* Q: dlm_recoverd takes 100%
@ 2012-08-28 8:54 Heiko Nardmann
0 siblings, 0 replies; only message in thread
From: Heiko Nardmann @ 2012-08-28 8:54 UTC (permalink / raw)
To: linux-kernel
Hi together,
maybe someone can give me a hint which ML to contact (if I am wrong here)?
In a two-node cluster system I see 'dlm_recoverd' taking 100% time of
one cpu for around 6 minutes. Here is small excerpt from a 'top' output
during that period:
top - 10:51:01 up 3 days, 17:21, 5 users, load average: 10.19, 5.39, 2.76
Tasks: 536 total, 3 running, 533 sleeping, 0 stopped, 0 zombie
Cpu(s): 1.2%us, 6.6%sy, 0.0%ni, 92.1%id, 0.1%wa, 0.0%hi, 0.0%si,
0.0%st
Mem: 12183344k total, 11827540k used, 355804k free, 160332k buffers
Swap: 14417912k total, 0k used, 14417912k free, 8299364k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
3121 root 20 0 0 0 0 R 100.0 0.0 3:36.15 dlm_recoverd
The cluster nodes use a shared SAN (GFS2). The second node has been
rebooted while I experience this behaviour. The real problem is that my
application is unable to open a file on the SAN for these 6 minutes.
After the reboot of the second node all is fine again and the
application succeeds in opening the file. So I am not sure what can
cause those two symptoms.
Thanks in advance for any hint!
Kind regards,
Heiko
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2012-08-28 8:55 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2012-08-28 8:54 Q: dlm_recoverd takes 100% Heiko Nardmann
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).