Roland Dreier wrote:
    Sean> I haven't been able to determine the cause of the MAD
    Sean> crashes, so I was going to separate the CQs for QP 0 and 1
    Sean> to give me more context/state information when a completion
    Sean> occurs.

    Sean> Is this a change that we want permanently?  If so, I will
    Sean> cleanup the change for submission, otherwise, I'll just do
    Sean> it quickly to help identify the cause of the issue.

I don't see a reason to care either way, so as far as I see, we may as
well stick with what we've got.  On the other hand, if splitting the
CQs is an improvement then we should do it.

Separately would likely increase the number of interrupts seen by the system, but allows separate completion processing of SMI and GSI traffic... I don't see a strong reason for the change, and am only making the change to give myself more context when a completion event occurs at this point. (So I'll know exactly which queue I should be accessing.)

- Sean
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general

To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general

Reply via email to