[asterisk-users] Asterisk V/s FreeSwitch

[Bryant Zimmerman]

----------------------------------------
 From: "Stefan Schmidt" <sst at sil.at>
Sent: Thursday, February 09, 2012 8:24 AM
To: asterisk-users at lists.digium.com
Subject: Re: [asterisk-users] Asterisk V/s FreeSwitch

just done the test again.

13500 concurrent calls at 1750 cps with open rtp ports but without much
media transportet, only signaling. see attached screenshot.

10000 concurrent calls with media playing musiconhold but i only have a
100mbit connection on this server so i cant do more here.

the version is asterisk 1.8 - unleashed-the-beast which is my own dev
branch which has some important performance backports from 10.

best regards

ps:
also this is the output of sipp:

sipp -m 13500 -r 1750 -sf sipload.xml -mi 213.x.x.x 213.y.y.y:5060
Resolving remote host '213.x.x.x'... Done.
------------------------------ Scenario Screen -------- [1-9]: Change
Screen --
Call-rate(length)     Port   Total-time  Total-calls  Remote-host
1750.0(0 ms)/1.000s   5061      22.76 s        13500  213.x.x.x:5060(UDP)

Call limit reached (-m 13500), 0.685 s period  0 ms scheduler resolution
0 calls (limit 78750)                  Peak was 13500 calls, after 7 s
0 Running, 0 Paused, 3 Woken up
0 out-of-call msg (discarded)
1 open sockets

Messages  Retrans   Timeout
Unexpected-Msg
INVITE ---------->         13500     0
100 <----------         13500     0                   0
180 <----------         0         0                   0
200 <----------         13500     0                   0
ACK ---------->         13500     0
Pause [    15.0s]         13500                         0
BYE ---------->         13500     0         0
200 <----------         13500     0                   0
------------------------------ Test Terminated
--------------------------------

----------------------------- Statistics Screen ------- [1-9]: Change
Screen --
Start Time             | 2012-02-09 12:50:06

Last Reset Time        | 2012-02-09 12:50:28

Current Time           | 2012-02-09 12:50:29

-------------------------+---------------------------+----------------------
----
Counter Name           | Periodic value            | Cumulative value
-------------------------+---------------------------+----------------------
----
Elapsed Time           | 00:00:00:684              | 00:00:22:763

Call Rate              |    0.000 cps              |  593.068 cps

-------------------------+---------------------------+----------------------
----
Incoming call created  |        0                  |        0

OutGoing call created  |        0                  |    13500

Total Call created     |                           |    13500

Current Call           |        0                  |

-------------------------+---------------------------+----------------------
----
Successful call        |     1174                  |    13500

Failed call            |        0                  |        0

-------------------------+---------------------------+----------------------
----
Call Length            | 00:00:15:015              | 00:00:15:011

------------------------------ Test Terminated
--------------------------------

Am 09.02.12 12:57, schrieb Sammy Govind:
> Wow,
> I bet even asterisk developers wouldn't believe so. What have they done 
!.
> No, actually can you tell if server was processing media along with the
> calls as well !?
> 
> I once tested without media and really I had some 1000+ CCs on asterisk
> server on a regular dev machine with choppy audio on an actual call  
while
> still under stress.
> 
> Kindly please confirm your stats.
> 
> Regards,
> Sammy
> 
> On Thu, Feb 9, 2012 at 4:49 PM, Stefan Schmidt <sst at sil.at> wrote:
> 
>> Am 07.02.12 12:38, schrieb virendra bhati:
>>> Hi List,
>>>
>>> Why FreeSwitch can handle more then 1,000CC and asterisk only 25CC ? 
What
>>> technology FreeSwitch is used and asterisk don't. I don't know it's 
the
>>> right or wrong but this question come to my mind...
>>>
>> I had done some load tests with asterisk 10 and my highest results was:
>>
>> 1750 calls per seconds up to
>> 13000 concurrent calls
>>
>> done on a intel xeon with dual six core and hyperthreading (= 24 cores)
>> and 12 GB ram. the sysload was around 2.5 during this test.
>>
>> so i am not impressed by 1000 concurrent calls.
>>
>> best regards
>>
>> stefan
>>
>> --
Stefan

Did you use a published guide to setup your test or would you be willing to 
give some kind of step by step so I could setup a Similar test I would like 
to see how far I can push several of our builds. I really would like to get 
solid numbers on some of my configs. 

Thanks
Bryant

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.digium.com/pipermail/asterisk-users/attachments/20120209/65ade634/attachment.htm>