From: Nick Piggin Make sure to count kernel preemption as a context switch. A short cut has been preventing it. kernel/sched.c | 37 +++++++++++++++---------------------- 1 files changed, 15 insertions(+), 22 deletions(-) diff -puN kernel/sched.c~context-switch-accounting-fix kernel/sched.c --- 25/kernel/sched.c~context-switch-accounting-fix 2003-11-11 19:29:37.000000000 -0800 +++ 25-akpm/kernel/sched.c 2003-11-11 19:29:37.000000000 -0800 @@ -1513,33 +1513,20 @@ need_resched: spin_lock_irq(&rq->lock); - /* - * if entering off of a kernel preemption go straight - * to picking the next task. - */ - if (unlikely(preempt_count() & PREEMPT_ACTIVE)) - goto pick_next_task; - - switch (prev->state) { - case TASK_INTERRUPTIBLE: - if (unlikely(signal_pending(prev))) { + if (prev->state != TASK_RUNNING && + likely(!(preempt_count() & PREEMPT_ACTIVE)) ) { + if (unlikely(signal_pending(prev)) && + prev->state == TASK_INTERRUPTIBLE) prev->state = TASK_RUNNING; - break; - } - default: - deactivate_task(prev, rq); - prev->nvcsw++; - break; - case TASK_RUNNING: - prev->nivcsw++; + else + deactivate_task(prev, rq); } -pick_next_task: - if (unlikely(!rq->nr_running)) { + #ifdef CONFIG_SMP + if (unlikely(!rq->nr_running)) load_balance(rq, 1, cpu_to_node_mask(smp_processor_id())); - if (rq->nr_running) - goto pick_next_task; #endif + if (unlikely(!rq->nr_running)) { next = rq->idle; rq->expired_timestamp = 0; goto switch_tasks; @@ -1586,6 +1573,12 @@ switch_tasks: prev->timestamp = now; if (likely(prev != next)) { + if (prev->state == TASK_RUNNING || + unlikely(preempt_count() & PREEMPT_ACTIVE)) + prev->nivcsw++; + else + prev->nvcsw++; + next->timestamp = now; rq->nr_switches++; rq->curr = next; _