cowloop technology

Kris Kennaway kkenn at xor.obsecurity.org
Fri Jan 20 14:36:38 PST 2006


On 2006-01-20, talon at xxxxxxxxxxxxxxxx <talon at xxxxxxxxxxxxxxxx> wrote:
> Kris Kennaway wrote:
>
>
>> 
>> Well, I asked because I *have* measured and found no measurable
>> performance lost in real-world scenarios.  Can you be more specific
>> about the reference you are thinking of?
>
> I have measured also, and i cannot agree with you in general. I have
> an Athlon machine, single processor on which FreeBSD-6 works very well,
> and i cannot see any performance difference with FreeBSD-4, and i have 
> a P4 machine, hyperthreaded ,in which disk operations are rather slow
> (yes i know enabling hyperthreading is dumb). Since it is well known that 
> lock operations are cheaper on Athlon than P4, i am not much surprised but
> there are machines on which FreeBSD-6 is definitely slower. This being said,
> i like so much the added functionalities in FreeBSD-6 that i don't care.

That sounds like general P4 architectural crappiness affecting many
parts of the system, not overhead coming from GEOM.  Or it's some
other problems specific to that machine, e.g. slow disk hardware or a
driver problem.

Kris





More information about the Kernel mailing list