[LU-6188] EL7 client recovery-small test_10a: failed to chmod /mnt/lustre

• Status: Open
• Project: Lustre
• Affects Version/s: Lustre 2.7.0, Lustre 2.10.0
• Type: Bug
• Priority: Minor
• Reporter: Maloo
• Assignee: WC Triage
• Resolution: Unresolved

Environment

server: lustre-master build # 2830 RHL6
client: EL7

• 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/56b80cd8-a49a-11e4-a1ef-5254006e85c2.

The sub-test test_10a failed with the following error:

failed to chmod /mnt/lustre: 1

MDT console

5:31:02:Lustre: DEBUG MARKER: == recovery-small test 10a: finish request on server after client eviction (bug 1521) ================ 07:28:26 (1422113306)
15:31:02:LustreError: 30437:0:(ldlm_lockd.c:654:ldlm_handle_ast_error()) ### client (nid 10.2.4.215@tcp) failed to reply to blocking AST (req status 0 rc -110), evict it ns: mdt-lustre-MDT0000_UUID lock: ffff8800687e47c0/0xa9178a7ed4369af1 lrc: 4/0,0 mode: PR/PR res: [0x200000007:0x1:0x0].0 bits 0x13 rrc: 3 type: IBT flags: 0x60200000000020 nid: 10.2.4.215@tcp remote: 0xec8d64307714b77d expref: 1929 pid: 30437 timeout: 4299711953 lvb_type: 0
15:31:02:LustreError: 138-a: lustre-MDT0000: A client on nid 10.2.4.215@tcp was evicted due to a lock blocking callback time out: rc -110
15:31:02:LNet: Service thread pid 30437 completed after 110.06s. This indicates the system was overloaded (too many service threads, or there were not enough hardware resources).
15:31:02:Lustre: DEBUG MARKER: /usr/sbin/lctl mark  recovery-small test_10a: @@@@@@ FAIL: failed to chmod \/mnt\/lustre: 1 
15:31:02:Lustre: DEBUG MARKER: recovery-small test_10a: @@@@@@ FAIL: failed to chmod /mnt/lustre: 1

Comments

[Sarah Liu]

also seen in interop test https://testing.hpdd.intel.com/test_sets/c6ef7464-b7eb-11e4-a27e-5254006e85c2
server: 2.5.3
client: lustre-master build # 2856