> I'll check that out, and if all works fine I'll release a patch. By the way,
> how *do* you measure network performance the best way? What I have done now
You set up 2 or more machines, send data and time it. :)
[Perhaps someone more qualified would like to give some advise here]
There are some networking benchmarks (netperf, ttcp), "ping -f" gives
round-trip times. They should be able to tell if a change makes things
noticably better or worse.
I've probably missed some important benchmark, go search ...
I doubt that this change is measurable at that level. You could instead
insert some time measuring inside the driver and see if things like
interrupt processing of 10000 interrupts goes from 100x to 99x, for some
Did I hear timepegs? http://www.uow.edu.au/~andrewm/linux/,
but that patch hasn't been updated since 2.4.1-pre10-1 :(
It has some other potentially useful stuff, like cyclesoak.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to email@example.com
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/