James Carlson wrote:
Garrett D'Amore writes:
In any case, this is *debug*, not normal usage, and should never be
needed if the hardware and drivers are working properly. (I.e. if they
aren't suffering from bugs.) An mdb or /etc/system tunable is fine
here... it may require the customer to unplumb/replumb the interface,
but, again, we do not expect this to be used unless our
software/hardware is somehow buggy. Its far better that we make sure
the checksum support is bug free than that we give customers some knob
to control it, IMO.
It sounds like we're in sync on that.
"Advanced usage" != debug usage. Those values are perfectly reasonable
things for the customer to tune, at least as long as we don't have a
facility in place to auto-tune them. (One could argue that the
bcopy/dma stuff should not be customer tunable, but right now we don't
have any facility to auto-tune them. The ipg properties are definitely
a customer tunable, and do represent unusual/advanced usage, but they
aren't something that we can auto-tune for the customer.)
Yep; agreed. The ipg bits are strange, but they're on-the-wire
properties rather than being things merely inside of Solaris.
I really do think that the bcopy issue needs more work. Putting a
fundamental internal design issue like that into the hands of
customers to resolve strikes me as a very poor compromise.
I agree wholeheartedly.
But we need to provide _something_ here, until we have a better
solution. Maybe you have heard me pitch my ideas for a Nemo II
project. This is the sort of thing that should be handled as part of
Nemo II. Maybe someday I'll be able to get a funded project to further
enhance Nemo to do this sort of thing. (Heck, maybe someday I'll be
able to get funding to get a regular full time position! :-)
-- Garrett
_______________________________________________
networking-discuss mailing list
[email protected]
