Issac Goldstand wrote: > I've just recieved an OK to do some Benchmarks on a server cluster of > 16+1 (master) dual 450 Mhz machines (master node is dual 650). I plan > on doing benchmarks and comparing perfornance for the following setups, > so far: > > > > Server cluster using httpd process on each individual node and front > end round-robin scheme > > Singe server on master node using MOSIX and high volume of child > processes > > Trying to think of method to test optimal performance on Beowolf type > cluster > > > > I will also try to play around with different Apache-2 setups if I can > figure out how to do so... > > > > If people have any suggestions for other things to test, or ways to test > it, please let me know.
You can try to use Apache::Benchmark which I've started some 1.5 years ago, but have never finished it so it wasn't released yet. But I think it can be quite helpful, at least to start with. You can get it from: http://stason.org/works/modules/Apache-Benchmark-0.01.tar.gz I plan to resume working on this project as a ASF sub-project of httpd-test (like Apache::Test) and eventually release it on CPAN, once I port it to work with HTTP::ApacheBench and mod_perl 2.0's Apache::Test. The problem is that currently the module is written in a way that the client and the server are supposed to be run on the same machine, since the client reconfigures/starts/stops the server. The architecture should be extended to use PVM or some similar framework to be able to start/stop/configure server on a remote machine. _____________________________________________________________________ Stas Bekman JAm_pH -- Just Another mod_perl Hacker http://stason.org/ mod_perl Guide http://perl.apache.org/guide mailto:[EMAIL PROTECTED] http://ticketmaster.com http://apacheweek.com http://singlesheaven.com http://perl.apache.org http://perlmonth.com/
