2/2
--
SUSE Labs, Novell Inc.
During periodic load balancing, don't hold this runqueue's lock while
scanning remote runqueues, which can take a non trivial amount of time
especially on very large systems.
Holding the runqueue lock will only help to stabalise ->nr_running,
however this isn't doesn't do much to help because tasks being woken
will simply get held up on the runqueue lock, so ->nr_running would
not provide a really accurate picture of runqueue load in that case
anyway.
What's more, ->nr_running (and possibly the cpu_load averages) of
remote runqueues won't be stable anyway, so load balancing is always
an inexact operation.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c 2005-08-02 21:35:38.000000000 +1000
+++ linux-2.6/kernel/sched.c 2005-08-02 21:35:38.000000000 +1000
@@ -2051,7 +2051,6 @@ static int load_balance(int this_cpu, ru
int nr_moved, all_pinned = 0;
int active_balance = 0;
- spin_lock(&this_rq->lock);
schedstat_inc(sd, lb_cnt[idle]);
group = find_busiest_group(sd, this_cpu, &imbalance, idle);
@@ -2078,18 +2077,16 @@ static int load_balance(int this_cpu, ru
* still unbalanced. nr_moved simply stays zero, so it is
* correctly treated as an imbalance.
*/
- double_lock_balance(this_rq, busiest);
+ double_rq_lock(this_rq, busiest);
nr_moved = move_tasks(this_rq, this_cpu, busiest,
imbalance, sd, idle, &all_pinned);
- spin_unlock(&busiest->lock);
+ double_rq_unlock(this_rq, busiest);
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(all_pinned))
goto out_balanced;
}
- spin_unlock(&this_rq->lock);
-
if (!nr_moved) {
schedstat_inc(sd, lb_failed[idle]);
sd->nr_balance_failed++;
@@ -2132,8 +2129,6 @@ static int load_balance(int this_cpu, ru
return nr_moved;
out_balanced:
- spin_unlock(&this_rq->lock);
-
schedstat_inc(sd, lb_balanced[idle]);
sd->nr_balance_failed = 0;
