Is the TSC timecounter safe on SMP system?

Doug White dwhite at gumbysoft.com
Fri Aug 13 10:38:30 PDT 2004


On Fri, 13 Aug 2004, Andrew Gallatin wrote:

>
> I have a system where the TSC timecounter is quite a bit more accurate
> (or perhaps its just much cheaper) than the ACPI timecounter.  This is a
> single CPU, HTT system running an SMP kernel.
>
> A simple program which calls gettimeofday() in a tight loop, looking
> for the microseconds to change sees ~998,000 microsecond updates/sec
> with kern.timecounter.hardware=TSC, and 28,500 updates/sec with ACPI-safe.
>
> 1) Is it safe to switch to TSC?

If you like your ticks bouncing around; you'll get different values
depending on which CPU you read.

> 2) If yes, would it be safe to switch to TSC if this was a real
>    SMP system with multiple physical cpus?

TSC in a single-package HTT situation would be interesting to research, if
it is shared across the pipelines.

--
Doug White                    |  FreeBSD: The Power to Serve
dwhite at gumbysoft.com          |  www.FreeBSD.org


More information about the freebsd-current mailing list