From: Avi Kivity <avi@qumranet.com>
To: weigelt@metux.de
Cc: linux kernel list <linux-kernel@vger.kernel.org>,
kvm-devel <kvm-devel@lists.sourceforge.net>,
Izik Eidus <izike@qumranet.com>
Subject: Re: Automatic page sharing/consolidation
Date: Wed, 16 Apr 2008 14:41:29 +0300 [thread overview]
Message-ID: <4805E5E9.4080402@qumranet.com> (raw)
In-Reply-To: <20080416013033.GA3057@nibiru.local>
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.
--
error compiling committee.c: too many arguments to function
WARNING: multiple messages have this Message-ID (diff)
From: Avi Kivity <avi@qumranet.com>
To: weigelt@metux.de
Cc: kvm-devel <kvm-devel@lists.sourceforge.net>,
linux kernel list <linux-kernel@vger.kernel.org>
Subject: Re: Automatic page sharing/consolidation
Date: Wed, 16 Apr 2008 14:41:29 +0300 [thread overview]
Message-ID: <4805E5E9.4080402@qumranet.com> (raw)
In-Reply-To: <20080416013033.GA3057@nibiru.local>
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.
--
error compiling committee.c: too many arguments to function
-------------------------------------------------------------------------
This SF.net email is sponsored by the 2008 JavaOne(SM) Conference
Don't miss this year's exciting event. There's still time to save $100.
Use priority code J8TL2D2.
http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone
next prev parent reply other threads:[~2008-04-16 11:41 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-04-16 1:30 Automatic page sharing/consolidation Enrico Weigelt
2008-04-16 11:41 ` Avi Kivity [this message]
2008-04-16 11:41 ` Avi Kivity
2008-04-16 12:51 ` Izik Eidus
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4805E5E9.4080402@qumranet.com \
--to=avi@qumranet.com \
--cc=izike@qumranet.com \
--cc=kvm-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=weigelt@metux.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.