Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 28 Oct 2005 22:37:32 +0200
From:      "Poul-Henning Kamp" <phk@phk.freebsd.dk>
To:        John-Mark Gurney <gurney_j@resnet.uoregon.edu>
Cc:        Michael VInce <mv@roq.com>, current@freebsd.org
Subject:   Re: Timers and timing, was: MySQL Performance 6.0rc1 
Message-ID:  <35317.1130531852@critter.freebsd.dk>
In-Reply-To: Your message of "Fri, 28 Oct 2005 13:18:57 PDT." <20051028201857.GQ4115@funkthat.com> 

next in thread | previous in thread | raw e-mail | index | archive | help
In message <20051028201857.GQ4115@funkthat.com>, John-Mark Gurney writes:
>Michael VInce wrote this message on Fri, Oct 28, 2005 at 22:33 +1000:
>> Hey guys, I been watching this thread and I can confirm that MySQL and 
>> the Super-smack benchmark greatly rely on this,
>> I was able to increase performance %600 by changing 
>> kern.timecounter.hardware to dummy.
>
>This is probably because dummy doesn't actually do any real
>timecounting... and that the times that the benchmark took was longer
>then reported by the machine..  dummy just increments a counter, and
>means that the times returned only have a relation to how often/much
>the time "hardware" was queried...

The dummy timecounter is there only to make the kernel survive during
early boot and to push timecounters further down the list of things
one have to deal with when porting FreeBSD to a new achitecture.

But if you _truly_ don't care about time, it's undisputed the fastest
timecounter "hardware" we have :-)

-- 
Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk@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.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?35317.1130531852>