + The expiry interval for application master reporting. + yarn.am.liveness-monitor.expiry-interval-ms + 600000 + + + + The Kerberos principal for the resource manager. + yarn.resourcemanager.principal + + + + The address of the scheduler interface. + yarn.resourcemanager.scheduler.address + ${yarn.resourcemanager.hostname}:8030 + + + + Number of threads to handle scheduler interface. + yarn.resourcemanager.scheduler.client.thread-count + 50 + + + + + This configures the HTTP endpoint for Yarn Daemons.The following + values are supported: + - HTTP_ONLY : Service is provided only on http + - HTTPS_ONLY : Service is provided only on https + + yarn.http.policy + HTTP_ONLY + + + + + The http address of the RM web application. + If only a host is provided as the value, + the webapp will be served on a random port. + + yarn.resourcemanager.webapp.address + ${yarn.resourcemanager.hostname}:8088 + + + + + The https address of the RM web application. + If only a host is provided as the value, + the webapp will be served on a random port. + + yarn.resourcemanager.webapp.https.address + ${yarn.resourcemanager.hostname}:8090 + + + + + The Kerberos keytab file to be used for spnego filter for the RM web + interface. + + yarn.resourcemanager.webapp.spnego-keytab-file + + + + + + The Kerberos principal to be used for spnego filter for the RM web + interface. + + yarn.resourcemanager.webapp.spnego-principal + + + + + + Add button to kill application in the RM Application view. + + yarn.resourcemanager.webapp.ui-actions.enabled + true + + + + yarn.resourcemanager.resource-tracker.address + ${yarn.resourcemanager.hostname}:8031 + + + + Are acls enabled. + yarn.acl.enable + false + + + + Are reservation acls enabled. + yarn.acl.reservation-enable + false + + + + ACL of who can be admin of the YARN cluster. + yarn.admin.acl + * + + + + The address of the RM admin interface. + yarn.resourcemanager.admin.address + ${yarn.resourcemanager.hostname}:8033 + + + + Number of threads used to handle RM admin interface. + yarn.resourcemanager.admin.client.thread-count + 1 + + + + Maximum time to wait to establish connection to + ResourceManager. + yarn.resourcemanager.connect.max-wait.ms + 900000 + + + + How often to try connecting to the + ResourceManager. + yarn.resourcemanager.connect.retry-interval.ms + 30000 + + + + The maximum number of application attempts. It's a global + setting for all application masters. Each application master can specify + its individual maximum number of application attempts via the API, but the + individual number cannot be more than the global upper bound. If it is, + the resourcemanager will override it. The default number is set to 2, to + allow at least one retry for AM. + yarn.resourcemanager.am.max-attempts + 2 + + + + How often to check that containers are still alive. + yarn.resourcemanager.container.liveness-monitor.interval-ms + 600000 + + + + The keytab for the resource manager. + yarn.resourcemanager.keytab + /etc/krb5.keytab + + + + Flag to enable override of the default kerberos authentication + filter with the RM authentication filter to allow authentication using + delegation tokens(fallback to kerberos if the tokens are missing). Only + applicable when the http authentication type is kerberos. + yarn.resourcemanager.webapp.delegation-token-auth-filter.enabled + true + + + + Flag to enable cross-origin (CORS) support in the RM. This flag + requires the CORS filter initializer to be added to the filter initializers + list in core-site.xml. + yarn.resourcemanager.webapp.cross-origin.enabled + false + + + + How long to wait until a node manager is considered dead. + yarn.nm.liveness-monitor.expiry-interval-ms + 600000 + + + + Path to file with nodes to include. + yarn.resourcemanager.nodes.include-path + + + + + Path to file with nodes to exclude. + yarn.resourcemanager.nodes.exclude-path + + + + + The expiry interval for node IP caching. -1 disables the caching + yarn.resourcemanager.node-ip-cache.expiry-interval-secs + -1 + + + + Number of threads to handle resource tracker calls. + yarn.resourcemanager.resource-tracker.client.thread-count + 50 + + + + The class to use as the resource scheduler. + yarn.resourcemanager.scheduler.class + org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler + + + + The minimum allocation for every container request at the RM, + in MBs. Memory requests lower than this will throw a + InvalidResourceRequestException. + yarn.scheduler.minimum-allocation-mb + 1024 + + + + The maximum allocation for every container request at the RM, + in MBs. Memory requests higher than this will throw a + InvalidResourceRequestException. + yarn.scheduler.maximum-allocation-mb + 8192 + + + + The minimum allocation for every container request at the RM, + in terms of virtual CPU cores. Requests lower than this will throw a + InvalidResourceRequestException. + yarn.scheduler.minimum-allocation-vcores + 1 + + + + The maximum allocation for every container request at the RM, + in terms of virtual CPU cores. Requests higher than this will throw a + InvalidResourceRequestException. + yarn.scheduler.maximum-allocation-vcores + 4 + + + + + Used by node labels. If set to true, the port should be included in the + node name. Only usable if your scheduler supports node labels. + + yarn.scheduler.include-port-in-node-name + false + + + + Enable RM to recover state after starting. If true, then + yarn.resourcemanager.store.class must be specified. + yarn.resourcemanager.recovery.enabled + false + + + + Should RM fail fast if it encounters any errors. By defalt, it + points to ${yarn.fail-fast}. Errors include: + 1) exceptions when state-store write/read operations fails. + + yarn.resourcemanager.fail-fast + ${yarn.fail-fast} + + + + Should YARN fail fast if it encounters any errors. + This is a global config for all other components including RM,NM etc. + If no value is set for component-specific config (e.g yarn.resourcemanager.fail-fast), + this value will be the default. + + yarn.fail-fast + false + + + + Enable RM work preserving recovery. This configuration is private + to YARN for experimenting the feature. + + yarn.resourcemanager.work-preserving-recovery.enabled + true + + + + Set the amount of time RM waits before allocating new + containers on work-preserving-recovery. Such wait period gives RM a chance + to settle down resyncing with NMs in the cluster on recovery, before assigning + new containers to applications. + + yarn.resourcemanager.work-preserving-recovery.scheduling-wait-ms + 10000 + + + + The class to use as the persistent store. + + If org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore + is used, the store is implicitly fenced; meaning a single ResourceManager + is able to use the store at any point in time. More details on this + implicit fencing, along with setting up appropriate ACLs is discussed + under yarn.resourcemanager.zk-state-store.root-node.acl. + + yarn.resourcemanager.store.class + org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore + + + + When automatic failover is enabled, number of zookeeper + operation retry times in ActiveStandbyElector + yarn.resourcemanager.ha.failover-controller.active-standby-elector.zk.retries + + + + + The maximum number of completed applications RM state + store keeps, less than or equals to ${yarn.resourcemanager.max-completed-applications}. + By default, it equals to ${yarn.resourcemanager.max-completed-applications}. + This ensures that the applications kept in the state store are consistent with + the applications remembered in RM memory. + Any values larger than ${yarn.resourcemanager.max-completed-applications} will + be reset to ${yarn.resourcemanager.max-completed-applications}. + Note that this value impacts the RM recovery performance.Typically, + a smaller value indicates better performance on RM recovery. + + yarn.resourcemanager.state-store.max-completed-applications + ${yarn.resourcemanager.max-completed-applications} + + + + Host:Port of the ZooKeeper server to be used by the RM. This + must be supplied when using the ZooKeeper based implementation of the + RM state store and/or embedded automatic failover in a HA setting. + + yarn.resourcemanager.zk-address + + + + + Number of times RM tries to connect to ZooKeeper. + yarn.resourcemanager.zk-num-retries + 1000 + + + + Retry interval in milliseconds when connecting to ZooKeeper. + When HA is enabled, the value here is NOT used. It is generated + automatically from yarn.resourcemanager.zk-timeout-ms and + yarn.resourcemanager.zk-num-retries. + + yarn.resourcemanager.zk-retry-interval-ms + 1000 + + + + Full path of the ZooKeeper znode where RM state will be + stored. This must be supplied when using + org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore + as the value for yarn.resourcemanager.store.class + yarn.resourcemanager.zk-state-store.parent-path + /rmstore + + + + ZooKeeper session timeout in milliseconds. Session expiration + is managed by the ZooKeeper cluster itself, not by the client. This value is + used by the cluster to determine when the client's session expires. + Expirations happens when the cluster does not hear from the client within + the specified session timeout period (i.e. no heartbeat). + yarn.resourcemanager.zk-timeout-ms + 10000 + + + + ACL's to be used for ZooKeeper znodes. + yarn.resourcemanager.zk-acl + world:anyone:rwcda + + + + + ACLs to be used for the root znode when using ZKRMStateStore in a HA + scenario for fencing. + + ZKRMStateStore supports implicit fencing to allow a single + ResourceManager write-access to the store. For fencing, the + ResourceManagers in the cluster share read-write-admin privileges on the + root node, but the Active ResourceManager claims exclusive create-delete + permissions. + + By default, when this property is not set, we use the ACLs from + yarn.resourcemanager.zk-acl for shared admin access and + rm-address:random-number for username-based exclusive create-delete + access. + + This property allows users to set ACLs of their choice instead of using + the default mechanism. For fencing to work, the ACLs should be + carefully set differently on each ResourceManger such that all the + ResourceManagers have shared admin access and the Active ResourceManger + takes over (exclusively) the create-delete access. + + yarn.resourcemanager.zk-state-store.root-node.acl + + + + + Specify the auths to be used for the ACL's specified in both the + yarn.resourcemanager.zk-acl and + yarn.resourcemanager.zk-state-store.root-node.acl properties. This + takes a comma-separated list of authentication mechanisms, each of the + form 'scheme:auth' (the same syntax used for the 'addAuth' command in + the ZK CLI). + + yarn.resourcemanager.zk-auth + + + + URI pointing to the location of the FileSystem path where + RM state will be stored. This must be supplied when using + org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore + as the value for yarn.resourcemanager.store.class + yarn.resourcemanager.fs.state-store.uri + ${hadoop.tmp.dir}/yarn/system/rmstore + + + + + hdfs client retry policy specification. hdfs client retry + is always enabled. Specified in pairs of sleep-time and number-of-retries + and (t0, n0), (t1, n1), ..., the first n0 retries sleep t0 milliseconds on + average, the following n1 retries sleep t1 milliseconds on average, and so on. + + yarn.resourcemanager.fs.state-store.retry-policy-spec + 2000, 500 + + + + the number of retries to recover from IOException in + FileSystemRMStateStore. + + yarn.resourcemanager.fs.state-store.num-retries + 0 + + + + Retry interval in milliseconds in FileSystemRMStateStore. + + yarn.resourcemanager.fs.state-store.retry-interval-ms + 1000 + + + + Local path where the RM state will be stored when using + org.apache.hadoop.yarn.server.resourcemanager.recovery.LeveldbRMStateStore + as the value for yarn.resourcemanager.store.class + yarn.resourcemanager.leveldb-state-store.path + ${hadoop.tmp.dir}/yarn/system/rmstore + + + + The time in seconds between full compactions of the leveldb + database. Setting the interval to zero disables the full compaction + cycles. + yarn.resourcemanager.leveldb-state-store.compaction-interval-secs + 3600 + + + + Enable RM high-availability. When enabled, + (1) The RM starts in the Standby mode by default, and transitions to + the Active mode when prompted to. + (2) The nodes in the RM ensemble are listed in + yarn.resourcemanager.ha.rm-ids + (3) The id of each RM either comes from yarn.resourcemanager.ha.id + if yarn.resourcemanager.ha.id is explicitly specified or can be + figured out by matching yarn.resourcemanager.address.