From: Anthony Liguori <aliguori@linux.vnet.ibm.com>
To: David Pilger <pilger.david@gmail.com>
Cc: xen-devel <xen-devel@lists.xensource.com>,
Ryan Harper <ryanh@us.ibm.com>
Subject: Re: NUMA and SMP
Date: Mon, 15 Jan 2007 11:21:37 -0600 [thread overview]
Message-ID: <45ABB821.4090402@linux.vnet.ibm.com> (raw)
In-Reply-To: <280848580701140355l7ed6a198l21aa3b36fc8bddbd@mail.gmail.com>
David Pilger wrote:
> Hi all,
>
> 1. Does desktop computers, such as intel dual core really benefit from
> NUMA?
No. NUMA standards Non-Uniform Memory Architecture. It's basically a
system where you have nodes (which are essentially independent
computers) that are connected via a high speed bus. Each node has it's
own memory but through the magic of NUMA, every node can access the
other nodes memory as if it's own. Most NUMA systems (if not all) are
very high end servers.
> 2. Does it have a real effect on the performance of Xen?
On a NUMA system, absolutely. If you have a domain running on a
particular node, you want to make sure that it's using memory that's in
it's node if at all possible. Accessing memory on a local node is
considerably faster than access memory on other nodes. Prior to Ryan's
NUMA work, Xen would just blindly allocate memory to a domain without
taking into account memory locality.
> 3. Can't we let the guest OS manage NUMA instead of Xen? what is the
> difference? and why is it implemented in Xen?
If a guest OS spans multiple nodes, then you would want it to be NUMA
aware. However, you always want Xen to, at least, be NUMA aware so that
it allocates memory appropriately.
Regards,
Anthony Liguori
> Thanks,
> David.
next prev parent reply other threads:[~2007-01-15 17:21 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-01-14 11:55 NUMA and SMP David Pilger
2007-01-14 19:00 ` Ryan Harper
2007-01-15 17:21 ` Anthony Liguori [this message]
2007-01-16 10:47 ` Petersson, Mats
2007-01-16 13:55 ` Emmanuel Ackaouy
2007-01-16 14:19 ` Petersson, Mats
2007-01-16 16:13 ` Emmanuel Ackaouy
2007-01-16 16:30 ` Petersson, Mats
2007-03-20 13:10 ` tgh
2007-03-20 13:19 ` Petersson, Mats
2007-03-20 13:49 ` tgh
2007-03-20 15:50 ` Petersson, Mats
2007-03-20 16:45 ` Ryan Harper
2007-03-20 16:47 ` Petersson, Mats
2007-03-20 13:51 ` Daniel Stodden
2007-03-21 1:08 ` tgh
2007-03-21 2:45 ` Daniel Stodden
2007-03-22 1:16 ` tgh
2007-03-22 10:42 ` Daniel Stodden
2007-03-22 12:13 ` tgh
2007-03-22 12:28 ` Daniel Stodden
2007-03-22 13:02 ` Ryan Harper
2007-03-22 14:56 ` Daniel Stodden
2007-03-22 15:12 ` Ryan Harper
2007-03-22 15:38 ` Daniel Stodden
2007-03-22 16:01 ` Ryan Harper
2007-03-22 16:22 ` Daniel Stodden
2007-03-22 17:02 ` Ryan Harper
2007-03-23 5:47 ` tgh
2007-03-23 14:42 ` Ryan Harper
2007-03-23 14:48 ` Petersson, Mats
2007-03-28 1:50 ` tgh
2007-03-28 2:01 ` Ryan Harper
2007-03-28 21:25 ` The context switch overhead comparison between vmexit/vmentry and hypercall Liang Yang
2007-01-16 14:51 ` Re: NUMA and SMP ron minnich
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=45ABB821.4090402@linux.vnet.ibm.com \
--to=aliguori@linux.vnet.ibm.com \
--cc=pilger.david@gmail.com \
--cc=ryanh@us.ibm.com \
--cc=xen-devel@lists.xensource.com \
/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.