591c5eb1ee
Integrate the Spark plugin in Sahara. It adds the capability of provisioning Spark clusters with (Cloudera) HDFS. The plugin assumes the use of VM images generated with the Savanna diskimage-builder and the '-p spark' option. Implements: blueprint spark-plugin Wiki: https://wiki.openstack.org/wiki/Sahara/SparkPlugin This code is running on our Bigfoot research cluster. Change-Id: Ic105f7de64248bdfb05879ededf35503bc04925b
633 lines
20 KiB
XML
633 lines
20 KiB
XML
<?xml version="1.0"?>
|
|
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
|
|
|
|
<!-- Do not modify this file directly. Instead, copy entries that you -->
|
|
<!-- wish to modify from this file into core-site.xml and change them -->
|
|
<!-- there. If core-site.xml does not already exist, create it. -->
|
|
|
|
<configuration>
|
|
|
|
<!--- global properties -->
|
|
|
|
<property>
|
|
<name>hadoop.tmp.dir</name>
|
|
<value>/tmp/hadoop-${user.name}</value>
|
|
<description>A base for other temporary directories.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.native.lib</name>
|
|
<value>true</value>
|
|
<description>Should native hadoop libraries, if present, be used.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.http.filter.initializers</name>
|
|
<value></value>
|
|
<description>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.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.security.group.mapping</name>
|
|
<value>org.apache.hadoop.security.ShellBasedUnixGroupsMapping</value>
|
|
<description>Class for user to group mapping (get groups for a given user)
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.security.authorization</name>
|
|
<value>false</value>
|
|
<description>Is service-level authorization enabled?</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.security.instrumentation.requires.admin</name>
|
|
<value>false</value>
|
|
<description>
|
|
Indicates if administrator ACLs are required to access
|
|
instrumentation servlets (JMX, METRICS, CONF, STACKS).
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.security.authentication</name>
|
|
<value>simple</value>
|
|
<description>Possible values are simple (no authentication), and kerberos
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.security.token.service.use_ip</name>
|
|
<value>true</value>
|
|
<description>Controls whether tokens always use IP addresses. DNS changes
|
|
will not be detected if this option is enabled. Existing client connections
|
|
that break will always reconnect to the IP of the original host. New clients
|
|
will connect to the host's new IP but fail to locate a token. Disabling
|
|
this option will allow existing and new clients to detect an IP change and
|
|
continue to locate the new host's token.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.security.use-weak-http-crypto</name>
|
|
<value>false</value>
|
|
<description>If enabled, use KSSL to authenticate HTTP connections to the
|
|
NameNode. Due to a bug in JDK6, using KSSL requires one to configure
|
|
Kerberos tickets to use encryption types that are known to be
|
|
cryptographically weak. If disabled, SPNEGO will be used for HTTP
|
|
authentication, which supports stronger encryption types.
|
|
</description>
|
|
</property>
|
|
|
|
<!--
|
|
<property>
|
|
<name>hadoop.security.service.user.name.key</name>
|
|
<value></value>
|
|
<description>Name of the kerberos principal of the user that owns
|
|
a given service daemon
|
|
</description>
|
|
</property>
|
|
-->
|
|
|
|
<!--- logging properties -->
|
|
|
|
<property>
|
|
<name>hadoop.logfile.size</name>
|
|
<value>10000000</value>
|
|
<description>The max size of each log file</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.logfile.count</name>
|
|
<value>10</value>
|
|
<description>The max number of log files</description>
|
|
</property>
|
|
|
|
<!-- i/o properties -->
|
|
<property>
|
|
<name>io.file.buffer.size</name>
|
|
<value>4096</value>
|
|
<description>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.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.bytes.per.checksum</name>
|
|
<value>512</value>
|
|
<description>The number of bytes per checksum. Must not be larger than
|
|
io.file.buffer.size.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.skip.checksum.errors</name>
|
|
<value>false</value>
|
|
<description>If true, when a checksum error is encountered while
|
|
reading a sequence file, entries are skipped, instead of throwing an
|
|
exception.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.compression.codecs</name>
|
|
<value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec,org.apache.hadoop.io.compress.SnappyCodec</value>
|
|
<description>A list of the compression codec classes that can be used
|
|
for compression/decompression.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.serializations</name>
|
|
<value>org.apache.hadoop.io.serializer.WritableSerialization</value>
|
|
<description>A list of serialization classes that can be used for
|
|
obtaining serializers and deserializers.</description>
|
|
</property>
|
|
|
|
<!-- file system properties -->
|
|
|
|
<property>
|
|
<name>fs.defaultFS</name>
|
|
<value>file:///</value>
|
|
<description>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.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.trash.interval</name>
|
|
<value>0</value>
|
|
<description>Number of minutes between trash checkpoints.
