Roland,
From: Roland Dreier [mailto:[EMAIL PROTECTED]
If this were some feature that allowed us to do something new, or made
applications more efficient, or something like that, I'd be all for
it, specs be damned. But in this case it's just bloating driver code
to work around buggy
To aid error messages and port of some applications it would be better
if wc-opcode could at least indicate if the failed CQE was for the RQ
or SQ.
I disagree. The spec is very clear on this point and I don't see any
reason to bloat driver code to work around buggy applications. In
fact I
Roland,
From: Roland Dreier
I disagree. The spec is very clear on this point and I don't see any
reason to bloat driver code to work around buggy applications. In
fact I would support removing the population of error work completions
from other drivers if it shrinks the code.
I don't
I don't understand why you are taking such a non-cooperative posture for
a simple request. All hardware models support this capability and it's
a 1 line change for mthca to parallel the other drivers.
Most previous stacks, including VAPI, had this capability.
While I agree