Uploaded image for project: 'Lustre'
  1. Lustre
  2. LU-9322

parallel-scale test_connectathon: connectathon failed: 1

Details

    • Bug
    • Resolution: Fixed
    • Minor
    • Lustre 2.10.0
    • Lustre 2.10.0
    • None
    • onyx-44, Full,
      RHEL7.3, DNE, ZFS, master branch, v2.10.55, b3550
    • 3
    • 9223372036854775807

    Description

      https://testing.hpdd.intel.com/test_sessions/4b44547b-cba5-4172-ab2c-b902e4049a92

      From test_log:

      test telldir cookies
      expected file 94 at cookie 0, found .
      special tests failed
       parallel-scale test_connectathon: @@@@@@ FAIL: connectathon failed: 1 
        Trace dump:
        = /usr/lib64/lustre/tests/test-framework.sh:4893:error()
        = /usr/lib64/lustre/tests/functions.sh:542:run_connectathon()
        = /usr/lib64/lustre/tests/parallel-scale.sh:100:test_connectathon()
        = /usr/lib64/lustre/tests/test-framework.sh:5169:run_one()
        = /usr/lib64/lustre/tests/test-framework.sh:5208:run_one_logged()
        = /usr/lib64/lustre/tests/test-framework.sh:5055:run_test()
        = /usr/lib64/lustre/tests/parallel-scale.sh:102:main()
      

      From OST console (onyx-44vm8):

      LustreError: 784:0:(ofd_dev.c:1688:ofd_create_hdl()) lustre-OST0005: invalid precreate request for 0x0:302369, last_id 302881. Likely MDS last_id corruption
      LustreError: 784:0:(ofd_dev.c:1688:ofd_create_hdl()) Skipped 120 previous similar messages
      

      From MDS console (onyx-44vm7):

      LustreError: 28135:0:(osp_precreate.c:917:osp_precreate_cleanup_orphans()) lustre-OST0005-osc-MDT0000: cannot cleanup orphans: rc = -22
      LustreError: 28135:0:(osp_precreate.c:917:osp_precreate_cleanup_orphans()) Skipped 120 previous similar messages
      

      May be related to LU-8806. It also has a "cannot cleanup orphans" message, but with a different return code.

      Attachments

        Issue Links

          Activity

            [LU-9322] parallel-scale test_connectathon: connectathon failed: 1

            Resolving issue because the patches were reverted and we haven't seen this issue for at least the past six months.

            jamesanunez James Nunez (Inactive) added a comment - Resolving issue because the patches were reverted and we haven't seen this issue for at least the past six months.

            both, actually. the fix depends on the reverts.

            bzzz Alex Zhuravlev added a comment - both, actually. the fix depends on the reverts.
            jhammond John Hammond added a comment -

            Alex, would you suggest one of your changes https://review.whamcloud.com/#/c/25925/ or https://review.whamcloud.com/#/c/25926 here?

            jhammond John Hammond added a comment - Alex, would you suggest one of your changes https://review.whamcloud.com/#/c/25925/ or https://review.whamcloud.com/#/c/25926 here?

            People

              wc-triage WC Triage
              jcasper James Casper (Inactive)
              Votes:
              1 Vote for this issue
              Watchers:
              5 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: