Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752870Ab1ECGhE (ORCPT ); Tue, 3 May 2011 02:37:04 -0400 Received: from ipmail05.adl6.internode.on.net ([150.101.137.143]:13425 "EHLO ipmail05.adl6.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751666Ab1ECGhC (ORCPT ); Tue, 3 May 2011 02:37:02 -0400 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AvsEAAShv015LBza/2dsb2JhbACmDniIcrtlDoVyBJ0z Date: Tue, 3 May 2011 16:36:58 +1000 From: Dave Chinner To: Christian Kujau Cc: Markus Trippelsdorf , LKML , xfs@oss.sgi.com, minchan.kim@gmail.com Subject: Re: 2.6.39-rc4+: oom-killer busy killing tasks Message-ID: <20110503063657.GB9114@dastard> References: <20110428233751.GR12436@dastard> <20110429201701.GA13166@x4.trippels.de> <20110501080149.GD13542@dastard> <20110502121958.GA2978@dastard> <20110503005114.GE2978@dastard> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1924 Lines: 46 On Mon, May 02, 2011 at 09:04:40PM -0700, Christian Kujau wrote: > On Tue, 3 May 2011 at 10:51, Dave Chinner wrote: > > Can you run an event trace of all the XFS events during a find for > > me? Don't do it over the entire subset of the filesystem - only > > You mean "event tracing", as in Documentation/trace/events.txt. For > that I will have to enable CONFIG_FTRACE and CONFIG_FUNCTION_TRACER and > probably others, right? > > Looking at http://lwn.net/Articles/341899, I see CONFIG_EVENT_TRACING > and the way to enable event tracing for "all events in fs/xfs" would be: > > echo 1 > /sys/kernel/debug/tracing/events/xfs/enable Download trace-cmd and use that - more efficient and easier to specify the events to record... > > 100,000 inodes is sufficient (i.e. kill the find once the xfs inode > > cache slab reaches 100k inodes. While still running the event trace, > > can you then drop the caches (echo 3 > /proc/sys/vm/drop_caches) and > > check that the xfs inode cache is emptied? If it isn't emptied, drop > > caches again to see if that empties it. If you coul dthen post the > > event trace, I might be able to see what is going strange with the > > shrinker and/or reclaim. > > Will try to do all that. > > I wonder why nobody else is affected by this. Because nobody else runs > powerpc or UP any more? I'm sure other people's filesystems are way bigger > than mine, with much more inodes to cache... XFS on uniprocessor, 32 bit, highmem system is pretty rare. Let alone on an old powerpc platform. It's so far out in left field that I'd expect the only test coverage we get is your laptop.... Cheers, Dave. -- Dave Chinner david@fromorbit.com -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/