From: "J. K. Cliburn" Subject: Re: NFS regression? Odd delays and lockups accessing an NFS export. Date: Mon, 18 Aug 2008 14:37:45 -0500 Message-ID: <48A9CF89.9090304@bellsouth.net> References: <20080818185048.GO20684@miggy.org> Reply-To: jacliburn-Bdlq13kUjeyLZ21kGMrzwg@public.gmane.org Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed To: Grant Coady , linux-kernel , neilb@suse.de, bfields@fieldses.org, linux-nfs@vger.kernel.org Return-path: Received: from yx-out-2324.google.com ([74.125.44.28]:16419 "EHLO yx-out-2324.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1764476AbYHRThs (ORCPT ); Mon, 18 Aug 2008 15:37:48 -0400 Received: by yx-out-2324.google.com with SMTP id 8so1333219yxm.1 for ; Mon, 18 Aug 2008 12:37:47 -0700 (PDT) In-Reply-To: <20080818185048.GO20684-QVNlIYdkypLYtjvyW6yDsg@public.gmane.org> Sender: linux-nfs-owner@vger.kernel.org List-ID: Athanasius wrote: > On Mon, Aug 18, 2008 at 12:02:20PM +1000, Grant Coady wrote: >> I've been using NFS here for years, lately there's something odd going on >> since about a month or so. Previously reported last month: >> http://www.gossamer-threads.com/lists/linux/kernel/951419?page=last >> >> Now with 2.6.27-rc3 on one of the client boxes I get a complete stall >> at odd times when accessing the server's exported directory, cannot >> see a pattern to it. Eventually recovers after a Ctrl-C. Nothing in >> the server or client log files. Not easy to reproduce either. > > I wonder if this is what I've been seeing. I've been otherwise too > busy to properly report it, thinking that *someone* else must also be > seeing it and it's being worked on, else it's a subtle configuration > problem my end. > > I first started seeing this with 2.6.26 on the client end, I see you're running the atl1 driver on your client. I'm chasing an intermittent bug in that driver that seems to be affected by certain offload parameters. Try disabling TSO and see if things improve. ethtool -K eth0 tso off Let me know if it helps. Jay