[LU-317] Test failure on test suite runracer

• Status: Resolved
• Project: Lustre
• Type: Bug
• Priority: Minor
• Reporter: Maloo
• Assignee: WC Triage
• Resolution: Cannot Reproduce
• Severity: 3

Description

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

This issue relates to the following test suite run: https://maloo.whamcloud.com/test_sets/af539930-7cf2-11e0-b5bf-52540025f9af.

Comments

[Jinshan Xiong (Inactive)]

there is no lustre log gathered so it's hard to know the root cause of this problem. The most interesting information is from the client stack trace:

19:35:04:ldlm_bl_13    S ffff81032ae5e040     0 10671      1         10672  4530 (L-TLB)
19:35:04: ffff810317721b00 0000000000000046 0000000000000001 ffff81031c4d0560
19:35:04: ffff81031c4d0560 000000000000000a ffff81031844d100 ffff81032ae5e040
19:35:04: 000002d1a63e8387 000000000000df8d ffff81031844d2e8 000000001f70d058
19:35:04:Call Trace:
19:35:04: [<ffffffff8003da83>] lock_timer_base+0x1b/0x3c
19:35:04: [<ffffffff8001cc7d>] __mod_timer+0x100/0x10f
19:35:04: [<ffffffff800638ab>] schedule_timeout+0x8a/0xad
19:35:04: [<ffffffff80097cc1>] process_timeout+0x0/0x5
19:35:04: [<ffffffff888c1e50>] :obdclass:cl_sync_io_wait+0x1a0/0x4b0
19:35:04: [<ffffffff888b7c7d>] :obdclass:cl_page_gang_lookup+0x2bd/0x370
19:35:04: [<ffffffff8008cf9d>] default_wake_function+0x0/0xe
19:35:04: [<ffffffff888bf486>] :obdclass:cl_lock_page_out+0x1a6/0x2f0
19:35:04: [<ffffffff88b2e2fe>] :osc:osc_lock_flush+0x4e/0x90
19:35:04: [<ffffffff88b2f50d>] :osc:osc_lock_cancel+0x7d/0x170
19:35:04: [<ffffffff888ba608>] :obdclass:cl_lock_cancel0+0xa8/0x120
19:35:04: [<ffffffff888bad99>] :obdclass:cl_lock_cancel+0x99/0x110
19:35:04: [<ffffffff88b2ff08>] :osc:osc_ldlm_blocking_ast+0x168/0x2b0
19:35:04: [<ffffffff88956110>] :ptlrpc:ldlm_handle_bl_callback+0x160/0x260
19:35:04: [<ffffffff88b2fda0>] :osc:osc_ldlm_blocking_ast+0x0/0x2b0
19:35:04: [<ffffffff8003bc4e>] remove_wait_queue+0x1c/0x2c
19:35:05: [<ffffffff8895c5d2>] :ptlrpc:ldlm_bl_thread_main+0x292/0x420
19:35:05: [<ffffffff8008cf9d>] default_wake_function+0x0/0xe
19:35:05: [<ffffffff800b7a4b>] audit_syscall_exit+0x336/0x362
19:35:05: [<ffffffff8005dfb1>] child_rip+0xa/0x11
19:35:05: [<ffffffff8895c340>] :ptlrpc:ldlm_bl_thread_main+0x0/0x420
19:35:05: [<ffffffff8005dfa7>] child_rip+0x0/0x11

It's looks like the client had some problem to flush pages to OST.