Re: Is the TSC timecounter safe on SMP system?

From: Doug White <dwhite_at_gumbysoft.com>
Date: Fri, 13 Aug 2004 10:38:29 -0700 (PDT)
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
Received on Fri Aug 13 2004 - 15:38:30 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:06 UTC