From: Avi Kivity <avi@redhat.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: kvm@vger.kernel.org, Mike Galbraith <efault@gmx.de>,
vatsa@linux.vnet.ibm.com, qemu-devel@nongnu.org,
Chris Wright <chrisw@sous-sol.org>,
Anthony Liguori <aliguori@linux.vnet.ibm.com>
Subject: [Qemu-devel] Re: [PATCH] qemu-kvm: response to SIGUSR1 to start/stop a VCPU (v2)
Date: Thu, 02 Dec 2010 11:07:54 +0200 [thread overview]
Message-ID: <4CF761EA.6050200@redhat.com> (raw)
In-Reply-To: <1291230476.32004.1922.camel@laptop>
On 12/01/2010 09:07 PM, Peter Zijlstra wrote:
> >
> > The pause loop exiting& directed yield patches I am working on
> > preserve inter-vcpu fairness by round robining among the vcpus
> > inside one KVM guest.
>
> I don't necessarily think that's enough.
>
> Suppose you've got 4 vcpus, one is holding a lock and 3 are spinning.
> They'll end up all three donating some time to the 4th.
>
> The only way to make that fair again is if due to future contention the
> 4th cpu donates an equal amount of time back to the resp. cpus it got
> time from. Guest lock patterns and host scheduling don't provide this
> guarantee.
>
That is fine. Fairness is pointless if it there's no work to be done
for the other three threads. Just like if you have four processes, one
of which if processing, the others sleeping, cpu is not divided equally.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2010-12-02 9:08 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-23 16:49 [Qemu-devel] [PATCH] qemu-kvm: response to SIGUSR1 to start/stop a VCPU (v2) Anthony Liguori
2010-11-23 19:35 ` Blue Swirl
2010-11-23 21:46 ` Anthony Liguori
2010-11-23 23:43 ` Paolo Bonzini
2010-11-24 1:15 ` Anthony Liguori
2010-11-24 2:08 ` Paolo Bonzini
2010-11-24 8:18 ` [Qemu-devel] " Avi Kivity
2010-11-24 13:58 ` Anthony Liguori
2010-11-24 14:23 ` Avi Kivity
2010-12-01 12:37 ` Srivatsa Vaddagiri
2010-12-01 12:56 ` Avi Kivity
2010-12-01 16:12 ` Srivatsa Vaddagiri
2010-12-01 16:25 ` Peter Zijlstra
2010-12-01 17:17 ` Chris Wright
2010-12-01 17:22 ` Peter Zijlstra
2010-12-01 17:26 ` Rik van Riel
2010-12-01 19:07 ` Peter Zijlstra
2010-12-01 19:24 ` Rik van Riel
2010-12-01 19:35 ` Peter Zijlstra
2010-12-01 19:42 ` Rik van Riel
2010-12-01 19:47 ` Peter Zijlstra
2010-12-02 9:07 ` Avi Kivity [this message]
2010-12-01 17:46 ` Chris Wright
2010-12-01 17:29 ` Srivatsa Vaddagiri
2010-12-01 17:45 ` Peter Zijlstra
2010-12-01 18:00 ` Srivatsa Vaddagiri
2010-12-01 19:09 ` Peter Zijlstra
2010-12-02 9:17 ` Avi Kivity
2010-12-02 11:47 ` Srivatsa Vaddagiri
2010-12-02 12:22 ` Srivatsa Vaddagiri
2010-12-02 12:41 ` Avi Kivity
2010-12-02 13:13 ` Srivatsa Vaddagiri
2010-12-02 13:49 ` Avi Kivity
2010-12-02 15:27 ` Srivatsa Vaddagiri
2010-12-02 15:28 ` Srivatsa Vaddagiri
2010-12-02 15:33 ` Avi Kivity
2010-12-02 15:44 ` Srivatsa Vaddagiri
2010-12-02 12:19 ` Srivatsa Vaddagiri
2010-12-02 12:42 ` Avi Kivity
2010-12-02 9:14 ` 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=4CF761EA.6050200@redhat.com \
--to=avi@redhat.com \
--cc=a.p.zijlstra@chello.nl \
--cc=aliguori@linux.vnet.ibm.com \
--cc=chrisw@sous-sol.org \
--cc=efault@gmx.de \
--cc=kvm@vger.kernel.org \
--cc=qemu-devel@nongnu.org \
--cc=vatsa@linux.vnet.ibm.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).