Date: Thu, 07 Apr 2011 10:58:16 -0700 From: Chuck Swiger <cswiger@mac.com> To: Andriy Gapon <avg@freebsd.org> Cc: FreeBSD current <freebsd-current@FreeBSD.org> Subject: Re: prefer tsc timecounter when it's good Message-ID: <709EE35F-B124-4670-81BD-FBFE6121928B@mac.com> In-Reply-To: <4D9DF086.9020906@FreeBSD.org> References: <4D9DF086.9020906@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi-- On Apr 7, 2011, at 10:12 AM, Andriy Gapon wrote: > what do you think about the following change? > The idea is mark TSC as the best timecounter when it's invariant and synchronized > between cores. > Unfortunately I don't have code to auto-detect the synchronization and keep > relying on the corresponding tunable. I thought about auto-setting it for > single-package configurations, but even that information is currently not trivial > to get out of our mp (i386/amd64) machdep code. In theory, most machines with P-state invariant TSCs should have their counters completely synchronized, even if there are multiple packages: http://software.intel.com/en-us/forums/showthread.php?t=74798 http://www.intel.com/Assets/PDF/manual/253668.pdf ...the exception would be very large machines with multiple mainboards. Regards, -- -Chuck
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?709EE35F-B124-4670-81BD-FBFE6121928B>