From: Kirill Korotaev <dev@sw.ru>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>,
haveblue@us.ibm.com, linux-kernel@vger.kernel.org,
herbert@13thfloor.at, devel@openvz.org, serue@us.ibm.com,
akpm@osdl.org, sam@vilain.net,
Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>,
Pavel Emelianov <xemul@sw.ru>, Stanislav Protassov <st@sw.ru>
Subject: Re: [RFC] Virtualization steps
Date: Wed, 29 Mar 2006 05:39:00 +0400 [thread overview]
Message-ID: <4429E534.8030206@sw.ru> (raw)
In-Reply-To: <4428FEA5.9020808@yahoo.com.au>
Nick,
>> First of all, what it does which low level virtualization can't:
>> - it allows to run 100 containers on 1GB RAM
>> (it is called containers, VE - Virtual Environments,
>> VPS - Virtual Private Servers).
>> - it has no much overhead (<1-2%), which is unavoidable with hardware
>> virtualization. For example, Xen has >20% overhead on disk I/O.
>
> Are any future hardware solutions likely to improve these problems?
Probably you are aware of VT-i/VT-x technologies and planned virtualized
MMU and I/O MMU from Intel and AMD.
These features should improve the performance somehow, but there is
still a limit for decreasing the overhead, since at least disk, network,
video and such devices should be emulated.
>> OS kernel virtualization
>> ~~~~~~~~~~~~~~~~~~~~~~~~
>
> Is this considered secure enough that multiple untrusted VEs are run
> on production systems?
it is secure enough. What makes it secure? In general:
- virtualization, which makes resources private
- resource control, which makes VE to be limited with its usages
In more technical details virtualization projects make user access (and
capabilities) checks stricter. Moreover, OpenVZ is using "denied by
default" approach to make sure it is secure and VE users are not allowed
something else.
Also, about 2-3 month ago we had a security review of OpenVZ project
made by Solar Designer. So, in general such virtualization approach
should be not less secure than VM-like one. VM core code is bigger and
there is enough chances for bugs there.
> What kind of users want this, who can't use alternatives like real
> VMs?
Many companies, just can't share their names. But in general no
enterprise and hosting companies need to run different OSes on the same
machine. For them it is quite natural to use N machines for Linux and M
for Windows. And since VEs are much more lightweight and easier to work
with, they like it very much.
Just for example, OpenVZ core is running more than 300,000 VEs worldwide.
Thanks,
Kirill
next prev parent reply other threads:[~2006-03-29 1:39 UTC|newest]
Thread overview: 125+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-03-24 17:19 [RFC] Virtualization steps Kirill Korotaev
2006-03-24 17:33 ` Nick Piggin
2006-03-24 19:25 ` Dave Hansen
2006-03-24 19:53 ` Eric W. Biederman
2006-03-28 4:28 ` Bill Davidsen
2006-03-28 5:31 ` Sam Vilain
2006-03-28 6:45 ` [Devel] " Kir Kolyshkin
2006-03-28 21:59 ` Sam Vilain
2006-03-28 22:24 ` Kir Kolyshkin
2006-03-28 23:28 ` Sam Vilain
2006-03-29 9:13 ` Kirill Korotaev
2006-03-29 11:08 ` Sam Vilain
2006-03-29 13:45 ` Herbert Poetzl
2006-03-29 14:47 ` Kirill Korotaev
2006-03-29 17:29 ` Herbert Poetzl
2006-03-29 21:37 ` Sam Vilain
2006-04-12 8:28 ` Kirill Korotaev
2006-04-13 1:05 ` Herbert Poetzl
2006-04-13 6:52 ` Kirill Korotaev
2006-04-13 13:42 ` Herbert Poetzl
2006-04-13 21:33 ` Cedric Le Goater
2006-04-13 22:45 ` Herbert Poetzl
2006-04-14 7:41 ` Kirill Korotaev
2006-04-14 9:56 ` Cedric Le Goater
2006-04-15 19:29 ` Herbert Poetzl
2006-04-13 22:51 ` Kir Kolyshkin
2006-04-14 10:08 ` Cedric Le Goater
2006-04-15 19:31 ` Herbert Poetzl
2006-03-28 8:52 ` Herbert Poetzl
