From: "Siddha, Suresh B" 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 Acked-by: Ingo Molnar Signed-off-by: Andrew Morton --- 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 2005-09-07 20:11:04.000000000 -0700 +++ devel-akpm/kernel/sched.c 2005-09-07 20:11:04.000000000 -0700 @@ -2225,6 +2225,16 @@ 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; @@ -2265,6 +2275,8 @@ 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)) @@ -2457,7 +2469,8 @@ 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. */ _