From: Bryan O'Sullivan Subject: Re: RE: 2.4.19 NFSALL performance oddity Date: 09 Oct 2002 10:03:49 -0700 Sender: nfs-admin@lists.sourceforge.net Message-ID: <1034183029.19855.2.camel@plokta.s8.com> References: <5CA6F03EF05E0046AC5594562398B91653BCAE@poexmb3.conoco.net> <15778.2247.997239.729461@charged.uio.no> Mime-Version: 1.0 Content-Type: text/plain Cc: "Heflin, Roger A." , nfs@lists.sourceforge.net Return-path: Received: from server.s8.com ([66.77.12.139]) by usw-sf-list1.sourceforge.net with esmtp (Exim 3.31-VA-mm2 #1 (Debian)) id 17zKFl-00034o-00 for ; Wed, 09 Oct 2002 10:04:09 -0700 To: trond.myklebust@fys.uio.no In-Reply-To: <15778.2247.997239.729461@charged.uio.no> Errors-To: nfs-admin@lists.sourceforge.net List-Help: List-Post: List-Subscribe: , List-Id: Discussion of NFS under Linux development, interoperability, and testing. List-Unsubscribe: , List-Archive: On Mon, 2002-10-07 at 15:20, Trond Myklebust wrote: > FYI: I updated 2.4.19-NFS_ALL on Saturday with a couple of > bugfixes. Among them was one which fixes a queueing bottleneck when a > timeout+resend occurs. We've tried to reproduce Roger's numbers locally, using a patched 2.4.19 NFS_ALL server with 2G of RAM and a Red Hat 7.3 client, over 100baseT. We could not reproduce the bad performance he's seeing. Bonnie++ is giving perfectly respectable numbers.