Socket recv behaviour in real-time context
Socket recv behaviour in real-time context
- Subject: Socket recv behaviour in real-time context
- From: Stéphane Letz <email@hidden>
- Date: Fri, 13 Mar 2009 18:30:03 +0100
Hi,
We are using UDP sockets to transmit audio in real-time between 2
machines. Basically the "master" machine is synchronized on the audio
interrupt and send/recv audio packets on the "slave" machine. The
"slave" machine is synchronized on incoming packets (that is waiting
for an incoming packet on the socket to start it's audio cycle). The
"slave" machine reception thread is set-up in real-time mode (using
thread_policy_set /THREAD_TIME_CONSTRAINT_POLICY kind of API).
It works quite reliably until we start to load the slave machine (like
starting a big compilation). In this case the RT slave thread does not
"wake up" the the right time, and we have quite big latencies (up to
50 millisecond latency measured on a MacPro Intel 4 cores 10.5.6 when
the audio cycle is supposed to be 5 millisecond). More precisely it
seems the socket recv operation blocks a lot of time.
We configure the socket with SO_SNDBUF/SO_RCVBUF and possibly
SO_RCVTIMEO kind of options. The same code works without problem on
Linux.
Are they special socket options to add in this case on OSX? Is this a
known problem for sockets on OSX?
Thanks.
Stephane Letz
_______________________________________________
Do not post admin requests to the list. They will be ignored.
Coreaudio-api mailing list (email@hidden)
Help/Unsubscribe/Update your Subscription:
This email sent to email@hidden