[Beowulf] NFS & Scaling issues
ballen at gravity.phys.uwm.edu
Tue Apr 10 03:20:45 PDT 2007
> 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.
More information about the Beowulf