686 lines
45 KiB
JSON
686 lines
45 KiB
JSON
[
|
|
{
|
|
"desc": "The health test thresholds of the number of file descriptors used. Specified as a percentage of file descriptor limit.",
|
|
"display_name": "File Descriptor Monitoring Thresholds",
|
|
"name": "resourcemanager_fd_thresholds",
|
|
"value": "{\"critical\":\"70.0\",\"warning\":\"50.0\"}"
|
|
},
|
|
{
|
|
"desc": "For applications that request containers on particular racks, the minimum time in milliseconds the Fair Scheduler waits before accepting a placement on another rack. Requires Fair Scheduler continuous scheduling to be enabled. If continuous scheduling is disabled, yarn.scheduler.fair.locality.threshold.rack should be used instead.",
|
|
"display_name": "Fair Scheduler Rack Locality Delay",
|
|
"name": "yarn_scheduler_fair_locality_delay_rack_ms",
|
|
"value": "4000"
|
|
},
|
|
{
|
|
"desc": "Whether or not periodic stacks collection is enabled.",
|
|
"display_name": "Stacks Collection Enabled",
|
|
"name": "stacks_collection_enabled",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ResourceManager Advanced Configuration Snippet (Safety Valve) for yarn-site.xml parameter.",
|
|
"display_name": "Suppress Parameter Validation: ResourceManager Advanced Configuration Snippet (Safety Valve) for yarn-site.xml",
|
|
"name": "role_config_suppression_resourcemanager_config_safety_valve",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The method used to collect stacks. The jstack option involves periodically running the jstack command against the role's daemon process. The servlet method is available for those roles that have an HTTP server endpoint exposing the current stacks traces of all threads. When the servlet method is selected, that HTTP endpoint is periodically scraped.",
|
|
"display_name": "Stacks Collection Method",
|
|
"name": "stacks_collection_method",
|
|
"value": "jstack"
|
|
},
|
|
{
|
|
"desc": "The expiry interval to wait until a NodeManager is considered dead.",
|
|
"display_name": "NodeManager Monitor Expiry",
|
|
"name": "yarn_nm_liveness_monitor_expiry_interval_ms",
|
|
"value": "600000"
|
|
},
|
|
{
|
|
"desc": "The HTTP port of the ResourceManager web application.",
|
|
"display_name": "ResourceManager Web Application HTTP Port",
|
|
"name": "resourcemanager_webserver_port",
|
|
"value": "8088"
|
|
},
|
|
{
|
|
"desc": "The period to review when computing unexpected exits.",
|
|
"display_name": "Unexpected Exits Monitoring Period",
|
|
"name": "unexpected_exits_window",
|
|
"value": "5"
|
|
},
|
|
{
|
|
"desc": "The address of the applications manager interface in the ResourceManager.",
|
|
"display_name": "ResourceManager Address",
|
|
"name": "yarn_resourcemanager_address",
|
|
"value": "8032"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Heap Dump Directory parameter.",
|
|
"display_name": "Suppress Parameter Validation: Heap Dump Directory",
|
|
"name": "role_config_suppression_oom_heap_dump_dir",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Enables the health test that the Cloudera Manager Agent can successfully contact and gather metrics from the web server.",
|
|
"display_name": "Web Metric Collection",
|
|
"name": "resourcemanager_web_metric_collection_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The periodic interval that the ResourceManager will check whether ApplicationMasters is still alive.",
|
|
"display_name": "ApplicationMaster Monitor Interval",
|
|
"name": "yarn_resourcemanager_amliveliness_monitor_interval_ms",
|
|
"value": "1000"
|
|
},
|
|
{
|
|
"desc": "Number of threads used to handle the ResourceManager admin interface.",
|
|
"display_name": "Admin Client Thread Count",
|
|
"name": "yarn_resourcemanager_admin_client_thread_count",
|
|
"value": "1"
|
|
},
|
|
{
|
|
"desc": "When set, Cloudera Manager will send alerts when this entity's configuration changes.",
|
|
"display_name": "Enable Configuration Change Alerts",
|
|
"name": "enable_config_alerts",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "When set, generates heap dump file when java.lang.OutOfMemoryError is thrown.",
|
|
"display_name": "Dump Heap When Out of Memory",
|
|
"name": "oom_heap_dump_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "If enabled, the ResourceManager binds to the wildcard address (\"0.0.0.0\") on all of its ports.",
|
|
"display_name": "Bind ResourceManager to Wildcard Address",
|
|
"name": "yarn_rm_bind_wildcard",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Fair Scheduler XML Advanced Configuration Snippet (Safety Valve) parameter.",
|
|
"display_name": "Suppress Parameter Validation: Fair Scheduler XML Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "role_config_suppression_resourcemanager_fair_scheduler_configuration",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ResourceManager Environment Advanced Configuration Snippet (Safety Valve) parameter.",
|
|
"display_name": "Suppress Parameter Validation: ResourceManager Environment Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "role_config_suppression_resourcemanager_role_env_safety_valve",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the File Descriptors heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: File Descriptors",
|
|
"name": "role_health_suppression_resource_manager_file_descriptor",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Stacks Collection Directory parameter.",
|
|
"display_name": "Suppress Parameter Validation: Stacks Collection Directory",
|
|
"name": "role_config_suppression_stacks_collection_directory",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The address of the admin interface in the ResourceManager.",
|
|
"display_name": "Administration Address",
|
|
"name": "yarn_resourcemanager_admin_address",
|
|
"value": "8033"
|
|
},
|
|
{
|
|
"desc": "The periodic interval that the ResourceManager will check whether NodeManagers are still alive.",
|
|
"display_name": "NodeManager Monitor Interval",
|
|
"name": "yarn_resourcemanager_nm_liveness_monitor_interval_ms",
|
|
"value": "1000"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's log directory. Specified as a percentage of the capacity on that filesystem. This setting is not used if a Log Directory Free Space Monitoring Absolute Thresholds setting is configured.",
|
|
"display_name": "Log Directory Free Space Monitoring Percentage Thresholds",
|
|
"name": "log_directory_free_space_percentage_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "<p>This file contains the rules that govern how log messages are turned into events by the custom log4j appender that this role loads. It is in JSON format, and is composed of a list of rules. Every log message is evaluated against each of these rules in turn to decide whether or not to send an event for that message. If a log message matches multiple rules, the first matching rule is used. </p><p>Each rule has some or all of the following fields:</p><ul><li><code>alert</code> - whether or not events generated from this rule should be promoted to alerts. A value of \"true\" will cause alerts to be generated. If not specified, the default is \"false\".</li><li><code>rate</code> <b>(mandatory)</b> - the maximum number of log messages matching this rule that can be sent as events every minute. If more than <code>rate</code> matching log messages are received in a single minute, the extra messages are ignored. If rate is less than 0, the number of messages per minute is unlimited.</li><li><code>periodminutes</code> - the number of minutes during which the publisher will only publish <code>rate</code> events or fewer. If not specified, the default is <b>one minute</b></li><li><code>threshold</code> - apply this rule only to messages with this log4j severity level or above. An example is \"WARN\" for warning level messages or higher.</li><li><code>content</code> - match only those messages for which contents match this regular expression.</li><li><code>exceptiontype</code> - match only those messages that are part of an exception message. The exception type must match this regular expression.</li></ul><p>Example:</p><ul><li><pre>{\"alert\": false, \"rate\": 10, \"exceptiontype\": \"java.lang.StringIndexOutOfBoundsException\"}</pre>This rule sends events to Cloudera Manager for every <code>StringIndexOutOfBoundsException</code>, up to a maximum of 10 every minute.</li><li><pre>{\"alert\": false, \"rate\": 1, \"periodminutes\": 1, \"exceptiontype\": \".*\"}, {\"alert\": true, \"rate\": 1, \"periodminutes\": 1, \"threshold\":\"ERROR\"}</pre>In this example, an event generated may not be promoted to alert if an exception is in the ERROR log message, because the first rule with alert = false will match.</li></ul>",
|
|
"display_name": "Rules to Extract Events from Log Files",
|
|
"name": "log_event_whitelist",
|
|
"value": "{\n \"version\": \"0\",\n \"rules\": [\n {\"alert\": false, \"rate\": 1, \"periodminutes\": 1, \"threshold\":\"FATAL\"},\n {\"alert\": false, \"rate\": 0, \"threshold\":\"WARN\", \"content\": \".* is deprecated. Instead, use .*\"},\n {\"alert\": false, \"rate\": 0, \"threshold\":\"WARN\", \"content\": \".* is deprecated. Use .* instead\"},\n {\"alert\": false, \"rate\": 1, \"periodminutes\": 2, \"exceptiontype\": \".*\"},\n {\"alert\": false, \"rate\": 1, \"periodminutes\": 1, \"threshold\":\"WARN\"}\n ]\n}\n"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Swap Memory Usage heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Swap Memory Usage",
|
|
"name": "role_health_suppression_resource_manager_swap_memory_usage",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The maximum number of application attempts. This is a global setting for all ApplicationMasters. Each ApplicationMaster can specify its individual maximum through the API, but if the individual maximum is more than the global maximum, the ResourceManager overrides it.",
|
|
"display_name": "ApplicationMaster Maximum Attempts",
|
|
"name": "yarn_resourcemanager_am_max_retries",
|
|
"value": "2"
|
|
},
|
|
{
|
|
"desc": "For advanced use only. A string to be inserted into <strong>nodes_exclude.txt</strong> for this role only.",
