On 12/06/16 10:56, Anonim Stefan wrote: > Hi, > > I am doing some basic benchmarks with Kamailio. I am using a VM with 1 > CPU i7 2,50 GHz and Kamailio with children=1. > > This is what I measure for each request, inside the benchmark block: > - app_python processing (some euclidian distance based on a dlg_var > input) -> same for all requests > - uac_req_send() OPTIONS -> same for all requests > > I am running SIPp tests for 1000 calls with 1,10,50,100,150,200 calls > per second. > > What I see is that the Global average processing time per request > decreases with the increasing rate; I expected it to increase with the > increasing rate. Is there an explanation for this, or am I doing > something wrong ?! I haven't looked at your scripts so far, but it could be the caching done by OS or the python interpreter -- as there is higher rate, the used pages of memory get hit often and not released to swap.
Cheers, Daniel -- Daniel-Constantin Mierla http://www.asipto.com - http://www.kamailio.org http://twitter.com/#!/miconda - http://www.linkedin.com/in/miconda
_______________________________________________ SIP Express Router (SER) and Kamailio (OpenSER) - sr-users mailing list sr-users@lists.sip-router.org http://lists.sip-router.org/cgi-bin/mailman/listinfo/sr-users
