Re: Strange scheduling behavoir in SMP (kernel 2.2.14)

From: Jeffrey B. Siegal (jbs@quiotix.com)
Date: Wed Feb 02 2000 - 05:37:05 EST


> A different, more conservative, gamble would be to schedule on the
> cold processor right away but reconsider when the previously
> favored processor becomes free.

The problem with this is that you trash the cache on the cold processor, and
then, when you move it over, the cache on the previous cpu may not even be
warm any more.

Hard to say if this would really be better than the current behavior.

-
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 Feb 07 2000 - 21:00:07 EST