linux-kernel - RE: PROBLEM: zone_reclaim is hanging high priority real time user pthreads

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <980E20D8E719A84BBF593FDE6AEC23DA0AEB4B84E9@ESESSCMS0351.eemea.ericsson.se>
Date:	Wed, 8 Jun 2011 08:53:24 +0200
From:	Bertil Engelholm <bertil.engelholm@...csson.com>
To:	Mel Gorman <mgorman@...e.de>
CC:	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: RE: PROBLEM: zone_reclaim is hanging high priority real time user
 pthreads

Unfortunally the users have now got a problem with zone reclaim disabled.
This time it's a pthread that seems to be stalling for more than 30 seconds !!
We had seen this problem before but I was hoping that disabling zone reclaim
would solve this as well.

I have not had the time to do some trouble shooting yet so I'm kind of hoping
that someone can give some tips what can cause such long stalling. It's not
everything that is stalling, other pthreads that detect this hanging pthread 
are allowed to execute. So the behaviour looks the same as when zone reclaim
hijacked our pthreads. So there seems to be more kernel functions working in 
the same way. The question is what it can be that takes such a long time ?

/Bertil

-----Original Message-----
From: Mel Gorman [mailto:mgorman@...e.de] 
Sent: den 2 juni 2011 13:02
To: Bertil Engelholm
Cc: linux-kernel@...r.kernel.org
Subject: Re: PROBLEM: zone_reclaim is hanging high priority real time user pthreads

On Fri, May 27, 2011 at 01:22:42PM +0200, Bertil Engelholm wrote:
> Thanx for the response. Since a few days back we have tried disabling 
> the zone reclaim and the system behaves much better so that seems to 
> be the short term solution we'll go for.

Good news.

> I also assume that if you have real time pthreads that are sensitive 
> to stalls you might have to disable zone reclaim also in later kernels 
> even though the zone reclaim implementation have been radically improved.
> 

It'd be one possibility. However, I understand that at least one person is considering adding an additional level of watermarks that is dependant on the number of real-time threads in the system and their expected usage. The idea would be that latency sensitive applications would be allowed to use a number of pages between two watermarks were other users would wake kswapd or enter direct reclaim. I don't know where that currently stands though.

Thanks.

--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/