[openib-general] DAPL for openib

[Roland Dreier]

    Michael> What was the data structure you had in mind for this?  On
    Michael> linux tree is the easiest I think , but thats not O(1).
    Michael> If you want to, a tree can keep mutiple identical items I
    Michael> think.

I think the O(1) data structure Sean has in mind is a dispatch table :)
I guess we could have a linked list of consumers in entry so that
dispatch just takes time proportional to the number of consumers for a
given MAD.

If need be O(log n) doesn't seem unacceptable to me either.

 - R.