2008/9/11 Fabio Margarido <[EMAIL PROTECTED]>: >> Profiling data would be useful, e.g,, there might be somewhere that >> stack spends far too much time which starves the retransmission >> handling. > > Hmm... I believe that if I run my application under Valgrind it won't come > even close to being able to handle the call rate we're using, and the > results will be different. Is there another way to get such data which might > be interesting to you?
I meant compiling the library with profiling options (like gprof ww/ gcc), which would show where the stack will spend its time and if it is really starving something. >> A trace would be excellent, preferrably tcpdump on both hosts running >> sipp and Sofia. > > What I already have is a Wireshark trace obtained from the machine running > SIPp (both SIPp scripts run on the same machine, bound to different network > interfaces), with all the messages from the test. Would that suffice? As far as I'm concerned, wireshark is just a fancy gui for tcpdump. A trace from wireshark would be excellent. > don't know how I can send this to you, however. The total size is about 250 > MB. Any ideas? Upload it somewhere and send me URL? You can send it to gmail, too. -- Pekka.Pessi mail at nokia.com ------------------------------------------------------------------------- This SF.Net email is sponsored by the Moblin Your Move Developer's challenge Build the coolest Linux based applications with Moblin SDK & win great prizes Grand prize is a trip for two to an Open Source event anywhere in the world http://moblin-contest.org/redirect.php?banner_id=100&url=/ _______________________________________________ Sofia-sip-devel mailing list Sofia-sip-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/sofia-sip-devel
