From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Morton Subject: Re: shrink_dcache_sb scalability problem. Date: Thu, 13 Apr 2006 01:52:57 -0700 Message-ID: <20060413015257.5b9d0972.akpm@osdl.org> References: <20060413082210.GM1484909@melbourne.sgi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org Return-path: Received: from smtp.osdl.org ([65.172.181.4]:20200 "EHLO smtp.osdl.org") by vger.kernel.org with ESMTP id S1751168AbWDMIxM (ORCPT ); Thu, 13 Apr 2006 04:53:12 -0400 To: David Chinner In-Reply-To: <20060413082210.GM1484909@melbourne.sgi.com> Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org David Chinner wrote: > > After recently upgrading a build machine to 2.6.16, we started > seeing 10-50s pauses where the machine would appear to hang. This sounds like the recent thread "Avoid excessive time spend on concurrent slab shrinking" over on linux-mm. Have you read through that? http://marc.theaimsgroup.com/?l=linux-mm&r=1&b=200603&w=2 http://marc.theaimsgroup.com/?l=linux-mm&r=3&b=200604&w=2 It ended up somewaht inconclusive, but it looks like we do have a bit of a problem, but it got exacerbated by an XFS slowness.