|
|
"display_name": "ResourceManager Advanced Configuration Snippet (Safety Valve) for nodes_exclude.txt",
|
|
"name": "rm_hosts_exclude_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Enable continuous scheduling in the Fair Scheduler. When enabled, scheduling decisions are decoupled from NodeManager heartbeats, leading to faster resource allocations.",
|
|
"display_name": "Enable Fair Scheduler Continuous Scheduling",
|
|
"name": "yarn_scheduler_fair_continuous_scheduling_enabled",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's heap dump directory.",
|
|
"display_name": "Heap Dump Directory Free Space Monitoring Absolute Thresholds",
|
|
"name": "heap_dump_directory_free_space_absolute_thresholds",
|
|
"value": "{\"critical\":\"5.36870912E9\",\"warning\":\"1.073741824E10\"}"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Web Server Status heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Web Server Status",
|
|
"name": "role_health_suppression_resource_manager_web_metric_collection",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The periodic interval that the ResourceManager will check whether containers are still alive.",
|
|
"display_name": "Container Monitor Interval",
|
|
"name": "yarn_resourcemanager_container_liveness_monitor_interval_ms",
|
|
"value": "600000"
|
|
},
|
|
{
|
|
"desc": "The maximum size, in megabytes, per log file for ResourceManager logs. Typically used by log4j or logback.",
|
|
"display_name": "ResourceManager Max Log Size",
|
|
"name": "max_log_size",
|
|
"value": "200"
|
|
},
|
|
{
|
|
"desc": "<p>The configured triggers for this role. This is a JSON-formatted list of triggers. These triggers are evaluated as part as the health system. Every trigger expression is parsed, and if the trigger condition is met, the list of actions provided in the trigger expression is executed.</p><p>Each trigger has the following fields:</p><ul><li><code>triggerName</code> <b>(mandatory)</b> - The name of the trigger. This value must be unique for the specific role. </li><li><code>triggerExpression</code> <b>(mandatory)</b> - A tsquery expression representing the trigger. </li><li><code>streamThreshold</code> <b>(optional)</b> - The maximum number of streams that can satisfy a condition of a trigger before the condition fires. By default set to 0, and any stream returned causes the condition to fire. </li><li><code>enabled</code> <b> (optional)</b> - By default set to 'true'. If set to 'false', the trigger is not evaluated.</li><li><code>expressionEditorConfig</code> <b> (optional)</b> - Metadata for the trigger editor. If present, the trigger should only be edited from the Edit Trigger page; editing the trigger here can lead to inconsistencies.</li></ul><p>For example, the following JSON formatted trigger configured for a DataNode fires if the DataNode has more than 1500 file descriptors opened:</p><p><pre>[{\"triggerName\": \"sample-trigger\",\n \"triggerExpression\": \"IF (SELECT fd_open WHERE roleName=$ROLENAME and last(fd_open) > 1500) DO health:bad\",\n \"streamThreshold\": 0, \"enabled\": \"true\"}]</pre></p><p>See the trigger rules documentation for more details on how to write triggers using tsquery.</p><p>The JSON format is evolving and may change and, as a result, backward compatibility is not guaranteed between releases.</p>",
|
|
"display_name": "Role Triggers",
|
|
"name": "role_triggers",
|
|
"value": "[]"
|
|
},
|
|
{
|
|
"desc": "For advanced use only. A string to be inserted into <strong>mapred-site.xml</strong> for this role only.",
|
|
"display_name": "ResourceManager Advanced Configuration Snippet (Safety Valve) for mapred-site.xml",
|
|
"name": "resourcemanager_mapred_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "For applications that request containers on particular racks, the number of scheduling opportunities since the last container assignment to wait before accepting a placement on another rack. Expressed as a float between 0 and 1, which, as a fraction of the cluster size, is the number of scheduling opportunities to pass up. If not set, this means don't pass up any scheduling opportunities. Requires Fair Scheduler continuous scheduling to be disabled. If continuous scheduling is enabled, yarn.scheduler.fair.locality-delay-rack-ms should be used instead.",
|
|
"display_name": "Fair Scheduler Rack Locality Threshold",
|
|
"name": "resourcemanager_fair_scheduler_locality_threshold_rack",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "The class to use as the resource scheduler. FairScheduler is only supported in CDH 4.2.1 and later.",
|
|
"display_name": "Scheduler Class",
|
|
"name": "yarn_resourcemanager_scheduler_class",
|
|
"value": "org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler"
|
|
},
|
|
{
|
|
"desc": "Advanced Configuration Snippet (Safety Valve) for Hadoop Metrics2. Properties will be inserted into <strong>hadoop-metrics2.properties</strong>.",
|
|
