Re: Timers and timing, was: MySQL Performance 6.0rc1

From: Poul-Henning Kamp <phk_at_phk.freebsd.dk>
Date: Fri, 28 Oct 2005 11:43:32 +0200
In message <20051028091016.GC3596_at_garage.freebsd.pl>, Pawel Jakub Dawidek write
s:
>
>--eHhjakXzOLJAF9wJ
>Content-Type: text/plain; charset=iso-8859-2
>Content-Disposition: inline
>Content-Transfer-Encoding: quoted-printable
>
>On Fri, Oct 28, 2005 at 10:47:06AM +0200, Poul-Henning Kamp wrote:
>+> In message <20051028083337.GB3596_at_garage.freebsd.pl>, Pawel Jakub Dawide=
>k write
>+> s:
>+>=20
>+> >Hmm:) On mine t43:
>+> >
>+> >       null function: 0.00403
>+> >            getpid(): 0.30784
>+> >              time(): 1.94495
>+> >      gettimeofday(): 1.94236
>+> >
>+> >Timecounter "i8254" frequency 1193182 Hz quality 0
>+>=20
>+> ...This is not relevant information, because...
>+>=20
>+> >kern.timecounter.hardware: ACPI-fast
>+>=20
>+> You're using the ACPI-fast timecounter.
>
>I thought so:) Is there a way to switch used timecounter or is this choosen
>automatically?

By default the timecounter with the highest score is selected (but
negative scores are never selected automatically).

You can override this with
	sysctl kern.timecounter.hardware=something
where something is one of the timecounters listed in kern.timecounter.choice

-- 
Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk_at_FreeBSD.ORG         | TCP/IP since RFC 956
FreeBSD committer       | BSD since 4.3-tahoe    
Never attribute to malice what can adequately be explained by incompetence.
Received on Fri Oct 28 2005 - 07:43:38 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:46 UTC