[LU-15763] large-scale test_3a: LustreError: (file.c:243:ll_close_inode_openhandle()) mdc close failed: rc = -108

• Type: Bug
• Resolution: Unresolved
• Priority: Major
• Affects Version/s: Lustre 2.12.9, Lustre 2.15.0
• Labels: failing_tests
• Severity: 3
• Assignee: Alex Deiter
• Reporter: Maloo

Description

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

This issue relates to the following test suite run: https://testing.whamcloud.com/test_sets/cde24d83-d48d-4472-a697-ac0b030ae772

Test run timed out after nfsv4 scale, multiple stack dumps on various nodes, example:

[11156.489772] Lustre: DEBUG MARKER: ./compilebench -D /mnt/lustre/d0.parallel-scale-nfs/d0.compilebench.513626 -i 2 -r 2 --makej
[16428.917978] compilebench (518595): drop_caches: 3
[16733.594234] compilebench (518595): drop_caches: 3
[18407.728842] sysrq: SysRq : Changing Loglevel
[18407.737126] sysrq: Loglevel set to 8
[18407.740113] sysrq: SysRq : Show State
[18407.740908] task:systemd         state:S stack:    0 pid:    1 ppid:     0 flags:0x00000000
[18407.742495] Call Trace:
[18407.743081]  __schedule+0x2c4/0x700
[18407.743825]  schedule+0x37/0xa0
[18407.744493]  schedule_hrtimeout_range_clock+0xf7/0x110
[18407.745550]  ? seq_release+0x24/0x30
[18407.746279]  ep_poll+0x403/0x460
[18407.747000]  ? wake_up_q+0x80/0x80
[18407.747713]  do_epoll_wait+0xb0/0xd0
[18407.748453]  __x64_sys_epoll_wait+0x1a/0x20
[18407.749299]  do_syscall_64+0x5b/0x1a0
[18407.750070]  entry_SYSCALL_64_after_hwframe+0x65/0xca
[18407.751089] RIP: 0033:0x7f87afd9c0f7
[18407.751837] Code: Unable to access opcode bytes at RIP 0x7f87afd9c0cd.
[18407.753097] RSP: 002b:00007ffe859313f0 EFLAGS: 00000293 ORIG_RAX: 00000000000000e8
[18407.754551] RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007f87afd9c0f7
[18407.755919] RDX: 000000000000006a RSI: 00007ffe85931430 RDI: 0000000000000004
[18407.757299] RBP: 00007ffe85931430 R08: 0000000000000000 R09: 00007ffe85931a80
[18407.758669] R10: 00000000ffffffff R11: 0000000000000293 R12: 000000000000006a
[18407.760038] R13: 00000000ffffffff R14: 00007ffe85931430 R15: 0000000000000001
[18407.761415] task:kthreadd        state:S stack:    0 pid:    2 ppid:     0 flags:0x80004000
[18407.762995] Call Trace:

Issue Links

• is related to: LU-15795 kernel update RHEL8.6
• is related to: LU-14697 change performance-sanity to use mdtest