From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756184Ab0HQIZQ (ORCPT ); Tue, 17 Aug 2010 04:25:16 -0400 Received: from casper.infradead.org ([85.118.1.10]:59447 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752411Ab0HQIZO convert rfc822-to-8bit (ORCPT ); Tue, 17 Aug 2010 04:25:14 -0400 Subject: Re: [RFC][PATCH] Per file dirty limit throttling From: Peter Zijlstra To: Nikanth Karthikesan Cc: Wu Fengguang , Bill Davidsen , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Jens Axboe , Andrew Morton , Jan Kara In-Reply-To: <201008171039.23701.knikanth@suse.de> References: <201008160949.51512.knikanth@suse.de> <1281956742.1926.1217.camel@laptop> <201008171039.23701.knikanth@suse.de> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8BIT Date: Tue, 17 Aug 2010 10:24:35 +0200 Message-ID: <1282033475.1926.2093.camel@laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.28.3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2010-08-17 at 10:39 +0530, Nikanth Karthikesan wrote: > Oh, nice. Per-task limit is an elegant solution, which should help during > most of the common cases. > > But I just wonder what happens, when > 1. The dirtier is multiple co-operating processes > 2. Some app like a shell script, that repeatedly calls dd with seek and skip? > People do this for data deduplication, sparse skipping etc.. > 3. The app dies and comes back again. Like a VM that is rebooted, and > continues writing to a disk backed by a file on the host. > > Do you think, in those cases this might still be useful? Those cases do indeed defeat the current per-task-limit, however I think the solution to that is to limit the amount of writeback done by each blocked process. Jan Kara had some good ideas in that department. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail203.messagelabs.com (mail203.messagelabs.com [216.82.254.243]) by kanga.kvack.org (Postfix) with ESMTP id 641C26B01F0 for ; Tue, 17 Aug 2010 04:25:06 -0400 (EDT) Subject: Re: [RFC][PATCH] Per file dirty limit throttling From: Peter Zijlstra In-Reply-To: <201008171039.23701.knikanth@suse.de> References: <201008160949.51512.knikanth@suse.de> <1281956742.1926.1217.camel@laptop> <201008171039.23701.knikanth@suse.de> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Date: Tue, 17 Aug 2010 10:24:35 +0200 Message-ID: <1282033475.1926.2093.camel@laptop> Mime-Version: 1.0 Sender: owner-linux-mm@kvack.org To: Nikanth Karthikesan Cc: Wu Fengguang , Bill Davidsen , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Jens Axboe , Andrew Morton , Jan Kara List-ID: On Tue, 2010-08-17 at 10:39 +0530, Nikanth Karthikesan wrote: > Oh, nice. Per-task limit is an elegant solution, which should help durin= g=20 > most of the common cases. >=20 > But I just wonder what happens, when > 1. The dirtier is multiple co-operating processes > 2. Some app like a shell script, that repeatedly calls dd with seek and s= kip?=20 > People do this for data deduplication, sparse skipping etc.. > 3. The app dies and comes back again. Like a VM that is rebooted, and=20 > continues writing to a disk backed by a file on the host. >=20 > Do you think, in those cases this might still be useful?=20 Those cases do indeed defeat the current per-task-limit, however I think the solution to that is to limit the amount of writeback done by each blocked process. Jan Kara had some good ideas in that department. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org