jmeter-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Jordi Salvat i Alabart <>
Subject Re: threadgroups etc
Date Wed, 03 Dec 2003 15:56:35 GMT
You're right in that the throughput should generally increase as you add 
threads -- unless you're really saturating some resource.

However, 2 threadgroups with N threads and 1 sampler will usually 
generate more throughput than 1 threadgroup with N threads and 2 
samplers. To be equivalent, the 2nd case should be 1 threadgroup with 
2*N threads and 2 samplers. In fact, the number of samplers does not 
matter at all, if you think about it. Only the number of concurrent 
threads matters.



En/na Jorg Heymans ha escrit:
> Hi,
> How come i get more throughput on my application when i create two 
> identical threadgroups (with one sampler), then when I create one 
> threadgroup with two identical samplers?
> Adding more threads to a threadgroup means lower throughput, although 
> the CPU's are not maxed out. Adding another identical threadgroup means 
> a higher throughput.
> If threads in a threadgroup simulate concurrent users, what effect have 
> identical threadgroups then?
> How can i make sense of all this?
> Thanks
> JOrg
> ---------------------------------------------------------------------
> To unsubscribe, e-mail:
> For additional commands, e-mail:

To unsubscribe, e-mail:
For additional commands, e-mail:

View raw message