19 Sep
2003
19 Sep
'03
9:26 a.m.
An interesting historical sidenote on this came from of
our programmers,
who was deep in the BeOS. He told me that their timeslice was 3 msecs
once everyone had 500 MHz machines. It was down to 1 msec for the never
released R6 version... back in, what 1999? 2000?
the sad part is that the HRT patch completely removes *any* dependency
on the timeslice or timer interrupt frequency. you get timing by
reprogramming the APIC so that it interrupts the CPU at exactly the
right time. the APIC has usec resolution for this. its a much better
design than just cranking up HZ, and in fact, I would probably leave
HZ at 100 with this patch in place.
Open source is a bit slower to move, but at least it
sticks around!
So true. Anyway, at least there will be a patch; the most recent one
for 2.4.20 just came out.
--p