From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dave Chinner Subject: Re: [PATCH] writeback: Don't wait for completion in writeback_inodes_sb_nr Date: Wed, 29 Jun 2011 10:54:22 +1000 Message-ID: <20110629005422.GQ32466@dastard> References: <1309304616-8657-1-git-send-email-curtw@google.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Al Viro , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org To: Curt Wohlgemuth Return-path: Received: from ipmail05.adl6.internode.on.net ([150.101.137.143]:26059 "EHLO ipmail05.adl6.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753128Ab1F2Ayf (ORCPT ); Tue, 28 Jun 2011 20:54:35 -0400 Content-Disposition: inline In-Reply-To: <1309304616-8657-1-git-send-email-curtw@google.com> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Tue, Jun 28, 2011 at 04:43:35PM -0700, Curt Wohlgemuth wrote: > Contrary to the comment block atop writeback_inodes_sb_nr(), > we *were* calling > > wait_for_completion(&done); > > which should not be done, as this is not called for data > integrity sync. > > Signed-off-by: Curt Wohlgemuth The comment says it does not wait for IO to be -completed-. The function as implemented waits for IO to be *submitted*. This provides the callers with same blocking semantics (i.e. request queue full) as if the caller submitted the IO themselves. The code that uses this function rely on this blocking to delay the next set of operations they do until after IO has been started, so removing the completion will change their behaviour significantly. Cheers, Dave. -- Dave Chinner david@fromorbit.com