> Not only that, they mention that each test was run _twice_ to get an > average score. With hotspot JVMs this is ridiculous, you need to run at > least a dozen or more cycles so that the hotspots are recompiled... This > alone discredits the results in my eyes.
Yes, running a load or performance test by running only two tests makes really no sense with a JVM. On some complex telco systems we notice that a JVM becomes "hot" after many minutes with at least 100 req/s (so running only two tests is REALLY RIDICULOUS) Jérôme -- http://motrech.free.fr/ http://www.frutch.org/
