Re: Maintaining near constant TPS

On 4 February 2014 06:07, [email protected] <[email protected]> wrote:

> 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..???
>

This might be your problem:

http://grinder.sourceforge.net/g3/garbage-collection.html

Regards,
Gary

------------------------------------------------------------------------------
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

_______________________________________________
grinder-use mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/grinder-use