[Freeswitch-users] RTP delay > 100ms by performance testing with freeswitch as trancoding device SILK to G711a
Anton Kvashenkin
anton.jugatsu at gmail.com
Tue Jul 3 14:28:32 MSD 2012
Can you share please what sysctl params you tweaked?
2012/6/28 Hoexum, Edwin <edwin.hoexum at office.ziggo.nl>
> Gents,****
>
> ** **
>
> I am trying to do some load testing on a freeswitch for transcoding from
> SILK to G711a. The question is: Is the limit for RTP sessions limited
> to CPU power or are there also limits on the freeswitch application and can
> I tune freeswitch to do the job for 1500 sessions or more. ****
>
> ** **
>
> At the moment freeswitch is the best transcoding device for SILK to G711a
> that I know of. Also compared to the big companies who deliver transcoding
> devices. ****
>
> ** **
>
> SETUP:****
>
> ** **
>
> 3 X G7 HP DL 380 with 16 G mem 6 core 12 CPU’s****
>
> ** **
>
> 1 for SIPP UAC (1Gb interface for media and Signaling)****
>
> 1 for Freeswitch (trancoding function SILK to G711a) 1Gb interface for
> media and Signaling****
>
> 1 for SIPP UAS (1Gb interface for media and Signaling)****
>
> ** **
>
> First tuning OS (with help from the wiki and some LINUX sysctl tuning)****
>
> ** **
>
> ** **
>
> SIPP UAC <-> Freeswitch****
>
> ** **
>
> ** **
>
> root at mnd-rc0001-srvot02:~# iperf -c 172.23.125.46 -u -d -b 400m****
>
> ------------------------------------------------------------****
>
> Server listening on UDP port 5001****
>
> Receiving 1470 byte datagrams****
>
> UDP buffer size: 64.0 KByte (default)****
>
> ------------------------------------------------------------****
>
> ------------------------------------------------------------****
>
> Client connecting to 172.23.125.46, UDP port 5001****
>
> Sending 1470 byte datagrams****
>
> UDP buffer size: 64.0 KByte (default)****
>
> ------------------------------------------------------------****
>
> [ 4] local 172.23.125.42 port 46443 connected with 172.23.125.46 port 5001
> ****
>
> [ 3] local 172.23.125.42 port 5001 connected with 172.23.125.46 port 39259
> ****
>
> [ ID] Interval Transfer Bandwidth****
>
> [ 4] 0.0-10.0 sec 483 MBytes 405 Mbits/sec****
>
> [ 4] Sent 344796 datagrams****
>
> [ 3] 0.0-10.0 sec 483 MBytes 406 Mbits/sec 0.001 ms 0/344828
> (0%)****
>
> [ 3] 0.0-10.0 sec 1 datagrams received out-of-order****
>
> [ 4] Server Report:****
>
> [ 4] 0.0-10.0 sec 483 MBytes 405 Mbits/sec 0.004 ms 261/344795
> (0.076%)****
>
> [ 4] 0.0-10.0 sec 1 datagrams received out-of-order****
>
> root at mnd-rc0001-srvot02:~# ****
>
> ** **
>
> ** **
>
> ** **
>
> Linux mnd-rc0001-srvot06 2.6.32-28-vserver #55~ppa1-Ubuntu SMP Fri Feb 4
> 21:25:09 UTC 2011 x86_64 GNU/Linux****
>
> Ubuntu 10.04 LTS****
>
> ** **
>
> Welcome to Ubuntu!****
>
> * Documentation: https://help.ubuntu.com/****
>
> Last login: Thu Jun 21 15:01:35 2012 from 172.21.88.65****
>
> root at mnd-rc0001-srvot06:~# iperf -s -u -i1****
>
> ------------------------------------------------------------****
>
> Server listening on UDP port 5001****
>
> Receiving 1470 byte datagrams****
>
> UDP buffer size: 64.0 KByte (default)****
>
> ------------------------------------------------------------****
>
> ------------------------------------------------------------****
>
> Client connecting to 172.23.125.42, UDP port 5001****
>
> Sending 1470 byte datagrams****
>
> UDP buffer size: 64.0 KByte (default)****
