Andrew Pogrebennyk wrote: > On 29.07.2010 17:49, Olle E. Johansson wrote: >> And yes, I have tested the 2.000 channels in a lot of different settings, >> with various boxes and various pieces of test equipment. The 10.000 channels >> test was between two HP servers and we reached a limit on the GB ethernet >> interface, not the CPU. > > 2.000 channels with RTP agrees with my experience too (and I was > monitoring RTP quality on all channels). BTW I came across this link: > http://www.thirdlane.com/forum/10000-channels-on-asterisk-milestone-reached > - were those 10.000 channels running the p2p RTP bridge so asterisk did > not proxy the RTP stream after re-INVITE between endpoints? > I'm just slightly confused by this sentence: "SIP to SIP calls, the p2p > RTP bridge, basically running a media proxy". > fwiw, we have hit the limit with SEMS and G711 conference (including de- and encoding) at 5000 calls on very good servers, but the problems that started there were that UDP traffic got lost when sending (most probably the issue in linux kernel when sending high UDP load Andrei reported some time ago), so you start having packet loss there.
Because mediaproxy 2 is relaying RTP in the kernel (like iptrtpproxy), I believe it could push the limits even more. BR Stefan -- Stefan Sayer VoIP Services Consulting and Development Warschauer Str. 24 10243 Berlin tel:+491621366449 sip:[email protected] email/xmpp:[email protected] _______________________________________________ Users mailing list [email protected] http://lists.opensips.org/cgi-bin/mailman/listinfo/users
