Re: [Announce] [patch] Modular Scheduler Core and Completely Fair Scheduler [CFS]

[Ingo Molnar]

* Daniel Walker <dwalker@xxxxxxxxxx> wrote:

> One other thing, what happens in the case of slow, frequency changing, 
> are/or inaccurate clocks .. Is the old sched_clock behavior still 
> tolerated?

yeah, good question. Yesterday i did a quick testboot with that too, and 
it seemed to behave pretty OK with the low-res [jiffies based] 
sched_clock() too. Although in that case things are much more of an 
approximation and rounding/arithmetics artifacts are possible. CFS works 
best with a high-resolution cycle counter.

	Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/