"display_name": "Hadoop Metrics2 Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "hadoop_metrics2_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "The amount of stacks data that is retained. After the retention limit is reached, the oldest data is deleted.",
|
|
"display_name": "Stacks Collection Data Retention",
|
|
"name": "stacks_collection_data_retention",
|
|
"value": "104857600"
|
|
},
|
|
{
|
|
"desc": "When enabled, any applications that were running on the cluster when the ResourceManager died will be recovered when the ResourceManager next starts. <strong>Note:</strong> If RM-HA is enabled, then this configuration is always enabled.",
|
|
"display_name": "Enable ResourceManager Recovery",
|
|
"name": "yarn_resourcemanager_recovery_enabled",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ApplicationMaster Maximum Attempts parameter.",
|
|
"display_name": "Suppress Parameter Validation: ApplicationMaster Maximum Attempts",
|
|
"name": "role_config_suppression_yarn_resourcemanager_am_max_retries",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The expiry interval to wait until an ApplicationMaster is considered dead.",
|
|
"display_name": "ApplicationMaster Monitor Expiry",
|
|
"name": "yarn_am_liveness_monitor_expiry_interval_ms",
|
|
"value": "600000"
|
|
},
|
|
{
|
|
"desc": "Enter an XML string that represents the Capacity Scheduler configuration.",
|
|
"display_name": "Capacity Scheduler Configuration Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "resourcemanager_capacity_scheduler_configuration",
|
|
"value": "<?xml version=\"1.0\"?>\n<configuration>\n <property>\n <name>yarn.scheduler.capacity.root.queues</name>\n <value>default</value>\n </property>\n <property>\n <name>yarn.scheduler.capacity.root.capacity</name>\n <value>100</value>\n </property>\n <property>\n <name>yarn.scheduler.capacity.root.default.capacity</name>\n <value>100</value>\n </property>\n</configuration>\n"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Audit Pipeline Test heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Audit Pipeline Test",
|
|
"name": "role_health_suppression_resource_manager_audit_health",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for unexpected exits encountered within a recent period specified by the unexpected_exits_window configuration for the role.",
|
|
"display_name": "Unexpected Exits Thresholds",
|
|
"name": "unexpected_exits_thresholds",
|
|
"value": "{\"critical\":\"any\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Hadoop Metrics2 Advanced Configuration Snippet (Safety Valve) parameter.",
|
|
"display_name": "Suppress Parameter Validation: Hadoop Metrics2 Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "role_config_suppression_hadoop_metrics2_safety_valve",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The largest amount of physical memory, in MiB, that can be requested for a container.",
|
|
"display_name": "Container Memory Maximum",
|
|
"name": "yarn_scheduler_maximum_allocation_mb",
|
|
"value": "65536"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ResourceManager Advanced Configuration Snippet (Safety Valve) for nodes_exclude.txt parameter.",
|
|
"display_name": "Suppress Parameter Validation: ResourceManager Advanced Configuration Snippet (Safety Valve) for nodes_exclude.txt",
|
|
"name": "role_config_suppression_rm_hosts_exclude_safety_valve",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's heap dump directory. Specified as a percentage of the capacity on that filesystem. This setting is not used if a Heap Dump Directory Free Space Monitoring Absolute Thresholds setting is configured.",
|
|
"display_name": "Heap Dump Directory Free Space Monitoring Percentage Thresholds",
|
|
"name": "heap_dump_directory_free_space_percentage_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"never\"}"
|
|
},
|
|
{
|
|
"desc": "When enabled, if a pool's minimum share is not met for some period of time, the Fair Scheduler preempts applications in other pools. Preemption guarantees that production applications are not starved while also allowing the cluster to be used for experimental and research applications. To minimize wasted computation, the Fair Scheduler preempts the most recently launched applications.",
|
|
"display_name": "Enable Fair Scheduler Preemption",
|
|
"name": "resourcemanager_fair_scheduler_preemption",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "For applications that request containers on particular nodes, the number of scheduling opportunities since the last container assignment to wait before accepting a placement on another node. Expressed as a float between 0 and 1, which, as a fraction of the cluster size, is the number of scheduling opportunities to pass up. If not set, this means don't pass up any scheduling opportunities. Requires Fair Scheduler continuous scheduling to be disabled. If continuous scheduling is enabled, yarn.scheduler.fair.locality-delay-node-ms should be used instead.",
|
|
"display_name": "Fair Scheduler Node Locality Threshold",
|
|
