On Fri, Nov 18, 2011 at 4:38 PM, Jeff Trawick <[email protected]> wrote:
> > > but my fears about the performance of the design seem to be confirmed. > my > > fastest run so far with trunk + this patch, > > > > Requests per second: 7749.66 [#/sec] (mean) > > backing up to the prior state (with the mutex), it would seem trivial > to implement mutex macros that would maintain a rough contention % by > using trylock first when built with some debug flag??? > yeah, that sounds do-able. > now what is bad contention? that depends on the extra CPU usage for > dispatch and latency and xxx??? no idea what that would be; ~1-2%? > it's hard to say for sure. but we know it's bad if we eliminate the contention and throughput or SMP scalability or some other measure of performance improves. we haven't seen that here. Greg
