Re: [PATCH] x86 (64): make calibrate_APIC_clock() smp-safe

From: "H. Peter Anvin" <hpa@zytor.com>
To: Martin Wilck <martin.wilck@fujitsu-siemens.com>
Cc: Thomas Gleixner <tglx@linutronix.de>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"Wichert, Gerhard" <Gerhard.Wichert@fujitsu-siemens.com>
Subject: Re: [PATCH] x86 (64): make calibrate_APIC_clock() smp-safe
Date: Thu, 24 Jul 2008 09:31:48 -0400	[thread overview]
Message-ID: <48888444.1020305@zytor.com> (raw)
In-Reply-To: <48885DDC.9010003@fujitsu-siemens.com>

Martin Wilck wrote:
> Hi Thomas and Peter, hi everyone,
> 
> Asynchrounous events (e.g.SMIs) which occur during the APIC timer 
> calibration can cause timer miscalibrations, sometimes by large amounts.
> 
> This patch fixes this by two separate measures:
>   a) make sure that no significant interruption occurs between APIC and
>      TSC reads
>   b) make sure that the measurement loop isn't significantly longer
>      than originally intended.
> 
> I am sorry, due to a misconfiguration of our SMTP server I need to send 
> the patch as attachment.
> 

The other thing we may want to consider is doing multiple runs of the 
calibration loop.  I suspect we'd get a more accurate result running, 
say, 9 loops of the 1/9 the current duration and looking either for the 
best result or the median (NOT the mean.)

	-hpa