Uploaded image for project: 'OpenShift Bugs'
  1. OpenShift Bugs
  2. OCPBUGS-30002

Overall cpu utilization and per pod management CPU utilization higher in 4.15 than 4.14

XMLWordPrintable

    • Icon: Bug Bug
    • Resolution: Not a Bug
    • Icon: Undefined Undefined
    • None
    • 4.15
    • Telco Performance
    • None
    • Important
    • No
    • Rejected
    • False
    • Hide

      None

      Show
      None
    • Release Note Not Required
    • In Progress
    • 3/12: Root cause identified as increase in kubelet CPU utilization (OCPBUGS-30652). Will keep this Jira open until that issue is fixed.

      Description of problem:

      
          

      Version-Release number of selected component (if applicable):

          at least as far back as OCP 4.15.0-rc.5 and newer
          

      How reproducible:

          Always
          

      Steps to Reproduce:

          1. Deploy SNO spoke with Telco DU profile applied
          2. Run cpu_util and review results
          3.
          

      Actual results:

          increase cpu utilization 20% - 56% depending on management pod, as noted during steady workload 12h test in cpu_util  run
          

      Expected results:

          CPU utilization metrics should be close to or lower than previous release z-streams
          

      Additional info:

      
          

              bwensley@redhat.com Bart Wensley
              rhn-support-dgonyier Dwaine Gonyier
              Dwaine Gonyier Dwaine Gonyier
              Votes:
              0 Vote for this issue
              Watchers:
              5 Start watching this issue

                Created:
                Updated:
                Resolved: