Uploaded image for project: 'Lustre'
  1. Lustre
  2. LU-6480

leak cmid in kiblnd_dev_need_failover

Details

    • Bug
    • Resolution: Fixed
    • Minor
    • Lustre 2.8.0
    • None
    • None
    • 3
    • 9223372036854775807

    Description

      cmid created by kiblnd_dev_need_failover should always be destroyed, however it is not the case in current implementation so we will leak a cmid on each time call of this function. Fortunately this leak can only happen when dev_failover is enabled.

      Attachments

        Issue Links

          Activity

            [LU-6480] leak cmid in kiblnd_dev_need_failover

            Landed for 2.8.

            jgmitter Joseph Gmitter (Inactive) added a comment - Landed for 2.8.

            Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/14603/
            Subject: LU-6480 o2iblnd: leak cmid in kiblnd_dev_need_failover
            Project: fs/lustre-release
            Branch: master
            Current Patch Set:
            Commit: 6646307454ff710bcff5df71de398e60b00f494e

            gerrit Gerrit Updater added a comment - Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/14603/ Subject: LU-6480 o2iblnd: leak cmid in kiblnd_dev_need_failover Project: fs/lustre-release Branch: master Current Patch Set: Commit: 6646307454ff710bcff5df71de398e60b00f494e

            Liang Zhen (liang.zhen@intel.com) uploaded a new patch: http://review.whamcloud.com/14603
            Subject: LU-6480 o2iblnd: leak cmid in kiblnd_dev_need_failover
            Project: fs/lustre-release
            Branch: master
            Current Patch Set: 1
            Commit: 795c7a3a009e524dfe103dd0d129648963169fcb

            gerrit Gerrit Updater added a comment - Liang Zhen (liang.zhen@intel.com) uploaded a new patch: http://review.whamcloud.com/14603 Subject: LU-6480 o2iblnd: leak cmid in kiblnd_dev_need_failover Project: fs/lustre-release Branch: master Current Patch Set: 1 Commit: 795c7a3a009e524dfe103dd0d129648963169fcb

            It seemed to happen only if actual device failover has happened under the IB bonding device. Very rare I'd say.

            isaac Isaac Huang (Inactive) added a comment - It seemed to happen only if actual device failover has happened under the IB bonding device. Very rare I'd say.

            People

              liang Liang Zhen (Inactive)
              liang Liang Zhen (Inactive)
              Votes:
              0 Vote for this issue
              Watchers:
              4 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: