Messages in this thread Patch in this message |  | | From | Nicholas Piggin <> | Subject | [RFC PATCH] kernel/sched/core: busy wait before going idle | Date | Sun, 15 Apr 2018 23:31:49 +1000 |
| |
This is a quick hack for comments, but I've always wondered -- if we have a short term polling idle states in cpuidle for performance -- why not skip the context switch and entry into all the idle states, and just wait for a bit to see if something wakes up again.
It's not uncommon to see various going-to-idle work in kernel profiles. This might be a way to reduce that (and just the cost of switching registers and kernel stack to idle thread). This can be an important path for single thread request-response throughput.
tbench bandwidth seems to be improved (the numbers aren't too stable but they pretty consistently show some gain). 10-20% would be a pretty nice gain for such workloads
clients 1 2 4 8 16 128 vanilla 232 467 823 1819 3218 9065 patched 310 503 962 2465 3743 9820
--- kernel/sched/core.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e8afd6086f23..30a0b13edfa5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3404,6 +3404,7 @@ static void __sched notrace __schedule(bool preempt) struct rq_flags rf; struct rq *rq; int cpu; + bool do_idle_spin = true; cpu = smp_processor_id(); rq = cpu_rq(cpu); @@ -3428,6 +3429,7 @@ static void __sched notrace __schedule(bool preempt) rq_lock(rq, &rf); smp_mb__after_spinlock(); +idle_spin_end: /* Promote REQ to ACT */ rq->clock_update_flags <<= 1; update_rq_clock(rq); @@ -3437,6 +3439,32 @@ static void __sched notrace __schedule(bool preempt) if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; } else { + /* + * Busy wait before switching to idle thread. This + * is marked unlikely because we're idle so jumping + * out of line doesn't matter too much. + */ + if (unlikely(do_idle_spin && rq->nr_running == 1)) { + u64 start; + + do_idle_spin = false; + + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); + rq_unlock_irq(rq, &rf); + + spin_begin(); + start = local_clock(); + while (!need_resched() && prev->state && + !signal_pending_state(prev->state, prev)) { + spin_cpu_relax(); + if (local_clock() - start > 1000000) + break; + } + spin_end(); + + rq_lock_irq(rq, &rf); + goto idle_spin_end; + } deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK); prev->on_rq = 0; -- 2.17.0
|  |