2006-03-28 9:00 ` Nick Piggin
2006-03-28 14:26 ` Herbert Poetzl
2006-03-28 14:44 ` Nick Piggin
2006-03-29 6:05 ` Eric W. Biederman
2006-03-29 6:19 ` Sam Vilain
2006-03-29 18:20 ` Chris Wright
2006-03-29 22:36 ` Sam Vilain
2006-03-29 22:52 ` Chris Wright
2006-03-29 23:01 ` Sam Vilain
2006-03-29 23:13 ` Chris Wright
2006-03-29 23:18 ` Sam Vilain
2006-03-29 23:28 ` Chris Wright
2006-03-30 1:02 ` Eric W. Biederman
2006-03-30 1:36 ` Chris Wright
2006-03-30 1:41 ` David Lang
2006-03-30 2:04 ` Chris Wright
2006-03-30 14:32 ` Serge E. Hallyn
2006-03-30 15:30 ` Herbert Poetzl
2006-03-30 16:43 ` Serge E. Hallyn
2006-03-30 18:00 ` Eric W. Biederman
2006-03-31 13:40 ` Serge E. Hallyn
2006-03-30 16:07 ` Stephen Smalley
2006-03-30 16:15 ` Serge E. Hallyn
2006-03-30 18:55 ` Chris Wright
2006-03-30 18:44 ` Eric W. Biederman
2006-03-30 19:07 ` Chris Wright
2006-03-31 5:36 ` Eric W. Biederman
2006-03-31 5:51 ` Chris Wright
2006-03-31 6:52 ` Eric W. Biederman
2006-03-30 18:53 ` Chris Wright
2006-03-30 2:48 ` Eric W. Biederman
2006-03-30 19:23 ` Chris Wright
2006-03-31 6:00 ` Eric W. Biederman
2006-03-31 14:52 ` Stephen Smalley
2006-03-31 16:39 ` Eric W. Biederman
2006-03-30 13:29 ` Serge E. Hallyn
2006-03-30 13:37 ` Eric W. Biederman
2006-03-30 14:55 ` Serge E. Hallyn
2006-03-30 2:24 ` Sam Vilain
2006-03-30 3:01 ` Eric W. Biederman
2006-03-30 3:26 ` Nick Piggin
2006-03-30 10:30 ` Eric W. Biederman
2006-04-11 10:32 ` Kirill Korotaev
2006-04-11 11:14 ` Nick Piggin
2006-04-11 14:44 ` Kirill Korotaev
2006-03-28 9:00 ` Kirill Korotaev
2006-03-28 14:41 ` Bill Davidsen
2006-03-28 15:03 ` Eric W. Biederman
2006-03-28 17:48 ` Jeff Dike
2006-03-28 23:07 ` Sam Vilain
2006-03-29 20:56 ` Bill Davidsen
2006-03-28 20:29 ` [Devel] " Jun OKAJIMA
2006-03-28 20:50 ` Kir Kolyshkin
2006-03-28 21:38 ` Jun OKAJIMA
2006-03-28 21:51 ` Eric W. Biederman
2006-03-28 23:18 ` Sam Vilain
2006-04-03 16:47 ` Bill Davidsen
2006-04-11 10:38 ` Kirill Korotaev
2006-04-11 16:20 ` Herbert Poetzl
2006-04-11 18:12 ` Kir Kolyshkin
2006-04-12 5:12 ` Andi Kleen
2006-04-12 6:55 ` Kirill Korotaev
2006-04-12 6:53 ` Andi Kleen
2006-04-12 7:51 ` Kirill Korotaev
2006-04-12 17:03 ` Andi Kleen
2006-04-12 17:20 ` Eric W. Biederman
2006-04-13 16:54 ` Alexey Kuznetsov
2006-04-30 13:22 ` Bill Davidsen
2006-04-30 21:34 ` Sam Vilain
2006-05-01 12:27 ` Kirill Korotaev
2006-05-03 20:32 ` Bill Davidsen
2006-03-28 9:02 ` Kirill Korotaev
2006-03-28 9:15 ` Nick Piggin
2006-03-28 15:35 ` Herbert Poetzl
2006-03-28 15:53 ` Nick Piggin
2006-03-28 16:31 ` Eric W. Biederman
2006-03-29 21:37 ` Bill Davidsen
2006-03-28 16:15 ` Eric W. Biederman
2006-03-28 23:04 ` Sam Vilain
2006-03-29 1:39 ` Kirill Korotaev [this message]
2006-03-29 13:47 ` Herbert Poetzl
2006-03-28 15:48 ` [Devel] " Matt Ayres
2006-03-28 16:42 ` Eric W. Biederman
2006-03-28 17:04 ` Matt Ayres
2006-03-29 0:55 ` Kirill Korotaev
2006-03-24 18:36 ` Eric W. Biederman
2006-03-24 21:19 ` Herbert Poetzl
2006-03-27 18:45 ` Eric W. Biederman
2006-03-28 8:51 ` Kirill Korotaev
2006-03-28 12:53 ` Serge E. Hallyn
2006-03-28 22:51 ` Sam Vilain
2006-03-29 20:30 ` Dave Hansen
2006-03-29 20:47 ` Eric W. Biederman
2006-03-29 22:44 ` Sam Vilain
2006-03-30 13:51 ` Kirill Korotaev
2006-03-28 21:58 ` Eric W. Biederman
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=4429E534.8030206@sw.ru \
--to=dev@sw.ru \
--cc=akpm@osdl.org \
--cc=devel@openvz.org \
--cc=ebiederm@xmission.com \
--cc=haveblue@us.ibm.com \
--cc=herbert@13thfloor.at \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
--cc=sam@vilain.net \
--cc=serue@us.ibm.com \
--cc=st@sw.ru \
--cc=xemul@sw.ru \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox