On Wed, 2006-04-05 at 10:56 -0700, Sean Hefty wrote: > Arlin Davis wrote: > > I did not see the original thread/patch from Steve so I don't have the > > entire context of this issue but it sounds like we need to fix the code > > so that the destroy QP (dat_ep_free) blocks until the event processing > > is complete, always destroy the QP and cm_id from this call, and remove > > cleanup from any async event processing threads. Is this what Steve was > > attempting to do with his patch? > > There's still the issue that the event processing thread is the one calling > dat_ep_free, in which case, you need to ensure that it is finished with all > event processing before this call is made. >
The event processing thread is not the one calling dat_ep_free(). As I said before, with my new patch, the event processing thread never calls dat_ep_free() (or really dapli_conn_destroy()). The dat event processing thread only posts events into an EVD and wakes up the consumer thread. Arlin/James, please confirm this? Cuz maybe I'm confused? Steve. _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
