All of lore.kernel.org
 help / color / mirror / Atom feed
From: Laurent Vivier <Laurent.Vivier@bull.net>
To: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: kvm-devel@lists.sourceforge.net,
	linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [kvm-devel] [PATCH 0/2][KVM] guest time accounting
Date: Mon, 13 Aug 2007 17:36:07 +0200	[thread overview]
Message-ID: <46C07A67.8060107@bull.net> (raw)
In-Reply-To: <200708131722.43936.borntraeger@de.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 1159 bytes --]

Christian Borntraeger wrote:
> Am Montag, 13. August 2007 schrieb Laurent Vivier:
>>>> As guest accounting is hw dependent, I think we should add a hook in the
>>>> accounting functions.
>>>>   
>>> Isn't PF_VM exactly such a hook?  All the hypervisor needs to do is to
>>> set/unset it correctly?
>> In fact, no.
>>
>> PF_VM is used to know we have entered a virtual CPU (the hypervisor set it,
>> the scheduler unset it on accounting)
> 
> Why not do something like the following. (This patch does not work as it 
> relies on the no-existing var cputime_since_last_update, but it shows the 
> idea)

Yes, I think it is a really good idea, much more cleaner.

But doing like that you can have cpustat->system decreasing and thus negative
values in "top".

It is why I modify account_system_time() (see my last patch) to decrease the
value to add to system time accordingly the value we add in cpustat->guest, and
thus system time never decreases. We cannot do that when we call
account_system_time() from KVM part.

Laurent
-- 
------------- Laurent.Vivier@bull.net  --------------
          "Software is hard" - Donald Knuth


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

WARNING: multiple messages have this Message-ID (diff)
From: Laurent Vivier <Laurent.Vivier-6ktuUTfB/bM@public.gmane.org>
To: Christian Borntraeger
	<borntraeger-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>
Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
	linux-kernel
	<linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Re: [PATCH 0/2][KVM] guest time accounting
Date: Mon, 13 Aug 2007 17:36:07 +0200	[thread overview]
Message-ID: <46C07A67.8060107@bull.net> (raw)
In-Reply-To: <200708131722.43936.borntraeger-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>


[-- Attachment #1.1: Type: text/plain, Size: 1179 bytes --]

Christian Borntraeger wrote:
> Am Montag, 13. August 2007 schrieb Laurent Vivier:
>>>> As guest accounting is hw dependent, I think we should add a hook in the
>>>> accounting functions.
>>>>   
>>> Isn't PF_VM exactly such a hook?  All the hypervisor needs to do is to
>>> set/unset it correctly?
>> In fact, no.
>>
>> PF_VM is used to know we have entered a virtual CPU (the hypervisor set it,
>> the scheduler unset it on accounting)
> 
> Why not do something like the following. (This patch does not work as it 
> relies on the no-existing var cputime_since_last_update, but it shows the 
> idea)

Yes, I think it is a really good idea, much more cleaner.

But doing like that you can have cpustat->system decreasing and thus negative
values in "top".

It is why I modify account_system_time() (see my last patch) to decrease the
value to add to system time accordingly the value we add in cpustat->guest, and
thus system time never decreases. We cannot do that when we call
account_system_time() from KVM part.

Laurent
-- 
------------- Laurent.Vivier-6ktuUTfB/bM@public.gmane.org  --------------
          "Software is hard" - Donald Knuth


[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

[-- Attachment #2: Type: text/plain, Size: 315 bytes --]

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >>  http://get.splunk.com/

[-- Attachment #3: Type: text/plain, Size: 186 bytes --]

