From: "Chuck Lever" Subject: Re: [PATCH 6/8] knfsd: repcache: use client IP address in hash Date: Thu, 12 Oct 2006 10:19:31 -0400 Message-ID: <76bd70e30610120719u3b5e48fch8a0da89ed8ed6a6c@mail.gmail.com> References: <1160566130.8530.17.camel@hole.melbourne.sgi.com> <1160620200.6596.36.camel@lade.trondhjem.org> <20061012082126.GM8568@sgi.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: Neil Brown , Linux NFS Mailing List , Trond Myklebust Return-path: Received: from sc8-sf-mx2-b.sourceforge.net ([10.3.1.92] helo=mail.sourceforge.net) by sc8-sf-list2-new.sourceforge.net with esmtp (Exim 4.43) id 1GY1PK-0000OI-9Y for nfs@lists.sourceforge.net; Thu, 12 Oct 2006 07:19:34 -0700 Received: from wr-out-0506.google.com ([64.233.184.224]) by mail.sourceforge.net with esmtp (Exim 4.44) id 1GY1PJ-00055U-RT for nfs@lists.sourceforge.net; Thu, 12 Oct 2006 07:19:35 -0700 Received: by wr-out-0506.google.com with SMTP id 67so127400wri for ; Thu, 12 Oct 2006 07:19:31 -0700 (PDT) To: "Greg Banks" In-Reply-To: <20061012082126.GM8568@sgi.com> List-Id: "Discussion of NFS under Linux development, interoperability, and testing." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: nfs-bounces@lists.sourceforge.net Errors-To: nfs-bounces@lists.sourceforge.net On 10/12/06, Greg Banks wrote: > On Wed, Oct 11, 2006 at 07:30:00PM -0700, Trond Myklebust wrote: > > On Wed, 2006-10-11 at 21:28 +1000, Greg Banks wrote: > > > knfsd: Use the client's IP address in the duplicate request cache > > > hash function, instead of just the XID. This avoids contention > > > on hash buckets when the workload has many clients whose XIDs are > > > nearly in lockstep, a property seen on compute clusters using NFS > > > for shared storage. > > > > Note that some platforms (in particular the *BSDs) use an MD5 checksum > > of the first couple of 100 bytes of the RPC header+message instead of > > relying on the XID. That is a good deal safer w.r.t. port reuse by other > > clients etc. > > > > I hear that there was a Cthon presentation on this subject. It sounds > very interesting, does anyone have a URL? > > I presume the approach involves masking out the IPID and TCP sequence > number? Otherwise retries would never hash to the same value as the > original requests, thus defeating the repcache entirely. The hash starts at the beginning of the RPC header, so the IP and TCP/UDP headers are skipped. -- "We who cut mere stones must always be envisioning cathedrals" -- Quarry worker's creed ------------------------------------------------------------------------- Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642 _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs