From: Nick Piggin <nickpiggin@yahoo.com.au>

The fundamental problem that Suresh has with balance on exec and fork is that
it only tries to balance the top level domain with the flag set.

This was worked around by removing degenerate domains, but is still a problem
if people want to start using more complex sched-domains, especially
multilevel NUMA that ia64 is already using.

This patch makes balance on fork and exec try balancing over not just the top
most domain with the flag set, but all the way down the domain tree.

Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---

 25-akpm/kernel/sched.c |   45 ++++++++++++++++++++++++++++++++++++++-------
 1 files changed, 38 insertions(+), 7 deletions(-)

diff -puN kernel/sched.c~sched-multilevel-sbe-sbf kernel/sched.c
--- 25/kernel/sched.c~sched-multilevel-sbe-sbf	2005-04-07 03:14:29.000000000 -0700
+++ 25-akpm/kernel/sched.c	2005-04-07 03:14:29.000000000 -0700
@@ -1321,21 +1321,24 @@ void fastcall wake_up_new_task(task_t * 
 			sd = tmp;
 
 	if (sd) {
+		cpumask_t span;
 		int new_cpu;
 		struct sched_group *group;
 
+again:
 		schedstat_inc(sd, sbf_cnt);
+		span = sd->span;
 		cpu = task_cpu(p);
 		group = find_idlest_group(sd, p, cpu);
 		if (!group) {
 			schedstat_inc(sd, sbf_balanced);
-			goto no_forkbalance;
+			goto nextlevel;
 		}
 
 		new_cpu = find_idlest_cpu(group, cpu);
 		if (new_cpu == -1 || new_cpu == cpu) {
 			schedstat_inc(sd, sbf_balanced);
-			goto no_forkbalance;
+			goto nextlevel;
 		}
 
 		if (cpu_isset(new_cpu, p->cpus_allowed)) {
@@ -1345,9 +1348,21 @@ void fastcall wake_up_new_task(task_t * 
 			rq = task_rq_lock(p, &flags);
 			cpu = task_cpu(p);
 		}
+
+		/* Now try balancing at a lower domain level */
+nextlevel:
+		sd = NULL;
+		for_each_domain(cpu, tmp) {
+			if (cpus_subset(span, tmp->span))
+				break;
+			if (tmp->flags & SD_BALANCE_FORK)
+				sd = tmp;
+		}
+
+		if (sd)
+			goto again;
 	}
 
-no_forkbalance:
 #endif
 	/*
 	 * We decrease the sleep average of forking parents
@@ -1713,25 +1728,41 @@ void sched_exec(void)
 			sd = tmp;
 
 	if (sd) {
+		cpumask_t span;
 		struct sched_group *group;
+again:
 		schedstat_inc(sd, sbe_cnt);
+		span = sd->span;
 		group = find_idlest_group(sd, current, this_cpu);
 		if (!group) {
 			schedstat_inc(sd, sbe_balanced);
-			goto out;
+			goto nextlevel;
 		}
 		new_cpu = find_idlest_cpu(group, this_cpu);
 		if (new_cpu == -1 || new_cpu == this_cpu) {
 			schedstat_inc(sd, sbe_balanced);
-			goto out;
+			goto nextlevel;
 		}
 
 		schedstat_inc(sd, sbe_pushed);
 		put_cpu();
 		sched_migrate_task(current, new_cpu);
-		return;
+
+		/* Now try balancing at a lower domain level */
+		this_cpu = get_cpu();
+nextlevel:
+		sd = NULL;
+		for_each_domain(this_cpu, tmp) {
+			if (cpus_subset(span, tmp->span))
+				break;
+			if (tmp->flags & SD_BALANCE_EXEC)
+				sd = tmp;
+		}
+
+		if (sd)
+			goto again;
 	}
-out:
+
 	put_cpu();
 }
 
_