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 | 15 ++++++++++++++-
1 files changed, 14 insertions(+), 1 deletion(-)
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 2005-08-30 18:45:57.000000000 -0700
+++ devel-akpm/kernel/sched.c 2005-08-30 18:45:57.000000000 -0700
@@ -2219,6 +2219,16 @@ 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;
@@ -2259,6 +2269,8 @@ out_balanced:
schedstat_inc(sd, lb_balanced[idle]);
sd->nr_balance_failed = 0;
+
+out_one_pinned:
/* tune up the balancing interval */
if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
(sd->balance_interval < sd->max_interval))
@@ -2451,7 +2463,8 @@ static void rebalance_tick(int this_cpu,
if (j - sd->last_balance >= interval) {
if (load_balance(this_cpu, this_rq, sd, idle)) {
- /* We've pulled tasks over so either we're no
+ /*
+ * We've pulled tasks over so either we're no
* longer idle, or one of our SMT siblings is
* not idle.
*/
_