Re: [RFC] Implementing temporal affinity

From: Stuart MacDonald (
Date: Fri Aug 25 2000 - 15:20:46 EST

From: "Chris Swiedler" <>
> We would only set last_cpu IF the process has run for N cycles, where N is
> enough to fill the CPU cache. If 15 cycles loads the cache, then N=15. So
> that case, B's last_cpu would be set, and it would be tied to that
> processor. The actual value is tunable, and depends largely on the size of
> the L2 cache.

And that would be my misunderstanding. :-) I've been
assuming that the CPU would prefetch a wack of stuff
for process B (from my example) on the first instruction
of process B. I guess it only fills the cache as things
are needed.


To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
Please read the FAQ at

This archive was generated by hypermail 2b29 : Thu Aug 31 2000 - 21:00:16 EST