On Thu, 2011-01-13 at 14:10 -0500, Bart Van Assche wrote:
> On Thu, Jan 13, 2011 at 4:21 PM, David Dillow <[email protected]> wrote:
> > Please drop the unlikely -- it isn't at all unlikely on the hardware and
> > loads I run.
[snip]
> But it surprises me that on the hardware and loads you run it
> regularly happens that iu == NULL -- a recent patch had the exact
> purpose to avoid that ("IB/srp: Reduce number of BUSY conditions").
> With that patch it should only occur that iu == NULL if the target
> violates the SRP spec by sending target-initiated information units so
> fast that there is more than one unanswered request.

Some devices return credits in batches, so we have IUs but no credits to
send them.

-- 
Dave Dillow
National Center for Computational Science
Oak Ridge National Laboratory
(865) 241-6602 office


--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to