Subject: Re: degrading performance (NFS v.3 client)
From: Trond Myklebust <trond.myklebust@fys.uio.no>
To: r31dmaeu@pc0312b.rz.unibw-muenchen.de
Cc: linux-kernel@vger.kernel.org
In-Reply-To: <47A1E4AB.2010504@pc0312a.rz.unibw-muenchen.de>
References: <47A1E4AB.2010504@pc0312a.rz.unibw-muenchen.de>
Content-Type: text/plain
Date: Thu, 31 Jan 2008 17:44:33 -0500
Message-Id: <1201819473.11897.34.camel@heimdal.trondhjem.org>
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1074
Lines: 36


On Thu, 2008-01-31 at 16:09 +0100, Claude Frantz wrote:
> Hello !
> 
> Please allow me to submit to you a question related to a system which
> is a NFS v3 client for a Netapp server. The home directories are
> NFS attached. The following behaviour occurs sometimes. The system 
> becomes very slow. The load average is increasing but the most
> interesting observation is the increase of the %iowait. After
> reboot the system is running well for many days, then the problem 
> occurs again.
> 
> Any idea ?

Hi,

Have you tried analysing the NFS performances using Chuck's nfs-iostat
utility? You can pick up a copy at
    http://oss.oracle.com/~cel/linux-2.6/2.6.24/

Try looking both at

	nfs-iostat 10 --page
and
	nfs-iostat 10 --attr

to see what the differences are between the 'fast' and 'slow' cases...

Cheers
  Trond

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/