[PATCH 0/3] Fix request completion holes

[Sagi Grimberg]

>>> Then it would need to signal the SEND if remote invalidate is used,
>>> otherwise it only needs to signal the local invalidate for the RKEY..
>>
>> Also if its simply using the local dma lkey without sending any rkey.
> 
> Right, OK, to be clear, my emails were only about the case where there
> was a SEND and INVALIDATE required together, I wasn't discussing SEND
> alone, that is already as good as it can be I think :)

Not arguing here :)