I have made tests some month ago on a double 1.1 MHz server
having 1200
msgs/sec
(none durable) with one publisher and 5 subscribers (all of them
receiving the 1200 msg/sec). The publisher and subscribers
where running on two other hosts.
The xmlBlaster server had a CPU load of 40% with this scenario.
(The publisher was adjusted to send 1200 msg/sec).
All in all, this doesn't sound too far off my non-durable tests. I'm using
10 publishers and 1 subscriber and I think the single subscriber acts as a
bottleneck. I've also noticed that you use JRockit, which I think is faster
than the standard Sun JVM. I also haven't tuned.