[LU-6776] osc_request.c:1670:osc_build_rpc()) ASSERTION( oap->oap_page_off + oap->oap_brw_page.count == ((1UL) << 12) ) failed

• Status: Resolved
• Project: Lustre
• Affects Version/s: Lustre 2.8.0
• Type: Bug
• Priority: Major
• Reporter: Oleg Drokin
• Assignee: WC Triage
• Resolution: Duplicate
• Severity: 3

Description

I've been having these crashes on an on and off basis for the past several weeks mostly in racer:

<0>[68116.792556] LustreError: 2052:0:(osc_request.c:1670:osc_build_rpc()) ASSERTION( oap->oap_page_off + oap->oap_brw_page.count == ((1UL) << 12) ) failed: 
<0>[68116.793462] LustreError: 2052:0:(osc_request.c:1670:osc_build_rpc()) LBUG
<4>[68116.793927] Pid: 2052, comm: ptlrpcd_2
<4>[68116.794279] 
<4>[68116.794280] Call Trace:
<4>[68116.794939]  [<ffffffffa042d885>] libcfs_debug_dumpstack+0x55/0x80 [libcfs]
<4>[68116.795388]  [<ffffffffa042de87>] lbug_with_loc+0x47/0xb0 [libcfs]
<4>[68116.795841]  [<ffffffffa0ad4b44>] osc_build_rpc+0xe84/0x1500 [osc]
<4>[68116.796332]  [<ffffffffa0439c41>] ? libcfs_debug_msg+0x41/0x50 [libcfs]
<4>[68116.796785]  [<ffffffffa0aefaba>] osc_io_unplug0+0x112a/0x1af0 [osc]
<4>[68116.797207]  [<ffffffff810149a9>] ? sched_clock+0x9/0x10
<4>[68116.797609]  [<ffffffffa0439c41>] ? libcfs_debug_msg+0x41/0x50 [libcfs]
<4>[68116.798055]  [<ffffffffa0af2a11>] osc_io_unplug+0x11/0x20 [osc]
<4>[68116.798485]  [<ffffffffa0acc656>] brw_queue_work+0x36/0xd0 [osc]
<4>[68116.798944]  [<ffffffffa07d9650>] work_interpreter+0x30/0x100 [ptlrpc]
<4>[68116.799405]  [<ffffffffa07e2f93>] ptlrpc_check_set+0x613/0x1bf0 [ptlrpc]
<4>[68116.799851]  [<ffffffff81522574>] ? _spin_lock_irqsave+0x24/0x30
<4>[68116.800348]  [<ffffffffa0811543>] ptlrpcd_check+0x3e3/0x630 [ptlrpc]
<4>[68116.800809]  [<ffffffffa0811dab>] ptlrpcd+0x35b/0x430 [ptlrpc]
<4>[68116.801218]  [<ffffffff81061630>] ? default_wake_function+0x0/0x20
<4>[68116.801677]  [<ffffffffa0811a50>] ? ptlrpcd+0x0/0x430 [ptlrpc]
<4>[68116.802097]  [<ffffffff8109ce4e>] kthread+0x9e/0xc0
<4>[68116.802523]  [<ffffffff8100c24a>] child_rip+0xa/0x20
<4>[68116.802905]  [<ffffffff8109cdb0>] ? kthread+0x0/0xc0
<4>[68116.803280]  [<ffffffff8100c240>] ? child_rip+0x0/0x20
<4>[68116.803672] 
<0>[68116.883279] Kernel panic - not syncing: LBUG

This is a tip of master with a couple of patches, in particular http://review.whamcloud.com/#/c/10458/16

tag in my source tree: master-20150629
crashdump and modules are available in /exports/crashdumps/192.168.10.218-2015-06-30-05\:31\:17/

Issue Links

• is related to: LU-6666 osc_brw_prep_request()) ASSERTION( pa...

Comments

[Jinshan Xiong (Inactive)]

duplicate of LU-6666