linux-kernel - Re: Over-eager swapping

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

Message-ID: <4F95F553.5030301@kernel.org>
Date:	Tue, 24 Apr 2012 09:35:31 +0900
From:	Minchan Kim <minchan@...nel.org>
To:	Richard Davies <richard@...chsys.com>
CC:	linux-kernel@...r.kernel.org, linux-mm@...ck.org,
	Minchan Kim <minchan.kim@...il.com>,
	Wu Fengguang <fengguang.wu@...el.com>,
	Balbir Singh <balbir@...ux.vnet.ibm.com>,
	Christoph Lameter <cl@...ux-foundation.org>,
	Lee Schermerhorn <lee.schermerhorn@...com>,
	Chris Webb <chris@...chsys.com>
Subject: Re: Over-eager swapping

On 04/23/2012 06:27 PM, Richard Davies wrote:

> We run a number of relatively large x86-64 hosts with twenty or so qemu-kvm
> virtual machines on each of them, and I'm have some trouble with over-eager
> swapping on some of the machines. This is resulting in load spikes during the
> swapping and customer reports of very poor response latency from the virtual
> machines which have been swapped out, despite the hosts apparently having
> large amounts of free memory, and running fine if swap is turned off.
> 
> 
> All of the hosts are currently running a 3.1.4 or 3.2.2 kernel and have ksm
> enabled with 64GB of RAM and 2x eight-core AMD Opteron 6128 processors.
> However, we have seen this same problem since 2010 on a 2.6.32.7 kernel and
> older hardware - see http://marc.info/?l=linux-mm&m=128075337008943
> (previous helpful contributors cc:ed here - thanks).
> 
> We have /proc/sys/vm/swappiness set to 0. The kernel config is here:
> http://users.org.uk/config-3.1.4


Although you set swappiness to 0, kernel can swap out anon pages in
current implementation. I think it's a severe problem.

Couldn't this patch help you?
http://permalink.gmane.org/gmane.linux.kernel.mm/74824
It can prevent anon pages's swap out until few page cache remain.

-- 
Kind regards,
Minchan Kim
--
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/