Bug #104
closedbdi problem on EPERM from osd
0%
Description
last sysfs file: /sys/class/net/lo/operstate
CPU 1
Modules linked in: ceph [last unloaded: ceph]
Pid: 5724, comm: flush-0:15 Not tainted 2.6.34-rc5 #6 PDSMi+/PDSMi
RIP: 0010:[<ffffffff810357ac>] [<ffffffff810357ac>] finish_task_switch+0x6c/0xb0
RSP: 0018:ffff88011e889d50 EFLAGS: 00010202
RAX: 000000000000eaa0 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff88011e2cec60 RDI: ffff88011e2caca0
RBP: 60ffff88011dca15 R08: ffff88011e888000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffff88011e2cec60
R13: 0000000000000001 R14: ffff88011e2caca0 R15: ffff88011e2cec60
FS: 0000000000000000(0000) GS:ffff880001a80000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00007fead5b9fe40 CR3: 00000000017ce000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process flush-0:15 (pid: 5724, threadinfo ffff88011e888000, task ffff88011e2caca0)
Stack:
ffff880001a92240 ffff88011e2caca0 ffff88011dca1500 0000000000000001
<0> 0000000000000000 ffffffff81582215 ffff88011ed1de08 ffff880100000000
<0> ffff88011fc42640 0000000000012240 0000000000004000 0000000000004000
Call Trace:
[<ffffffff81582215>] ? schedule+0x2a5/0x7a0
[<ffffffff815829f4>] ? schedule_timeout+0x134/0x1e0
[<ffffffff81047930>] ? process_timeout+0x0/0x10
[<ffffffff810d611a>] ? bdi_writeback_task+0x6a/0xd0
[<ffffffff81096210>] ? bdi_start_fn+0x0/0xd0
[<ffffffff81096273>] ? bdi_start_fn+0x63/0xd0
[<ffffffff81096210>] ? bdi_start_fn+0x0/0xd0
[<ffffffff8105260e>] ? kthread+0x8e/0xa0
[<ffffffff81003194>] ? kernel_thread_helper+0x4/0x10
[<ffffffff81052580>] ? kthread+0x0/0xa0
[<ffffffff81003190>] ? kernel_thread_helper+0x0/0x10
Code: 74 24 0f 1f 44 00 00 48 8b 03 48 89 df 0f 18 08 48 8b 43 10 65 8b 34 25 d8 d1 00 00 ff 10 48 8b 1b 48 85 db 75 e1 48 85 ed 74 0b <f0> ff 4d 54 0f 94 c0 84 c0 75 0f 49 83 fd 40 74 13 5b 5d 41 5c
RIP [<ffffffff810357ac>] finish_task_switch+0x6c/0xb0
RSP <ffff88011e889d50>
Updated by Sage Weil almost 14 years ago
ladder0:
mount -a
echo asdf > /c/foo
sync
<crash>
Updated by Sage Weil almost 14 years ago
- Subject changed from bdi problem after unloading, loading, mounting, umounting, mounting on ladder0 to bdi problem on EPERM from osd
the problem is when writepages_finish gets a -1 result code.
Updated by Sage Weil almost 14 years ago
problem was use of invalid wbc in completion. fixed by commit:54ad023ba8108d0163acc931ed4b5e4a8a3a7327
Updated by Sage Weil almost 14 years ago
- Status changed from In Progress to Resolved