Ah yes, that should be a good place to start. As I understand it,
the soft timers really depend on a lightweight path between the
trigger that initiates the check (e.g. return from system call)
and the check that (usually) finds that nothing needs to be done.
> Seems, the experimental results summarized there are not quite legal.
Yeah, I don't find the TCP results very illuminating either. But the
other things look more promising, e.g. that they found soft timers
to be actually quite reliable for producing short delays.
I'm mainly interested in a) an alternative to udelay/mdelay, and b)
a good event source for TBF. I'll gladly leave the design of yet
another TCP improvement, including ten or more years of academic
warfare, to other people ;-)
- Werner
-- _________________________________________________________________________ / Werner Almesberger, ICA, EPFL, CH werner.almesberger@ica.epfl.ch / /_IN_N_032__Tel_+41_21_693_6621__Fax_+41_21_693_6610_____________________/- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/