[LU-6456] EL7 client replay-vbr test_10b: transno should restart from one: got 0xb600000002

• Status: Resolved
• Project: Lustre
• Affects Version/s: Lustre 2.8.0
• Type: Bug
• Priority: Critical
• Reporter: Maloo
• Assignee: Hongchao Zhang
• Resolution: Duplicate
• Severity: 3

Description

This issue was created by maloo for sarah <[e-mail]>

This issue relates to the following test suite run: https://testing.hpdd.intel.com/test_sets/ce29134a-df8a-11e4-bf2e-5254006e85c2.

The sub-test test_10b failed with the following error:

transno should restart from one: got 0xb600000002

[25155.973416] Lustre: DEBUG MARKER: chown 500:500 /mnt/lustre/f10b.replay-vbr-b
[25159.981458] LustreError: 11-0: lustre-MDT0000-mdc-ffff880065508800: operation obd_ping to node 10.2.4.203@tcp failed: rc = -107
[25159.985436] LustreError: Skipped 6 previous similar messages
[25241.755788] Lustre: 8753:0:(client.c:2754:ptlrpc_replay_interpret()) @@@ Version mismatch during replay
  req@ffff880050055200 x1498032511197364/t777389080602(777389080602) o36->lustre-MDT0000-mdc-ffff880078fa0000@10.2.4.203@tcp:12/10 lens 488/424 e 0 to 0 dl 1428640049 ref 2 fl Interpret:R/4/0 rc -75/-75
[25241.762787] Lustre: 8753:0:(client.c:2754:ptlrpc_replay_interpret()) Skipped 4 previous similar messages
[25248.775065] Lustre: 8753:0:(import.c:1298:completed_replay_interpret()) lustre-MDT0000-mdc-ffff880078fa0000: version recovery fails, reconnecting
[25248.780234] LustreError: 167-0: lustre-MDT0000-mdc-ffff880078fa0000: This client was evicted by lustre-MDT0000; in progress operations using this service will fail.
[25248.784424] LustreError: Skipped 4 previous similar messages
[25248.787265] LustreError: 8029:0:(lmv_obd.c:1482:lmv_statfs()) can't stat MDS #0 (lustre-MDT0000-mdc-ffff880078fa0000), error -5
[25248.791274] LustreError: 8029:0:(lmv_obd.c:1482:lmv_statfs()) Skipped 4 previous similar messages
[25248.793564] LustreError: 8029:0:(llite_lib.c:1786:ll_statfs_internal()) md_statfs fails: rc = -5
[25248.795810] LustreError: 8029:0:(llite_lib.c:1786:ll_statfs_internal()) Skipped 4 previous similar messages
[25248.798460] LustreError: 6714:0:(vvp_io.c:1429:vvp_io_init()) lustre: refresh file layout [0x200026560:0xd:0x0] error -5.
[25250.481544] Lustre: DEBUG MARKER: /usr/sbin/lctl mark  replay-vbr test_10b: @@@@@@ FAIL: transno should restart from one: got 0xb600000002 
[25250.598974] Lustre: DEBUG MARKER: replay-vbr test_10b: @@@@@@ FAIL: transno should restart from one: got 0xb600000002

Issue Links

• duplicates: LU-6455 EL7 client replay-vbr test_4i: versio...

Comments

[Andreas Dilger]

This may just be fallout from earlier LU-6455 failures.

[Peter Jones]

Hongchao

Is this a duplicate of LU-6455?

Peter

[Hongchao Zhang]

it seem to be the same issue of LU-6455, which the version of some inode is bumped up by some unknown operations,
and it's better to confirm it when the patch for LU-6455 is ready.

[Andreas Dilger]

Closing as a duplicate of LU-6455.