From: Peter Zijlstra <peterz@infradead.org>
To: Glauber Costa <glommer@redhat.com>
Cc: Avi Kivity <avi@redhat.com>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
aliguori@us.ibm.com, Rik van Riel <riel@redhat.com>,
Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>,
Venkatesh Pallipadi <venki@google.com>
Subject: Re: [PATCH v2 4/6] KVM-GST: KVM Steal time registration
Date: Tue, 01 Feb 2011 17:17:10 +0100 [thread overview]
Message-ID: <1296577030.26581.236.camel@laptop> (raw)
In-Reply-To: <1296575618.5081.13.camel@mothafucka.localdomain>
On Tue, 2011-02-01 at 13:53 -0200, Glauber Costa wrote:
>
> And since the granularity of the cpu accounting is too coarse, we end up
> with much more steal time than we should, because things that are less
> than 1 unity of cputime, are often rounded up to 1 unity of cputime.
See, that! is the problem, don't round up like that.
What you can do is: steal_ticks = steal_time_clock() / TICK_NSEC, or
simply keep a steal time delta and every time it overflows
cputime_one_jiffy insert a steal-time tick.
Venki might have created some infrastructure for doing this with the
IRQ_TIME accounting mess, but irqtime_account_process_tick() still gives
me a head-ache.
next prev parent reply other threads:[~2011-02-01 16:16 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-01-28 19:52 [PATCH v2 0/6] KVM Steal time, new submission Glauber Costa
2011-01-28 19:52 ` [PATCH v2 1/6] KVM-HDR: KVM Steal time implementation Glauber Costa
2011-01-29 1:28 ` Rik van Riel
2011-01-28 19:52 ` [PATCH v2 2/6] KVM-HV: " Glauber Costa
2011-01-29 1:46 ` Rik van Riel
2011-01-30 13:13 ` Avi Kivity
2011-02-01 15:48 ` Glauber Costa
2011-02-01 17:09 ` Avi Kivity
2011-02-01 19:58 ` Glauber Costa
2011-02-02 10:09 ` Avi Kivity
2011-01-31 11:07 ` Peter Zijlstra
2011-01-28 19:52 ` [PATCH v2 3/6] KVM-GST: KVM Steal time accounting Glauber Costa
2011-01-29 1:16 ` Jeremy Fitzhardinge
2011-01-29 1:27 ` Glauber Costa
2011-01-29 1:53 ` Rik van Riel
2011-01-30 14:04 ` Avi Kivity
2011-01-30 16:45 ` lidong chen
2011-02-01 15:58 ` Glauber Costa
2011-02-01 15:57 ` Glauber Costa
2011-02-02 10:11 ` Avi Kivity
2011-02-02 10:51 ` Avi Kivity
2011-02-02 11:57 ` Glauber Costa
2011-01-28 19:52 ` [PATCH v2 4/6] KVM-GST: KVM Steal time registration Glauber Costa
2011-01-29 2:16 ` Rik van Riel
2011-01-30 13:16 ` Avi Kivity
2011-02-01 15:53 ` Glauber Costa
2011-02-01 16:17 ` Peter Zijlstra [this message]
2011-02-01 17:00 ` Glauber Costa
2011-02-01 17:44 ` Peter Zijlstra
2011-02-01 20:20 ` Venkatesh Pallipadi
2011-01-31 11:11 ` Peter Zijlstra
2011-01-28 19:52 ` [PATCH v2 5/6] KVM-GST: adjust scheduler cpu power Glauber Costa
2011-01-31 11:25 ` Peter Zijlstra
2011-01-31 11:27 ` Peter Zijlstra
2011-02-01 15:59 ` Glauber Costa
2011-02-01 16:19 ` Peter Zijlstra
2011-02-01 16:22 ` Glauber Costa
2011-02-01 18:59 ` Peter Zijlstra
2011-02-01 19:55 ` Glauber Costa
2011-02-01 20:04 ` Peter Zijlstra
2011-01-28 19:52 ` [PATCH v2 6/6] Describe KVM_MSR_STEAL_TIME Glauber Costa
2011-01-30 13:19 ` Avi Kivity
2011-02-01 15:54 ` Glauber Costa
2011-02-02 10:14 ` 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=1296577030.26581.236.camel@laptop \
--to=peterz@infradead.org \
--cc=aliguori@us.ibm.com \
--cc=avi@redhat.com \
--cc=glommer@redhat.com \
--cc=jeremy.fitzhardinge@citrix.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=riel@redhat.com \
--cc=venki@google.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