[Beowulf] NFS & Scaling issues

[Bruce Allen]

> Amrik Singh wrote:

>> Recently we started noticing very high (70-90%) wait states on the file 
>> servers when compute nodes. We have tried to optimize the NFS through 
>> increasing the number of daemons and the rsize and wsize but to no avail.

>> PS: All the nodes are running SuSE 10.0 and servers are running SuSE10.0 
>> and 10.1 and all the drives are formatted with reiserfs.
>
> Hmmm... I remember Reiser has had a problem in the past when file systems get 
> full or nearly so.

ReiserFS still has these problems.  I ran into them myself about nine 
months ago when a file system got full.  Hans Reiser has written that he 
can produce a file system defragmenter/optimizer that would fix this. 
But he was waiting for a paying customer before doing so.

Unless someone else has written a defragmenter, then this is probably 
still a problem.  I am moving away from ReiserFS because of this.

Cheers,
 	Bruce