>
> ------------------------------------------------------------****
>
> [ 5] local 172.23.125.46 port 39259 connected with 172.23.125.42 port 5001
> ****
>
> [ 3] local 172.23.125.46 port 5001 connected with 172.23.125.42 port 46443
> ****
>
> [ ID] Interval Transfer Bandwidth****
>
> [ 5] 0.0- 1.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 0.0- 1.0 sec 48.4 MBytes 406 Mbits/sec 0.004 ms 262/34754
> (0.75%)****
>
> [ 5] 1.0- 2.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 1.0- 2.0 sec 48.3 MBytes 405 Mbits/sec 0.005 ms 0/34476 (0%)
> ****
>
> [ 5] 2.0- 3.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 2.0- 3.0 sec 48.3 MBytes 405 Mbits/sec 0.005 ms 0/34480 (0%)
> ****
>
> [ 5] 3.0- 4.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 3.0- 4.0 sec 48.3 MBytes 406 Mbits/sec 0.004 ms 0/34483 (0%)
> ****
>
> [ 5] 4.0- 5.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 4.0- 5.0 sec 48.3 MBytes 406 Mbits/sec 0.005 ms 0/34482 (0%)
> ****
>
> [ 5] 5.0- 6.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 5.0- 6.0 sec 48.3 MBytes 405 Mbits/sec 0.004 ms 0/34474 (0%)
> ****
>
> [ 5] 6.0- 7.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 6.0- 7.0 sec 48.3 MBytes 405 Mbits/sec 0.005 ms 0/34477 (0%)
> ****
>
> [ 5] 7.0- 8.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 7.0- 8.0 sec 48.3 MBytes 405 Mbits/sec 0.004 ms 0/34480 (0%)
> ****
>
> [ 5] 8.0- 9.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 3] 8.0- 9.0 sec 48.3 MBytes 406 Mbits/sec 0.005 ms 0/34482 (0%)
> ****
>
> [ 5] 9.0-10.0 sec 48.3 MBytes 406 Mbits/sec****
>
> [ 5] 0.0-10.0 sec 483 MBytes 406 Mbits/sec****
>
> [ 5] Sent 344829 datagrams****
>
> [ 3] 0.0-10.0 sec 483 MBytes 405 Mbits/sec 0.004 ms 261/344795
> (0.076%)****
>
> [ 3] 0.0-10.0 sec 1 datagrams received out-of-order****
>
> [ 5] Server Report:****
>
> [ 5] 0.0-10.0 sec 483 MBytes 406 Mbits/sec 0.000 ms 0/344828
> (0%)****
>
> [ 5] 0.0-10.0 sec 1 datagrams received out-of-order****
>
> ** **
>
> ** **
>
> UDP traffic looks fine.****
>
> ** **
>
> SIPP (UAC) inject SILK RTP (PCAP ) and send this to Freeswitch. Freeswitch
> send this G711a to the SIPP( UAS).****
>
> ** **
>
> I doing some testing and until 700 sessions it look fine (Packed loss
> <0.1% and delay <40ms)****
>
> ** **
>
> If I do more sessions 10% of packet have no packet loss but delay of more
> the 100ms.****
>
> ** **
>
> ** **
>
> SIPP uac side:****
>
> ** **
>
> ------------------------------ Scenario Screen -------- [1-9]: Change
> Screen --****
>
> Call-rate(length) Port Total-time Total-calls Remote-host****
>
> 50.0(0 ms)/1.000s 5060 230.53 s 2000 172.23.125.12:5060
> (UDP)****
>
> ** **
>
> Call limit reached (-m 2000), 0.000 s period 0 ms scheduler resolution*
> ***
>
> 0 calls (limit 4500) Peak was 2000 calls, after 40 s**
> **
>
> 0 Running, 1654 Paused, 0 Woken up****
>
> 0 dead call msg (discarded) 6459 out-of-call msg
> (discarded) ****
>
> 1 open sockets ** **
>
> ** **
>
> Messages Retrans Timeout
> Unexpected-Msg****
>
> Pause [ 2000ms] 2000 0 **
> **
>
> INVITE ----------> 2000 0 0 **
> **
>
> 100 <---------- 2000 0 0 0 **
> **
>
> 183 <---------- 0 0 0 0 **
> **
>
> 400 <---------- 0 0 0 0 **
> **
>
> 401 <---------- 0 0 0 0 **
> **
>
> 403 <---------- 0 0 0 0 **
> **
>
> 404 <---------- 0 0 0 0 **
> **
>
> 405 <---------- 0 0 0 0 **
> **
>
