Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756037AbYAGUXb (ORCPT ); Mon, 7 Jan 2008 15:23:31 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752574AbYAGUXX (ORCPT ); Mon, 7 Jan 2008 15:23:23 -0500 Received: from neuf-infra-smtp-out-sp604007av.neufgp.fr ([84.96.92.120]:34434 "EHLO neuf-infra-smtp-out-sp604007av.neufgp.fr" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752407AbYAGUXX (ORCPT ); Mon, 7 Jan 2008 15:23:23 -0500 Mime-Version: 1.0 (Apple Message framework v753) In-Reply-To: References: Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: =?ISO-8859-1?Q?Guillaume_Laur=E8s?= Subject: Re: PROBLEM: I/O scheduler problem with an 8 SATA disks raid 5 under heavy load ? Date: Mon, 7 Jan 2008 21:22:57 +0100 To: linux-kernel@vger.kernel.org X-Mailer: Apple Mail (2.753) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 858 Lines: 23 Well, I should have tried to answer my own question earlier... but there is still a problem. A quick reading of Wikipedia later, I can tell the following. First, the anticipatory scheduler seems to be the worse choice when dealing with raid arrays. Now, a better choice in my case could be: - the CFQ scheduler for the array in the dom0; - and the NOOP scheduler for the VBDs in the domUs (seems already there by default btw) However even with CFQ/NOOP I keep getting soft resets, only the sata_nv SATA ports, when under load. Any thoughs ? Thanks to all who did not flame me on this one ...;-) GoM -- 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/