From mboxrd@z Thu Jan  1 00:00:00 1970
From: Tao Ma <tm@tao.ma>
Subject: Re: [Bug 18632] "INFO: task" dpkg "blocked for more than 120 seconds.
Date: Thu, 09 Jun 2011 21:56:48 +0800
Message-ID: <4DF0D120.3010200@tao.ma>
References: <bug-18632-27@https.bugzilla.kernel.org/> <201106082138.p58Lchgj002615@demeter2.kernel.org> <20110608150241.8412a63d.akpm@linux-foundation.org> <20110609033217.GA10741@localhost> <20110609035426.GA12061@localhost> <20110609082718.GA10335@infradead.org> <20110609090906.GA19186@localhost> <20110609110214.GA9017@infradead.org> <20110609121117.GA5768@localhost> <20110609121742.GA29569@infradead.org> <20110609124315.GA8789@localhost>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Cc: Christoph Hellwig <hch@infradead.org>,
	Carlos Alberto Lopez Perez <clopez@igalia.com>,
	Dave Chinner <david@fromorbit.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Jan Kara <jack@suse.cz>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	"bugzilla-daemon@bugzilla.kernel.org"
	<bugzilla-daemon@bugzilla.kernel.org>,
	"daaugusto@gmail.com" <daaugusto@gmail.com>,
	"kernel-bugzilla@cygnusx-1.org" <kernel-bugzilla@cygnusx-1.org>,
	"listposter@gmail.com" <listposter@gmail.com>,
	"justincase@yopmail.com" <justincase@yopmail.com>,
	Jens Axboe <axboe@kernel.dk>, Vivek Goyal <vgoyal@redhat.com>
To: Wu Fengguang <fengguang.wu@intel.com>
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from oproxy8-pub.bluehost.com ([69.89.22.20]:47087 "HELO
	oproxy8-pub.bluehost.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with SMTP id S1757944Ab1FIN5K (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Thu, 9 Jun 2011 09:57:10 -0400
In-Reply-To: <20110609124315.GA8789@localhost>
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

On 06/09/2011 08:43 PM, Wu Fengguang wrote:
>>> It's definitely a problem that cfq delays async writes too much.
>>> However in Carlos's report,
>>>
>>>         https://bugzilla.kernel.org/attachment.cgi?id=61222
>>>
>>> there are no sync(1) or fsync running at all. So it may be indicating
>>> a different problem.
>>
>> If you have a heavy read load we still need to write back timestamps,
>> and it kinda sounds like he's hitting that.  No guarantee that actuall
>> is the cause, though.
> 
> Right, in the other email I do find the reads.
> 
> So Carlos, it's worthwhile to try the deadline scheduler, which will
> at least improve read/write workloads (likely the one you are running)
> that don't involve sync/fsync.
yes, deadline scheduler surely should help in this cases.

Regards,
Tao