From: Ian Thurlbeck Subject: Re: Strange delays on NFS server Date: Wed, 25 Aug 2004 09:40:36 +0100 Sender: nfs-admin@lists.sourceforge.net Message-ID: <412C5084.9050605@stams.strath.ac.uk> References: <20040811164135.GA11101@suse.de> <411B8987.1030609@stams.strath.ac.uk> <411CD601.1080308@RedHat.com> <4120AB46.1080606@stams.strath.ac.uk> <20040816131434.GL3510@suse.de> <4120C8D5.3040606@stams.strath.ac.uk> <20040816145435.GQ3510@suse.de> <4124CD95.7020007@stams.strath.ac.uk> <20040820095854.GC23176@suse.de> <412B0EDE.5010206@stams.strath.ac.uk> <20040825020241.GB16037@sgi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Cc: Olaf Kirch , nfs@lists.sourceforge.net Return-path: Received: from sc8-sf-mx1-b.sourceforge.net ([10.3.1.11] helo=sc8-sf-mx1.sourceforge.net) by sc8-sf-list2.sourceforge.net with esmtp (Exim 4.30) id 1BztKp-0006di-K2 for nfs@lists.sourceforge.net; Wed, 25 Aug 2004 01:40:47 -0700 Received: from vif-img1.cc.strath.ac.uk ([130.159.248.61] helo=khafre.cc.strath.ac.uk) by sc8-sf-mx1.sourceforge.net with esmtp (TLSv1:DES-CBC3-SHA:168) (Exim 4.34) id 1BztKn-0000MI-Uw for nfs@lists.sourceforge.net; Wed, 25 Aug 2004 01:40:47 -0700 Received: from dunnet.stams.strath.ac.uk ([130.159.240.95]:42213) by khafre.cc.strath.ac.uk with smtp (Exim 4.20 #1) id 1BztKe-0004GZ-Da for ; Wed, 25 Aug 2004 09:40:36 +0100 To: Greg Banks In-Reply-To: <20040825020241.GB16037@sgi.com> Errors-To: nfs-admin@lists.sourceforge.net List-Unsubscribe: , List-Id: Discussion of NFS under Linux development, interoperability, and testing. List-Post: List-Help: List-Subscribe: , List-Archive: Greg Banks wrote: > On Tue, Aug 24, 2004 at 10:48:14AM +0100, Ian Thurlbeck wrote: > >>What on earth could be writing up to 3GB of data to the drive ? >>As before the usual suspects of kjournald, kupdated, bdflush and >>nfsd turn up on the process list. >> >>Just how big is the nfs write cache on a typical server ? > > > It can be most of RAM. > > >>Is it >>writing the whole lot one go ? > > > It might be. What ratio of COMMIT to WRITE calls are you > seeing in nfsstat? Does the export have "sync" or "async" > in its options? > > Greg. Greg Server stats since reboot Monday morning. It is lightly loaded mostly: Server nfs v3: null getattr setattr lookup access readlink 85912 2% 1626277 46% 12375 0% 135833 3% 1295417 36% 773 0% read write create mkdir symlink mknod 136099 3% 151569 4% 7899 0% 64 0% 194 0% 0 0% remove rmdir rename link readdir readdirplus 6270 0% 37 0% 2931 0% 969 0% 266 0% 4893 0% fsstat fsinfo pathconf commit 1508 0% 890 0% 0 0% 41205 1% So that's about 4 writes for every commit. File system export: /export/raid50 @unix(rw,sync,no_wdelay,hide,nocrossmnt,secure,root_squash, no_all_squash,subtree_check,secure_locks,mapping=identity, anonuid=-2,anongid=-2) I've got Neil's script running to correlate disk writes with nfs ops and these slowdown event times. I'll post the results in a day or so. Thanks Ian -- Ian Thurlbeck http://www.stams.strath.ac.uk/ Statistics and Modelling Science, University of Strathclyde Livingstone Tower, 26 Richmond Street, Glasgow, UK, G1 1XH Tel: +44 (0)141 548 3667 Fax: +44 (0)141 552 2079 ------------------------------------------------------- SF.Net email is sponsored by Shop4tech.com-Lowest price on Blank Media 100pk Sonic DVD-R 4x for only $29 -100pk Sonic DVD+R for only $33 Save 50% off Retail on Ink & Toner - Free Shipping and Free Gift. http://www.shop4tech.com/z/Inkjet_Cartridges/9_108_r285 _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs