DNS Performance Numbers

O. Hartmann ohartman at zedat.fu-berlin.de
Wed Nov 22 14:27:41 UTC 2006

Marcelo Gardini do Amaral wrote:
> On Sat, Nov 18, 2006 at 02:52:33PM +0100, O. Hartmann wrote:
>> These results looks very puzzling to me.
>> As far as I know, multithreading and/or multiprocessors should perform
>> better anyway than a single threaded application within other
>> applications on an UP box. Strange results ...And more strange than this
>> is the result taken from the FBSD 4.11 box! Is there an explanation why
>> FreeBSD performs so bad beyond 4.X and on SMP boxes? Please show me
>> threads ...
> The results were discussed in the following threads:
> http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011748.html
> http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011756.html
> http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011767.html
> http://lists.freebsd.org/pipermail/freebsd-net/2006-September/011771.html
> ...

Thank you very much for the search. To be honest, it looks very 
disappointing to me. At this moment I regret not having more substantle 
opportunities to test, but with the end of this year or with the 
beginning of next year my department starts using Opteron blade systems 
for our research purposes and I may have the chance to test, too (SUN 
X4100 or SUN X1200 M2 are discussed, but I'm not sure).

My hope is still that FreeBSD evolves to be worth being used in science, 
especially for clustering and high performance computing. It seems that 
Linux has made it due its support by many Compiler vendors (Pathscale, 
Intel) and, obviously, its much better network und SMP performance.


More information about the freebsd-performance mailing list