linux-kernel - Re: Automatic page sharing/consolidation

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: <4805F64A.5070800@qumranet.com>
Date:	Wed, 16 Apr 2008 15:51:22 +0300
From:	Izik Eidus <izike@...ranet.com>
To:	Avi Kivity <avi@...ranet.com>
CC:	weigelt@...ux.de, linux kernel list <linux-kernel@...r.kernel.org>,
	kvm-devel <kvm-devel@...ts.sourceforge.net>
Subject: Re: Automatic page sharing/consolidation

Avi Kivity wrote:
> Enrico Weigelt wrote:
>> Hi folks,
>>
>> I'm using dozens of VE's / jails to separate applications
>> (even complete webapps w/ their own httpd) for easier maintenance
>> and better security. But this tends to consume a lot of memory,
>> since code sharing (.so's) cannot take effect here (each jail/VE
>> has it's completely own tree).
>> Now I wonder if it might be possible to let the kernel automatically
>> find out equal pages and map them together.
>> A little compasion showed up that at least 50% of the code could be
>> shared (maybe more with some tuning, and maybe even data). So it's
>> (IMHO) really worth it.
>>
>> Would this be possible ? What had to be done for this ?
>>   
> 
> Izik (copied) is working on this for kvm.  Results so far are very
> encouraging, but currently merged pages are not swappable.
> 
we have module that posted with kernel patchs in the mm list, you can actualy run it and play with it
there were some bugs that we fixed with it, but i am still not sending it, beacuse i change there quite alot of things
in order to get swapping possible for the pages that are shared.
-- 
woof.
--
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/