|
|
If zero, the trash feature is disabled.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.file.impl</name>
|
|
<value>org.apache.hadoop.fs.LocalFileSystem</value>
|
|
<description>The FileSystem for file: uris.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.hdfs.impl</name>
|
|
<value>org.apache.hadoop.hdfs.DistributedFileSystem</value>
|
|
<description>The FileSystem for hdfs: uris.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.s3.impl</name>
|
|
<value>org.apache.hadoop.fs.s3.S3FileSystem</value>
|
|
<description>The FileSystem for s3: uris.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.s3n.impl</name>
|
|
<value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value>
|
|
<description>The FileSystem for s3n: (Native S3) uris.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.kfs.impl</name>
|
|
<value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value>
|
|
<description>The FileSystem for kfs: uris.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.hftp.impl</name>
|
|
<value>org.apache.hadoop.hdfs.HftpFileSystem</value>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.hsftp.impl</name>
|
|
<value>org.apache.hadoop.hdfs.HsftpFileSystem</value>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.webhdfs.impl</name>
|
|
<value>org.apache.hadoop.hdfs.web.WebHdfsFileSystem</value>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.ftp.impl</name>
|
|
<value>org.apache.hadoop.fs.ftp.FTPFileSystem</value>
|
|
<description>The FileSystem for ftp: uris.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.ramfs.impl</name>
|
|
<value>org.apache.hadoop.fs.InMemoryFileSystem</value>
|
|
<description>The FileSystem for ramfs: uris.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.har.impl</name>
|
|
<value>org.apache.hadoop.fs.HarFileSystem</value>
|
|
<description>The filesystem for Hadoop archives. </description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.har.impl.disable.cache</name>
|
|
<value>true</value>
|
|
<description>Don't cache 'har' filesystem instances.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.checkpoint.dir</name>
|
|
<value>${hadoop.tmp.dir}/dfs/namesecondary</value>
|
|
<description>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.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.checkpoint.edits.dir</name>
|
|
<value>${fs.checkpoint.dir}</value>
|
|
<description>Determines where on the local filesystem the DFS secondary
|
|
name node should store the temporary edits to merge.
|
|
If this is a comma-delimited list of directoires then teh edits is
|
|
replicated in all of the directoires for redundancy.
|
|
Default value is same as fs.checkpoint.dir
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.checkpoint.period</name>
|
|
<value>3600</value>
|
|
<description>The number of seconds between two periodic checkpoints.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.checkpoint.size</name>
|
|
<value>67108864</value>
|
|
<description>The size of the current edit log (in bytes) that triggers
|
|
a periodic checkpoint even if the fs.checkpoint.period hasn't expired.
|
|
</description>
|
|
</property>
|
|
|
|
|
|
|
|
<property>
|
|
<name>fs.s3.block.size</name>
|
|
<value>67108864</value>
|
|
<description>Block size to use when writing files to S3.</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.s3.buffer.dir</name>
|
|
<value>${hadoop.tmp.dir}/s3</value>
|
|
<description>Determines where on the local filesystem the S3 filesystem
|
|
should store files before sending them to S3
|
|
(or after retrieving them from S3).
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.s3.maxRetries</name>
|
|
<value>4</value>
|
|
<description>The maximum number of retries for reading or writing files to S3,
|
|
before we signal failure to the application.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>fs.s3.sleepTimeSeconds</name>
|
|
<value>10</value>
|
|
<description>The number of seconds to sleep between each S3 retry.
|
|
</description>
|
|
</property>
|
|
|
|
|
|
<property>
|
|
<name>local.cache.size</name>
|
|
<value>10737418240</value>
|
|
<description>The limit on the size of cache you want to keep, set by default
|
|
to 10GB. This will act as a soft limit on the cache directory for out of band data.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.seqfile.compress.blocksize</name>
|
|
<value>1000000</value>
|
|
<description>The minimum block size for compression in block compressed
|
|
SequenceFiles.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.seqfile.lazydecompress</name>
|
|
<value>true</value>
|
|
<description>Should values of block-compressed SequenceFiles be decompressed
|
|
only when necessary.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.seqfile.sorter.recordlimit</name>
|
|
<value>1000000</value>
|
|
<description>The limit on number of records to be kept in memory in a spill
|
|
in SequenceFiles.Sorter
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.mapfile.bloom.size</name>
|
|
<value>1048576</value>
|
|
<description>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.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>io.mapfile.bloom.error.rate</name>
|
|
<value>0.005</value>
|
|
<description>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%).
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.util.hash.type</name>
|
|
<value>murmur</value>
|
|
<description>The default implementation of Hash. Currently this can take one of the
|
|
two values: 'murmur' to select MurmurHash and 'jenkins' to select JenkinsHash.
|
|
</description>
|
|
</property>
|
|
|
|
|
|
<!-- ipc properties -->
|
|
|
|
<property>
|
|
<name>ipc.client.idlethreshold</name>
|
|
<value>4000</value>
|
|
<description>Defines the threshold number of connections after which
|
|
connections will be inspected for idleness.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>ipc.client.kill.max</name>
|
|
<value>10</value>
|
|
<description>Defines the maximum number of clients to disconnect in one go.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>ipc.client.connection.maxidletime</name>
|
|
<value>10000</value>
|
|
<description>The maximum time in msec after which a client will bring down the
|
|
connection to the server.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>ipc.client.connect.max.retries</name>
|
|
<value>10</value>
|
|
<description>Indicates the number of retries a client will make to establish
|
|
a server connection.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>ipc.server.listen.queue.size</name>
|
|
<value>128</value>
|
|
<description>Indicates the length of the listen queue for servers accepting
|
|
client connections.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>ipc.server.tcpnodelay</name>
|
|
<value>false</value>
|
|
<description>Turn on/off Nagle's algorithm for the TCP socket connection on
|
|
the server. Setting to true disables the algorithm and may decrease latency
|
|
with a cost of more/smaller packets.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>ipc.client.tcpnodelay</name>
|
|
<value>false</value>
|
|
<description>Turn on/off Nagle's algorithm for the TCP socket connection on
|
|
the client. Setting to true disables the algorithm and may decrease latency
|
|
with a cost of more/smaller packets.
|
|
</description>
|
|
</property>
|
|
|
|
|
|
<!-- Web Interface Configuration -->
|
|
|
|
<property>
|
|
<name>webinterface.private.actions</name>
|
|
<value>false</value>
|
|
<description> If set to true, the web interfaces of JT and NN may contain
|
|
actions, such as kill job, delete file, etc., that should
|
|
not be exposed to public. Enable this option if the interfaces
|
|
are only reachable by those who have the right authorization.
|
|
</description>
|
|
</property>
|
|
|
|
<!-- Proxy Configuration -->
|
|
|
|
<property>
|
|
<name>hadoop.rpc.socket.factory.class.default</name>
|
|
<value>org.apache.hadoop.net.StandardSocketFactory</value>
|
|
<description> Default SocketFactory to use. This parameter is expected to be
|
|
formatted as "package.FactoryClassName".
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.rpc.socket.factory.class.ClientProtocol</name>
|
|
<value></value>
|
|
<description> 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.
|
|
</description>
|
|
</property>
|
|
|
|
|
|
|
|
<property>
|
|
<name>hadoop.socks.server</name>
|
|
<value></value>
|
|
<description> Address (host:port) of the SOCKS server to be used by the
|
|
SocksSocketFactory.
