I would like to benchmark a powerfull webcluster with autobench. The problem is that autobench (which uses httperf) can only use one core, thus limiting the amount of load that a client can put on the web cluster. One core is definatly not enough to saturate a cluster of multiple servers.
autobench ships with autobenchd, which can be run on many clients, to make a "client cluster". My problem is I don't have many clients, but only one powerfull multicore client. I tried to run multiple instances of autobenchd on my client, but then autobench_admin only connects to one of these instances.
I could of course use virtualisation to make multiple virtual clients on my physcial server, but that would waste performance and also take more time to set up. Is there a way to make autobench take advantage of a multicore machine?
