Maintaining near constant TPS

Hello everyone.

I am simulating 1000 users by running 1000 parallel threads using multiple
agents on different remote machines (not all threads are simultaneously
active as there is an initial sleep time and a force sleep between threads).
So, i have some 20 tests running in a particular ratio.

Here is what i am currently seeing. If i give a 10 second sleep time between
each run of the thread, I see that my TPS fluctuates between 0 to 270. Most
of the time my grinder is in sleep mode and suddenly it shoots up to 270
putting extreme load on the server. Is there any way i can control this and
maintain an approximately  170-180 TPS constantly..???

As per my knowledge, this number cannot be controlled as we have no control
over how and when and how the server is processing these. Is there a
solution for this problem or do i just have to deal with it..?





--
View this message in context: http://grinder.996249.n3.nabble.com/Maintaining-near-constant-TPS-tp8754.html
Sent from the Grinder - User mailing list archive at Nabble.com.

------------------------------------------------------------------------------
Managing the Performance of Cloud-Based Applications
Take advantage of what the Cloud has to offer - Avoid Common Pitfalls.
Read the Whitepaper.
http://pubads.g.doubleclick.net/gampad/clk?id=121051231&iu=/4140/ostg.clktrk