> 406 <---------- 0 0 0 0 **
> **
>
> 408 <---------- 0 0 0 0 **
> **
>
> 415 <---------- 0 0 0 0 **
> **
>
> 433 <---------- 0 0 0 0 **
> **
>
> 480 <---------- 0 0 0 0 **
> **
>
> 481 <---------- 0 0 0 0 **
> **
>
> 484 <---------- 0 0 0 0 **
> **
>
> 485 <---------- 0 0 0 0 **
> **
>
> 486 <---------- 0 0 0 0 **
> **
>
> 487 <---------- 0 0 0 0 **
> **
>
> 488 <---------- 0 0 0 0 **
> **
>
> 489 <---------- 0 0 0 0 **
> **
>
> 500 <---------- 0 0 0 0 **
> **
>
> 502 <---------- 0 0 0 0 **
> **
>
> 503 <---------- 0 0 0 0 **
> **
>
> 180 <---------- 2000 0 0 0 **
> **
>
> 200 <---------- E-RTD1 2000 0 0 0 **
> **
>
> ACK ----------> 2000 0 **
> **
>
> Pause [ 500ms] 2000 0 **
> **
>
> [ NOP ] ****
>
> BYE <---------- 2000 0 0 0 **
> **
>
> 200 ----------> 2000 0 **
> **
>
> ------------------------------ Test Terminated
> --------------------------------****
>
> ** **
>
> ** **
>
> ----------------------------- Statistics Screen ------- [1-9]: Change
> Screen --****
>
> Start Time | 2012-06-28 20:17:17:312
> 1340907437.312927 ****
>
> Last Reset Time | 2012-06-28 20:21:07:857
> 1340907667.857562 ****
>
> Current Time | 2012-06-28 20:21:07:857
> 1340907667.857769 ****
>
>
> -------------------------+---------------------------+--------------------------
> ****
>
> Counter Name | Periodic value | Cumulative value***
> *
>
>
> -------------------------+---------------------------+--------------------------
> ****
>
> Elapsed Time | 00:00:00:000 |
> 00:03:50:544 ****
>
> Call Rate | 0.000 cps | 8.675
> cps ****
>
>
> -------------------------+---------------------------+--------------------------
> ****
>
> Incoming call created | 0 |
> 0 ****
>
> OutGoing call created | 0 |
> 2000 ****
>
> Total Call created | |
> 2000 ****
>
> Current Call | 0
> | ****
>
> ** **
>
> ** **
>
> ** **
>
> SIPP UAS side:****
>
> ** **
>
> ------------------------------ Scenario Screen -------- [1-9]: Change
> Screen --****
>
> Port Total-time Total-calls Transport****
>
> 5060 65.10 s 2000 UDP****
>
> ** **
>
> 0 new calls during 1.001 s period 1 ms scheduler resolution****
>
> 2000 calls Peak was 2000 calls, after 44 s**
> **
>
> 0 Running, 2002 Paused, 4 Woken up****
>
> 0 dead call msg (discarded) ** **
>
> 3 open sockets ** **
>
> 2021 Total echo RTP pckts 1st stream 5.327 last period RTP rate (kB/s)
> ****
>
> 0 Total echo RTP pckts 2nd stream 0.000 last period RTP rate (kB/s)
> ****
>
> ** **
>
> Messages Retrans Timeout
> Unexpected-Msg****
>
> ----------> INVITE 2000 0 0 0 ***
> *
>
> <---------- 100 2000 0 **
> **
>
> [ 500ms] Pause 2000 0 **
> **
>
> <---------- 180 2000 0 **
> **
>
> <---------- 200 2000 0 0 **
> **
>
> ----------> ACK 2000 0 0 0 **
> **
>
> [ 3:08] Pause 2000 0 **
> **
>
> <---------- BYE 0 0 0 **
> **
>
> ----------> 200 0 0 0 0 **
> **
>
> ------------------------------ Sipp Server Mode
> -------------------------------****
>
> ** **
>
> ** **
>
>
> ##############################################################################
> ****
>
> ** **
>
> MPSTAT –A 5 on freeswitch:****
>
> ** **
>
> ** **
>
> 8:29:50 CPU %usr %nice %sys %iowait %irq %soft %steal
> %guest %idle****
>
> 18:29:55 all 24.84 0.00 25.63 0.00 0.02 7.46
> 0.00 0.00 42.05****
>
> 18:29:55 0 43.52 0.00 26.72 0.00 0.00 4.05 0.00
> 0.00 25.71****
>
> 18:29:55 1 27.88 0.00 39.18 0.00 0.00 3.12
> 0.00 0.00 29.82****
>
> 18:29:55 2 27.70 0.00 33.40 0.00 0.00 4.17
> 0.00 0.00 34.72****
>
> 18:29:55 3 25.57 0.00 35.98 0.00 0.00 3.03
> 0.00 0.00 35.42****
>
> 18:29:55 4 27.36 0.00 27.56 0.00 0.00 2.56
> 0.00 0.00 42.52****
>
> 18:29:55 5 25.45 0.00 24.44 0.00 0.00 2.22
> 0.00 0.00 47.88****
>
> 18:29:55 6 24.77 0.00 31.28 0.00 0.00 2.98
> 0.00 0.00 40.97****
>
> 18:29:55 7 23.05 0.00 23.81 0.00 0.00 2.67
> 0.00 0.00 50.48****
>
> 18:29:55 8 22.22 0.00 23.03 0.00 0.20 2.02
> 0.00 0.00 52.53****
>
> 18:29:55 9 4.84 0.00 5.71 0.00 0.00 62.86
> 0.00 0.00 26.59****
>
> 18:29:55 10 23.36 0.00 17.01 0.00 0.00 2.46
> 0.00 0.00 57.17****
>
> 18:29:55 11 20.21 0.00 15.11 0.00 0.00 2.98
> 0.00 0.00 61.70****
>
> ** **
>
> 18:29:50 CPU intr/s****
>
> 18:29:55 all 30433.80****
>
> 18:29:55 0 0.00****
>
> 18:29:55 1 0.00****
>
> 18:29:55 2 0.00****
>
> 18:29:55 3 0.00****
>
> 18:29:55 4 0.00****
>
> 18:29:55 5 0.00****
>
> 18:29:55 6 0.00****
>
> 18:29:55 7 0.00****
>
> 18:29:55 8 0.00****
>
> 18:29:55 9 0.00****
>
> 18:29:55 10 0.00****
>
> 18:29:55 11 0.00****
>
> ** **
>
> 18:29:50 CPU 0/s 1/s 8/s****
>
> 18:29:55 0 0.00 0.00 0.00****
>
> 18:29:55 1 0.00 0.00 0.00****
>
> 18:29:55 2 0.00 0.00 0.00****
>
> 18:29:55 3 0.00 0.00 0.00****
>
> 18:29:55 4 0.00 0.00 0.00****
>
> 18:29:55 5 0.00 0.00 0.00****
>
> 18:29:55 6 0.00 0.00 0.00****
>
> 18:29:55 7 0.00 0.00 0.00****
>
> 18:29:55 8 0.00 0.00 0.00****
>
> 18:29:55 9 0.00 0.00 0.00****
>
> 18:29:55 10 0.00 0.00 0.00****
>
> 18:29:55 11 0.00 0.00 0.00****
>
> ** **
>
> I tested it with G711a to G711a and got the same result. ****
>
> ** **
>
> I tested also some RTP parameters like ** **
>
> ** **
>
> <param name="rtp-autoflush-during-bridge" value="true"/> or false****
>
> <param name="rtp-autoflush" value="true"/> or false****
>
> ** **
>
> The lot of the module are not activated like CDR stuff.****
>
> ** **
>
> *mvg,*
>
> *Edwin*
>
> ** **
>
> ------------------------------
> This message is confidential and may be privileged. Any review,
> retransmission, dissemination or other use of, taking any action with
> reference to this information by persons other then the intended recipient
> is prohibited. If you receive this message in error, please notify the
> sender by reply e-mail and delete this message from all computers. Please
> note that e-mails are susceptible to change. The sender will not accept
> liability for the improper or incomplete transmission of the information
> contained in this message.
>
> Spaar het milieu door deze e-mail niet te printen/Please consider the
> environment before printing this email.
>
> _________________________________________________________________________
> Professional FreeSWITCH Consulting Services:
> consulting at freeswitch.org
> http://www.freeswitchsolutions.com
>
>
>
>
> Official FreeSWITCH Sites
> http://www.freeswitch.org
> http://wiki.freeswitch.org
> http://www.cluecon.com
>
> Join Us At ClueCon - Aug 7-9, 2012
>
> FreeSWITCH-users mailing list
> FreeSWITCH-users at lists.freeswitch.org
> http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
> UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
> http://www.freeswitch.org
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.freeswitch.org/pipermail/freeswitch-users/attachments/20120703/b1507e3d/attachment-0001.html
Join us at ClueCon 2011 Aug 9-11, 2011
More information about the FreeSWITCH-users
mailing list