From: Steve Dickson Subject: Re: NFS server not responding Date: Thu, 04 Dec 2003 12:17:05 -0500 Sender: nfs-admin@lists.sourceforge.net Message-ID: <3FCF6C11.5010503@RedHat.com> References: <1070375865.20333.74.camel@wibbit.firebox.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Return-path: Received: from sc8-sf-mx2-b.sourceforge.net ([10.3.1.12] helo=sc8-sf-mx2.sourceforge.net) by sc8-sf-list2.sourceforge.net with esmtp (Exim 4.24) id 1ARx5R-0002CN-PG for nfs@lists.sourceforge.net; Thu, 04 Dec 2003 09:16:21 -0800 Received: from mx1.redhat.com ([66.187.233.31]) by sc8-sf-mx2.sourceforge.net with esmtp (Exim 4.24) id 1ARx5R-0002L0-9l for nfs@lists.sourceforge.net; Thu, 04 Dec 2003 09:16:21 -0800 Received: from int-mx1.corp.redhat.com (int-mx1.corp.redhat.com [172.16.52.254]) by mx1.redhat.com (8.11.6/8.11.6) with ESMTP id hB4HGE213506 for ; Thu, 4 Dec 2003 12:16:14 -0500 Received: from lacrosse.corp.redhat.com (lacrosse.corp.redhat.com [172.16.52.154]) by int-mx1.corp.redhat.com (8.11.6/8.11.6) with ESMTP id hB4HGE230931 for ; Thu, 4 Dec 2003 12:16:14 -0500 Received: from RedHat.com (dickson.boston.redhat.com [172.16.65.20]) by lacrosse.corp.redhat.com (8.11.6/8.11.6) with ESMTP id hB4HGE310465 for ; Thu, 4 Dec 2003 12:16:14 -0500 To: nfs@lists.sourceforge.net In-Reply-To: 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: Trond Myklebust wrote: >Nobody on this list is directly responsible for the Fedore Core 1 >kernel, ...... > > This not completely accurate.... I am responsible for FC1... And it is my goal to keep FC1 (and beyond) as stable as possible... >I have no problems on *any* of the machines in the test-rigs I have at >my disposition when using a standard 2.4.23 kernel. For the record, >those few that I have used with the Fedora kernel have been fine too >(though I haven't made any detailed tests of that) > > I not seen this either... FC1 does have the latest retrans improvements # 03/10/11 trond.myklebust@fys.uio.no 1.1148.17.3 # UDP round trip timer fix. ... # 03/10/11 trond.myklebust@fys.uio.no 1.1148.17.2 # A request cannot be used as part of the RTO estimation ... # 03/07/08 trond.myklebust@fys.uio.no 1.1003.1.58 # Back out some congestion control changes that were causing trouble... With the only difference being FC1 has a longer RTO_MIN -#define RPC_RTO_MIN (HZ/30) +#define RPC_RTO_MIN (HZ/10) And these patches did show a noticeable improvement in bring down the number of retrans at least in my testing (w/out being overly verbose) >So now, what have you tried in order to diagnose this problem? > > ifconfig will show if the driver is dropping frames. netstat -s will show if there are udp fragmentation issues and ethereal is good at showing whether the ip stack or network are dropping the packets.... SteveD. ------------------------------------------------------- This SF.net email is sponsored by: SF.net Giveback Program. Does SourceForge.net help you be more productive? Does it help you create better code? SHARE THE LOVE, and help us help YOU! Click Here: http://sourceforge.net/donate/ _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs