From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751986Ab0BNWCo (ORCPT ); Sun, 14 Feb 2010 17:02:44 -0500 Received: from bld-mail14.adl6.internode.on.net ([150.101.137.99]:43710 "EHLO mail.internode.on.net" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751856Ab0BNWCm (ORCPT ); Sun, 14 Feb 2010 17:02:42 -0500 Date: Mon, 15 Feb 2010 09:02:29 +1100 From: Dave Chinner To: Christoph Hellwig Cc: Justin Piszcz , linux-kernel@vger.kernel.org, linux-raid@vger.kernl.org, xfs@oss.sgi.com, Alan Piszcz Subject: Re: 2.6.32.3 x86_64 - XFS hangs, all I/O to D-state bug (again) Message-ID: <20100214220229.GB28392@discord.disaster> References: <20100211145123.GA13114@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100211145123.GA13114@infradead.org> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Feb 11, 2010 at 09:51:23AM -0500, Christoph Hellwig wrote: > Can you check if this still happens with the patch below? > > > Index: linux-2.6/fs/xfs/linux-2.6/xfs_buf.c > =================================================================== > --- linux-2.6.orig/fs/xfs/linux-2.6/xfs_buf.c 2010-02-11 15:47:49.677253958 +0100 > +++ linux-2.6/fs/xfs/linux-2.6/xfs_buf.c 2010-02-11 15:48:03.630005040 +0100 > @@ -1158,8 +1158,7 @@ _xfs_buf_ioapply( > bp->b_flags &= ~_XBF_RUN_QUEUES; > rw = (bp->b_flags & XBF_WRITE) ? WRITE_META : READ_META; > } else { > - rw = (bp->b_flags & XBF_WRITE) ? WRITE : > - (bp->b_flags & XBF_READ_AHEAD) ? READA : READ; > + rw = (bp->b_flags & XBF_WRITE) ? WRITE : READ; > } We don't ever issue readahead on the AGF buffers, so I'm not sure this will fix the hang. More often than not a hang like this is caused by a write IO completion not occurring.... Cheers, Dave. -- Dave Chinner david@fromorbit.com