On Fri, 30 Apr 1999, Rudy Moore wrote:
> The problem with that approach is that it won't give you an accurate
> result. By changing the size and instructions in the spinlock code
> you're changing how it behaves... So you'll get profiling data on
> something that you're not really interested in.
maybe true. i coded up something based on yesterday's post, and found it
increased overall system performance (although system CPU time was also
somewhat greater). clearly a different kernel.
but this suggests that perhaps the current spinlock implementation is
*too* fast -- if locks took a little longer to check, perhaps the
checker would find a free lock a higher percentage of the time.
> Another idea - still not perfect - would be to check system time before
> you enter the lock and after you exit.
i'll consider about that, but i think the same problem exists -- it will
change the timing picture.
- Chuck Lever
--
corporate: <[EMAIL PROTECTED]>
personal: <[EMAIL PROTECTED]> or <[EMAIL PROTECTED]>
The Linux Scalability project:
http://www.citi.umich.edu/projects/linux-scalability/
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
