Queuemetrics - aajisaka/hadoop-metrics GitHub Wiki

  • running_0 (*)
    • Current number of running apps elapsed time are less than 60 min
  • running_60 (*)
    • Current number of running apps elapsed time are between 60 and 300 min
  • running_300 (*)
    • Current number of running apps elapsed time are between 300 and 1440 min
  • running_1440 (*)
    • Current number of running apps elapsed time are more than 1440 min
  • AppsSubmitted
    • Total number of apps submitted
  • AppsRunning
    • Current number of running apps
  • AppsPending
    • Current number of pending apps
  • AppsCompleted
    • Total number of apps completed
  • AppsKilled
    • Total number of apps killed
  • AppsFailed
    • Total number of apps failed
  • AllocatedMB
    • Current allocated memory in MB
  • AllocatedVCores
    • Current allocated CPU in virtual cores
  • AllocatedContainers
    • Current number of allocated containers
  • AggregateContainersAllocated
    • Total number of allocated containers
  • AggregateContainersReleased
    • Total number of released containers
  • AvailableMB
    • Current available memory in MB
  • AvailableVCores
    • Current available CPU in virtual cores
  • PendingMB
    • Current pending memory allocation in MB
  • PendingVCores
    • Current pending CPU allocation in MB
  • PendingContainers
    • Current number of pending containers
  • ReservedMB
    • Current reserved memory in MB
  • ReservedVCores
    • Current reserved CPU in virtual cores
  • ReservedContainers
    • Current number of reserved containers
  • ActiveUsers
    • Current number of active users
  • ActiveApplications
    • Current number of active applications
  • FairShareMB (**)
    • Current fair share of memory in MB
  • FairShareVCores (**)
    • Current fair share of CPU in VCores
  • MinShareMB (**)
    • Minimum share of memory in MB
  • MinShareVCores (**)
    • Minimum share of CPU in VCores
  • MaxShareMB (**)
    • Maximum share of memory in MB
  • MaxShareVCores (**)
    • Maximum share of CPU in VCores

For more details, see org.apache.hadoop.yarn.server.resourcemanager.scheduler.QueueMetrics.java and org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FSQueueMetrics.java.

(*) You can set the property yarn.resourcemanager.metrics.runtime.buckets in yarn-site.xml to change the buckets (default: 60,300,1440). (**) These metrics are available when you are using FairScheduler.