Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753874Ab0BXC0L (ORCPT ); Tue, 23 Feb 2010 21:26:11 -0500 Received: from eagle.jhcloos.com ([207.210.242.212]:57840 "EHLO eagle.jhcloos.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753260Ab0BXC0J (ORCPT ); Tue, 23 Feb 2010 21:26:09 -0500 From: James Cloos To: Dave Chinner Cc: Mikael Abrahamsson , linux-kernel@vger.kernel.org, dm-devel@redhat.com Subject: Re: disk/crypto performance regression 2.6.31 -> 2.6.32 (mmap problem?) In-Reply-To: <20100223224111.GC16175@discord.disaster> (Dave Chinner's message of "Wed, 24 Feb 2010 09:41:11 +1100") References: <20100223044818.GD22370@discord.disaster> <20100223133219.GB16175@discord.disaster> <20100223224111.GC16175@discord.disaster> User-Agent: Gnus/5.110011 (No Gnus v0.11) Emacs/23.1.90 (gnu/linux) Face: iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAABHNCSVQICAgIfAhkiAAAAI1J REFUOE+lU9ESgCAIg64P1y+ngUdxhl5H8wFbbM0OmUiEhKkCYaZThXCo6KE5sCbA1DDX3genvO4d eBQgEMaM5qy6uWk4SfBYfdu9jvBN9nSVDOKRtwb+I3epboOsOX5pZbJNsBJFvmQQ05YMfieIBnYX FK2N6dOawd97r/e8RjkTLzmMsiVgrAoEugtviCM3v2WzjgAAAABJRU5ErkJggg== Copyright: Copyright 2009 James Cloos OpenPGP: ED7DAEA6; url=http://jhcloos.com/public_key/0xED7DAEA6.asc OpenPGP-Fingerprint: E9E9 F828 61A4 6EA9 0F2B 63E7 997A 9F17 ED7D AEA6 Date: Tue, 23 Feb 2010 21:25:30 -0500 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 873 Lines: 18 M> You're right, it doesn't say that anymore in 2.6.31, so I think I'm M> indeed running with barriers on. When barriers were added to ext4, I saw a similar slowdown on lock- and sync- heavy workloads. Based on a recent thread on the ext4 list I've started using deadline rather than cfq on that disk. There are some slowdowns on that disk's other partition, but the overall throughput is significantly better than using the combination of cfq, ext4 and barriers. You might want to test out deadline and/or noop. Cf: /sys/block/*/queue/scheduler -JimC -- James Cloos OpenPGP: 1024D/ED7DAEA6 -- 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/