{id} with local address + (4) The actual physical addresses come from the configs of the pattern + - {rpc-config}.{id} + yarn.resourcemanager.ha.enabled + false + + + + Enable automatic failover. + By default, it is enabled only when HA is enabled + yarn.resourcemanager.ha.automatic-failover.enabled + true + + + + Enable embedded automatic failover. + By default, it is enabled only when HA is enabled. + The embedded elector relies on the RM state store to handle fencing, + and is primarily intended to be used in conjunction with ZKRMStateStore. + + yarn.resourcemanager.ha.automatic-failover.embedded + true + + + + The base znode path to use for storing leader information, + when using ZooKeeper based leader election. + yarn.resourcemanager.ha.automatic-failover.zk-base-path + /yarn-leader-election + + + + Name of the cluster. In a HA setting, + this is used to ensure the RM participates in leader + election for this cluster and ensures it does not affect + other clusters + yarn.resourcemanager.cluster-id + + + + + The list of RM nodes in the cluster when HA is + enabled. See description of yarn.resourcemanager.ha + .enabled for full details on how this is used. + yarn.resourcemanager.ha.rm-ids + + + + + The id (string) of the current RM. When HA is enabled, this + is an optional config. The id of current RM can be set by explicitly + specifying yarn.resourcemanager.ha.id or figured out by matching + yarn.resourcemanager.address.{id} with local address + See description of yarn.resourcemanager.ha.enabled + for full details on how this is used. + yarn.resourcemanager.ha.id + + + + + When HA is enabled, the class to be used by Clients, AMs and + NMs to failover to the Active RM. It should extend + org.apache.hadoop.yarn.client.RMFailoverProxyProvider + yarn.client.failover-proxy-provider + org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvider + + + + When HA is enabled, the max number of times + FailoverProxyProvider should attempt failover. When set, + this overrides the yarn.resourcemanager.connect.max-wait.ms. When + not set, this is inferred from + yarn.resourcemanager.connect.max-wait.ms. + yarn.client.failover-max-attempts + + + + + When HA is enabled, the sleep base (in milliseconds) to be + used for calculating the exponential delay between failovers. When set, + this overrides the yarn.resourcemanager.connect.* settings. When + not set, yarn.resourcemanager.connect.retry-interval.ms is used instead. + + yarn.client.failover-sleep-base-ms + + + + + When HA is enabled, the maximum sleep time (in milliseconds) + between failovers. When set, this overrides the + yarn.resourcemanager.connect.* settings. When not set, + yarn.resourcemanager.connect.retry-interval.ms is used instead. + yarn.client.failover-sleep-max-ms + + + + + When HA is enabled, the number of retries per + attempt to connect to a ResourceManager. In other words, + it is the ipc.client.connect.max.retries to be used during + failover attempts + yarn.client.failover-retries + 0 + + + + When HA is enabled, the number of retries per + attempt to connect to a ResourceManager on socket timeouts. In other + words, it is the ipc.client.connect.max.retries.on.timeouts to be used + during failover attempts + yarn.client.failover-retries-on-socket-timeouts + 0 + + + + The maximum number of completed applications RM keeps. + yarn.resourcemanager.max-completed-applications + 10000 + + + + Interval at which the delayed token removal thread runs + yarn.resourcemanager.delayed.delegation-token.removal-interval-ms + 30000 + + + + If true, ResourceManager will have proxy-user privileges. + Use case: In a secure cluster, YARN requires the user hdfs delegation-tokens to + do localization and log-aggregation on behalf of the user. If this is set to true, + ResourceManager is able to request new hdfs delegation tokens on behalf of + the user. This is needed by long-running-service, because the hdfs tokens + will eventually expire and YARN requires new valid tokens to do localization + and log-aggregation. Note that to enable this use case, the corresponding + HDFS NameNode has to configure ResourceManager as the proxy-user so that + ResourceManager can itself ask for new tokens on behalf of the user when + tokens are past their max-life-time. + yarn.resourcemanager.proxy-user-privileges.enabled + false + + + + Interval for the roll over for the master key used to generate + application tokens + + yarn.resourcemanager.am-rm-tokens.master-key-rolling-interval-secs + 86400 + + + + Interval for the roll over for the master key used to generate + container tokens. It is expected to be much greater than + yarn.nm.liveness-monitor.expiry-interval-ms and + yarn.resourcemanager.rm.container-allocation.expiry-interval-ms. Otherwise the + behavior is undefined. + + yarn.resourcemanager.container-tokens.master-key-rolling-interval-secs + 86400 + + + + The heart-beat interval in milliseconds for every NodeManager in the cluster. + yarn.resourcemanager.nodemanagers.heartbeat-interval-ms + 1000 + + + + The minimum allowed version of a connecting nodemanager. The valid values are + NONE (no version checking), EqualToRM (the nodemanager's version is equal to + or greater than the RM version), or a Version String. + yarn.resourcemanager.nodemanager.minimum.version + NONE + + + + Enable a set of periodic monitors (specified in + yarn.resourcemanager.scheduler.monitor.policies) that affect the + scheduler. + yarn.resourcemanager.scheduler.monitor.enable + false + + + + The list of SchedulingEditPolicy classes that interact with + the scheduler. A particular module may be incompatible with the + scheduler, other policies, or a configuration of either. + yarn.resourcemanager.scheduler.monitor.policies + org.apache.hadoop.yarn.server.resourcemanager.monitor.capacity.ProportionalCapacityPreemptionPolicy + + + + The class to use as the configuration provider. + If org.apache.hadoop.yarn.LocalConfigurationProvider is used, + the local configuration will be loaded. + If org.apache.hadoop.yarn.FileSystemBasedConfigurationProvider is used, + the configuration which will be loaded should be uploaded to remote File system first. + + yarn.resourcemanager.configuration.provider-class + org.apache.hadoop.yarn.LocalConfigurationProvider + + + + + + The value specifies the file system (e.g. HDFS) path where ResourceManager + loads configuration if yarn.resourcemanager.configuration.provider-class + is set to org.apache.hadoop.yarn.FileSystemBasedConfigurationProvider. + + yarn.resourcemanager.configuration.file-system-based-store + /yarn/conf + + + + The setting that controls whether yarn system metrics is + published on the timeline server or not by RM. + yarn.resourcemanager.system-metrics-publisher.enabled + false + + + + Number of worker threads that send the yarn system metrics + data. + yarn.resourcemanager.system-metrics-publisher.dispatcher.pool-size + 10 + + + + Number of diagnostics/failure messages can be saved in RM for + log aggregation. It also defines the number of diagnostics/failure + messages can be shown in log aggregation web ui. + yarn.resourcemanager.max-log-aggregation-diagnostics-in-memory + 10 + + + + + + + RM DelegationTokenRenewer thread count + + yarn.resourcemanager.delegation-token-renewer.thread-count + 50 + + + + + RM secret key update interval in ms + + yarn.resourcemanager.delegation.key.update-interval + 86400000 + + + + + RM delegation token maximum lifetime in ms + + yarn.resourcemanager.delegation.token.max-lifetime + 604800000 + + + + + RM delegation token update interval in ms + + yarn.resourcemanager.delegation.token.renew-interval + 86400000 + + + + + Thread pool size for RMApplicationHistoryWriter. + + yarn.resourcemanager.history-writer.multi-threaded-dispatcher.pool-size + 10 + + + + + Comma-separated list of values (in minutes) for schedule queue related + metrics. + + yarn.resourcemanager.metrics.runtime.buckets + 60,300,1440 + + + + + Interval for the roll over for the master key used to generate + NodeManager tokens. It is expected to be set to a value much larger + than yarn.nm.liveness-monitor.expiry-interval-ms. + + yarn.resourcemanager.nm-tokens.master-key-rolling-interval-secs + 86400 + + + + + Flag to enable the ResourceManager reservation system. + + yarn.resourcemanager.reservation-system.enable + false + + + + + The Java class to use as the ResourceManager reservation system. + By default, is set to + org.apache.hadoop.yarn.server.resourcemanager.reservation.CapacityReservationSystem + when using CapacityScheduler and is set to + org.apache.hadoop.yarn.server.resourcemanager.reservation.FairReservationSystem + when using FairScheduler. + + yarn.resourcemanager.reservation-system.class + + + + + + The plan follower policy class name to use for the ResourceManager + reservation system. + By default, is set to + org.apache.hadoop.yarn.server.resourcemanager.reservation.CapacitySchedulerPlanFollower + is used when using CapacityScheduler, and is set to + org.apache.hadoop.yarn.server.resourcemanager.reservation.FairSchedulerPlanFollower + when using FairScheduler. + + yarn.resourcemanager.reservation-system.plan.follower + + + + + + Step size of the reservation system in ms + + yarn.resourcemanager.reservation-system.planfollower.time-step + 1000 + + + + + The expiry interval for a container + + yarn.resourcemanager.rm.container-allocation.expiry-interval-ms + 600000 + + + + + + The hostname of the NM. + yarn.nodemanager.hostname + 0.0.0.0 + + + + The address of the container manager in the NM. + yarn.nodemanager.address + ${yarn.nodemanager.hostname}:0 + + + + + The actual address the server will bind to. If this optional address is + set, the RPC and webapp servers will bind to this address and the port specified in + yarn.nodemanager.address and yarn.nodemanager.webapp.address, respectively. This is + most useful for making NM listen to all interfaces by setting to 0.0.0.0. + + yarn.nodemanager.bind-host + + + + + Environment variables that should be forwarded from the NodeManager's environment to the container's. + yarn.nodemanager.admin-env + MALLOC_ARENA_MAX=$MALLOC_ARENA_MAX + + + + Environment variables that containers may override rather than use NodeManager's default. + yarn.nodemanager.env-whitelist + JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME + + + + who will execute(launch) the containers. + yarn.nodemanager.container-executor.class + org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor + + + + + Number of threads container manager uses. + yarn.nodemanager.container-manager.thread-count + 20 + + + + Number of threads used in cleanup. + yarn.nodemanager.delete.thread-count + 4 + + + + + Number of seconds after an application finishes before the nodemanager's + DeletionService will delete the application's localized file directory + and log directory. + + To diagnose Yarn application problems, set this property's value large + enough (for example, to 600 = 10 minutes) to permit examination of these + directories. After changing the property's value, you must restart the + nodemanager in order for it to have an effect. + + The roots of Yarn applications' work directories is configurable with + the yarn.nodemanager.local-dirs property (see below), and the roots + of the Yarn applications' log directories is configurable with the + yarn.nodemanager.log-dirs property (see also below). + + yarn.nodemanager.delete.debug-delay-sec + 0 + + + + Keytab for NM. + yarn.nodemanager.keytab + /etc/krb5.keytab + + + + List of directories to store localized files in. An + application's localized file directory will be found in: + ${yarn.nodemanager.local-dirs}/usercache/${user}/appcache/application_${appid}. + Individual containers' work directories, called container_${contid}, will + be subdirectories of this. + + yarn.nodemanager.local-dirs + ${hadoop.tmp.dir}/nm-local-dir + + + + It limits the maximum number of files which will be localized + in a single local directory. If the limit is reached then sub-directories + will be created and new files will be localized in them. If it is set to + a value less than or equal to 36 [which are sub-directories (0-9 and then + a-z)] then NodeManager will fail to start. For example; [for public + cache] if this is configured with a value of 40 ( 4 files + + 36 sub-directories) and the local-dir is "/tmp/local-dir1" then it will + allow 4 files to be created directly inside "/tmp/local-dir1/filecache". + For files that are localized further it will create a sub-directory "0" + inside "/tmp/local-dir1/filecache" and will localize files inside it + until it becomes full. If a file is removed from a sub-directory that + is marked full, then that sub-directory will be used back again to + localize files. + + yarn.nodemanager.local-cache.max-files-per-directory + 8192 + + + + Address where the localizer IPC is. + yarn.nodemanager.localizer.address + ${yarn.nodemanager.hostname}:8040 + + + + Interval in between cache cleanups. + yarn.nodemanager.localizer.cache.cleanup.interval-ms + 600000 + + + + Target size of localizer cache in MB, per nodemanager. It is + a target retention size that only includes resources with PUBLIC and + PRIVATE visibility and excludes resources with APPLICATION visibility + + yarn.nodemanager.localizer.cache.target-size-mb + 10240 + + + + Number of threads to handle localization requests. + yarn.nodemanager.localizer.client.thread-count + 5 + + + + Number of threads to use for localization fetching. + yarn.nodemanager.localizer.fetch.thread-count + 4 + + + + + + yarn.nodemanager.container-localizer.java.opts + -Xmx256m + + + + + Where to store container logs. An application's localized log directory + will be found in ${yarn.nodemanager.log-dirs}/application_${appid}. + Individual containers' log directories will be below this, in directories + named container_{$contid}. Each container directory will contain the files + stderr, stdin, and syslog generated by that container. + + yarn.nodemanager.log-dirs + ${yarn.log.dir}/userlogs + + + + Whether to enable log aggregation. Log aggregation collects + each container's logs and moves these logs onto a file-system, for e.g. + HDFS, after the application completes. Users can configure the + "yarn.nodemanager.remote-app-log-dir" and + "yarn.nodemanager.remote-app-log-dir-suffix" properties to determine + where these logs are moved to. Users can access the logs via the + Application Timeline Server. + + yarn.log-aggregation-enable + false + + + + How long to keep aggregation logs before deleting them. -1 disables. + Be careful set this too small and you will spam the name node. + yarn.log-aggregation.retain-seconds + -1 + + + + How long to wait between aggregated log retention checks. + If set to 0 or a negative value then the value is computed as one-tenth + of the aggregated log retention time. Be careful set this too small and + you will spam the name node. + yarn.log-aggregation.retain-check-interval-seconds + -1 + + + + + How long for ResourceManager to wait for NodeManager to report its + log aggregation status. If waiting time of which the log aggregation + status is reported from NodeManager exceeds the configured value, RM + will report log aggregation status for this NodeManager as TIME_OUT + + yarn.log-aggregation-status.time-out.ms + 600000 + + + + Time in seconds to retain user logs. Only applicable if + log aggregation is disabled + + yarn.nodemanager.log.retain-seconds + 10800 + + + + Where to aggregate logs to. + yarn.nodemanager.remote-app-log-dir + /tmp/logs + + + The remote log dir will be created at + {yarn.nodemanager.remote-app-log-dir}/${user}/{thisParam} + + yarn.nodemanager.remote-app-log-dir-suffix + logs + + + + Generate additional logs about container launches. + Currently, this creates a copy of the launch script and lists the + directory contents of the container work dir. When listing directory + contents, we follow symlinks to a max-depth of 5(including symlinks + which point to outside the container work dir) which may lead to a + slowness in launching containers. + + yarn.nodemanager.log-container-debug-info.enabled + false + + + + Amount of physical memory, in MB, that can be allocated + for containers. If set to -1 and + yarn.nodemanager.resource.detect-hardware-capabilities is true, it is + automatically calculated(in case of Windows and Linux). + In other cases, the default is 8192MB. + + yarn.nodemanager.resource.memory-mb + -1 + + + + Amount of physical memory, in MB, that is reserved + for non-YARN processes. This configuration is only used if + yarn.nodemanager.resource.detect-hardware-capabilities is set + to true and yarn.nodemanager.resource.memory-mb is -1. If set + to -1, this amount is calculated as + 20% of (system memory - 2*HADOOP_HEAPSIZE) + + yarn.nodemanager.resource.system-reserved-memory-mb + -1 + + + + Whether physical memory limits will be enforced for + containers. + yarn.nodemanager.pmem-check-enabled + true + + + + Whether virtual memory limits will be enforced for + containers. + yarn.nodemanager.vmem-check-enabled + true + + + + Ratio between virtual memory to physical memory when + setting memory limits for containers. Container allocations are + expressed in terms of physical memory, and virtual memory usage + is allowed to exceed this allocation by this ratio. + + yarn.nodemanager.vmem-pmem-ratio + 2.1 + + + + Number of vcores that can be allocated + for containers. This is used by the RM scheduler when allocating + resources for containers. This is not used to limit the number of + CPUs used by YARN containers. If it is set to -1 and + yarn.nodemanager.resource.detect-hardware-capabilities is true, it is + automatically determined from the hardware in case of Windows and Linux. + In other cases, number of vcores is 8 by default. + yarn.nodemanager.resource.cpu-vcores + -1 + + + + Flag to determine if logical processors(such as + hyperthreads) should be counted as cores. Only applicable on Linux + when yarn.nodemanager.resource.cpu-vcores is set to -1 and + yarn.nodemanager.resource.detect-hardware-capabilities is true. + + yarn.nodemanager.resource.count-logical-processors-as-cores + false + + + + Multiplier to determine how to convert phyiscal cores to + vcores. This value is used if yarn.nodemanager.resource.cpu-vcores + is set to -1(which implies auto-calculate vcores) and + yarn.nodemanager.resource.detect-hardware-capabilities is set to true. The + number of vcores will be calculated as + number of CPUs * multiplier. + + yarn.nodemanager.resource.pcores-vcores-multiplier + 1.0 + + + + Percentage of CPU that can be allocated + for containers. This setting allows users to limit the amount of + CPU that YARN containers use. Currently functional only + on Linux using cgroups. The default is to use 100% of CPU. + + yarn.nodemanager.resource.percentage-physical-cpu-limit + 100 + + + + Enable auto-detection of node capabilities such as + memory and CPU. + + yarn.nodemanager.resource.detect-hardware-capabilities + false + + + + NM Webapp address. + yarn.nodemanager.webapp.address + ${yarn.nodemanager.hostname}:8042 + + + + + The https adddress of the NM web application. + + yarn.nodemanager.webapp.https.address + 0.0.0.0:8044 + + + + + The Kerberos keytab file to be used for spnego filter for the NM web + interface. + + yarn.nodemanager.webapp.spnego-keytab-file + + + + + + The Kerberos principal to be used for spnego filter for the NM web + interface. + + yarn.nodemanager.webapp.spnego-principal + + + + + How often to monitor the node and the containers. + yarn.nodemanager.resource-monitor.interval-ms + 3000 + + + + Class that calculates current resource utilization. + yarn.nodemanager.resource-calculator.class + + + + How often to monitor containers. If not set, the value for + yarn.nodemanager.resource-monitor.interval-ms will be used. + yarn.nodemanager.container-monitor.interval-ms + + + + Class that calculates containers current resource utilization. + If not set, the value for yarn.nodemanager.resource-calculator.class will + be used. + yarn.nodemanager.container-monitor.resource-calculator.class + + + + Frequency of running node health script. + yarn.nodemanager.health-checker.interval-ms + 600000 + + + + Script time out period. + yarn.nodemanager.health-checker.script.timeout-ms + 1200000 + + + + The health check script to run. + yarn.nodemanager.health-checker.script.path + + + + + The arguments to pass to the health check script. + yarn.nodemanager.health-checker.script.opts + + + + + Frequency of running disk health checker code. + yarn.nodemanager.disk-health-checker.interval-ms + 120000 + + + + The minimum