Re: [PATCH] Performance regression in 2.6.7-rc3

[Ingo Molnar <mingo@elte.hu>]

* Con Kolivas <kernel@kolivas.org> wrote:

> with a little bit of detective work and help from Wli we tracked down that 
> this patch caused it:
> [PATCH] sched: improve wakeup-affinity

> A massive increase in idle time was observed and the throughput
> dropped by 40% Reversing this patch gave these results:

> backsched1: http://khack.osdl.org/stp/293865/
> Composite 	Query Processing Power 	Throughput Numerical Quantity
> 193.93 	145.95 	257.67
> 
> It may be best to reverse this patch until the regression is better 
> understood.

agreed. It is weird because Nick said that pgsql was tested with the
patch - and we applied the patch based on those good results. Nick?

Anyway, does the patch below fix the pgsql problem? It reverts to the
more agressive idle-balancing variant (which isnt strictly necessary for
the bw_pipe problem).

	Ingo

Signed-off-by: Ingo Molnar <mingo@elte.hu>

--- linux/kernel/sched.c
+++ linux/kernel/sched.c
@@ -1625,8 +1626,7 @@
 	return busiest;
 
 out_balanced:
-	if (busiest && idle != NOT_IDLE && max_load > SCHED_LOAD_SCALE) {
+	if (busiest && (idle == NEWLY_IDLE ||
+			(idle == IDLE && max_load > SCHED_LOAD_SCALE)) ) {
 		*imbalance = 1;
 		return busiest;
 	}