From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751134Ab1HDE0y (ORCPT ); Thu, 4 Aug 2011 00:26:54 -0400 Received: from cantor2.suse.de ([195.135.220.15]:42767 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750722Ab1HDE0t (ORCPT ); Thu, 4 Aug 2011 00:26:49 -0400 Date: Thu, 4 Aug 2011 14:26:39 +1000 From: NeilBrown To: Namhyung Kim Cc: linux-raid@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] md: use REQ_NOIDLE flag in md_super_write() Message-ID: <20110804142639.6484de94@notabene.brown> In-Reply-To: <1312387077-26617-1-git-send-email-namhyung@gmail.com> References: <1312387077-26617-1-git-send-email-namhyung@gmail.com> X-Mailer: Claws Mail 3.7.9 (GTK+ 2.22.1; x86_64-unknown-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 On Thu, 4 Aug 2011 00:57:57 +0900 Namhyung Kim wrote: > Queue idling is used for the anticipation of immediate > sequencial I/O's but md_super_write() is a kind of one- > shot operation, coupled with md_super_wait(), so the > idling in this case will be just a waste of time. > > Specifying REQ_NOIDLE prevents it. Instead of adding > the flag to submit_bio() directly, use pre-defined > macro WRITE_FLUSH_FUA. > > Signed-off-by: Namhyung Kim > --- > drivers/md/md.c | 2 +- > 1 files changed, 1 insertions(+), 1 deletions(-) > > diff --git a/drivers/md/md.c b/drivers/md/md.c > index d97a62534798..8650e9a0ce7c 100644 > --- a/drivers/md/md.c > +++ b/drivers/md/md.c > @@ -848,7 +848,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, > bio->bi_end_io = super_written; > > atomic_inc(&mddev->pending_writes); > - submit_bio(REQ_WRITE | REQ_SYNC | REQ_FLUSH | REQ_FUA, bio); > + submit_bio(WRITE_FLUSH_FUA, bio); > } > > void md_super_wait(mddev_t *mddev) Applied, thanks. NeilBrown