From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754078Ab2AaLIF (ORCPT ); Tue, 31 Jan 2012 06:08:05 -0500 Received: from mga03.intel.com ([143.182.124.21]:49771 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753991Ab2AaLID (ORCPT ); Tue, 31 Jan 2012 06:08:03 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.71,315,1320652800"; d="scan'208";a="101482299" Date: Tue, 31 Jan 2012 18:57:54 +0800 From: Wu Fengguang To: Christoph Hellwig Cc: Shaohua Li , lkml , linux-mm , Andrew Morton , Jens Axboe , Herbert Poetzl , Eric Dumazet , Vivek Goyal Subject: Re: [PATCH] fix readahead pipeline break caused by block plug Message-ID: <20120131105754.GA3867@localhost> References: <1327996780.21268.42.camel@sli10-conroe> <20120131103416.GA1661@localhost> <20120131104621.GA27003@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20120131104621.GA27003@infradead.org> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jan 31, 2012 at 05:46:21AM -0500, Christoph Hellwig wrote: > On Tue, Jan 31, 2012 at 06:34:16PM +0800, Wu Fengguang wrote: > > } > > > > + blk_start_plug(&plug); > > written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs); > > + blk_finish_plug(&plug); > > Please move the plugging into ->direct_IO for both read and write, as > that is the boundary between generic highlevel code, and low-level block > code that should know about plugs. The problem is, there are a dozen of ->direct_IO callback functions. While there are only two ->direct_IO() callers, one for READ and another for WRITE, which are much easier to deal with. Thanks, Fengguang