"name": "resourcemanager_fair_scheduler_locality_threshold_node",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Number of CPU shares to assign to this role. The greater the number of shares, the larger the share of the host's CPUs that will be given to this role when the host experiences CPU contention. Must be between 2 and 262144. Defaults to 1024 for processes not managed by Cloudera Manager.",
|
|
"display_name": "Cgroup CPU Shares",
|
|
"name": "rm_cpu_shares",
|
|
"value": "1024"
|
|
},
|
|
{
|
|
"desc": "For applications that request containers on particular nodes, the minimum time in milliseconds the Fair Scheduler waits before accepting a placement on another node. Requires Fair Scheduler continuous scheduling to be enabled. If continuous scheduling is disabled, yarn.scheduler.fair.locality.threshold.node should be used instead.",
|
|
"display_name": "Fair Scheduler Node Locality Delay",
|
|
"name": "yarn_scheduler_fair_locality_delay_node_ms",
|
|
"value": "2000"
|
|
},
|
|
{
|
|
"desc": "The minimum log level for ResourceManager logs",
|
|
"display_name": "ResourceManager Logging Threshold",
|
|
"name": "log_threshold",
|
|
"value": "INFO"
|
|
},
|
|
{
|
|
"desc": "The amount of time allowed after this role is started that failures of health tests that rely on communication with this role will be tolerated.",
|
|
"display_name": "Health Test Startup Tolerance",
|
|
"name": "resourcemanager_startup_tolerance_minutes",
|
|
"value": "5"
|
|
},
|
|
{
|
|
"desc": "When enabled, ResourceManager has proxy user privileges.",
|
|
"display_name": "Enable ResourceManager Proxy User Privileges",
|
|
"name": "yarn_resourcemanager_proxy_user_privileges_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "An XML string that will be inserted verbatim into the Fair Scheduler allocations file. For CDH5, overrides the configuration set using the Pools configuration UI. For CDH4, this is the only way to configure the Fair Scheduler for YARN.",
|
|
"display_name": "Fair Scheduler XML Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "resourcemanager_fair_scheduler_configuration",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "For advanced use only. A string to be inserted into <strong>nodes_allow.txt</strong> for this role only.",
|
|
"display_name": "ResourceManager Advanced Configuration Snippet (Safety Valve) for nodes_allow.txt",
|
|
"name": "rm_hosts_allow_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Process Status heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Process Status",
|
|
"name": "role_health_suppression_resource_manager_scm_health",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Log Directory Free Space heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Log Directory Free Space",
|
|
"name": "role_health_suppression_resource_manager_log_directory_free_space",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The maximum number of completed applications that the ResourceManager keeps.",
|
|
"display_name": "Max Completed Applications",
|
|
"name": "yarn_resourcemanager_max_completed_applications",
|
|
"value": "10000"
|
|
},
|
|
{
|
|
"desc": "For advanced use only. A string to be inserted into <strong>yarn-site.xml</strong> for this role only.",
|
|
"display_name": "ResourceManager Advanced Configuration Snippet (Safety Valve) for yarn-site.xml",
|
|
"name": "resourcemanager_config_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Capacity Scheduler Configuration Advanced Configuration Snippet (Safety Valve) parameter.",
|
|
"display_name": "Suppress Parameter Validation: Capacity Scheduler Configuration Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "role_config_suppression_resourcemanager_capacity_scheduler_configuration",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "When set, this role's process is automatically (and transparently) restarted in the event of an unexpected failure.",
|
|
"display_name": "Automatically Restart Process",
|
|
"name": "process_auto_restart",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ResourceManager Logging Advanced Configuration Snippet (Safety Valve) parameter.",
|
|
"display_name": "Suppress Parameter Validation: ResourceManager Logging Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "role_config_suppression_log4j_safety_valve",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ResourceManager Advanced Configuration Snippet (Safety Valve) for nodes_allow.txt parameter.",
|
|
"display_name": "Suppress Parameter Validation: ResourceManager Advanced Configuration Snippet (Safety Valve) for nodes_allow.txt",
|
|
"name": "role_config_suppression_rm_hosts_allow_safety_valve",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The address of the scheduler interface in the ResourceManager.",
|
|
"display_name": "Scheduler Address",
|
|
"name": "yarn_resourcemanager_scheduler_address",
|
|
"value": "8030"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Rules to Extract Events from Log Files parameter.",
|
|
"display_name": "Suppress Parameter Validation: Rules to Extract Events from Log Files",
