From: "Siddha, Suresh B" <suresh.b.siddha@intel.com>
Jack Steiner brought this issue at my OLS talk.
Take a scenario where two tasks are pinned to two HT threads in a physical
package. Idle packages in the system will keep kicking migration_thread on
the busy package with out any success.
We will run into similar scenarios in the presence of CMP/NUMA.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---
kernel/sched.c | 11 +++++++++++
1 files changed, 11 insertions(+)
diff -puN kernel/sched.c~sched-dont-kick-alb-in-the-presence-of-pinned-task kernel/sched.c
--- devel/kernel/sched.c~sched-dont-kick-alb-in-the-presence-of-pinned-task 2005-08-21 23:49:39.000000000 -0700
+++ devel-akpm/kernel/sched.c 2005-08-21 23:49:39.000000000 -0700
@@ -2220,6 +2220,16 @@ static int load_balance(int this_cpu, ru
if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
spin_lock(&busiest->lock);
+
+ /* don't kick the migration_thread, if the curr
+ * task on busiest cpu can't be moved to this_cpu
+ */
+ if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
+ spin_unlock(&busiest->lock);
+ all_pinned = 1;
+ goto out_one_pinned;
+ }
+
if (!busiest->active_balance) {
busiest->active_balance = 1;
busiest->push_cpu = this_cpu;
@@ -2257,6 +2267,7 @@ static int load_balance(int this_cpu, ru
out_balanced:
spin_unlock(&this_rq->lock);
+out_one_pinned:
schedstat_inc(sd, lb_balanced[idle]);
sd->nr_balance_failed = 0;
_