_______________________________________________
kvm-devel mailing list
kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
https://lists.sourceforge.net/lists/listinfo/kvm-devel

  reply	other threads:[~2007-08-13 16:32 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-08-10 15:58 [PATCH 0/2][KVM] guest time accounting Laurent Vivier
2007-08-13  8:01 ` [kvm-devel] " Avi Kivity
2007-08-13  8:01   ` Avi Kivity
2007-08-13  8:13   ` [kvm-devel] " Laurent Vivier
2007-08-13  8:13     ` Laurent Vivier
2007-08-13  8:38     ` [kvm-devel] " Avi Kivity
2007-08-13  8:38     ` Avi Kivity
2007-08-13  8:38       ` Avi Kivity
2007-08-13 13:08       ` [kvm-devel] " Laurent Vivier
2007-08-13 13:08       ` Laurent Vivier
2007-08-13 13:08         ` Laurent Vivier
2007-08-13 13:22         ` [kvm-devel] " Avi Kivity
2007-08-13 13:22         ` Avi Kivity
2007-08-13 13:22           ` Avi Kivity
2007-08-13 14:15     ` [kvm-devel] " Christian Borntraeger
2007-08-13 14:15     ` Christian Borntraeger
2007-08-13 14:15       ` Christian Borntraeger
2007-08-13 14:19       ` [kvm-devel] " Avi Kivity
2007-08-13 14:19       ` Avi Kivity
2007-08-13 14:19         ` Avi Kivity
2007-08-13 14:26         ` [kvm-devel] " Christian Borntraeger
2007-08-13 14:26         ` Christian Borntraeger
2007-08-13 14:26           ` Christian Borntraeger
2007-08-13 14:37           ` [kvm-devel] " Avi Kivity
2007-08-13 14:37             ` Avi Kivity
2007-08-13 20:40             ` [kvm-devel] " Heiko Carstens
2007-08-13 20:40               ` Heiko Carstens
2007-08-19  9:32               ` List stripping out cc's (was: Re: [kvm-devel] [PATCH 0/2][KVM] guest time accounting) Avi Kivity
2007-08-19  9:32                 ` List stripping out cc's (was: " Avi Kivity
2007-08-19 19:53                 ` List stripping out cc's Jeff Garzik
2007-08-19 19:53                   ` Jeff Garzik
2007-08-19 20:10                   ` Avi Kivity
2007-08-19 20:10                   ` Avi Kivity
2007-08-19 20:10                     ` Avi Kivity
2007-08-19 19:53                 ` Jeff Garzik
2007-08-19  9:32               ` List stripping out cc's (was: Re: [kvm-devel] [PATCH 0/2][KVM] guest time accounting) Avi Kivity
2007-08-13 20:40             ` [kvm-devel] [PATCH 0/2][KVM] guest time accounting Heiko Carstens
2007-08-13 14:37           ` Avi Kivity
2007-08-13  8:13   ` Laurent Vivier
2007-08-13  8:01 ` Avi Kivity
2007-08-13 14:05 ` Christian Borntraeger
2007-08-13 14:05   ` Christian Borntraeger
2007-08-13 14:10   ` [kvm-devel] " Avi Kivity
2007-08-13 14:10     ` Avi Kivity
2007-08-13 14:22     ` [kvm-devel] " Christian Borntraeger
2007-08-13 14:22       ` Christian Borntraeger
2007-08-13 14:22   ` [kvm-devel] " Laurent Vivier
2007-08-13 14:22     ` Laurent Vivier
2007-08-13 14:30     ` [kvm-devel] " Avi Kivity
2007-08-13 14:30       ` Avi Kivity
2007-08-13 14:41       ` [kvm-devel] " Laurent Vivier
2007-08-13 14:41         ` Laurent Vivier
2007-08-13 15:22         ` [kvm-devel] " Christian Borntraeger
2007-08-13 15:22           ` Christian Borntraeger
2007-08-13 15:36           ` Laurent Vivier [this message]
2007-08-13 15:36             ` Laurent Vivier

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=46C07A67.8060107@bull.net \
    --to=laurent.vivier@bull.net \
    --cc=borntraeger@de.ibm.com \
    --cc=kvm-devel@lists.sourceforge.net \
    --cc=linux-kernel@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 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.