Uploaded image for project: 'Couchbase Server'
  1. Couchbase Server
  2. MB-34943

Decrease in timer creation throughput

    XMLWordPrintable

    Details

    • Type: Task
    • Status: In Progress
    • Priority: Major
    • Resolution: Unresolved
    • Affects Version/s: 6.5.0
    • Fix Version/s: 6.5.0
    • Component/s: test-execution
    • Labels:
    • Environment:
      6.5.0 - 3687

      Description

      Environment: 6.5.0 - 3687
      Test run :
      Timers created/sec, 1 bucket x 100M x 1KB, 4KV + 1Eventing node, no context, single function-CreateTimer

      Measurements :

      Build Timers created/sec
      6.5.0 - 3633 48,837, 50393, 49347
      6.5.0 - 3687 39,011, 45819
      6.5.0 - 3694 37638, 50260, 38282, 45592
      6.5.0 -4000 41579,40593

      Logs : https://s3-us-west-2.amazonaws.com/perf-artifacts/jenkins-themis-3321/172.23.97.177.zip

        Attachments

        No reviews matched the request. Check your Options in the drop-down menu of this sections header.

          Activity

          Hide
          jeelan.poola Jeelan Poola added a comment - - edited

          There have been no changes that would affect timers creation throughput between 6.5.0 - 3633 & 6.5.0 - 3687 in eventing. At this point, this looks likely due to some external factors and may clear up in a future build.

          Show
          jeelan.poola Jeelan Poola added a comment - - edited There have been no changes that would affect timers creation throughput between 6.5.0 - 3633 & 6.5.0 - 3687 in eventing. At this point, this looks likely due to some external factors and may clear up in a future build.
          Hide
          wayne Wayne Siu added a comment - - edited

          Updated the table with a few more data points.

          Looks like this test has a very high variance. Mahesh Mandhare Jyotsna Nayak

          Let's take the ticket back and monitor it and/or see if we could understand why the test result varies this much in the newer builds or post 6.5.0-3633.

          Show
          wayne Wayne Siu added a comment - - edited Updated the table with a few more data points. Looks like this test has a very high variance. Mahesh Mandhare Jyotsna Nayak Let's take the ticket back and monitor it and/or see if we could understand why the test result varies this much in the newer builds or post 6.5.0-3633.

            People

            Assignee:
            jyotsna.nayak Jyotsna Nayak
            Reporter:
            jyotsna.nayak Jyotsna Nayak
            Votes:
            0 Vote for this issue
            Watchers:
            5 Start watching this issue

              Dates

              Created:
              Updated:

                Gerrit Reviews

                There are no open Gerrit changes

                  PagerDuty