|
|
"name": "role_config_suppression_log_event_whitelist",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the CDH Version Validator configuration validator.",
|
|
"display_name": "Suppress Configuration Validator: CDH Version Validator",
|
|
"name": "role_config_suppression_cdh_version_validator",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Hard memory limit to assign to this role, enforced by the Linux kernel. When the limit is reached, the kernel will reclaim pages charged to the process. If reclaiming fails, the kernel may kill the process. Both anonymous as well as page cache pages contribute to the limit. Use a value of -1 B to specify no limit. By default processes not managed by Cloudera Manager will have no limit.",
|
|
"display_name": "Cgroup Memory Hard Limit",
|
|
"name": "rm_memory_hard_limit",
|
|
"value": "-1"
|
|
},
|
|
{
|
|
"desc": "The period to review when computing the moving average of garbage collection time.",
|
|
"display_name": "Garbage Collection Duration Monitoring Period",
|
|
"name": "resourcemanager_gc_duration_window",
|
|
"value": "5"
|
|
},
|
|
{
|
|
"desc": "The timeout for the ResourceManager session with ZooKeeper. The session expires if the ZooKeeper ensemble does not hear from the ResourceManager within the specified timeout period (no heartbeat). Session expiration is managed by the ZooKeeper ensemble, not by the ResourceManager.",
|
|
"display_name": "ZooKeeper Session Timeout",
|
|
"name": "yarn_resourcemanager_zk_timeout_ms",
|
|
"value": "60000"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Host Health heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Host Health",
|
|
"name": "role_health_suppression_resource_manager_host_health",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds on the swap memory usage of the process.",
|
|
"display_name": "Process Swap Memory Thresholds",
|
|
"name": "process_swap_memory_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"any\"}"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for the weighted average time spent in Java garbage collection. Specified as a percentage of elapsed wall clock time.",
|
|
"display_name": "Garbage Collection Duration Thresholds",
|
|
"name": "resourcemanager_gc_duration_thresholds",
|
|
"value": "{\"critical\":\"60.0\",\"warning\":\"30.0\"}"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds for monitoring of free space on the filesystem that contains this role's log directory.",
|
|
"display_name": "Log Directory Free Space Monitoring Absolute Thresholds",
|
|
"name": "log_directory_free_space_absolute_thresholds",
|
|
"value": "{\"critical\":\"5.36870912E9\",\"warning\":\"1.073741824E10\"}"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the GC Duration heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: GC Duration",
|
|
"name": "role_health_suppression_resource_manager_gc_duration",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "If configured, overrides the process soft and hard rlimits (also called ulimits) for file descriptors to the configured value.",
|
|
"display_name": "Maximum Process File Descriptors",
|
|
"name": "rlimit_fds",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "The smallest number of virtual CPU cores that can be requested for a container. If using the Capacity or FIFO scheduler (or any scheduler, prior to CDH 5), virtual core requests will be rounded up to the nearest multiple of this number. This parameter has no effect prior to CDH 4.4.",
|
|
"display_name": "Container Virtual CPU Cores Minimum",
|
|
"name": "yarn_scheduler_minimum_allocation_vcores",
|
|
"value": "1"
|
|
},
|
|
{
|
|
"desc": "If using the Fair Scheduler, memory requests will be rounded up to the nearest multiple of this number. This parameter has no effect prior to CDH 5.",
|
|
"display_name": "Container Memory Increment",
|
|
"name": "yarn_scheduler_increment_allocation_mb",
|
|
"value": "512"
|
|
},
|
|
{
|
|
"desc": "When computing the overall ResourceManager health, consider the host's health.",
|
|
"display_name": "ResourceManager Host Health Test",
|
|
"name": "resourcemanager_host_health_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "When enabled, the Fair Scheduler will assign shares to individual apps based on their size, rather than providing an equal share to all apps regardless of size.",
|
|
"display_name": "Fair Scheduler Size-Based Weight",
|
|
"name": "resourcemanager_fair_scheduler_size_based_weight",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Path to directory where heap dumps are generated when java.lang.OutOfMemoryError error is thrown. This directory is automatically created if it does not exist. If this directory already exists, role user must have write access to this directory. If this directory is shared among multiple roles, it should have 1777 permissions. The heap dump files are created with 600 permissions and are owned by the role user. The amount of free space in this directory should be greater than the maximum Java Process heap size configured for this role.",
|
|
"display_name": "Heap Dump Directory",
|
|
"name": "oom_heap_dump_dir",
|
|
"value": "/tmp"
|
|
},
|
|
{
|
|
"desc": "The frequency with which stacks are collected.",
|
|
"display_name": "Stacks Collection Frequency",
|
|
"name": "stacks_collection_frequency",
|
|
"value": "5.0"
|
|
},
|
|
{
|
|
"desc": "The address of the resource tracker interface in the ResourceManager.",
|
|
"display_name": "Resource Tracker Address",
|
|
"name": "yarn_resourcemanager_resource_tracker_address",
|
|
"value": "8031"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Heap Dump Directory Free Space heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Heap Dump Directory Free Space",
|
|
"name": "role_health_suppression_resource_manager_heap_dump_directory_free_space",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ResourceManager Log Directory parameter.",
|
|
"display_name": "Suppress Parameter Validation: ResourceManager Log Directory",
|
|
"name": "role_config_suppression_resource_manager_log_dir",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "These arguments will be passed as part of the Java command line. Commonly, garbage collection flags, PermGen, or extra debugging flags would be passed here.",
|
|
"display_name": "Java Configuration Options for ResourceManager",
|
|
"name": "resource_manager_java_opts",
|
|
"value": "-XX:+UseParNewGC -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:+CMSParallelRemarkEnabled -Dlibrary.leveldbjni.path={{CONF_DIR}}"
|
|
},
|
|
{
|
|
"desc": "For advanced use only, a string to be inserted into <strong>log4j.properties</strong> for this role only.",
|
|
"display_name": "ResourceManager Logging Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "log4j_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "Enables multiple Fair Scheduler container assignments in one heartbeat, which improves cluster throughput when there are many small tasks to run.",
|
|
"display_name": "Fair Scheduler Assign Multiple Tasks",
|
|
"name": "resourcemanager_fair_scheduler_assign_multiple",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The health test thresholds on the duration of the metrics request to the web server.",
|
|
"display_name": "Web Metric Collection Duration",
|
|
"name": "resourcemanager_web_metric_collection_thresholds",
|
|
"value": "{\"critical\":\"never\",\"warning\":\"10000.0\"}"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the ResourceManager Advanced Configuration Snippet (Safety Valve) for mapred-site.xml parameter.",
|
|
"display_name": "Suppress Parameter Validation: ResourceManager Advanced Configuration Snippet (Safety Valve) for mapred-site.xml",
|
|
"name": "role_config_suppression_resourcemanager_mapred_safety_valve",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Directory where ResourceManager will place its log files.",
|
|
"display_name": "ResourceManager Log Directory",
|
|
"name": "resource_manager_log_dir",
|
|
"value": "/var/log/hadoop-yarn"
|
|
},
|
|
{
|
|
"desc": "Soft memory limit to assign to this role, enforced by the Linux kernel. When the limit is reached, the kernel will reclaim pages charged to the process if and only if the host is facing memory pressure. If reclaiming fails, the kernel may kill the process. Both anonymous as well as page cache pages contribute to the limit. Use a value of -1 B to specify no limit. By default processes not managed by Cloudera Manager will have no limit.",
|
|
"display_name": "Cgroup Memory Soft Limit",
|
|
"name": "rm_memory_soft_limit",
|
|
"value": "-1"
|
|
},
|
|
{
|
|
"desc": "Number of threads to handle resource tracker calls.",
|
|
"display_name": "Resource Tracker Thread Count",
|
|
"name": "yarn_resourcemanager_resource_tracker_client_thread_count",
|
|
"value": "50"
|
|
},
|
|
{
|
|
"desc": "If using the Fair Scheduler, virtual core requests will be rounded up to the nearest multiple of this number. This parameter has no effect prior to CDH 5.",
|
|
"display_name": "Container Virtual CPU Cores Increment",
|
|
"name": "yarn_scheduler_increment_allocation_vcores",
|
|
"value": "1"
|
|
},
|
|
{
|
|
"desc": "The HTTPS port of the ResourceManager web application.",
|
|
"display_name": "ResourceManager Web Application HTTPS Port (TLS/SSL)",
|
|
"name": "resourcemanager_webserver_https_port",
|
|
"value": "8090"
|
|
},
|
|
{
|
|
"desc": "Maximum size in bytes for the Java Process heap memory. Passed to Java -Xmx.",
|
|
"display_name": "Java Heap Size of ResourceManager in Bytes",
|
|
"name": "resource_manager_java_heapsize",
|
|
"value": "1073741824"
|
|
},
|
|
{
|
|
"desc": "Cloudera Manager agent monitors each service and each of its role by publishing metrics to the Cloudera Manager Service Monitor. Setting it to false will stop Cloudera Manager agent from publishing any metric for corresponding service/roles. This is usually helpful for services that generate large amount of metrics which Service Monitor is not able to process.",
|
|
"display_name": "Enable Metric Collection",
|
|
"name": "process_should_monitor",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The number of threads used to handle applications manager requests.",
|
|
"display_name": "Client Thread Count",
|
|
"name": "yarn_resourcemanager_client_thread_count",
|
|
"value": "50"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress the results of the Unexpected Exits heath test. The results of suppressed health tests are ignored when computing the overall health of the associated host, role or service, so suppressed health tests will not generate alerts.",
|
|
"display_name": "Suppress Health Test: Unexpected Exits",
|
|
"name": "role_health_suppression_resource_manager_unexpected_exits",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Role Triggers parameter.",
|
|
"display_name": "Suppress Parameter Validation: Role Triggers",
|
|
"name": "role_config_suppression_role_triggers",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The maximum number of rolled log files to keep for ResourceManager logs. Typically used by log4j or logback.",
|
|
"display_name": "ResourceManager Maximum Log File Backups",
|
|
"name": "max_log_backup_index",
|
|
"value": "10"
|
|
},
|
|
{
|
|
"desc": "When set, a SIGKILL signal is sent to the role process when java.lang.OutOfMemoryError is thrown.",
|
|
"display_name": "Kill When Out of Memory",
|
|
"name": "oom_sigkill_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "For advanced use only, key-value pairs (one on each line) to be inserted into a role's environment. Applies to configurations of this role except client configuration.",
|
|
"display_name": "ResourceManager Environment Advanced Configuration Snippet (Safety Valve)",
|
|
"name": "RESOURCEMANAGER_role_env_safety_valve",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "When set, Cloudera Manager will send alerts when the health of this role reaches the threshold specified by the EventServer setting eventserver_health_events_alert_threshold",
|
|
"display_name": "Enable Health Alerts for this Role",
|
|
"name": "enable_alerts",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The utilization threshold after which preemption kicks in. The utilization is computed as the maximum ratio of usage to capacity among all resources.",
|
|
"display_name": "Fair Scheduler Preemption Utilization Threshold",
|
|
"name": "yarn_scheduler_fair_preemption_cluster_utilization_threshold",
|
|
"value": "0.8"
|
|
},
|
|
{
|
|
"desc": "Whether to suppress configuration warnings produced by the built-in parameter validation for the Java Configuration Options for ResourceManager parameter.",
|
|
"display_name": "Suppress Parameter Validation: Java Configuration Options for ResourceManager",
|
|
"name": "role_config_suppression_resource_manager_java_opts",
|
|
"value": "false"
|
|
},
|
|
{
|
|
"desc": "The directory in which stacks logs are placed. If not set, stacks are logged into a <code>stacks</code> subdirectory of the role's log directory.",
|
|
"display_name": "Stacks Collection Directory",
|
|
"name": "stacks_collection_directory",
|
|
"value": null
|
|
},
|
|
{
|
|
"desc": "The number of threads used to handle requests through the scheduler interface.",
|
|
"display_name": "Scheduler Thread Count",
|
|
"name": "yarn_resourcemanager_scheduler_client_thread_count",
|
|
"value": "50"
|
|
},
|
|
{
|
|
"desc": "Weight for the read I/O requests issued by this role. The greater the weight, the higher the priority of the requests when the host experiences I/O contention. Must be between 100 and 1000. Defaults to 1000 for processes not managed by Cloudera Manager.",
|
|
"display_name": "Cgroup I/O Weight",
|
|
"name": "rm_io_weight",
|
|
"value": "500"
|
|
},
|
|
{
|
|
"desc": "When set to <b>true</b>, the Fair Scheduler uses the username as the default pool name, in the event that a pool name is not specified. When set to <b>false</b>, all applications are run in a shared pool, called <b>default</b>.",
|
|
"display_name": "Fair Scheduler User As Default Queue",
|
|
"name": "resourcemanager_fair_scheduler_user_as_default_queue",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "Enables the health test that the ResourceManager's process state is consistent with the role configuration",
|
|
"display_name": "ResourceManager Process Health Test",
|
|
"name": "resourcemanager_scm_health_enabled",
|
|
"value": "true"
|
|
},
|
|
{
|
|
"desc": "The largest number of virtual CPU cores that can be requested for a container. This parameter has no effect prior to CDH 4.4.",
|
|
"display_name": "Container Virtual CPU Cores Maximum",
|
|
"name": "yarn_scheduler_maximum_allocation_vcores",
|
|
"value": "32"
|
|
},
|
|
{
|
|
"desc": "The smallest amount of physical memory, in MiB, that can be requested for a container. If using the Capacity or FIFO scheduler (or any scheduler, prior to CDH 5), memory requests will be rounded up to the nearest multiple of this number.",
|
|
"display_name": "Container Memory Minimum",
|
|
"name": "yarn_scheduler_minimum_allocation_mb",
|
|
"value": "1024"
|
|
}
|
|
] |