From: Andi Kleen <andi@firstfloor.org>
To: Andre Przywara <andre.przywara@amd.com>
Cc: Avi Kivity <avi@redhat.com>, kvm@vger.kernel.org
Subject: Re: [PATCH 0/3] KVM-userspace: add NUMA support for guests
Date: Fri, 28 Nov 2008 09:14:29 +0100 [thread overview]
Message-ID: <87fxlcxo62.fsf@basil.nowhere.org> (raw)
In-Reply-To: <492F1DD9.8030901@amd.com> (Andre Przywara's message of "Thu, 27 Nov 2008 23:23:21 +0100")
Andre Przywara <andre.przywara@amd.com> writes:
> It also improves the one node case by pinning a guest to this node and
> avoiding access of remote memory from one VCPU.
It depends -- it's not necessarily an improvement. e.g. if it leads to
some CPUs being idle while others are oversubscribed because of the
pinning you typically lose more than you win. In general default
pinning is a bad idea in my experience.
Alternative more flexible strategies:
- Do a mapping from CPU to node at runtime by using getcpu()
- Migrate to complete nodes using migrate_pages when qemu detects
node migration on the host.
-Andi
--
ak@linux.intel.com
next prev parent reply other threads:[~2008-11-28 8:14 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-11-27 22:23 [PATCH 0/3] KVM-userspace: add NUMA support for guests Andre Przywara
2008-11-28 8:14 ` Andi Kleen [this message]
2008-11-29 18:43 ` Avi Kivity
2008-11-29 20:10 ` Andi Kleen
2008-11-29 20:35 ` Avi Kivity
2008-11-30 15:41 ` Andi Kleen
2008-11-30 15:38 ` Avi Kivity
2008-11-30 16:05 ` Andi Kleen
2008-11-30 16:38 ` Avi Kivity
2008-11-30 17:04 ` Andi Kleen
2008-11-30 17:11 ` Avi Kivity
2008-11-30 17:42 ` Andi Kleen
2008-11-30 18:07 ` Avi Kivity
2008-11-30 18:55 ` Andi Kleen
2008-11-30 19:11 ` Skywing
2008-11-30 20:08 ` Avi Kivity
2008-11-30 20:07 ` Avi Kivity
2008-11-30 21:41 ` Andi Kleen
2008-11-30 21:50 ` Avi Kivity
2008-11-30 22:08 ` Skywing
2008-11-28 10:40 ` Daniel P. Berrange
2008-11-29 18:29 ` Avi Kivity
2008-12-01 14:15 ` Andre Przywara
2008-12-01 14:29 ` Avi Kivity
2008-12-01 15:27 ` Anthony Liguori
2008-12-01 15:34 ` Anthony Liguori
2008-12-01 15:37 ` Avi Kivity
2008-12-01 15:49 ` Anthony Liguori
2008-12-01 14:44 ` Daniel P. Berrange
2008-12-01 14:53 ` Avi Kivity
2008-12-01 15:18 ` Anthony Liguori
2008-12-01 15:35 ` Avi Kivity
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=87fxlcxo62.fsf@basil.nowhere.org \
--to=andi@firstfloor.org \
--cc=andre.przywara@amd.com \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
/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