From mboxrd@z Thu Jan  1 00:00:00 1970
From: Junichi Nomura <j-nomura@ce.jp.nec.com>
Subject: Re: [PATCH for-4.2 2/3] block,
 dm: don't copy bios for request clones
Date: Mon, 1 Jun 2015 01:14:26 +0000
Message-ID: <556BB1F1.4030404@ce.jp.nec.com>
References: <1432300445-9543-1-git-send-email-snitzer@redhat.com>
	<1432300445-9543-2-git-send-email-snitzer@redhat.com>
	<556410BB.3000103@ce.jp.nec.com> <20150527082157.GA25993@lst.de>
	<5565935A.4060408@ce.jp.nec.com> <5566B7E5.1070101@ce.jp.nec.com>
	<20150529165451.GA2682@lst.de>
Reply-To: device-mapper development <dm-devel@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <dm-devel-bounces@redhat.com>
In-Reply-To: <20150529165451.GA2682@lst.de>
Content-Language: ja-JP
Content-ID: <DE03550C4CA6CC4DB70FC9321E27D8A9@gisp.nec.co.jp>
List-Unsubscribe: <https://www.redhat.com/mailman/options/dm-devel>,
	<mailto:dm-devel-request@redhat.com?subject=unsubscribe>
List-Archive: <https://www.redhat.com/archives/dm-devel>
List-Post: <mailto:dm-devel@redhat.com>
List-Help: <mailto:dm-devel-request@redhat.com?subject=help>
List-Subscribe: <https://www.redhat.com/mailman/listinfo/dm-devel>,
	<mailto:dm-devel-request@redhat.com?subject=subscribe>
Sender: dm-devel-bounces@redhat.com
Errors-To: dm-devel-bounces@redhat.com
To: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>, device-mapper development <dm-devel@redhat.com>, Mike Snitzer <snitzer@redhat.com>
List-Id: dm-devel.ids

On 05/30/15 01:54, Christoph Hellwig wrote:
> On Thu, May 28, 2015 at 06:38:29AM +0000, Junichi Nomura wrote:
>> I'm also worried about partial completion case.
>> For successful partial completion, current code completes
>> bio before fully completing the request.
>> Your patch changes bios not completed until the request is
>> fully completed.
> 
> Yes.  Why are you worried about this case?

See below.

>> I'm not very sure how much impact does the removal of partial
>> completion have in the real world.
>> If partial completion is so negligible, I think it should be
>> handled in such a way all the cases, instead of special casing
>> REQ_CLONE.
> 
> It isn't negligible - under load it actually does matter that
> we handle partial completions as arrays decide to just complete
> a request partially, so if we don't handle them we might end
> up in a loop not making progress.

OK.

> But if we only do that once on
> path fail over it's not an actual issue.

But with your patch, the fail over happens after full completion
of the request. Is it ok?

-- 
Jun'ichi Nomura, NEC Corporation