From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id pBIKQv1g243538 for ; Sun, 18 Dec 2011 14:26:57 -0600 Received: from bombadil.infradead.org (173-166-109-252-newengland.hfc.comcastbusiness.net [173.166.109.252]) by cuda.sgi.com with ESMTP id HFfaOYoKsxC7qVYH for ; Sun, 18 Dec 2011 12:26:56 -0800 (PST) Date: Sun, 18 Dec 2011 15:26:51 -0500 From: Christoph Hellwig Subject: Re: xfs-trace-ilock-more Message-ID: <20111218202651.GA20799@infradead.org> References: <20111214024040.GA17780@infradead.org> <20111214182750.GH11114@wotan.suse.de> <4EE8F7F0.7070207@suse.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <4EE8F7F0.7070207@suse.com> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: Jeff Mahoney Cc: Mark Fasheh , Christoph Hellwig , xfs@oss.sgi.com On Wed, Dec 14, 2011 at 02:24:32PM -0500, Jeff Mahoney wrote: > That's pretty much the explanation. With heavy reader load, buffered > writes were stalling for 80 ms and sometimes longer. I suspected it > was contention on the ilock and the tracing with that patch > demonstrated a delay there. Since we were chasing a similar issue at > another site, it seemed worthwhile to just keep it around. We're still > tracking down the cause. I'm not sure if more recent kernels have the > same issue as there's been quite a lot of churn. Ok. I was a bit surprised that it was one out of only two XFS updates that went into a recent SLES security errata, and I never heard about it before. _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs