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 ?!
Thanks, Stefan
One more detail would be that I set the granularity equal to the call rate, but still I'm looking at the global average.
Hi,
Could you please include config and python script?
2016-06-12 12:03 GMT+03:00 Anonim Stefan fanx07@gmail.com:
One more detail would be that I set the granularity equal to the call rate, but still I'm looking at the global average.
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
Hi Konstantin,
This is the config+script I tested with (note: commented while). I tested with OPTIONS SIPp requests.
Thanks, Stefan
On Sun, Jun 12, 2016 at 12:08 PM, Konstantin M. evilzluk@gmail.com wrote:
Hi,
Could you please include config and python script?
2016-06-12 12:03 GMT+03:00 Anonim Stefan fanx07@gmail.com:
One more detail would be that I set the granularity equal to the call rate, but still I'm looking at the global average.
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
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
And the basic SIPp test file.
Stefan
On Sun, Jun 12, 2016 at 10:44 PM, Anonim Stefan fanx07@gmail.com wrote:
Hi Konstantin,
This is the config+script I tested with (note: commented while). I tested with OPTIONS SIPp requests.
Thanks, Stefan
On Sun, Jun 12, 2016 at 12:08 PM, Konstantin M. evilzluk@gmail.com wrote:
Hi,
Could you please include config and python script?
2016-06-12 12:03 GMT+03:00 Anonim Stefan fanx07@gmail.com:
One more detail would be that I set the granularity equal to the call rate, but still I'm looking at the global average.
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
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
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
-
Anonim Stefan -
Daniel-Constantin Mierla -
Konstantin M.