From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: with ECARTIS (v1.0.0; list xfs); Mon, 14 May 2007 17:05:45 -0700 (PDT) Received: from larry.melbourne.sgi.com (larry.melbourne.sgi.com [134.14.52.130]) by oss.sgi.com (8.12.10/8.12.10/SuSE Linux 0.7) with SMTP id l4F05efB021310 for ; Mon, 14 May 2007 17:05:41 -0700 Date: Tue, 15 May 2007 10:05:23 +1000 From: David Chinner Subject: Re: Review: Concurrent Multi-File Data Streams Message-ID: <20070515000523.GQ86004887@sgi.com> References: <000001c79544$44076ac0$0501010a@DCHATTERTONLAPTOP> <20070514223946.GA19487@one.firstfloor.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070514223946.GA19487@one.firstfloor.org> Sender: xfs-bounce@oss.sgi.com Errors-to: xfs-bounce@oss.sgi.com List-Id: xfs To: Andi Kleen Cc: David Chatterton , 'xfs-dev' , 'xfs-oss' , 'David Chinner' On Tue, May 15, 2007 at 12:39:46AM +0200, Andi Kleen wrote: > > So yes this is designed for a workload where the number of AGs is a multiple > > of the number of streams since mixing streams in the one AG is the problem > > it tries to avoid. > > Sounds like a awful special case. Is that common? Common enough to be a serious problem when running multiple 2k ingest and playout streams (320MB/s each). Cheers, Dave. -- Dave Chinner Principal Engineer SGI Australian Software Group