lkml.org 
[lkml]   [2012]   [Aug]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectQ: dlm_recoverd takes 100%
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


\
 
 \ /
  Last update: 2012-08-28 11:21    [W:0.026 / U:0.500 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site