Jason, Somewhere in Dotan's blog I saw him say that if you put a QP in the reset state that it - clears the SQ and RQ (if not SRQ) *AND* - also clears the completion queues Rxe does nothing special about moving a QP to reset. A few of the Python negative test cases intentionally force the QP into the error state and then the reset state before modifying back to RTS. They fail if they do more work and expect it to succeed but get flush errors instead left over from the earlier failed test. I have not found anything in the IBA that mentions this but it could be there. This will be a little tricky if the CQ is shared between more than one QP. But easier for me to fix than changing the Python code. Do you know how this is supposed to work? bob
