From: Siddha, Suresh B Date: Sat, 10 Sep 2005 07:26:21 +0000 (-0700) Subject: [PATCH] sched: allow the load to grow upto its cpu_power X-Git-Tag: v2.6.14-rc1~210 X-Git-Url: http://pilppa.com/gitweb/?a=commitdiff_plain;h=0c117f1b4d14380baeed9c883f765ee023da8761;p=linux-2.6-omap-h63xx.git [PATCH] sched: allow the load to grow upto its cpu_power Don't pull tasks from a group if that would cause the group's total load to drop below its total cpu_power (ie. cause the group to start going idle). Signed-off-by: Suresh Siddha Signed-off-by: Nick Piggin Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/kernel/sched.c b/kernel/sched.c index 1dc29dec38a..dbd4490afec 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1910,6 +1910,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, { struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups; unsigned long max_load, avg_load, total_load, this_load, total_pwr; + unsigned long max_pull; int load_idx; max_load = this_load = total_load = total_pwr = 0; @@ -1959,7 +1960,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, group = group->next; } while (group != sd->groups); - if (!busiest || this_load >= max_load) + if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE) goto out_balanced; avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr; @@ -1979,8 +1980,12 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * by pulling tasks to us. Be careful of negative numbers as they'll * appear as very large values with unsigned longs. */ + + /* Don't want to pull so many tasks that a group would go idle */ + max_pull = min(max_load - avg_load, max_load - SCHED_LOAD_SCALE); + /* How much load to actually move to equalise the imbalance */ - *imbalance = min((max_load - avg_load) * busiest->cpu_power, + *imbalance = min(max_pull * busiest->cpu_power, (avg_load - this_load) * this->cpu_power) / SCHED_LOAD_SCALE;