Hello all, I'm working on tuning an opensips server. I get this pesky: WARNING:core:utimer_ticker: utimer task <tm-utimer> already scheduled I was trying to get rid of them by playing with the tm timer_partitions parameter and the timer_workers core param. By increasing any of them doesn't increase performance. By increasing both of them, it actually decreases performance. The server is not at limit, the load on the UDP workers is around 50-60 with some spikes. I have around 3500+ cps sipp traffic.
My understanding is that by increasing the number of timer_partitions, we will have more procs walking in parallel over the timer structures. If we have on timer structure, we have one proc walking over it. How is this working for two timer structures? What is the difference between the first and the second timer structure? Should we expect less work for each proc? For now, to reduce the occurrence of the warning log, I increased the timer interval for tm-utimer from 100ms to 200ms. This should be ok as the timer has the TIMER_FLAG_DELAY_ON_DELAY flag set. Thanks, Ovidiu -- VoIP Embedded, Inc. http://www.voipembedded.com _______________________________________________ Users mailing list [email protected] http://lists.opensips.org/cgi-bin/mailman/listinfo/users
