From: trond.myklebust@fys.uio.no Subject: Re: [PATCH 2.6.3] Add write throttling to NFS client Date: Mon, 1 Mar 2004 20:03:58 +0100 (CET) Sender: nfs-admin@lists.sourceforge.net Message-ID: <35353.207.214.87.84.1078167838.squirrel@webmail.uio.no> References: <20040301081456.37082.qmail@web12823.mail.yahoo.com> <34574.207.214.87.84.1078162727.squirrel@webmail.uio.no> <40437AE4.4030407@lehman.com> <35336.207.214.87.84.1078166886.squirrel@webmail.uio.no> <404387DD.5010205@lehman.com> Mime-Version: 1.0 Content-Type: text/plain;charset=iso-8859-1 Cc: "Shantanu Goel" , "Bogdan Costescu" , "Charles Lever" , "Olaf Kirch" ,"Greg Banks" , 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 1Axsqj-00061X-Bd for nfs@lists.sourceforge.net; Mon, 01 Mar 2004 11:13:09 -0800 Received: from pat.uio.no ([129.240.130.16] ident=7411) by sc8-sf-mx1.sourceforge.net with esmtp (Exim 4.30) id 1AxsmR-00017h-6B for nfs@lists.sourceforge.net; Mon, 01 Mar 2004 11:08:43 -0800 To: "Shantanu Goel" In-Reply-To: <404387DD.5010205@lehman.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: P? m? , 01/03/2004 klokka 10:58, skreiv Shantanu Goel: > >Simple round robin is not going to play well with NFSv2 style write gathering on the server. Nor will it really work too efficiently with standard readahead. > >How about instead doing round-robin on blocks of, say, 16 requests per cookie (which is the current maximum readahead value)? That should allow > >the server some efficiency on block operations without sacrificing your fairness criterion. > > > We could make it static but how about we add a field "nr_batch" to rpc_clnt with a default of 16 but let the higher layer override it? This way the NFS layer can set it to a different value for different servers. If you want to make it tunable, then I suggest you just make it a global variable, and set it up as a sysctl in /proc/sys/sunrpc. I doubt there is much call for making this a per-mountpoint variable (we already have too many tunables in the "mount" structure as it is). Cheers, Trond ------------------------------------------------------- SF.Net is sponsored by: Speed Start Your Linux Apps Now. Build and deploy apps & Web services for Linux with a free DVD software kit from IBM. Click Now! http://ads.osdn.com/?ad_id=1356&alloc_id=3438&op=click _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs