[Linux-cluster] Node fenced when mounting gfs
Fajar A. Nugraha
fajar at telkom.net.id
Thu Jun 9 02:52:48 UTC 2005
David Teigland wrote:
>On Wed, Jun 08, 2005 at 12:27:34PM +0700, Fajar A. Nugraha wrote:
>
>
>
>>It seems that lincluster2 is too busy scanning log elements that it
>>cannot even send CMAN heartbeat. Which makes lincluster1 thinks
>>lincluster2 is dead, thus fencing it, and rebooting it.
>>
>>
>
>Can you run top or something on lincluster2 to monitor if it's doing
>anything or if the machine has actually hung?
>
>
>
It's not actually hung. If you type anything it will show up 10-30
seconds later. Top result :
Cpu(s): 0.0% us, 84.9% sy, 0.0% ni, 14.7% id, 0.4% wa, 0.0% hi, 0.0% si
Mem: 4023624k total, 952800k used, 3070824k free, 351616k buffers
Swap: 4194296k total, 0k used, 4194296k free, 288764k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
29791 root 18 0 1452 476 404 D 91.6 0.0 0:13.25 mount
29756 root 16 0 1952 524 448 S 88.7 0.0 0:12.83 tail
159 root 16 0 0 0 0 D 79.9 0.0 0:12.58 pdflush
29727 root 16 0 1924 1052 812 R 79.3 0.0 0:11.55 top
1 root 16 0 1408 484 432 S 0.0 0.0 0:01.00 init
2 root RT 0 0 0 0 S 0.0 0.0 0:00.05 migration/0
Regards,
Fajar
More information about the Linux-cluster
mailing list