[openib-general] Mellanox request CQ notification _really_ compliant?

[Roland Dreier]

 > The spec does not mandate the mechanism by which the cqe is made
 > available to the consumer. And other than ruling the order at which
 > cqes are generated, there are no guarantees re the time it will
 > take until a cqe is made visible to the consumer (unless there was
 > a completion event generated).  Given that, the app in your example
 > can not assume that the bind completion is already in the cq, at
 > least not to the extent that a single call to pollforcompletion
 > would be guaranteed to successfully retrieve it. So the app can not
 > really perceive the difference.

Heh, I thought that would be the explanation.  I guess it skates
inside what the spec allows, although it does lead to some amusing
consequences -- eg the app could go to sleep for an hour before
requesting completion notification, and then get an event instantly,
implying that the work completion was hovering outside the CQ for an
hour until just the instant that notification was requested....

 - R.