From: Rik van Riel <riel@redhat.com>
To: "Christoffer Dall" <cdall@linaro.org>,
"Radim Krčmář" <rkrcmar@redhat.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>,
Paolo Bonzini <pbonzini@redhat.com>,
kvm@vger.kernel.org, Marc Zyngier <marc.zyngier@arm.com>,
fweisbec@redhat.com
Subject: Re: vtime accounting
Date: Fri, 24 Mar 2017 11:04:38 -0400 [thread overview]
Message-ID: <1490367878.28917.2.camel@redhat.com> (raw)
In-Reply-To: <20170315084303.GJ1277@cbox>
On Wed, 2017-03-15 at 09:43 +0100, Christoffer Dall wrote:
> Yes, I think the key is whether you end up taking a timer interrupt
> before or after switchign PF_VCPU. So you can spend X jiffies in the
> guest, come back, change PF_VCPU (timer still hasen't expired), and
> then
> the timer expires immediately afterwards, and the whole block of
> jiffies
> that are incremented as a result of the timer gets accounted as
> kernel
> time.
>
> (Note that jiffies on clocksourced architectures is an arbitrary
> number,
> which somehow scales according to the clocksource frequency,
> depending
> on the CONFIG_HZ, so a single timer interrupt can increment jiffies
> by
> more than 1.
>
That really should not happen with nohz_full.
The housekeeping CPU should get a timer interrupt
every jiffy, unless something changed recently that
I am not aware of.
Frederic, am I totally off base?
next prev parent reply other threads:[~2017-03-24 15:04 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-08 10:57 vtime accounting Christoffer Dall
2017-03-09 8:16 ` Paolo Bonzini
2017-03-13 17:28 ` Radim Krčmář
2017-03-14 8:26 ` Christoffer Dall
2017-03-14 8:55 ` Marc Zyngier
2017-03-14 11:12 ` Christoffer Dall
2017-03-14 11:46 ` Marc Zyngier
2017-03-14 16:58 ` Radim Krčmář
2017-03-14 17:09 ` Paolo Bonzini
2017-03-14 18:41 ` Christoffer Dall
2017-03-14 19:32 ` Radim Krčmář
2017-03-14 20:01 ` Christoffer Dall
2017-03-14 21:52 ` Radim Krčmář
2017-03-15 8:09 ` Paolo Bonzini
2017-03-15 8:05 ` Paolo Bonzini
2017-03-15 8:30 ` Christoffer Dall
2017-03-14 18:39 ` Christoffer Dall
2017-03-14 20:27 ` Radim Krčmář
2017-03-14 21:53 ` Radim Krčmář
2017-03-15 8:43 ` Christoffer Dall
2017-03-15 15:57 ` Radim Krčmář
2017-03-15 16:48 ` Christoffer Dall
2017-03-15 17:09 ` Radim Krčmář
2017-03-24 15:04 ` Rik van Riel [this message]
2017-03-27 12:29 ` Wanpeng Li
2017-03-24 14:55 ` Rik van Riel
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=1490367878.28917.2.camel@redhat.com \
--to=riel@redhat.com \
--cc=cdall@linaro.org \
--cc=christoffer.dall@linaro.org \
--cc=fweisbec@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=marc.zyngier@arm.com \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.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.