[ofa-general] Re: Incorrect max_sge reported in mthca device query
Pete Wyckoff
pw at osc.edu
Thu Apr 5 10:25:26 PDT 2007
tom at opengridcomputing.com wrote on Thu, 05 Apr 2007 09:45 -0500:
> The challenge with the current query/request method is that as we've
> discussed the advertised max may not work. What makes the adjust/retry
> unworkable is that you don't know which of the advertised maxes caused
> the request to fail. So when you retry, which qp_attr do you adjust? The
> send sge? The recv sge? The qp depth?
As an aside, we discussed this topic in June 2006. See the thread
http://lists.openfabrics.org/pipermail/general/2006-June/thread.html#23417
for some insightful comments from MST and Tom Talpey. No conclusion
was reached regarding the ideal form of the API.
-- Pete
More information about the general
mailing list