Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753052AbYJBExg (ORCPT ); Thu, 2 Oct 2008 00:53:36 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751012AbYJBEx1 (ORCPT ); Thu, 2 Oct 2008 00:53:27 -0400 Received: from smtp1.linux-foundation.org ([140.211.169.13]:51128 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750811AbYJBEx0 (ORCPT ); Thu, 2 Oct 2008 00:53:26 -0400 Date: Wed, 1 Oct 2008 21:52:39 -0700 From: Andrew Morton To: Chris Mason Cc: linux-kernel , linux-fsdevel Subject: Re: [PATCH] Improve buffered streaming write ordering Message-Id: <20081001215239.ee2ae63f.akpm@linux-foundation.org> In-Reply-To: <1222886451.9158.34.camel@think.oraclecorp.com> References: <1222886451.9158.34.camel@think.oraclecorp.com> X-Mailer: Sylpheed 2.4.8 (GTK+ 2.12.5; x86_64-redhat-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 830 Lines: 17 On Wed, 01 Oct 2008 14:40:51 -0400 Chris Mason wrote: > The patch below changes write_cache_pages to only use writeback_index > when current_is_pdflush(). The basic idea is that pdflush is the only > one who has concurrency control against the bdi, so it is the only one > who can safely use and update writeback_index. Another approach would be to only update mapping->writeback_index if nobody else altered it meanwhile. That being said, I don't really see why we get lots of seekiness when two threads start their writing the file from the same offset. -- 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/