Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761897AbZCZXE7 (ORCPT ); Thu, 26 Mar 2009 19:04:59 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752848AbZCZXEr (ORCPT ); Thu, 26 Mar 2009 19:04:47 -0400 Received: from out2.smtp.messagingengine.com ([66.111.4.26]:34067 "EHLO out2.smtp.messagingengine.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761662AbZCZXEp (ORCPT ); Thu, 26 Mar 2009 19:04:45 -0400 Date: Fri, 27 Mar 2009 10:04:35 +1100 From: Bron Gondwana To: Alan Cox Cc: Matthew Garrett , Linus Torvalds , Theodore Tso , Ingo Molnar , Jan Kara , Andrew Morton , Arjan van de Ven , Peter Zijlstra , Nick Piggin , Jens Axboe , David Rees , Jesper Krogh , Linux Kernel Mailing List , Oleg Nesterov , Roland McGrath Subject: Re: ext3 IO latency measurements (was: Linux 2.6.29) Message-ID: <20090326230435.GA10884@brong.net> References: <20090326090630.GA9369@elte.hu> <20090326113705.GV32307@mit.edu> <20090326140312.GB14822@elte.hu> <20090326144707.GA6239@mit.edu> <20090326170714.GF6239@mit.edu> <20090326185900.166a1097@lxorguk.ukuu.org.uk> <20090326200258.GA10313@srcf.ucam.org> <20090326204209.1da6e791@lxorguk.ukuu.org.uk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090326204209.1da6e791@lxorguk.ukuu.org.uk> Organization: brong.net User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1018 Lines: 22 On Thu, Mar 26, 2009 at 08:42:09PM +0000, Alan Cox wrote: > > before performing the update. So while relatime doesn't conform, the > > practical difference is meaningless. You can't depend on atime being > > updated in a timely manner. > > POSIX says a disk write interrupted by a signal can be a short write. If > you do this in practice all hell breaks loose. > > A conforming implementation needs to conform with expectations not just > play lawyer games with users systems. Is this the same Alan Cox who thought a couple of months ago that having an insanely low default maximum number epoll instances was a reasonable answer to a theoretical DoS risk, despite it breaking pretty much every reasonable user of the epoll interface? Bron ( what stable interface? ) -- 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/