Hi, I have a system which has an average response time of 50ms and a standard deviation of 200.
At the moment I run with a target throughput of 60 requests per minute per thread. So that means I'll run into problems when responses go over 1 second because the thread will get "behind" its target. So I guess this means i'm running at quite a high load on each thread? Would that be right? The problem i have is that if i double the number of threads then my arrival rate starts getting into a weird 20 second loop of wildly varying rates, e.g. it jumps up and down by as much as 100 trx/s. So I want to guage how hard to push each thread based on the performance of the system, and then maybe work out how to bring in additional jmeters. I know questions like this are a bit of a how long is a length of string kind of question! But any numbers would help! ( I run headless via the jmeter ant task. ) Thanks, Dan ________________________________________________ Message sent using UebiMiau 2.7.10 --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
