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 13:43:26 -0700 Message-ID: <20070928134326.e3bb63b1.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> <20070928122628.965137f2.akpm@linux-foundation.org> <1191009148.6702.46.camel@heimdal.trondhjem.org> <20070928131012.4a03c53e.akpm@linux-foundation.org> <1191011538.6702.59.camel@heimdal.trondhjem.org> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Cc: nfs@lists.sourceforge.net, linux-pm@lists.linux-foundation.org, chakriin5@gmail.com, linux-kernel@vger.kernel.org, a.p.zijlstra@chello.nl To: Trond Myklebust Return-path: In-Reply-To: <1191011538.6702.59.camel@heimdal.trondhjem.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: linux-pm-bounces@lists.linux-foundation.org Errors-To: linux-pm-bounces@lists.linux-foundation.org List-ID: On Fri, 28 Sep 2007 16:32:18 -0400 Trond Myklebust wrote: > On Fri, 2007-09-28 at 13:10 -0700, Andrew Morton wrote: > > On Fri, 28 Sep 2007 15:52:28 -0400 > > Trond Myklebust wrote: > > > > > On Fri, 2007-09-28 at 12:26 -0700, Andrew Morton wrote: > > > > On Fri, 28 Sep 2007 15:16:11 -0400 Trond Myklebust wrote: > > > > > 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? > > > > > > I'm not sure that the hang that is illustrated here is so special. It is > > > an example of a bog-standard ext3 write, that ends up calling the NFS > > > client, which is hanging. The fact that it happens to be hanging on the > > > nfsd process is more or less irrelevant here: the same thing could > > > happen to any other process in the case where we have an NFS server that > > > is down. > > > > hm, so ext3 got stuck in nfs via __alloc_pages direct reclaim? > > > > We should be able to fix that by marking the backing device as > > write-congested. That'll have small race windows, but it should be a 99.9% > > fix? > > No. The problem would rather appear to be that we're doing > per-backing_dev writeback (if I read sync_sb_inodes() correctly), but > we're measuring variables which are global to the VM. The backing device > that we are selecting may not be writing out any dirty pages, in which > case, we're just spinning in balance_dirty_pages_ratelimited(). OK, so it's unrelated to page reclaim. > Should we therefore perhaps be looking at adding per-backing_dev stats > too? That's what mm-per-device-dirty-threshold.patch and friends are doing. Whether it works adequately is not really known at this time. Unfortunately kernel developers don't test -mm much.