Uploaded image for project: 'Lustre'
  1. Lustre
  2. LU-5886

DNE II Testing: Hung threads on MDS; evictions

Details

    • Bug
    • Resolution: Cannot Reproduce
    • Major
    • None
    • None
    • None
    • 3
    • 16457

    Description

      During DNE II testing (same run as LU-5883), both of our MDSes reported hung threads here:
      Nov 6 20:22:21 perses-esf-mds001 kernel: Pid: 21117, comm: mdt02_008
      Nov 6 20:22:21 perses-esf-mds001 kernel:
      Nov 6 20:22:21 perses-esf-mds001 kernel: Call Trace:
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0aaa1a1>] ? libcfs_debug_msg+0x41/0x50 [libcfs]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e32230>] ? ldlm_expired_completion_wait+0x0/0x360 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e36df5>] ldlm_completion_ast+0x665/0x9a0 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff81065df0>] ? default_wake_function+0x0/0x20
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e3619e>] ldlm_cli_enqueue_local+0x21e/0x810 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e36790>] ? ldlm_completion_ast+0x0/0x9a0 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa1559d70>] ? mdt_blocking_ast+0x0/0x2a0 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa156240d>] mdt_object_local_lock+0x1bd/0xa80 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa1559d70>] ? mdt_blocking_ast+0x0/0x2a0 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e36790>] ? ldlm_completion_ast+0x0/0x9a0 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa1562d35>] mdt_object_lock_internal+0x65/0x360 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa15630f4>] mdt_object_lock+0x14/0x20 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa156dd6c>] mdt_getattr_name_lock+0xd9c/0x1a50 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff8128a0ea>] ? strlcpy+0x4a/0x60
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e63774>] ? lustre_msg_get_flags+0x34/0xb0 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e65d40>] ? lustre_swab_ldlm_reply+0x0/0x40 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa156ef42>] mdt_intent_getattr+0x292/0x470 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa155bc44>] mdt_intent_policy+0x494/0xcf0 [mdt]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e16549>] ldlm_lock_enqueue+0x129/0x9d0 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e4235b>] ldlm_handle_enqueue0+0x51b/0x1340 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0a9a4ce>] ? cfs_timer_arm+0xe/0x10 [libcfs]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0ec3842>] tgt_enqueue+0x62/0x1d0 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0ec40ce>] tgt_request_handle+0x71e/0xb10 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e73964>] ptlrpc_main+0xe64/0x1990 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff810096f0>] ? __switch_to+0xd0/0x320
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff81527c20>] ? thread_return+0x4e/0x76e
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffffa0e72b00>] ? ptlrpc_main+0x0/0x1990 [ptlrpc]
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff8109aee6>] kthread+0x96/0xa0
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff8100c20a>] child_rip+0xa/0x20
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff8109ae50>] ? kthread+0x0/0xa0
      Nov 6 20:22:21 perses-esf-mds001 kernel: [<ffffffff8100c200>] ? child_rip+0x0/0x20
      Nov 6 20:22:21 perses-esf-mds001 kernel:

      Attachments

        Activity

          [LU-5886] DNE II Testing: Hung threads on MDS; evictions

          People

            di.wang Di Wang
            paf Patrick Farrell (Inactive)
            Votes:
            0 Vote for this issue
            Watchers:
            4 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: