[Linux-cluster] Node fenced when mounting gfs

[Fajar A. Nugraha]

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