Uploaded image for project: 'Lustre'
  1. Lustre
  2. LU-6584

OSS hit LBUG and crash

Details

    • Bug
    • Resolution: Fixed
    • Critical
    • Lustre 2.8.0
    • Lustre 2.7.0
    • 4
    • 9223372036854775807

    Description

      No sign or indication, ie lustre-log or error messages, OSS unexpectantly crash (please see console image).

      /var/log/messages is attached

      Attachments

        1. 23-6.png
          23-6.png
          47 kB
        2. log.28119.gz
          388 kB
        3. lustre-logs.tgz
          0.2 kB
        4. messages13
          271 kB
        5. panda-oss-23-6_messages
          1003 kB

        Activity

          [LU-6584] OSS hit LBUG and crash
          pjones Peter Jones added a comment -

          Fix landed for 2.8. We'll reopen if this issue still is hit on Hyperion. If there is still an issue at SDSC and it is not, as hoped, a duplicate of this issue then please open a new ticket to track that issue.

          pjones Peter Jones added a comment - Fix landed for 2.8. We'll reopen if this issue still is hit on Hyperion. If there is still an issue at SDSC and it is not, as hoped, a duplicate of this issue then please open a new ticket to track that issue.
          gerrit Gerrit Updater added a comment -

          Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/16685/
          Subject: LU-6584 osd: prevent int type overflow in osd_read_prep()
          Project: fs/lustre-release
          Branch: master
          Current Patch Set:
          Commit: efe3842c76b8041a048457779554ffa5ba76567d

          gerrit Gerrit Updater added a comment - Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/16685/ Subject: LU-6584 osd: prevent int type overflow in osd_read_prep() Project: fs/lustre-release Branch: master Current Patch Set: Commit: efe3842c76b8041a048457779554ffa5ba76567d
          tappro Mikhail Pershin added a comment -

          Rick, this particular issue existed in IO READ code path and doesn't related to LU-7106. I check OSD code quickly and didn't notice other similar issues at first glance.

          tappro Mikhail Pershin added a comment - Rick, this particular issue existed in IO READ code path and doesn't related to LU-7106 . I check OSD code quickly and didn't notice other similar issues at first glance.
          rpwagner Rick Wagner (Inactive) added a comment -

          Yes, we're scheduling a PM and push this out. Could this patch be related to LU-7106? In other words could the current code create an error that propagates back to the client as ENOSPC even when there's capacity on the OST?

          rpwagner Rick Wagner (Inactive) added a comment - Yes, we're scheduling a PM and push this out. Could this patch be related to LU-7106 ? In other words could the current code create an error that propagates back to the client as ENOSPC even when there's capacity on the OST?
          pjones Peter Jones added a comment -

          Will SDSC be able to try this patch out to confirm whether it fixes the issues that they have been experiencing?

          pjones Peter Jones added a comment - Will SDSC be able to try this patch out to confirm whether it fixes the issues that they have been experiencing?
          tappro Mikhail Pershin added a comment -

          It seems the reason of this issue is the int type overflow in lnb_rc. Instead of writing the (eof - file_offset) right into lnb_rc we have to check first it is not negative.

          tappro Mikhail Pershin added a comment - It seems the reason of this issue is the int type overflow in lnb_rc. Instead of writing the (eof - file_offset) right into lnb_rc we have to check first it is not negative.
          gerrit Gerrit Updater added a comment -

          Mike Pershin (mike.pershin@intel.com) uploaded a new patch: http://review.whamcloud.com/16685
          Subject: LU-6584 osd: prevent int type overflow in osd_read_prep()
          Project: fs/lustre-release
          Branch: master
          Current Patch Set: 1
          Commit: 687338302147dad5b09b964b8615a3b3adb78a7d

          gerrit Gerrit Updater added a comment - Mike Pershin (mike.pershin@intel.com) uploaded a new patch: http://review.whamcloud.com/16685 Subject: LU-6584 osd: prevent int type overflow in osd_read_prep() Project: fs/lustre-release Branch: master Current Patch Set: 1 Commit: 687338302147dad5b09b964b8615a3b3adb78a7d

          People

            tappro Mikhail Pershin
            haisong Haisong Cai (Inactive)
            Votes:
            0 Vote for this issue
            Watchers:
            15 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: