Details
-
Bug
-
Resolution: Won't Fix
-
Minor
-
Lustre 2.0.0, Lustre 2.1.0, Lustre 1.8.6
-
None
-
3
-
23,988
-
10541
Description
Cray testing indicates that SLES11SP1 (2.6.32 based) experiences a crash during boot:
kernel BUG at drivers/scsi/sd.c:2560!
invalid opcode: 0000 1 SMP
last sysfs file: /sys/devices/virtual/tty/ptyp9/uevent
CPU 5
Modules linked in: qla2xxx sg kdreg gpcd_gem ipogif_gem kgni_gem hwerr(P)
rca(P) hss_os(P) heartbeat simplex(P) ghal_gem cgm
Pid: 1497, comm: udevd Tainted: P
2.6.32.19-0.2.1_1.0000.5481-cray_gem_s #1
RIP: 0010:[<ffffffff812c55f8>] [<ffffffff812c55f8>]
sd_iostats_finish_req+0x198/0x1a0
RSP: 0000:ffff880028343df0 EFLAGS: 00010046
RAX: 0000000000000000 RBX: ffff880405a3b800 RCX: 0000000000002002
RDX: 0000000000000000 RSI: 0000000000000246 RDI: ffff880405a3bce0
RBP: ffff880028343e10 R08: 0000000000000000 R09: ffff880405beb080
R10: ffff8803fd293e08 R11: ffff8804058cb800 R12: ffff880405a3bae0
R13: ffff8803fcdcde00 R14: ffff880405a3bce0 R15: ffff8803fd293fd8
FS: 00007f3152536700(0000) GS:ffff880028340000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f315232f980 CR3: 00000003fd207000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process udevd (pid: 1497, threadinfo ffff8803fd292000, task ffff8803fd208b90)
Stack:
ffff8803fce53780 0000000000004000 ffff8803fcd69800 ffff8803fce53780
<0> ffff880028343e50 ffffffff812c5644 ffff880028343e50 ffffffff812b60f6
<0> ffff8803fcd69e28 0000000000004000 ffff8803fcd67400 ffff8803fc7aa800
Call Trace:
[<ffffffff812c5644>] sd_done+0x44/0x1c0
[<ffffffff812af58c>] scsi_finish_command+0x9c/0xe0
[<ffffffff812b67b4>] scsi_softirq_done+0xc4/0x150
[<ffffffff8121a39d>] blk_done_softirq+0x6d/0x80
[<ffffffff8103f32e>] __do_softirq+0xbe/0x160
[<ffffffff810035dc>] call_softirq+0x1c/0x30
[<ffffffff8100563d>] do_softirq+0x4d/0x80
[<ffffffff8103ed3d>] irq_exit+0x3d/0x50
[<ffffffff81004c23>] do_IRQ+0x73/0xe0
[<ffffffff81002e53>] ret_from_intr+0x0/0xa
[<ffffffff8108fd8b>] filemap_fault+0x3b/0x420
[<ffffffff810a7826>] __do_fault+0x56/0x4b0
[<ffffffff810a9e11>] handle_mm_fault+0x1b1/0x8b0
[<ffffffff81020f17>] do_page_fault+0x147/0x2c0
[<ffffffff813c296f>] page_fault+0x1f/0x30
[<00007f315232f980>] 0x7f315232f980
Code: c9 c3 90 4c 8d a4 c3 e0 02 00 00 e9 fd fe ff ff 0f 1f 00 41 f6 45 48 01
48 63 c2 4c 8d a4 c3 60 03 00 00 0f 85 e4 fe ff ff eb d8 <0f> 0b eb fc 30 48 89
5d e8 4c
RIP [<ffffffff812c55f8>] sd_iostats_finish_req+0x198/0x1a0
Yangsheng has a patch in the bug, but Vitaly thinks the patch is wrong.