<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<TITLE>Re: NFS Performance (was Re: [Beowulf] GPFS on Linux (x86))</TITLE>
</HEAD>
<BODY>
<!-- Converted from text/plain format -->
<P><FONT SIZE=2>I am puzzled by an sles9sp3 (2.6.9 kernel) nfs server that serves rhel3 (2.4.21 kernel) compute nodes. For some reason a lot of times the mounts fail (with default as well as modified parameters). The symptom is mount: rpc timeout. The server logs all authentification requests as successful. The switch is an oversubscribed hp 4108gl.<BR>
<BR>
Google turned up nothing useful.<BR>
<BR>
Any ideas?<BR>
<BR>
Michael<BR>
<BR>
-----Original Message-----<BR>
From: Brent Franks [<A HREF="mailto:brentasterisk@gmail.com">mailto:brentasterisk@gmail.com</A>]<BR>
Sent: Fri Sep 15 07:47:11 2006<BR>
To: Chris Samuel<BR>
Cc: beowulf@beowulf.org<BR>
Subject: Re: NFS Performance (was Re: [Beowulf] GPFS on Linux (x86))<BR>
<BR>
On 9/15/06, Chris Samuel <csamuel@vpac.org> wrote:<BR>
> Wild guess - NFS servers are running RHEL and using ext3 ?<BR>
<BR>
Exactly.<BR>
<BR>
> We used to have that problem with the 2 NFS servers for our 90 node cluster<BR>
> till we dumped RHEL, switched to Fedora and XFS and all our horrible NFS<BR>
> problems went away.<BR>
<BR>
Nice, any sort of comparison data in terms of differences in<BR>
throughput achieved?<BR>
<BR>
Additionally, are you writing your journal to a different partition?<BR>
<BR>
Thanks,<BR>
<BR>
- Brent<BR>
_______________________________________________<BR>
Beowulf mailing list, Beowulf@beowulf.org<BR>
To change your subscription (digest mode or unsubscribe) visit <A HREF="http://www.beowulf.org/mailman/listinfo/beowulf">http://www.beowulf.org/mailman/listinfo/beowulf</A><BR>
</FONT>
</P>
</BODY>
</HTML>