On 5/14/20 1:07 PM, Michal Soltys wrote:
On 5/13/20 6:17 PM, Song Liu wrote:
Are these captured back to back? I am asking because they showed
different
"Events" number.
Nah, they were captured between reboots. Back to back all event
fields show identical value (at 56291 now).
Also, when mdadm -A hangs, could you please capture /proc/$(pidof
mdadm)/stack ?
The output is empty:
xs22:/☠ ps -eF fww | grep mdadm
root 10332 9362 97 740 1884 25 12:47 pts/1 R+ 6:59 |
\_ mdadm -A /dev/md/r5_big /dev/md/r1_journal_big /dev/sdi1
/dev/sdg1 /dev/sdj1 /dev/sdh1
xs22:/☠ cd /proc/10332
xs22:/proc/10332☠ cat stack
xs22:/proc/10332☠
Hmm... Could you please share the strace output of "mdadm -A"
command? Like
strace mdadm -A /dev/md/r5_big /dev/md/r1_journal_big /dev/xxx ...
Thanks,
Song
I did one more thing - ran cat on that stack in another terminal every
0.1 seconds, this is what was found:
cat: /proc//stack: No such file or directory
cat: /proc//stack: No such file or directory
cat: /proc//stack: No such file or directory
[<0>] submit_bio_wait+0x5b/0x80
[<0>] r5l_recovery_read_page+0x1b6/0x200 [raid456]
[<0>] r5l_recovery_verify_data_checksum+0x19/0x70 [raid456]
[<0>] r5l_start+0x99e/0xe70 [raid456]
[<0>] md_start.part.48+0x2e/0x50 [md_mod]
[<0>] do_md_run+0x64/0x100 [md_mod]
[<0>] md_ioctl+0xe7d/0x17d0 [md_mod]
[<0>] blkdev_ioctl+0x4d0/0xa00
[<0>] block_ioctl+0x39/0x40
[<0>] do_vfs_ioctl+0xa4/0x630
[<0>] ksys_ioctl+0x60/0x90
[<0>] __x64_sys_ioctl+0x16/0x20
[<0>] do_syscall_64+0x52/0x160
[<0>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
cat: /proc//stack: No such file or directory
[<0>] submit_bio_wait+0x5b/0x80
Just FYI. I recalled that long sync IO could fire the warning in
submit_bio_wait.
Have you applied the commit de6a78b601c5 ("block: Prevent hung_check
firing during long sync IO")?
Thanks,
Guoqing