fraction of number of disks to be healthy for the + nodemanager to launch new containers. This correspond to both + yarn.nodemanager.local-dirs and yarn.nodemanager.log-dirs. i.e. If there + are less number of healthy local-dirs (or log-dirs) available, then + new containers will not be launched on this node. + yarn.nodemanager.disk-health-checker.min-healthy-disks + 0.25 + + + + The maximum percentage of disk space utilization allowed after + which a disk is marked as bad. Values can range from 0.0 to 100.0. + If the value is greater than or equal to 100, the nodemanager will check + for full disk. This applies to yarn.nodemanager.local-dirs and + yarn.nodemanager.log-dirs. + yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage + 90.0 + + + + The low threshold percentage of disk space used when a bad disk is + marked as good. Values can range from 0.0 to 100.0. This applies to + yarn.nodemanager.local-dirs and yarn.nodemanager.log-dirs. + Note that if its value is more than yarn.nodemanager.disk-health-checker. + max-disk-utilization-per-disk-percentage or not set, it will be set to the same value as + yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage. + yarn.nodemanager.disk-health-checker.disk-utilization-watermark-low-per-disk-percentage + + + + + The minimum space that must be available on a disk for + it to be used. This applies to yarn.nodemanager.local-dirs and + yarn.nodemanager.log-dirs. + yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb + 0 + + + + The path to the Linux container executor. + yarn.nodemanager.linux-container-executor.path + + + + The class which should help the LCE handle resources. + yarn.nodemanager.linux-container-executor.resources-handler.class + org.apache.hadoop.yarn.server.nodemanager.util.DefaultLCEResourcesHandler + + + + + The cgroups hierarchy under which to place YARN proccesses (cannot contain commas). + If yarn.nodemanager.linux-container-executor.cgroups.mount is false (that is, if cgroups have + been pre-configured), then this cgroups hierarchy must already exist and be writable by the + NodeManager user, otherwise the NodeManager may fail. + Only used when the LCE resources handler is set to the CgroupsLCEResourcesHandler. + yarn.nodemanager.linux-container-executor.cgroups.hierarchy + /hadoop-yarn + + + + Whether the LCE should attempt to mount cgroups if not found. + Only used when the LCE resources handler is set to the CgroupsLCEResourcesHandler. + yarn.nodemanager.linux-container-executor.cgroups.mount + false + + + + Where the LCE should attempt to mount cgroups if not found. Common locations + include /sys/fs/cgroup and /cgroup; the default location can vary depending on the Linux + distribution in use. This path must exist before the NodeManager is launched. + Only used when the LCE resources handler is set to the CgroupsLCEResourcesHandler, and + yarn.nodemanager.linux-container-executor.cgroups.mount is true. + yarn.nodemanager.linux-container-executor.cgroups.mount-path + + + + Delay in ms between attempts to remove linux cgroup + yarn.nodemanager.linux-container-executor.cgroups.delete-delay-ms + 20 + + + + This determines which of the two modes that LCE should use on + a non-secure cluster. If this value is set to true, then all containers + will be launched as the user specified in + yarn.nodemanager.linux-container-executor.nonsecure-mode.local-user. If + this value is set to false, then containers will run as the user who + submitted the application. + yarn.nodemanager.linux-container-executor.nonsecure-mode.limit-users + true + + + + The UNIX user that containers will run as when + Linux-container-executor is used in nonsecure mode (a use case for this + is using cgroups) if the + yarn.nodemanager.linux-container-executor.nonsecure-mode.limit-users is + set to true. + yarn.nodemanager.linux-container-executor.nonsecure-mode.local-user + nobody + + + + The allowed pattern for UNIX user names enforced by + Linux-container-executor when used in nonsecure mode (use case for this + is using cgroups). The default value is taken from /usr/sbin/adduser + yarn.nodemanager.linux-container-executor.nonsecure-mode.user-pattern + ^[_.A-Za-z0-9][-@_.A-Za-z0-9]{0,255}?[$]?$ + + + + This flag determines whether apps should run with strict resource limits + or be allowed to consume spare resources if they need them. For example, turning the + flag on will restrict apps to use only their share of CPU, even if the node has spare + CPU cycles. The default value is false i.e. use available resources. Please note that + turning this flag on may reduce job throughput on the cluster. + yarn.nodemanager.linux-container-executor.cgroups.strict-resource-usage + false + + + + Comma separated list of runtimes that are allowed when using + LinuxContainerExecutor. The allowed values are default and docker. + + yarn.nodemanager.runtime.linux.allowed-runtimes + default + + + + This configuration setting determines the capabilities + assigned to docker containers when they are launched. While these may not + be case-sensitive from a docker perspective, it is best to keep these + uppercase. + yarn.nodemanager.runtime.linux.docker.capabilities + CHOWN,DAC_OVERRIDE,FSETID,FOWNER,MKNOD,NET_RAW,SETGID,SETUID,SETFCAP,SETPCAP,NET_BIND_SERVICE,SYS_CHROOT,KILL,AUDIT_WRITE + + + + This configuration setting determines if + privileged docker containers are allowed on this cluster. + Use with extreme care. + yarn.nodemanager.runtime.linux.docker.privileged-containers.allowed + false + + + + This configuration setting determines who is allowed to run + privileged docker containers on this cluster. Use with extreme care. + + yarn.nodemanager.runtime.linux.docker.privileged-containers.acl + + + + + This flag determines whether memory limit will be set for the Windows Job + Object of the containers launched by the default container executor. + yarn.nodemanager.windows-container.memory-limit.enabled + false + + + + This flag determines whether CPU limit will be set for the Windows Job + Object of the containers launched by the default container executor. + yarn.nodemanager.windows-container.cpu-limit.enabled + false + + + + + Interval of time the linux container executor should try cleaning up + cgroups entry when cleaning up a container. + + yarn.nodemanager.linux-container-executor.cgroups.delete-timeout-ms + 1000 + + + + + The UNIX group that the linux-container-executor should run as. + + yarn.nodemanager.linux-container-executor.group + + + + + T-file compression types used to compress aggregated logs. + yarn.nodemanager.log-aggregation.compression-type + none + + + + The kerberos principal for the node manager. + yarn.nodemanager.principal + + + + + A comma separated list of services where service name should only + contain a-zA-Z0-9_ and can not start with numbers + yarn.nodemanager.aux-services + + + + + + No. of ms to wait between sending a SIGTERM and SIGKILL to a container + yarn.nodemanager.sleep-delay-before-sigkill.ms + 250 + + + + Max time to wait for a process to come up when trying to cleanup a container + yarn.nodemanager.process-kill-wait.ms + 2000 + + + + The minimum allowed version of a resourcemanager that a nodemanager will connect to. + The valid values are NONE (no version checking), EqualToNM (the resourcemanager's version is + equal to or greater than the NM version), or a Version String. + yarn.nodemanager.resourcemanager.minimum.version + NONE + + + + Max number of threads in NMClientAsync to process container + management events + yarn.client.nodemanager-client-async.thread-pool-max-size + 500 + + + + Max time to wait to establish a connection to NM + yarn.client.nodemanager-connect.max-wait-ms + 180000 + + + + Time interval between each attempt to connect to NM + yarn.client.nodemanager-connect.retry-interval-ms + 10000 + + + + + Max time to wait for NM to connect to RM. + When not set, proxy will fall back to use value of + yarn.resourcemanager.connect.max-wait.ms. + + yarn.nodemanager.resourcemanager.connect.max-wait.ms + + + + + + Time interval between each NM attempt to connect to RM. + When not set, proxy will fall back to use value of + yarn.resourcemanager.connect.retry-interval.ms. + + yarn.nodemanager.resourcemanager.connect.retry-interval.ms + + + + + + Maximum number of proxy connections to cache for node managers. If set + to a value greater than zero then the cache is enabled and the NMClient + and MRAppMaster will cache the specified number of node manager proxies. + There will be at max one proxy per node manager. Ex. configuring it to a + value of 5 will make sure that client will at max have 5 proxies cached + with 5 different node managers. These connections for these proxies will + be timed out if idle for more than the system wide idle timeout period. + Note that this could cause issues on large clusters as many connections + could linger simultaneously and lead to a large number of connection + threads. The token used for authentication will be used only at + connection creation time. If a new token is received then the earlier + connection should be closed in order to use the new token. This and + (yarn.client.nodemanager-client-async.thread-pool-max-size) are related + and should be in sync (no need for them to be equal). + If the value of this property is zero then the connection cache is + disabled and connections will use a zero idle timeout to prevent too + many connection threads on large clusters. + + yarn.client.max-cached-nodemanagers-proxies + 0 + + + + Enable the node manager to recover after starting + yarn.nodemanager.recovery.enabled + false + + + + The local filesystem directory in which the node manager will + store state when recovery is enabled. + yarn.nodemanager.recovery.dir + ${hadoop.tmp.dir}/yarn-nm-recovery + + + + The time in seconds between full compactions of the NM state + database. Setting the interval to zero disables the full compaction + cycles. + yarn.nodemanager.recovery.compaction-interval-secs + 3600 + + + + Whether the nodemanager is running under supervision. A + nodemanager that supports recovery and is running under supervision + will not try to cleanup containers as it exits with the assumption + it will be immediately be restarted and recover containers. + yarn.nodemanager.recovery.supervised + false + + + + + + + Adjustment to the container OS scheduling priority. In Linux, passed + directly to the nice command. + + yarn.nodemanager.container-executor.os.sched.priority.adjustment + 0 + + + + + Flag to enable container metrics + + yarn.nodemanager.container-metrics.enable + true + + + + + Container metrics flush period in ms. Set to -1 for flush on completion. + + yarn.nodemanager.container-metrics.period-ms + -1 + + + + + The delay time ms to unregister container metrics after completion. + + yarn.nodemanager.container-metrics.unregister-delay-ms + 10000 + + + + + Class used to calculate current container resource utilization. + + yarn.nodemanager.container-monitor.process-tree.class + + + + + + Flag to enable NodeManager disk health checker + + yarn.nodemanager.disk-health-checker.enable + true + + + + + Number of threads to use in NM log cleanup. Used when log aggregation + is disabled. + + yarn.nodemanager.log.deletion-threads-count + 4 + + + + + The Windows group that the windows-container-executor should run as. + + yarn.nodemanager.windows-secure-container-executor.group + + + + + + + yarn.nodemanager.docker-container-executor.exec-name + /usr/bin/docker + + Name or path to the Docker client. + + + + + + The Docker image name to use for DockerContainerExecutor + + yarn.nodemanager.docker-container-executor.image-name + + + + + + + mapreduce.job.hdfs-servers + ${fs.defaultFS} + + + + yarn.nodemanager.aux-services.mapreduce_shuffle.class + org.apache.hadoop.mapred.ShuffleHandler + + + + + + The kerberos principal for the proxy, if the proxy is not + running as part of the RM. + yarn.web-proxy.principal + + + + + Keytab for WebAppProxy, if the proxy is not running as part of + the RM. + yarn.web-proxy.keytab + + + + The address for the web proxy as HOST:PORT, if this is not + given then the proxy will run as part of the RM + yarn.web-proxy.address + + + + + + + + CLASSPATH for YARN applications. A comma-separated list + of CLASSPATH entries. When this value is empty, the following default + CLASSPATH for YARN applications would be used. + For Linux: + $HADOOP_CONF_DIR, + $HADOOP_COMMON_HOME/share/hadoop/common/*, + $HADOOP_COMMON_HOME/share/hadoop/common/lib/*, + $HADOOP_HDFS_HOME/share/hadoop/hdfs/*, + $HADOOP_HDFS_HOME/share/hadoop/hdfs/lib/*, + $HADOOP_YARN_HOME/share/hadoop/yarn/*, + $HADOOP_YARN_HOME/share/hadoop/yarn/lib/* + For Windows: + %HADOOP_CONF_DIR%, + %HADOOP_COMMON_HOME%/share/hadoop/common/*, + %HADOOP_COMMON_HOME%/share/hadoop/common/lib/*, + %HADOOP_HDFS_HOME%/share/hadoop/hdfs/*, + %HADOOP_HDFS_HOME%/share/hadoop/hdfs/lib/*, + %HADOOP_YARN_HOME%/share/hadoop/yarn/*, + %HADOOP_YARN_HOME%/share/hadoop/yarn/lib/* + + yarn.application.classpath + + + + + + + Indicate what is the current version of the running + timeline service. For example, if "yarn.timeline-service.version" is 1.5, + and "yarn.timeline-service.enabled" is true, it means the cluster will and + should bring up the timeline service v.1.5. + On the client side, if the client uses the same version of timeline service, + it should succeed. If the client chooses to use a smaller version in spite of this, + then depending on how robust the compatibility story is between versions, + the results may vary. + + yarn.timeline-service.version + 1.0f + + + + + In the server side it indicates whether timeline service is enabled or not. + And in the client side, users can enable it to indicate whether client wants + to use timeline service. If it's enabled in the client side along with + security, then yarn client tries to fetch the delegation tokens for the + timeline server. + + yarn.timeline-service.enabled + false + + + + The hostname of the timeline service web application. + yarn.timeline-service.hostname + 0.0.0.0 + + + + This is default address for the timeline server to start the + RPC server. + yarn.timeline-service.address + ${yarn.timeline-service.hostname}:10200 + + + + The http address of the timeline service web application. + yarn.timeline-service.webapp.address + ${yarn.timeline-service.hostname}:8188 + + + + The https address of the timeline service web application. + yarn.timeline-service.webapp.https.address + ${yarn.timeline-service.hostname}:8190 + + + + + The actual address the server will bind to. If this optional address is + set, the RPC and webapp servers will bind to this address and the port specified in + yarn.timeline-service.address and yarn.timeline-service.webapp.address, respectively. + This is most useful for making the service listen to all interfaces by setting to + 0.0.0.0. + + yarn.timeline-service.bind-host + + + + + + Defines the max number of applications could be fetched using REST API or + application history protocol and shown in timeline server web ui. + + yarn.timeline-service.generic-application-history.max-applications + 10000 + + + + Store class name for timeline store. + yarn.timeline-service.store-class + org.apache.hadoop.yarn.server.timeline.LeveldbTimelineStore + + + + Enable age off of timeline store data. + yarn.timeline-service.ttl-enable + true + + + + Time to live for timeline store data in milliseconds. + yarn.timeline-service.ttl-ms + 604800000 + + + + Store file name for leveldb timeline store. + yarn.timeline-service.leveldb-timeline-store.path + ${hadoop.tmp.dir}/yarn/timeline + + + + Length of time to wait between deletion cycles of leveldb timeline store in milliseconds. + yarn.timeline-service.leveldb-timeline-store.ttl-interval-ms + 300000 + + + + Size of read cache for uncompressed blocks for leveldb timeline store in bytes. + yarn.timeline-service.leveldb-timeline-store.read-cache-size + 104857600 + + + + Size of cache for recently read entity start times for leveldb timeline store in number of entities. + yarn.timeline-service.leveldb-timeline-store.start-time-read-cache-size + 10000 + + + + Size of cache for recently written entity start times for leveldb timeline store in number of entities. + yarn.timeline-service.leveldb-timeline-store.start-time-write-cache-size + 10000 + + + + Handler thread count to serve the client RPC requests. + yarn.timeline-service.handler-thread-count + 10 + + + + yarn.timeline-service.http-authentication.type + simple + + Defines authentication used for the timeline server HTTP endpoint. + Supported values are: simple | kerberos | #AUTHENTICATION_HANDLER_CLASSNAME# + + + + + yarn.timeline-service.http-authentication.simple.anonymous.allowed + true + + Indicates if anonymous requests are allowed by the timeline server when using + 'simple' authentication. + + + + + The Kerberos principal for the timeline server. + yarn.timeline-service.principal + + + + + The Kerberos keytab for the timeline server. + yarn.timeline-service.keytab + /etc/krb5.keytab + + + + Comma separated list of UIs that will be hosted + yarn.timeline-service.ui-names + + + + + + Default maximum number of retries for timeline service client + and value -1 means no limit. + + yarn.timeline-service.client.max-retries + 30 + + + + Client policy for whether timeline operations are non-fatal. + Should the failure to obtain a delegation token be considered an application + failure (option = false), or should the client attempt to continue to + publish information without it (option=true) + yarn.timeline-service.client.best-effort + false + + + + + Default retry time interval for timeline servive client. + + yarn.timeline-service.client.retry-interval-ms + 1000 + + + + Enable timeline server to recover state after starting. If + true, then yarn.timeline-service.state-store-class must be specified. + + yarn.timeline-service.recovery.enabled + false + + + + Store class name for timeline state store. + yarn.timeline-service.state-store-class + org.apache.hadoop.yarn.server.timeline.recovery.LeveldbTimelineStateStore + + + + Store file name for leveldb state store. + yarn.timeline-service.leveldb-state-store.path + ${hadoop.tmp.dir}/yarn/timeline + + + + + + yarn.timeline-service.entity-group-fs-store.active-dir + /tmp/entity-file-history/active + HDFS path to store active application's timeline data + + + + yarn.timeline-service.entity-group-fs-store.done-dir + /tmp/entity-file-history/done/ + HDFS path to store done application's timeline data + + + + yarn.timeline-service.entity-group-fs-store.group-id-plugin-classes + + + Plugins that can translate a timeline entity read request into + a list of timeline entity group ids, separated by commas. + + + + + yarn.timeline-service.entity-group-fs-store.summary-store + Summary storage for ATS v1.5 + org.apache.hadoop.yarn.server.timeline.LeveldbTimelineStore + + + + yarn.timeline-service.entity-group-fs-store.scan-interval-seconds + + Scan interval for ATS v1.5 entity group file system storage reader.This + value controls how frequent the reader will scan the HDFS active directory + for application status. + + 60 + + + + yarn.timeline-service.entity-group-fs-store.cleaner-interval-seconds + + Scan interval for ATS v1.5 entity group file system storage cleaner.This + value controls how frequent the reader will scan the HDFS done directory + for stale application data. + + 3600 + + + + yarn.timeline-service.entity-group-fs-store.retain-seconds + + How long the ATS v1.5 entity group file system storage will keep an + application's data in the done directory. + + 604800 + + + + yarn.timeline-service.entity-group-fs-store.leveldb-cache-read-cache-size + + Read cache size for the leveldb cache storage in ATS v1.5 plugin storage. + + 10485760 + + + + yarn.timeline-service.entity-group-fs-store.app-cache-size + + Size of the reader cache for ATS v1.5 reader. This value controls how many + entity groups the ATS v1.5 server should cache. If the number of active + read entity groups is greater than the number of caches items, some reads + may return empty data. This value must be greater than 0. + + 10 + + + + yarn.timeline-service.client.fd-flush-interval-secs + + Flush interval for ATS v1.5 writer. This value controls how frequent + the writer will flush the HDFS FSStream for the entity/domain. + + 10 + + + + yarn.timeline-service.client.fd-clean-interval-secs + + Scan interval for ATS v1.5 writer. This value controls how frequent + the writer will scan the HDFS FSStream for the entity/domain. + If the FSStream is stale for a long time, this FSStream will be close. + + 60 + + + + yarn.timeline-service.client.fd-retain-secs + + How long the ATS v1.5 writer will keep a FSStream open. + If this fsstream does not write anything for this configured time, + it will be close. + + 300 + + + + yarn.timeline-service.client.internal-timers-ttl-secs + + How long the internal Timer Tasks can be alive in writer. If there is no + write operation for this configured time, the internal timer tasks will + be close. + + 420 + + + + + + Whether the shared cache is enabled + yarn.sharedcache.enabled + false + + + + The root directory for the shared cache + yarn.sharedcache.root-dir + /sharedcache + + + + The level of nested directories before getting to the checksum + directories. It must be non-negative. + yarn.sharedcache.nested-level + 3 + + + + The implementation to be used for the SCM store + yarn.sharedcache.store.class + org.apache.hadoop.yarn.server.sharedcachemanager.store.InMemorySCMStore + + + + The implementation to be used for the SCM app-checker + yarn.sharedcache.app-checker.class + org.apache.hadoop.yarn.server.sharedcachemanager.RemoteAppChecker + + + + A resource in the in-memory store is considered stale + if the time since the last reference exceeds the staleness period. + This value is specified in minutes. + yarn.sharedcache.store.in-memory.staleness-period-mins + 10080 + + + + Initial delay before the in-memory store runs its first check + to remove dead initial applications. Specified in minutes. + yarn.sharedcache.store.in-memory.initial-delay-mins + 10 + + + + The frequency at which the in-memory store checks to remove + dead initial applications. Specified in minutes. + yarn.sharedcache.store.in-memory.check-period-mins + 720 + + + + The address of the admin interface in the SCM (shared cache manager) + yarn.sharedcache.admin.address + 0.0.0.0:8047 + + + + The number of threads used to handle SCM admin interface (1 by default) + yarn.sharedcache.admin.thread-count + 1 + + + + The address of the web application in the SCM (shared cache manager) + yarn.sharedcache.webapp.address + 0.0.0.0:8788 + + + + The frequency at which a cleaner task runs. + Specified in minutes. + yarn.sharedcache.cleaner.period-mins + 1440 + + + + Initial delay before the first cleaner task is scheduled. + Specified in minutes. + yarn.sharedcache.cleaner.initial-delay-mins + 10 + + + + The time to sleep between processing each shared cache + resource. Specified in milliseconds. + yarn.sharedcache.cleaner.resource-sleep-ms + 0 + + + + The address of the node manager interface in the SCM + (shared cache manager) + yarn.sharedcache.uploader.server.address + 0.0.0.0:8046 + + + + The number of threads used to handle shared cache manager + requests from the node manager (50 by default) + yarn.sharedcache.uploader.server.thread-count + 50 + + + + The address of the client interface in the SCM + (shared cache manager) + yarn.sharedcache.client-server.address + 0.0.0.0:8045 + + + + The number of threads used to handle shared cache manager + requests from clients (50 by default) + yarn.sharedcache.client-server.thread-count + 50 + + + + The algorithm used to compute checksums of files (SHA-256 by + default) + yarn.sharedcache.checksum.algo.impl + org.apache.hadoop.yarn.sharedcache.ChecksumSHA256Impl + + + + The replication factor for the node manager uploader for the + shared cache (10 by default) + yarn.sharedcache.nm.uploader.replication.factor + 10 + + + + The number of threads used to upload files from a node manager + instance (20 by default) + yarn.sharedcache.nm.uploader.thread-count + 20 + + + + + ACL protocol for use in the Timeline server. + + security.applicationhistory.protocol.acl + + + + + + + + Set to true for MiniYARNCluster unit tests + + yarn.is.minicluster + false + + + + + Set for MiniYARNCluster unit tests to control resource monitoring + + yarn.minicluster.control-resource-monitoring + false + + + + + Set to false in order to allow MiniYARNCluster to run tests without + port conflicts. + + yarn.minicluster.fixed.ports + false + + + + + Set to false in order to allow the NodeManager in MiniYARNCluster to + use RPC to talk to the RM. + + yarn.minicluster.use-rpc + false + + + + + As yarn.nodemanager.resource.memory-mb property but for the NodeManager + in a MiniYARNCluster. + + yarn.minicluster.yarn.nodemanager.resource.memory-mb + 4096 + + + + + + + Enable node labels feature + + yarn.node-labels.enabled + false + + + + + Retry policy used for FileSystem node label store. The policy is + specified by N pairs of sleep-time in milliseconds and number-of-retries + "s1,n1,s2,n2,...". + + yarn.node-labels.fs-store.retry-policy-spec + 2000, 500 + + + + + URI for NodeLabelManager. The default value is + /tmp/hadoop-yarn-${user}/node-labels/ in the local filesystem. + + yarn.node-labels.fs-store.root-dir + + + + + + Set configuration type for node labels. Administrators can specify + "centralized", "delegated-centralized" or "distributed". + + yarn.node-labels.configuration-type + centralized + + + + + + When "yarn.node-labels.configuration-type" is configured with "distributed" + in RM, Administrators can configure in NM the provider for the + node labels by configuring this parameter. Administrators can + configure "config", "script" or the class name of the provider. Configured + class needs to extend + org.apache.hadoop.yarn.server.nodemanager.nodelabels.NodeLabelsProvider. + If "config" is configured, then "ConfigurationNodeLabelsProvider" and if + "script" is configured, then "ScriptNodeLabelsProvider" will be used. + + yarn.nodemanager.node-labels.provider + + + + + When "yarn.nodemanager.node-labels.provider" is configured with "config", + "Script" or the configured class extends AbstractNodeLabelsProvider, then + periodically node labels are retrieved from the node labels provider. This + configuration is to define the interval period. + If -1 is configured then node labels are retrieved from provider only + during initialization. Defaults to 10 mins. + + yarn.nodemanager.node-labels.provider.fetch-interval-ms + 600000 + + + + + Interval at which NM syncs its node labels with RM. NM will send its loaded + labels every x intervals configured, along with heartbeat to RM. + + yarn.nodemanager.node-labels.resync-interval-ms + 120000 + + + + + When "yarn.nodemanager.node-labels.provider" is configured with "config" + then ConfigurationNodeLabelsProvider fetches the partition label from this + parameter. + + yarn.nodemanager.node-labels.provider.configured-node-partition + + + + + When "yarn.nodemanager.node-labels.provider" is configured with "Script" + then this configuration provides the timeout period after which it will + interrupt the script which queries the Node labels. Defaults to 20 mins. + + yarn.nodemanager.node-labels.provider.fetch-timeout-ms + 1200000 + + + + + + When node labels "yarn.node-labels.configuration-type" is + of type "delegated-centralized", administrators should configure + the class for fetching node labels by ResourceManager. Configured + class needs to extend + org.apache.hadoop.yarn.server.resourcemanager.nodelabels. + RMNodeLabelsMappingProvider. + + yarn.resourcemanager.node-labels.provider + + + + + + When "yarn.node-labels.configuration-type" is configured with + "delegated-centralized", then periodically node labels are retrieved + from the node labels provider. This configuration is to define the + interval. If -1 is configured then node labels are retrieved from + provider only once for each node after it registers. Defaults to 30 mins. + + yarn.resourcemanager.node-labels.provider.fetch-interval-ms + 1800000 + + + + The Node Label script to run. Script output Line starting with + "NODE_PARTITION:" will be considered as Node Label Partition. In case of + multiple lines have this pattern, then last one will be considered + + yarn.nodemanager.node-labels.provider.script.path + + + + The arguments to pass to the Node label script. + yarn.nodemanager.node-labels.provider.script.opts + + + + + The interval that the yarn client library uses to poll the + completion status of the asynchronous API of application client protocol. + + yarn.client.application-client-protocol.poll-interval-ms + 200 + + + + + The duration (in ms) the YARN client waits for an expected state change + to occur. -1 means unlimited wait time. + + yarn.client.application-client-protocol.poll-timeout-ms + -1 + + + + RSS usage of a process computed via + /proc/pid/stat is not very accurate as it includes shared pages of a + process. /proc/pid/smaps provides useful information like + Private_Dirty, Private_Clean, Shared_Dirty, Shared_Clean which can be used + for computing more accurate RSS. When this flag is enabled, RSS is computed + as Min(Shared_Dirty, Pss) + Private_Clean + Private_Dirty. It excludes + read-only shared mappings in RSS computation. + + yarn.nodemanager.container-monitor.procfs-tree.smaps-based-rss.enabled + false + + + + + URL for log aggregation server + + yarn.log.server.url + + + + + + RM Application Tracking URL + + yarn.tracking.url.generator + + + + + + Class to be used for YarnAuthorizationProvider + + yarn.authorization-provider + + + + + Defines how often NMs wake up to upload log files. + The default value is -1. By default, the logs will be uploaded when + the application is finished. By setting this configure, logs can be uploaded + periodically when the application is running. The minimum rolling-interval-seconds + can be set is 3600. + + yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds + -1 + + + + + Enable/disable intermediate-data encryption at YARN level. For now, + this only is used by the FileSystemRMStateStore to setup right + file-system security attributes. + + yarn.intermediate-data-encryption.enable + false + + + + Flag to enable cross-origin (CORS) support in the NM. This flag + requires the CORS filter initializer to be added to the filter initializers + list in core-site.xml. + yarn.nodemanager.webapp.cross-origin.enabled + false + + + + + Defines maximum application priority in a cluster. + If an application is submitted with a priority higher than this value, it will be + reset to this maximum value. + + yarn.cluster.max-application-priority + 0 + + + + + The default log aggregation policy class. Applications can + override it via LogAggregationContext. This configuration can provide + some cluster-side default behavior so that if the application doesn't + specify any policy via LogAggregationContext administrators of the cluster + can adjust the policy globally. + + yarn.nodemanager.log-aggregation.policy.class + org.apache.hadoop.yarn.server.nodemanager.containermanager.logaggregation.AllContainerLogAggregationPolicy + + + + + The default parameters for the log aggregation policy. Applications can + override it via LogAggregationContext. This configuration can provide + some cluster-side default behavior so that if the application doesn't + specify any policy via LogAggregationContext administrators of the cluster + can adjust the policy globally. + + yarn.nodemanager.log-aggregation.policy.parameters + + + + + + Enable/Disable AMRMProxyService in the node manager. This service is used to intercept + calls from the application masters to the resource manager. + + yarn.nodemanager.amrmproxy.enable + false + + + + + The address of the AMRMProxyService listener. + + yarn.nodemanager.amrmproxy.address + 0.0.0.0:8048 + + + + + The number of threads used to handle requests by the AMRMProxyService. + + yarn.nodemanager.amrmproxy.client.thread-count + 25 + + + + + The comma separated list of class names that implement the RequestInterceptor interface. This is used by the + AMRMProxyService to create the request processing pipeline for applications. + + yarn.nodemanager.amrmproxy.interceptor-class.pipeline + org.apache.hadoop.yarn.server.nodemanager.amrmproxy.DefaultRequestInterceptor + + + + + Choose different implementation of node label's storage + + yarn.node-labels.fs-store.impl.class + org.apache.hadoop.yarn.nodelabels.FileSystemNodeLabelsStore + + + + + The least amount of time(msec.) an inactive (decommissioned or shutdown) node can + stay in the nodes list of the resourcemanager after being declared untracked. + A node is marked untracked if and only if it is absent from both include and + exclude nodemanager lists on the RM. All inactive nodes are checked twice per + timeout interval or every 10 minutes, whichever is lesser, and marked appropriately. + The same is done when refreshNodes command (graceful or otherwise) is invoked. + + yarn.resourcemanager.node-removal-untracked.timeout-ms + 60000 + + diff --git a/sahara/plugins/vanilla/v2_8_2/versionhandler.py b/sahara/plugins/vanilla/v2_8_2/versionhandler.py new file mode 100644 index 0000000..8cc377b --- /dev/null +++ b/sahara/plugins/vanilla/v2_8_2/versionhandler.py @@ -0,0 +1,170 @@ +# Copyright (c) 2015 Mirantis Inc. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or +# implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from oslo_config import cfg + +from sahara import conductor +from sahara import context +from sahara.plugins import utils +from sahara.plugins.vanilla import abstractversionhandler as avm +from sahara.plugins.vanilla.hadoop2 import config as c +from sahara.plugins.vanilla.hadoop2 import keypairs +from sahara.plugins.vanilla.hadoop2 import recommendations_utils as ru +from sahara.plugins.vanilla.hadoop2 import run_scripts as run +from sahara.plugins.vanilla.hadoop2 import scaling as sc +from sahara.plugins.vanilla.hadoop2 import starting_scripts as s_scripts +from sahara.plugins.vanilla.hadoop2 import utils as u +from sahara.plugins.vanilla.hadoop2 import validation as vl +from sahara.plugins.vanilla import utils as vu +from sahara.plugins.vanilla.v2_8_2 import config_helper as c_helper +from sahara.plugins.vanilla.v2_8_2 import edp_engine +from sahara.swift import swift_helper +from sahara.utils import cluster as cluster_utils + + +conductor = conductor.API +CONF = cfg.CONF + + +class VersionHandler(avm.AbstractVersionHandler): + def __init__(self): + self.pctx = { + 'env_confs': c_helper.get_env_configs(), + 'all_confs': c_helper.get_plugin_configs() + } + + def get_plugin_configs(self): + return self.pctx['all_confs'] + + def get_node_processes(self): + return { + "Hadoop": [], + "MapReduce": ["historyserver"], + "HDFS": ["namenode", "datanode", "secondarynamenode"], + "YARN": ["resourcemanager", "nodemanager"], + "JobFlow": ["oozie"], + "Hive": ["hiveserver"], + "Spark": ["spark history server"], + "ZooKeeper": ["zookeeper"] + } + + def validate(self, cluster): + vl.validate_cluster_creating(self.pctx, cluster) + + def update_infra(self, cluster): + pass + + def configure_cluster(self, cluster): + c.configure_cluster(self.pctx, cluster) + + def start_cluster(self, cluster): + keypairs.provision_keypairs(cluster) + + s_scripts.start_namenode(cluster) + s_scripts.start_secondarynamenode(cluster) + s_scripts.start_resourcemanager(cluster) + + run.start_dn_nm_processes(utils.get_instances(cluster)) + run.await_datanodes(cluster) + + s_scripts.start_historyserver(cluster) + s_scripts.start_oozie(self.pctx, cluster) + s_scripts.start_hiveserver(self.pctx, cluster) + s_scripts.start_zookeeper(cluster) + + swift_helper.install_ssl_certs(cluster_utils.get_instances(cluster)) + + self._set_cluster_info(cluster) + s_scripts.start_spark(cluster) + + def decommission_nodes(self, cluster, instances): + sc.decommission_nodes(self.pctx, cluster, instances) + + def validate_scaling(self, cluster, existing, additional): + vl.validate_additional_ng_scaling(cluster, additional) + vl.validate_existing_ng_scaling(self.pctx, cluster, existing) + zk_ng = utils.get_node_groups(cluster, "zookeeper") + if zk_ng: + vl.validate_zookeeper_node_count(zk_ng, existing, additional) + + def scale_cluster(self, cluster, instances): + keypairs.provision_keypairs(cluster, instances) + sc.scale_cluster(self.pctx, cluster, instances) + + def _set_cluster_info(self, cluster): + nn = vu.get_namenode(cluster) + rm = vu.get_resourcemanager(cluster) + hs = vu.get_historyserver(cluster) + oo = vu.get_oozie(cluster) + sp = vu.get_spark_history_server(cluster) + info = {} + + if rm: + info['YARN'] = { + 'Web UI': 'http://%s:%s' % (rm.get_ip_or_dns_name(), '8088'), + 'ResourceManager': 'http://%s:%s' % ( + rm.get_ip_or_dns_name(), '8032') + } + + if nn: + info['HDFS'] = { + 'Web UI': 'http://%s:%s' % (nn.get_ip_or_dns_name(), '50070'), + 'NameNode': 'hdfs://%s:%s' % (nn.hostname(), '9000') + } + + if oo: + info['JobFlow'] = { + 'Oozie': 'http://%s:%s' % (oo.get_ip_or_dns_name(), '11000') + } + + if hs: + info['MapReduce JobHistory Server'] = { + 'Web UI': 'http://%s:%s' % (hs.get_ip_or_dns_name(), '19888') + } + + if sp: + info['Apache Spark'] = { + 'Spark UI': 'http://%s:%s' % (sp.management_ip, '4040'), + 'Spark History Server UI': + 'http://%s:%s' % (sp.management_ip, '18080') + } + + ctx = context.ctx() + conductor.cluster_update(ctx, cluster, {'info': info}) + + def get_edp_engine(self, cluster, job_type): + if job_type in edp_engine.EdpOozieEngine.get_supported_job_types(): + return edp_engine.EdpOozieEngine(cluster) + if job_type in edp_engine.EdpSparkEngine.get_supported_job_types(): + return edp_engine.EdpSparkEngine(cluster) + + return None + + def get_edp_job_types(self): + return (edp_engine.EdpOozieEngine.get_supported_job_types() + + edp_engine.EdpSparkEngine.get_supported_job_types()) + + def get_edp_config_hints(self, job_type): + return edp_engine.EdpOozieEngine.get_possible_job_config(job_type) + + def on_terminate_cluster(self, cluster): + u.delete_oozie_password(cluster) + keypairs.drop_key(cluster) + + def get_open_ports(self, node_group): + return c.get_open_ports(node_group) + + def recommend_configs(self, cluster, scaling): + ru.recommend_configs(cluster, self.get_plugin_configs(), scaling) diff --git a/sahara/tests/unit/plugins/vanilla/hadoop2/test_run_scripts.py b/sahara/tests/unit/plugins/vanilla/hadoop2/test_run_scripts.py index 9481af6..583c23f 100644 --- a/sahara/tests/unit/plugins/vanilla/hadoop2/test_run_scripts.py +++ b/sahara/tests/unit/plugins/vanilla/hadoop2/test_run_scripts.py @@ -189,6 +189,8 @@ class RunScriptsTest(base.SaharaTestCase): 'hadoop fs -mkdir /user && ' \ 'hadoop fs -mkdir /user/hadoop && ' \ 'hadoop fs -put /tmp/oozielib/share /user/hadoop/ && ' \ + 'hadoop fs -put /opt/oozie/libtools/commons-httpclient-3.1.jar ' \ + '/user/hadoop/share/lib/oozie/ &&' \ 'rm -rf /tmp/oozielib" hadoop' cmd_2 = 'sudo su - -c "/opt/oozie/bin/ooziedb.sh ' \ 'create -sqlfile oozie.sql ' \ @@ -291,10 +293,11 @@ class RunScriptsTest(base.SaharaTestCase): path = edp.get_hive_shared_conf_path('hadoop') is_mysql_enabled.return_value = True cluster = self.instance.cluster + self.instance.cluster.hadoop_version = '2.7.1' ng_cluster = self.instance.node_group.cluster get_oozie.return_value = None sql_script = files.get_file_text( - 'plugins/vanilla/hadoop2/resources/create_hive_db.sql') + 'plugins/vanilla/v2_7_1/resources/create_hive_db.sql') get_hive_password.return_value = '123' pwd_script = sql_script.replace('{{password}}', '123') rs.start_hiveserver_process(pctx, self.instance) diff --git a/sahara/tests/unit/plugins/vanilla/v2_8_2/__init__.py b/sahara/tests/unit/plugins/vanilla/v2_8_2/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/sahara/tests/unit/plugins/vanilla/v2_8_2/test_config_helper.py b/sahara/tests/unit/plugins/vanilla/v2_8_2/test_config_helper.py new file mode 100644 index 0000000..4c70be3 --- /dev/null +++ b/sahara/tests/unit/plugins/vanilla/v2_8_2/test_config_helper.py @@ -0,0 +1,77 @@ +# Copyright (c) 2017 EasyStack Inc. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or +# implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import mock + +from sahara.plugins import provisioning as p +from sahara.plugins.vanilla.hadoop2 import config_helper as h_helper +from sahara.plugins.vanilla.v2_8_2 import config_helper as v_helper +from sahara.tests.unit import base + + +class TestConfigHelper(base.SaharaTestCase): + + plugin_path = 'sahara.plugins.vanilla.v2_8_2.' + plugin_hadoop_path = 'sahara.plugins.vanilla.hadoop2.' + + def setUp(self): + super(TestConfigHelper, self).setUp() + + @mock.patch(plugin_hadoop_path + 'config_helper.PLUGIN_GENERAL_CONFIGS') + @mock.patch(plugin_path + 'config_helper.PLUGIN_ENV_CONFIGS') + @mock.patch(plugin_path + 'config_helper.PLUGIN_XML_CONFIGS') + @mock.patch(plugin_path + 'config_helper._get_spark_configs') + @mock.patch(plugin_path + 'config_helper._get_zookeeper_configs') + def test_init_all_configs(self, + _get_zk_configs, + _get_spark_configs, + PLUGIN_XML_CONFIGS, + PLUGIN_ENV_CONFIGS, + PLUGIN_GENERAL_CONFIGS): + configs = [] + configs.extend(PLUGIN_XML_CONFIGS) + configs.extend(PLUGIN_ENV_CONFIGS) + configs.extend(PLUGIN_GENERAL_CONFIGS) + configs.extend(_get_spark_configs()) + configs.extend(_get_zk_configs()) + init_configs = v_helper._init_all_configs() + self.assertEqual(init_configs, configs) + + def test_get_spark_configs(self): + h_helper.SPARK_CONFS = { + 'Spark': { + 'OPTIONS': [{ + 'name': 'test', + 'description': 'This is a test', + 'default': 'default', + 'priority': 1 + }] + } + } + spark_configs = v_helper._get_spark_configs() + for i in spark_configs: + self.assertIsInstance(i, p.Config) + + def test_get_plugin_configs(self): + self.assertEqual(v_helper.get_plugin_configs(), + v_helper.PLUGIN_CONFIGS) + + def test_get_xml_configs(self): + self.assertEqual(v_helper.get_xml_configs(), + v_helper.PLUGIN_XML_CONFIGS) + + def test_get_env_configs(self): + self.assertEqual(v_helper.get_env_configs(), + v_helper.ENV_CONFS) diff --git a/sahara/tests/unit/plugins/vanilla/v2_8_2/test_edp_engine.py b/sahara/tests/unit/plugins/vanilla/v2_8_2/test_edp_engine.py new file mode 100644 index 0000000..d77cb81 --- /dev/null +++ b/sahara/tests/unit/plugins/vanilla/v2_8_2/test_edp_engine.py @@ -0,0 +1,96 @@ +# Copyright (c) 2015 Red Hat, Inc. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or +# implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import mock + +from sahara.plugins.vanilla.v2_8_2 import edp_engine +from sahara.tests.unit import base as sahara_base +from sahara.utils import edp + + +class Vanilla2ConfigHintsTest(sahara_base.SaharaTestCase): + @mock.patch( + 'sahara.plugins.vanilla.confighints_helper.' + 'get_possible_hive_config_from', + return_value={}) + def test_get_possible_job_config_hive( + self, get_possible_hive_config_from): + expected_config = {'job_config': {}} + actual_config = edp_engine.EdpOozieEngine.get_possible_job_config( + edp.JOB_TYPE_HIVE) + get_possible_hive_config_from.assert_called_once_with( + 'plugins/vanilla/v2_8_2/resources/hive-default.xml') + self.assertEqual(expected_config, actual_config) + + @mock.patch('sahara.plugins.vanilla.hadoop2.edp_engine.EdpOozieEngine') + def test_get_possible_job_config_java(self, BaseVanillaEdpOozieEngine): + expected_config = {'job_config': {}} + BaseVanillaEdpOozieEngine.get_possible_job_config.return_value = ( + expected_config) + actual_config = edp_engine.EdpOozieEngine.get_possible_job_config( + edp.JOB_TYPE_JAVA) + (BaseVanillaEdpOozieEngine.get_possible_job_config. + assert_called_once_with(edp.JOB_TYPE_JAVA)) + self.assertEqual(expected_config, actual_config) + + @mock.patch( + 'sahara.plugins.vanilla.confighints_helper.' + 'get_possible_mapreduce_config_from', + return_value={}) + def test_get_possible_job_config_mapreduce( + self, get_possible_mapreduce_config_from): + expected_config = {'job_config': {}} + actual_config = edp_engine.EdpOozieEngine.get_possible_job_config( + edp.JOB_TYPE_MAPREDUCE) + get_possible_mapreduce_config_from.assert_called_once_with( + 'plugins/vanilla/v2_8_2/resources/mapred-default.xml') + self.assertEqual(expected_config, actual_config) + + @mock.patch( + 