From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756447AbZDDSNE (ORCPT ); Sat, 4 Apr 2009 14:13:04 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752197AbZDDSMx (ORCPT ); Sat, 4 Apr 2009 14:12:53 -0400 Received: from smtp1.linux-foundation.org ([140.211.169.13]:50752 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751291AbZDDSMw (ORCPT ); Sat, 4 Apr 2009 14:12:52 -0400 Date: Sat, 4 Apr 2009 11:10:03 -0700 (PDT) From: Linus Torvalds X-X-Sender: torvalds@localhost.localdomain To: Jens Axboe cc: Theodore Tso , Linux Kernel Developers List , Ext4 Developers List Subject: Re: [GIT PULL] Ext3 latency fixes In-Reply-To: <20090404180108.GH5178@kernel.dk> Message-ID: References: <1238742067-30814-1-git-send-email-tytso@mit.edu> <20090404135719.GA9812@mit.edu> <20090404151649.GE5178@kernel.dk> <20090404173412.GF5178@kernel.dk> <20090404180108.GH5178@kernel.dk> User-Agent: Alpine 2.00 (LFD 1167 2008-08-23) 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 On Sat, 4 Apr 2009, Jens Axboe wrote: > > > Also, I may be odd, but I really do think latency is more important than > > throughput. When my disk has latencies in the sub-milliseconds, I simply > > do not think it is _acceptable_ to have hickups that affect my workload in > > human-visible terms. > > Not everyone has an Intel SSD. The thing is, I know for a fact that the hickups were much worse _before_ I had the Intel SSD. With the SSD, I have to work a lot more to get them. Back when I had regular rotational disks, I definitely did not need to do any 2GB file creation at all. Just standard "yum update" would make my mail reader pause. Yeah, it's just for a short time, but it's very annoying. One second is quite noticeable when I type something, and it doesn't show up on the screen ("What? My Nehalem cannot keep up with my _typing_?"). 2-3 seconds it really feels bad. And by the time it takes 5+ seconds, I start moving my mouse around just to see whether the computer crashed. Linus