Uploaded image for project: 'Hadoop YARN'
  1. Hadoop YARN
  2. YARN-4678

Cluster used capacity is > 100 when container reserved

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Open
    • Major
    • Resolution: Unresolved
    • None
    • None
    • None
    • None

    Description

      Scenario:

      • Start cluster with Three NM's each having 8GB (cluster memory:24GB).
      • Configure queues with elasticity and userlimitfactor=10.
      • disable pre-emption.
      • run two job with different priority in different queue at the same time
        • yarn jar hadoop-mapreduce-examples-2.7.2.jar pi -Dyarn.app.priority=LOW -Dmapreduce.job.queuename=QueueA -Dmapreduce.map.memory.mb=4096 -Dyarn.app.mapreduce.am.resource.mb=1536 -Dmapreduce.job.reduce.slowstart.completedmaps=1.0 10 1000000000000
        • yarn jar hadoop-mapreduce-examples-2.7.2.jar pi -Dyarn.app.priority=HIGH -Dmapreduce.job.queuename=QueueB -Dmapreduce.map.memory.mb=4096 -Dyarn.app.mapreduce.am.resource.mb=1536 3 1000000000000
      • observe the cluster capacity which was used in RM web UI

      Attachments

        1. 0003-YARN-4678-testcase.patch
          4 kB
          Sunil G
        2. reservedCapInClusterMetrics.png
          57 kB
          Sunil G
        3. 0003-YARN-4678.patch
          23 kB
          Sunil G
        4. 0002-YARN-4678.patch
          22 kB
          Sunil G
        5. 0001-YARN-4678.patch
          23 kB
          Sunil G

        Activity

          People

            sunilg Sunil G
            brahmareddy Brahma Reddy Battula
            Votes:
            1 Vote for this issue
            Watchers:
            12 Start watching this issue

            Dates

              Created:
              Updated: