On 28 Jun 2001 15:56:06 -0700, Ian Holsman wrote: > damn meetings... the code is 90% there and lives in: > > http://webperf.org/a2/pool/ > > the code is designed to test 'pools' so SMS would have to implement > the pool function names... (for the first pass of the code anyway) > > ..Ian > > (hoping to complete it tomorrow) >
Ok.. the program is now there.. and seems to be working. This should be a good way of comparing SMS and the pool code once the pool->sms code is written.. the sample files being used are from a dump of a 'default-handler' and a include filter. (the include createas about ~34 pools .. compared to the '3' of the flat file no wonder its slow) ..ian > > > > On 28 Jun 2001 08:51:00 -0700, Justin Erenkrantz wrote: > > On Thu, Jun 28, 2001 at 08:28:41AM -0700, Ian Holsman wrote: > > > I'm in the middle of writing a pool-tester > > > which can take a file and pool allocation commands > > > (alloc/create/destroy/etc) > > > and replay them. > > > combine this with some threads, and a capture tool in the current pool > > > code and we should be able to test different pooling algorithms easily. > > > > > > (should be done today) > > > > Yea, please post when you are done! My gut feeling is that threaded APR > > is just awful at pool allocation right now. =) If we use SMS, it'd be > > nice to have some way of knowing whether we are faster than what we > > have now. Baselines (no matter how sucky) are good to have before > > embarking on such a change. I wonder how the SMS stuff will mix with a > > prefork MPM - which never needed locking in the first place. Be worth > > checking out. -- justin >
