From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932592AbYETOoD (ORCPT ); Tue, 20 May 2008 10:44:03 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1763519AbYETOnu (ORCPT ); Tue, 20 May 2008 10:43:50 -0400 Received: from mail2.shareable.org ([80.68.89.115]:45267 "EHLO mail2.shareable.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760722AbYETOnt (ORCPT ); Tue, 20 May 2008 10:43:49 -0400 Date: Tue, 20 May 2008 15:42:34 +0100 From: Jamie Lokier To: Ric Wheeler Cc: Theodore Tso , Chris Mason , Andrew Morton , Eric Sandeen , linux-ext4@vger.kernel.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org Subject: Re: [PATCH 0/4] (RESEND) ext3[34] barrier changes Message-ID: <20080520144233.GA16676@shareable.org> Mail-Followup-To: Ric Wheeler , Theodore Tso , Chris Mason , Andrew Morton , Eric Sandeen , linux-ext4@vger.kernel.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org References: <482DDA56.6000301@redhat.com> <20080517002030.GA7374@mit.edu> <20080516173552.e88183d9.akpm@linux-foundation.org> <200805172048.34455.chris.mason@oracle.com> <20080518013641.GH16496@mit.edu> <4830420D.4080608@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4830420D.4080608@gmail.com> User-Agent: Mutt/1.5.13 (2006-08-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Ric Wheeler wrote: > I will have to figure out to get this kind of test going without all > of my big EMC toys ;-) Fwiw, you can test correctness by running a nested VM-in-VM guest which simulates disk write cache and flush operations (which flush to the host kernel). I believe recent QEMU/KVM has this as an option. Data written by the innermost guest will reside in the middle kernel's write cache. Disk cache flush commands from the innermost kernel will cause the middle kernel to write dirty sectors to the outer kernel. Killing the outermost host process is roughly equivalent to pulling the plug on a real machine, but faster and without hurting real hardware. This might not tell you much about performance, but you should be able to run a lot of repeatable filesystem barrier tests this way. -- Jamie