At 11:11 AM 8/19/2005, Roland Dreier wrote:
Arlin
Yes, this is certainly another option; albeit one that
Arlin requires more system resources. Why not take
full advantage
Arlin of the FD resource we already have? It's
your call, but
Arlin uDAPL and other multi-thread applications
could make
Roland Dreier wrote:
Arlin the options to wake up this blocking cq_fd and thread are:
Arlin 1. signal the thread with pthread_kill , pthread_cancel
Arlin 2. poll cq_fd with timeout, wakeup periodically and check
Arlin for termination. 3. ibv_close_device () to force interrupt
Arlin Davis wrote:
Yes, this is certainly another option; albeit one that requires more
system resources. Why not take full advantage of the FD resource we
already have? It's your call, but uDAPL and other multi-thread
applications could make good use of a wakeup feature with these event
Arlin Yes, this is certainly another option; albeit one that
Arlin requires more system resources. Why not take full advantage
Arlin of the FD resource we already have? It's your call, but
Arlin uDAPL and other multi-thread applications could make good
Arlin use of a wakeup
Sean I'm leaning more towards Arlin's thinking on this, but
Sean whatever is decided, I think that uCM and uAT should match.
Doesn't this seem like a good argument against adding support for
synthetic events? We already have a perfectly good mechanism for
generating fd events (namely
Roland Dreier wrote:
Sean I'm leaning more towards Arlin's thinking on this, but
Sean whatever is decided, I think that uCM and uAT should match.
Doesn't this seem like a good argument against adding support for
synthetic events? We already have a perfectly good mechanism for
Arlin Hi Roland, I just noticed that when I call
Arlin ibv_close_device() it does not wakeup the poll cq_fd[0] in
Arlin a separate thread. Can you take a look?
OK, I'll see if there's something wrong.
Arlin While we are on the subject. Any chance of getting
Arlin something
Roland Dreier wrote:
Arlin Hi Roland, I just noticed that when I call
Arlin ibv_close_device() it does not wakeup the poll cq_fd[0] in
Arlin a separate thread. Can you take a look?
OK, I'll see if there's something wrong.
Arlin While we are on the subject. Any chance of getting
Arlin the options to wake up this blocking cq_fd and thread are:
Arlin 1. signal the thread with pthread_kill , pthread_cancel
Arlin 2. poll cq_fd with timeout, wakeup periodically and check
Arlin for termination. 3. ibv_close_device () to force interrupt
Arlin on the polling