From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753905AbZAaIr6 (ORCPT ); Sat, 31 Jan 2009 03:47:58 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751085AbZAaIru (ORCPT ); Sat, 31 Jan 2009 03:47:50 -0500 Received: from brick.kernel.dk ([93.163.65.50]:27208 "EHLO kernel.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750953AbZAaIrt (ORCPT ); Sat, 31 Jan 2009 03:47:49 -0500 Date: Sat, 31 Jan 2009 09:45:58 +0100 From: Jens Axboe To: Lorenzo Allegrucci Cc: linux-kernel@vger.kernel.org Subject: Re: SSD and IO schedulers Message-ID: <20090131084558.GV30821@kernel.dk> References: <4dcf7d360901301355l7ed26a5aob7ef6d79d9607b6b@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4dcf7d360901301355l7ed26a5aob7ef6d79d9607b6b@mail.gmail.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Jan 30 2009, Lorenzo Allegrucci wrote: > Hi, I was wondering how IO schedulers such as as-iosched, deadline and > cfq behave on SSD > (that have virtually no seek time), from a theoretical point of view. > How do they affect > performance on these devices? > I heard that the noop scheduler is often chosen by owners of EeePcs > (with a SSD unit). > They report superior performance by using this (quite simple) scheduler. > Are there any scientific benchmarks around? Just recently the io schedulers started checking for SSD devices, so today it should not matter performance wise (throughput) whether you use CFQ or NOOP on eg the eeepc. The io scheduler is still quite important for providing fair access to the device, especially on the cheaper end of the SSD segment. -- Jens Axboe