[LU-13800] replay-single test_121 crash

Sun, 16 Jan 2022 08:48:48 +0000

This issue was created by maloo for Vitaly Fertman <vitaly_fertman@xyratex.com>

This issue relates to the following test suite run: https://testing.whamcloud.com/test_sets/5d3ace2a-57b8-4dc0-be36-e132a11f3358

[10990.879432] Lustre: lustre-MDT0000: Client 35164bd3-7a9b-41ce-af74-479a9d6de9a6 (at 10.9.4.16@tcp) reconnected, waiting for 5 clients in recovery for 0:16
[10990.882040] Lustre: Skipped 19 previous similar messages
[10997.890669] Lustre: 28109:0:(ldlm_lib.c:1889:extend_recovery_timer()) lustre-MDT0000: extended recovery timer reached hard limit: 180, extend: 1
[10997.893042] Lustre: 28109:0:(ldlm_lib.c:1889:extend_recovery_timer()) Skipped 21 previous similar messages
[11011.888902] Lustre: lustre-MDT0000: Recovery already passed deadline 0:00. If you do not want to wait more, you may force taget eviction via 'lctl --device lustre-MDT0000 abort_recovery.
[11011.892648] Lustre: 28109:0:(ldlm_lib.c:1889:extend_recovery_timer()) lustre-MDT0000: extended recovery timer reached hard limit: 180, extend: 1
[11011.894957] Lustre: 28109:0:(ldlm_lib.c:1889:extend_recovery_timer()) Skipped 1 previous similar message
[11012.744361] LustreError: 28109:0:(ldlm_lib.c:2253:target_next_replay_lock()) ASSERTION( atomic_read(&obd->obd_lock_replay_clients) == 0 ) failed:
[11012.746755] LustreError: 28109:0:(ldlm_lib.c:2253:target_next_replay_lock()) LBUG
[11012.748063] Pid: 28109, comm: tgt_recover_0 3.10.0-1127.8.2.el7_lustre.x86_64 #1 SMP Tue Jun 2 06:36:17 UTC 2020
[11012.749915] Call Trace:
[11012.750428] [<ffffffffc082867c>] libcfs_call_trace+0x8c/0xc0 [libcfs]
[11012.751688] [<ffffffffc082899c>] lbug_with_loc+0x4c/0xa0 [libcfs]
[11012.752877] [<ffffffffc0d10efc>] target_recovery_thread+0x10cc/0x11a0 [ptlrpc]
[11012.754626] [<ffffffffbb2c6691>] kthread+0xd1/0xe0
[11012.755583] [<ffffffffbb992d37>] ret_from_fork_nospec_end+0x0/0x39
[11012.756777] [<ffffffffffffffff>] 0xffffffffffffffff
[11012.757756] Kernel panic - not syncing: LBUG
[11012.758576] CPU: 0 PID: 28109 Comm: tgt_recover_0 Kdump: loaded Tainted: G W OE ------------ 3.10.0-1127.8.2.el7_lustre.x86_64 #1
[11012.760760] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[11012.761762] Call Trace:
[11012.762224] [<ffffffffbb97ffa5>] dump_stack+0x19/0x1b
[11012.763129] [<ffffffffbb979541>] panic+0xe8/0x21f
[11012.763982] [<ffffffffc08289eb>] lbug_with_loc+0x9b/0xa0 [libcfs]
[11012.765100] [<ffffffffc0d10efc>] target_recovery_thread+0x10cc/0x11a0 [ptlrpc]
[11012.766421] [<ffffffffc0d0fe30>] ? replay_request_or_update.isra.23+0x8d0/0x8d0 [ptlrpc]
[11012.767825] [<ffffffffbb2c6691>] kthread+0xd1/0xe0
[11012.768673] [<ffffffffbb2c65c0>] ? insert_kthread_work+0x40/0x40
[11012.769723] [<ffffffffbb992d37>] ret_from_fork_nospec_begin+0x21/0x21
[11012.770847] [<ffffffffbb2c65c0>] ? insert_kthread_work+0x40/0x40

Whamcloud Community JIRA

[LU-13800] replay-single test_121 crash