From owner-freebsd-net@FreeBSD.ORG Fri May 13 08:29:12 2005 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 949C616A4CE for ; Fri, 13 May 2005 08:29:12 +0000 (GMT) Received: from antsrv1.ant.uni-bremen.de (antsrv2.ant.uni-bremen.de [134.102.176.17]) by mx1.FreeBSD.org (Postfix) with ESMTP id 54A4443D8C for ; Fri, 13 May 2005 08:29:11 +0000 (GMT) (envelope-from rebehn@ant.uni-bremen.de) Received: from bremerhaven.ant.uni-bremen.de ([134.102.176.10]) by antsrv2.ant.uni-bremen.de with esmtp (Exim 4.42) id 1DWVXe-0008AL-Cz; Fri, 13 May 2005 10:29:06 +0200 Message-ID: <42846562.2040700@ant.uni-bremen.de> Date: Fri, 13 May 2005 10:29:22 +0200 From: Heinrich Rebehn User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.7) Gecko/20050420 Debian/1.7.7-2 X-Accept-Language: en MIME-Version: 1.0 To: Mohan Srinivasan References: <20050511145350.9924.qmail@web80603.mail.yahoo.com> In-Reply-To: <20050511145350.9924.qmail@web80603.mail.yahoo.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Score: 0.0 (/) X-Spam-Report: Spam detection software, running on the system "antsrv2.ant.uni-bremen.de", hasmessageblock similar future email. If you have any questions, see the administrator of that system for details.Can you force the mount to NFS/UDP ? >> >>Yes, we use TCP. It is strongly recommended for multispeed networks and >>we did have problems with retransmissions using UDP. > > > I'm not disputing the merits of NFS/TCP. I suggested this merely as > a workaround, and to see if the bug in question is causing the hangs. [...] Content analysis details: (0.0 points, 5.0 required) pts rule name description -------------------------------------------------- cc: freebsd-net@freebsd.org Subject: Re: nfsrvstats.srvrpc_errs rapidly increasing X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 13 May 2005 08:29:12 -0000 Mohan Srinivasan wrote: >>>Are you using NFS/TCP ? Can you force the mount to NFS/UDP ? >> >>Yes, we use TCP. It is strongly recommended for multispeed networks and >>we did have problems with retransmissions using UDP. > > > I'm not disputing the merits of NFS/TCP. I suggested this merely as > a workaround, and to see if the bug in question is causing the hangs. I will try it on a single machine when the problem occurs again. ATM, everything runs flawlessly :-) > > >>Wouldn't it be better to fix the bug? Is there a problem report on this? > > > Of course it would be better to fix the bug. But until someone fixes it... > > There's no problem report on this. I wonder if it will ever get fixed then.. Since i am neither familiar with kernel sources nor with the internals of NFS: Could you show me, where the bug can be traced, i.e. at which point one can detect that the stream is out of sync? I would like to insert another log() in order to see, if - the error occurs at all - is in any way related to our problems. --Heinrich