From: "Jesper Krogh" Subject: NFS performance (Currently 2.6.20) Date: Wed, 6 Feb 2008 11:04:34 +0100 (CET) Message-ID: <3093.195.41.66.226.1202292274.squirrel@mail.jabbernet.dk> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII To: linux-nfs@vger.kernel.org Return-path: Received: from 2605ds1-ynoe.1.fullrate.dk ([90.184.12.24]:33269 "EHLO shrek.krogh.cc" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752874AbYBFKj5 (ORCPT ); Wed, 6 Feb 2008 05:39:57 -0500 Received: from localhost (localhost.localdomain [127.0.0.1]) by shrek.krogh.cc (Postfix) with ESMTP id 0D5D83BF2B6 for ; Wed, 6 Feb 2008 11:04:50 +0100 (CET) Received: from shrek.krogh.cc ([127.0.0.1]) by localhost (shrek.krogh.cc [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id bcnarTWB+WZJ for ; Wed, 6 Feb 2008 11:04:34 +0100 (CET) Received: from mail.jabbernet.dk (localhost.localdomain [127.0.0.1]) by shrek.krogh.cc (Postfix) with ESMTP id 9A7643BF212 for ; Wed, 6 Feb 2008 11:04:34 +0100 (CET) Sender: linux-nfs-owner@vger.kernel.org List-ID: Hi. I'm currently trying to optimize our NFS server. We're running in a cluster setup with a single NFS server and some compute nodes pulling data from it. Currently the dataset is less than 10GB so it fits in memory of the NFS-server. (confirmed via vmstat 1). Currently I'm getting around 500mbit (700 peak) of the server on a gigabit link and the server is CPU-bottlenecked when this happens. Clients having iowait around 30-50%. Is it reasonable to expect to be able to fill a gigabit link in this scenario? (I'd like to put in a 10Gbit interface, but when I have a cpu-bottleneck) Should I go for NFSv2 (default if I dont change mount options) NFSv3 ? or NFSv4 NFSv3 default mount options is around 1MB for rsize and wsize, but reading the nfs-man page, they suggest setting them "up to" around 32K. I probably only need some pointers to the documentation. Thanks. -- Jesper Krogh