From: Andrew Morton Subject: Re: A unresponsive file system can hang all I/O in the system on linux-2.6.23-rc6 (dirty_thresh problem?) Date: Fri, 28 Sep 2007 12:26:28 -0700 Message-ID: <20070928122628.965137f2.akpm@linux-foundation.org> References: <92cbf19b0709272332s25684643odaade0e98cb3a1f4@mail.gmail.com> <20070927235034.ae7bd73d.akpm@linux-foundation.org> <1190998853.6702.17.camel@heimdal.trondhjem.org> <20070928114930.2c201324.akpm@linux-foundation.org> <1191006971.6702.25.camel@heimdal.trondhjem.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: nfs@lists.sourceforge.net, linux-pm , lkml , Peter Zijlstra To: 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 1IbLV6-0007rf-LG for nfs@lists.sourceforge.net; Fri, 28 Sep 2007 12:27:48 -0700 Received: from smtp2.linux-foundation.org ([207.189.120.14]) by mail.sourceforge.net with esmtps (TLSv1:AES256-SHA:256) (Exim 4.44) id 1IbLVA-0005Az-DP for nfs@lists.sourceforge.net; Fri, 28 Sep 2007 12:27:53 -0700 In-Reply-To: <1191006971.6702.25.camel@heimdal.trondhjem.org> 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 Fri, 28 Sep 2007 15:16:11 -0400 Trond Myklebust wrote: > On Fri, 2007-09-28 at 11:49 -0700, Andrew Morton wrote: > > On Fri, 28 Sep 2007 13:00:53 -0400 Trond Myklebust wrote: > > > Do these patches also cause the memory reclaimers to steer clear of > > > devices that are congested (and stop waiting on a congested device if > > > they see that it remains congested for a long period of time)? Most of > > > the collateral blocking I see tends to happen in memory allocation... > > > > > > > No, they don't attempt to do that, but I suspect they put in place > > infrastructure which could be used to improve direct-reclaimer latency. In > > the throttle_vm_writeout() path, at least. > > > > Do you know where the stalls are occurring? throttle_vm_writeout(), or via > > direct calls to congestion_wait() from page_alloc.c and vmscan.c? (running > > sysrq-w five or ten times will probably be enough to determine this) > > Looking back, they were getting caught up in > balance_dirty_pages_ratelimited() and friends. See the attached > example... that one is nfs-on-loopback, which is a special case, isn't it? NFS on loopback used to hang, but then we fixed it. It looks like we broke it again sometime in the intervening four years or so. ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2005. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs