xfs
[Top] [All Lists]

Re: xfsaild causing 30+ wakeups/s on an idle system since 2.6.25-rcX

To: David Chinner <dgc@xxxxxxx>
Subject: Re: xfsaild causing 30+ wakeups/s on an idle system since 2.6.25-rcX
From: Török Edwin <edwintorok@xxxxxxxxx>
Date: Mon, 18 Feb 2008 11:41:39 +0200
Cc: Oliver Pinter <oliver.pntr@xxxxxxxxx>, xfs@xxxxxxxxxxx, Linux Kernel <linux-kernel@xxxxxxxxxxxxxxx>, Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>, Christoph Lameter <clameter@xxxxxxx>, Christoph Hellwig <hch@xxxxxxxxxxxxx>
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from:user-agent:mime-version:to:cc:subject:references:in-reply-to:content-type:content-transfer-encoding; bh=VDU7N4IQg4R5KMR+2yPcmZl/2b4e1tiQQBMqE9CEtGg=; b=O7UqJNJZwl2enCeDIVobjavdjwWF/jRLxtagTLBjSO7+afQoo3NCLCx7RWj24idYjG6Md6AV5H1qd3eF4wxDpqM7MVao3GGVwIKo9yJDJroK8Q4OyUT2DA3tNcfdiERs5ZIMD/GLyFyE2qVI4URagfC5u9zzA1obuArKZkIatuE=
Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:user-agent:mime-version:to:cc:subject:references:in-reply-to:content-type:content-transfer-encoding; b=uWlos2atQAGWSqPxBrAq99VL9lPpy3NHPeHvI6MwUWReEWo9ecWjOQrYJsYYroWxXbyO0ZiEB2B+e/WQDP3ZduB9U6aZ3c/Tl7Wn93YU9HFgy3FDb3JsrSKdHC8tDV12o56i71QF6AOFH659HeU/9qmv6cDlexxPLDmNpA0cWb8=
In-reply-to: <20080217224736.GX155407@xxxxxxx>
References: <47B863A9.5070206@xxxxxxxxx> <6101e8c40802170851w73db8130t9bcfdc5cf053f0dc@xxxxxxxxxxxxxx> <20080217224736.GX155407@xxxxxxx>
Sender: xfs-bounce@xxxxxxxxxxx
User-agent: Mozilla-Thunderbird 2.0.0.9 (X11/20080109)
David Chinner wrote:
> On Sun, Feb 17, 2008 at 05:51:08PM +0100, Oliver Pinter wrote:
>   
>> On 2/17/08, Török Edwin <edwintorok@xxxxxxxxx> wrote:
>>     
>>> Hi,
>>>
>>> xfsaild is causing many wakeups, a quick investigation shows
>>> xfsaild_push is always
>>> returning 30 msecs timeout value.
>>>       
>
> That's a bug

Ok. Your patches fixes the 30+ wakeups :)

> , and has nothing to do with power consumption. ;)
>   

I suggest using a sysctl value (such as
/proc/sys/vm/dirty_writeback_centisecs), instead of a hardcoded default
1000.
That would further reduce the wakeups.

>
> I only managed to reproduce this on a lazy superblock counter
> filesystem (i.e.  new mkfs and recent kernel), 

The filesystem was created in July 2007

> Can you see if the patch below fixes the problem.

Yes, it reduces wakeups to 1/sec.

Thanks,
--Edwin


<Prev in Thread] Current Thread [Next in Thread>