Date: Tue, 11 Dec 2007 14:37:38 +0100
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
Message-ID: <20071211133738.GA8150@elte.hu>
References: <475E8C8B.7070308@qumranet.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <475E8C8B.7070308@qumranet.com>
User-Agent: Mutt/1.5.17 (2007-11-01)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1025
Lines: 25


* 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
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/