|
|
</description>
|
|
</property>
|
|
|
|
|
|
<!-- Topology Configuration -->
|
|
|
|
<property>
|
|
<name>topology.node.switch.mapping.impl</name>
|
|
<value>org.apache.hadoop.net.ScriptBasedMapping</value>
|
|
<description> The default implementation of the DNSToSwitchMapping. It
|
|
invokes a script specified in topology.script.file.name to resolve
|
|
node names. If the value for topology.script.file.name is not set, the
|
|
default value of DEFAULT_RACK is returned for all node names.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>net.topology.impl</name>
|
|
<value>org.apache.hadoop.net.NetworkTopology</value>
|
|
<description> The default implementation of NetworkTopology which is classic three layer one.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>topology.script.file.name</name>
|
|
<value></value>
|
|
<description> 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.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>topology.script.number.args</name>
|
|
<value>100</value>
|
|
<description> The max number of args that the script configured with
|
|
topology.script.file.name should be run with. Each arg is an
|
|
IP address.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.security.uid.cache.secs</name>
|
|
<value>14400</value>
|
|
<description> NativeIO maintains a cache from UID to UserName. This is
|
|
the timeout for an entry in that cache. </description>
|
|
</property>
|
|
|
|
<!-- HTTP web-consoles Authentication -->
|
|
|
|
<property>
|
|
<name>hadoop.http.authentication.type</name>
|
|
<value>simple</value>
|
|
<description>
|
|
Defines authentication used for Oozie HTTP endpoint.
|
|
Supported values are: simple | kerberos | #AUTHENTICATION_HANDLER_CLASSNAME#
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.http.authentication.token.validity</name>
|
|
<value>36000</value>
|
|
<description>
|
|
Indicates how long (in seconds) an authentication token is valid before it has
|
|
to be renewed.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.http.authentication.signature.secret.file</name>
|
|
<value>${user.home}/hadoop-http-auth-signature-secret</value>
|
|
<description>
|
|
The signature secret for signing the authentication tokens.
|
|
If not set a random secret is generated at startup time.
|
|
The same secret should be used for JT/NN/DN/TT configurations.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.http.authentication.cookie.domain</name>
|
|
<value></value>
|
|
<description>
|
|
The domain to use for the HTTP cookie that stores the authentication token.
|
|
In order to authentiation to work correctly across all Hadoop nodes web-consoles
|
|
the domain must be correctly set.
|
|
IMPORTANT: when using IP addresses, browsers ignore cookies with domain settings.
|
|
For this setting to work properly all nodes in the cluster must be configured
|
|
to generate URLs with hostname.domain names on it.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.http.authentication.simple.anonymous.allowed</name>
|
|
<value>true</value>
|
|
<description>
|
|
Indicates if anonymous requests are allowed when using 'simple' authentication.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.http.authentication.kerberos.principal</name>
|
|
<value>HTTP/localhost@LOCALHOST</value>
|
|
<description>
|
|
Indicates the Kerberos principal to be used for HTTP endpoint.
|
|
The principal MUST start with 'HTTP/' as per Kerberos HTTP SPNEGO specification.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.http.authentication.kerberos.keytab</name>
|
|
<value>${user.home}/hadoop.keytab</value>
|
|
<description>
|
|
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.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.relaxed.worker.version.check</name>
|
|
<value>false</value>
|
|
<description>
|
|
By default datanodes refuse to connect to namenodes if their build
|
|
revision (svn revision) do not match, and tasktrackers refuse to
|
|
connect to jobtrackers if their build version (version, revision,
|
|
user, and source checksum) do not match. This option changes the
|
|
behavior of hadoop workers to only check for a version match (eg
|
|
"1.0.2") but ignore the other build fields (revision, user, and
|
|
source checksum).
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.skip.worker.version.check</name>
|
|
<value>false</value>
|
|
<description>
|
|
By default datanodes refuse to connect to namenodes if their build
|
|
revision (svn revision) do not match, and tasktrackers refuse to
|
|
connect to jobtrackers if their build version (version, revision,
|
|
user, and source checksum) do not match. This option changes the
|
|
behavior of hadoop workers to skip doing a version check at all.
|
|
This option supersedes the 'hadoop.relaxed.worker.version.check'
|
|
option.
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>hadoop.jetty.logs.serve.aliases</name>
|
|
<value>true</value>
|
|
<description>
|
|
Enable/Disable aliases serving from jetty
|
|
</description>
|
|
</property>
|
|
|
|
<property>
|
|
<name>ipc.client.fallback-to-simple-auth-allowed</name>
|
|
<value>false</value>
|
|
<description>
|
|
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.
|
|
</description>
|
|
</property>
|
|
|
|
</configuration>
|