public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: dor.laor@qumranet.com
Cc: tglx@linutronix.de,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	kvm-devel <kvm-devel@lists.sourceforge.net>
Subject: Re: Performance overhead of get_cycles_sync
Date: Tue, 11 Dec 2007 14:37:38 +0100	[thread overview]
Message-ID: <20071211133738.GA8150@elte.hu> (raw)
In-Reply-To: <475E8C8B.7070308@qumranet.com>


* Dor Laor <dor.laor@gmail.com> wrote:

> Hi Ingo, Thomas,
>
> In the latest kernel (2.6.24-rc3) I noticed a drastic performance 
> decrease for KVM networking. The reason is many vmexit (exit reason is 
> cpuid instruction) caused by calls to gettimeofday that uses tsc 
> sourceclock. read_tsc calls get_cycles_sync which might call cpuid in 
> order to serialize the cpu.
>
> Can you explain why the cpu needs to be serialized for every gettime 
> call? Do we need to be that accurate? (It will also slightly improve 
> physical hosts). I believe you have a reason and the answer is yes. In 
> that case can you replace the serializing instruction with an 
> instruction that does not trigger vmexit? Maybe use 'ltr' for example?

hm, where exactly does it call CPUID?

	Ingo

  reply	other threads:[~2007-12-11 13:37 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-12-11 13:11 Performance overhead of get_cycles_sync Dor Laor
2007-12-11 13:37 ` Ingo Molnar [this message]
     [not found]   ` <20071211133738.GA8150-X9Un+BFzKDI@public.gmane.org>
2007-12-11 14:11     ` Dor Laor
     [not found]       ` <475E9A92.4030001-atKUWr5tajBWk0Htik3J/w@public.gmane.org>
2007-12-11 14:27         ` Ingo Molnar
     [not found]           ` <20071211142717.GA15903-X9Un+BFzKDI@public.gmane.org>
2007-12-11 15:03             ` Dor Laor
2007-12-11 21:26             ` Joerg Roedel
     [not found]               ` <20071211212628.GB6537-5C7GfCeVMHo@public.gmane.org>
2007-12-12  0:19                 ` Dor Laor
2007-12-11 16:35           ` Arjan van de Ven
     [not found]             ` <20071211083513.56c2a385-NIQFrBLA1CpScpXdPBN83iCwEArCW2h5@public.gmane.org>
2007-12-11 17:03               ` Ingo Molnar
     [not found]                 ` <p73abohno0u.fsf@bingen.suse.de>
     [not found]                   ` <20071211201930.GB22397@elte.hu>
     [not found]                     ` <20071211201930.GB22397-X9Un+BFzKDI@public.gmane.org>
2007-12-11 20:29                       ` Ingo Molnar
2007-12-11 14:14     ` Dor Laor

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=20071211133738.GA8150@elte.hu \
    --to=mingo@elte.hu \
    --cc=dor.laor@qumranet.com \
    --cc=kvm-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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