Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754762AbZDMFf3 (ORCPT ); Mon, 13 Apr 2009 01:35:29 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754433AbZDMFfU (ORCPT ); Mon, 13 Apr 2009 01:35:20 -0400 Received: from night.yars.free.net ([193.233.48.54]:57039 "EHLO night.yars.free.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754418AbZDMFfT (ORCPT ); Mon, 13 Apr 2009 01:35:19 -0400 X-Greylist: delayed 2417 seconds by postgrey-1.27 at vger.kernel.org; Mon, 13 Apr 2009 01:35:18 EDT Date: Mon, 13 Apr 2009 08:54:52 +0400 From: "Alexander V. Lukyanov" To: Theodore Tso , linux-kernel@vger.kernel.org Subject: Re: 2.6.29.1 vs 2.6.27.21 ext4 performance problem Message-ID: <20090413045452.GA16038@night.netis.ru> References: <20090410151235.GA9690@proxy> <20090410163620.GA14814@mit.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090410163620.GA14814@mit.edu> User-Agent: Mutt/1.5.11 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 753 Lines: 19 On Fri, Apr 10, 2009 at 12:36:20PM -0400, Theodore Tso wrote: > Does the differences go away if you do echo 0 into > /sys/fs/ext4//inode_readahead_blks? Yes! Thanks for the tip. I think the problem here is that there are lots of files (2M per file system) and the access is random. > Are you seeing an increase in time, or decrease in transactions per > second, or just that there is is an increase in read rates? Load average goes up from 6 to 30, and request latency increases. -- Alexander.. -- 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/