In <15481.965138601@cygnus.co.uk> David Woodhouse (dwmw2@infradead.org) wrote:
> hpa@zytor.com said:
>> I don't think we want to do this! IMO, HZ should not get exported to
>> user space *AT ALL*. Instead, for the few interfaces that need it,
>> we'll export a "user space HZ" (USER_HZ) which is fixed. No need for
>> a kernel hack. When we support nonstandard values for HZ, we need to
>> fix the few interfaces that actually export jiffies values to convert
>> from "user jiffies" to real jiffies.
> No. Why do the arithmetic in the kernel when we could just export the raw
> data, with full accuracy, and let user-space sort it out?
Since then we'll need to fix 10'000 programs instead of one kernel when
sheduling will be made more adaptive (without fixed HZ) ?
> User-space may want to know the value of HZ for other reasons anyway.
> if (HZ < 1000) {
> perror("You must hack your kernel to improve scheduling latency");
> exit(1);
> }
Gah. Yes. Such code is EXACTLY reason to NOT export HZ.
-
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/
This archive was generated by hypermail 2b29 : Mon Aug 07 2000 - 21:00:07 EST