'sahara.plugins.vanilla.confighints_helper.' + 'get_possible_mapreduce_config_from', + return_value={}) + def test_get_possible_job_config_mapreduce_streaming( + self, get_possible_mapreduce_config_from): + expected_config = {'job_config': {}} + actual_config = edp_engine.EdpOozieEngine.get_possible_job_config( + edp.JOB_TYPE_MAPREDUCE_STREAMING) + get_possible_mapreduce_config_from.assert_called_once_with( + 'plugins/vanilla/v2_8_2/resources/mapred-default.xml') + self.assertEqual(expected_config, actual_config) + + @mock.patch( + 'sahara.plugins.vanilla.confighints_helper.' + 'get_possible_pig_config_from', + return_value={}) + def test_get_possible_job_config_pig( + self, get_possible_pig_config_from): + expected_config = {'job_config': {}} + actual_config = edp_engine.EdpOozieEngine.get_possible_job_config( + edp.JOB_TYPE_PIG) + get_possible_pig_config_from.assert_called_once_with( + 'plugins/vanilla/v2_8_2/resources/mapred-default.xml') + self.assertEqual(expected_config, actual_config) + + @mock.patch('sahara.plugins.vanilla.hadoop2.edp_engine.EdpOozieEngine') + def test_get_possible_job_config_shell(self, BaseVanillaEdpOozieEngine): + expected_config = {'job_config': {}} + BaseVanillaEdpOozieEngine.get_possible_job_config.return_value = ( + expected_config) + actual_config = edp_engine.EdpOozieEngine.get_possible_job_config( + edp.JOB_TYPE_SHELL) + (BaseVanillaEdpOozieEngine.get_possible_job_config. + assert_called_once_with(edp.JOB_TYPE_SHELL)) + self.assertEqual(expected_config, actual_config) diff --git a/sahara/tests/unit/plugins/vanilla/v2_8_2/test_versionhandler.py b/sahara/tests/unit/plugins/vanilla/v2_8_2/test_versionhandler.py new file mode 100644 index 0000000..55f3199 --- /dev/null +++ b/sahara/tests/unit/plugins/vanilla/v2_8_2/test_versionhandler.py @@ -0,0 +1,253 @@ +# Copyright (c) 2017 EasyStack Inc. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or +# implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import mock +import six +import testtools + +from sahara.conductor import resource as r +from sahara.plugins import exceptions as ex +from sahara.plugins.vanilla.v2_8_2.edp_engine import EdpOozieEngine +from sahara.plugins.vanilla.v2_8_2.edp_engine import EdpSparkEngine +from sahara.plugins.vanilla.v2_8_2 import versionhandler as v_h +from sahara.tests.unit import base +from sahara.tests.unit import testutils + + +class TestConfig(object): + def __init__(self, applicable_target, name, default_value): + self.applicable_target = applicable_target + self.name = name + self.default_value = default_value + + +class VersionHandlerTest(base.SaharaTestCase): + plugin_path = 'sahara.plugins.vanilla.' + plugin_hadoop2_path = 'sahara.plugins.vanilla.hadoop2.' + + def setUp(self): + super(VersionHandlerTest, self).setUp() + self.cluster = mock.Mock() + self.vh = v_h.VersionHandler() + + def test_get_plugin_configs(self): + self.vh.pctx['all_confs'] = 'haha' + conf = self.vh.get_plugin_configs() + self.assertEqual(conf, 'haha') + + def test_get_node_processes(self): + processes = self.vh.get_node_processes() + for k, v in six.iteritems(processes): + for p in v: + self.assertIsInstance(p, str) + + @mock.patch(plugin_hadoop2_path + + 'validation.validate_cluster_creating') + def test_validate(self, validate_create): + self.vh.pctx = mock.Mock() + self.vh.validate(self.cluster) + validate_create.assert_called_once_with(self.vh.pctx, + self.cluster) + + @mock.patch(plugin_path + + 'v2_8_2.versionhandler.VersionHandler.update_infra') + def test_update_infra(self, update_infra): + self.vh.update_infra(self.cluster) + update_infra.assert_called_once_with(self.cluster) + + @mock.patch(plugin_hadoop2_path + 'config.configure_cluster') + def test_configure_cluster(self, configure_cluster): + self.vh.pctx = mock.Mock() + self.vh.configure_cluster(self.cluster) + configure_cluster.assert_called_once_with(self.vh.pctx, self.cluster) + + @mock.patch(plugin_path + 'v2_8_2.versionhandler.run') + @mock.patch(plugin_path + 'v2_8_2.versionhandler.s_scripts') + @mock.patch('sahara.swift.swift_helper.install_ssl_certs') + @mock.patch(plugin_hadoop2_path + 'keypairs.provision_keypairs') + @mock.patch('sahara.plugins.utils.get_instances') + @mock.patch('sahara.utils.cluster.get_instances') + def test_start_cluster(self, c_get_instances, u_get_instances, + provision_keypairs, install_ssl_certs, + s_scripts, run): + self.vh.pctx = mock.Mock() + instances = mock.Mock() + c_get_instances.return_value = instances + u_get_instances.return_value = instances + self.vh._set_cluster_info = mock.Mock() + self.vh.start_cluster(self.cluster) + provision_keypairs.assert_called_once_with(self.cluster) + s_scripts.start_namenode.assert_called_once_with(self.cluster) + s_scripts.start_secondarynamenode.assert_called_once_with(self.cluster) + s_scripts.start_resourcemanager.assert_called_once_with(self.cluster) + s_scripts.start_historyserver.assert_called_once_with(self.cluster) + s_scripts.start_oozie.assert_called_once_with(self.vh.pctx, + self.cluster) + s_scripts.start_hiveserver.assert_called_once_with(self.vh.pctx, + self.cluster) + s_scripts.start_spark.assert_called_once_with(self.cluster) + run.start_dn_nm_processes.assert_called_once_with(instances) + run.await_datanodes.assert_called_once_with(self.cluster) + install_ssl_certs.assert_called_once_with(instances) + self.vh._set_cluster_info.assert_called_once_with(self.cluster) + + @mock.patch(plugin_hadoop2_path + 'scaling.decommission_nodes') + def test_decommission_nodes(self, decommission_nodes): + self.vh.pctx = mock.Mock() + cluster = mock.Mock() + instances = mock.Mock() + self.vh.decommission_nodes(cluster, instances) + decommission_nodes.assert_called_once_with(self.vh.pctx, + cluster, + instances) + + @mock.patch('sahara.utils.general.get_by_id') + @mock.patch(plugin_hadoop2_path + + 'validation.validate_additional_ng_scaling') + @mock.patch(plugin_hadoop2_path + + 'validation.validate_existing_ng_scaling') + def test_validate_scaling(self, vls, vla, get_by_id): + self.vh.pctx['all_confs'] = [TestConfig('HDFS', 'dfs.replication', -1)] + ng1 = testutils.make_ng_dict('ng1', '40', ['namenode'], 1) + ng2 = testutils.make_ng_dict('ng2', '41', ['datanode'], 2) + ng3 = testutils.make_ng_dict('ng3', '42', ['datanode'], 3) + additional = [ng2['id'], ng3['id']] + existing = {ng2['id']: 1} + cluster = testutils.create_cluster('test-cluster', 'tenant1', 'fake', + '0.1', [ng1, ng2, ng3]) + self.vh.validate_scaling(cluster, existing, additional) + vla.assert_called_once_with(cluster, additional) + vls.assert_called_once_with(self.vh.pctx, cluster, existing) + + ng4 = testutils.make_ng_dict('ng4', '43', ['datanode', 'zookeeper'], 3) + ng5 = testutils.make_ng_dict('ng5', '44', ['datanode', 'zookeeper'], 1) + existing = {ng4['id']: 2} + additional = {ng5['id']} + cluster = testutils.create_cluster('test-cluster', 'tenant1', 'fake', + '0.1', [ng1, ng4]) + + with testtools.ExpectedException(ex.ClusterCannotBeScaled): + self.vh.validate_scaling(cluster, existing, {}) + + get_by_id.return_value = r.NodeGroupResource(ng5) + + with testtools.ExpectedException(ex.ClusterCannotBeScaled): + self.vh.validate_scaling(cluster, {}, additional) + + @mock.patch(plugin_hadoop2_path + 'scaling.scale_cluster') + @mock.patch(plugin_hadoop2_path + 'keypairs.provision_keypairs') + def test_scale_cluster(self, provision_keypairs, scale_cluster): + self.vh.pctx = mock.Mock() + instances = mock.Mock() + self.vh.scale_cluster(self.cluster, instances) + provision_keypairs.assert_called_once_with(self.cluster, + instances) + scale_cluster.assert_called_once_with(self.vh.pctx, + self.cluster, + instances) + + @mock.patch("sahara.conductor.API.cluster_update") + @mock.patch("sahara.context.ctx") + @mock.patch(plugin_path + 'utils.get_namenode') + @mock.patch(plugin_path + 'utils.get_resourcemanager') + @mock.patch(plugin_path + 'utils.get_historyserver') + @mock.patch(plugin_path + 'utils.get_oozie') + @mock.patch(plugin_path + 'utils.get_spark_history_server') + def test_set_cluster_info(self, get_spark_history_server, get_oozie, + get_historyserver, get_resourcemanager, + get_namenode, ctx, cluster_update): + get_spark_history_server.return_value.management_ip = '1.2.3.0' + get_oozie.return_value.get_ip_or_dns_name = mock.Mock( + return_value='1.2.3.1') + get_historyserver.return_value.get_ip_or_dns_name = mock.Mock( + return_value='1.2.3.2') + get_resourcemanager.return_value.get_ip_or_dns_name = mock.Mock( + return_value='1.2.3.3') + get_namenode.return_value.get_ip_or_dns_name = mock.Mock( + return_value='1.2.3.4') + get_namenode.return_value.hostname = mock.Mock( + return_value='testnode') + self.vh._set_cluster_info(self.cluster) + info = {'YARN': { + 'Web UI': 'http://1.2.3.3:8088', + 'ResourceManager': 'http://1.2.3.3:8032' + }, + 'HDFS': { + 'Web UI': 'http://1.2.3.4:50070', + 'NameNode': 'hdfs://testnode:9000' + }, + 'JobFlow': { + 'Oozie': 'http://1.2.3.1:11000' + }, + 'MapReduce JobHistory Server': { + 'Web UI': 'http://1.2.3.2:19888' + }, + 'Apache Spark': { + 'Spark UI': 'http://1.2.3.0:4040', + 'Spark History Server UI': 'http://1.2.3.0:18080' + } + } + cluster_update.assert_called_once_with(ctx(), self.cluster, + {'info': info}) + + @mock.patch("sahara.service.edp.job_utils.get_plugin") + @mock.patch('sahara.plugins.utils.get_instance') + @mock.patch('os.path.join') + def test_get_edp_engine(self, join, get_instance, get_plugin): + job_type = '' + ret = self.vh.get_edp_engine(self.cluster, job_type) + self.assertIsNone(ret) + + job_type = 'Java' + ret = self.vh.get_edp_engine(self.cluster, job_type) + self.assertIsInstance(ret, EdpOozieEngine) + + job_type = 'Spark' + ret = self.vh.get_edp_engine(self.cluster, job_type) + self.assertIsInstance(ret, EdpSparkEngine) + + def test_get_edp_job_types(self): + job_types = ['Hive', 'Java', 'MapReduce', + 'MapReduce.Streaming', 'Pig', 'Shell', 'Spark'] + self.assertEqual(self.vh.get_edp_job_types(), job_types) + + def test_get_edp_config_hints(self): + job_type = 'Java' + ret = {'job_config': {'args': [], 'configs': []}} + self.assertEqual(self.vh.get_edp_config_hints(job_type), ret) + + @mock.patch(plugin_hadoop2_path + 'utils.delete_oozie_password') + @mock.patch(plugin_hadoop2_path + 'keypairs.drop_key') + def test_on_terminate_cluster(self, delete_oozie_password, drop_key): + self.vh.on_terminate_cluster(self.cluster) + delete_oozie_password.assert_called_once_with(self.cluster) + drop_key.assert_called_once_with(self.cluster) + + @mock.patch(plugin_hadoop2_path + 'config.get_open_ports') + def test_get_open_ports(self, get_open_ports): + node_group = mock.Mock() + self.vh.get_open_ports(node_group) + get_open_ports.assert_called_once_with(node_group) + + @mock.patch(plugin_hadoop2_path + + 'recommendations_utils.recommend_configs') + def test_recommend_configs(self, recommend_configs): + scaling = mock.Mock() + configs = mock.Mock() + self.vh.pctx['all_confs'] = configs + self.vh.recommend_configs(self.cluster, scaling) + recommend_configs.assert_called_once_with(self.cluster, + configs, + scaling)