fix perf. bug in wake-up load balancing for aim7 and db workload
PATCH 1/2 fix perf. bug in wake-up load balancing for aim7 and db workload
Revert commit d7102e95b7b9c00277562c29aad421d2d521c5f6, which causes more than 10% performance regression with aim7.
include/linux/sched.h renamed from include/linux/sched.h.orig +1 -4
@@ -697,12 +697,9 @@ struct task_struct {int lock_depth;/* BKL lock depth */ -#if defined(CONFIG_SMP ) -int last_waker_cpu;/* CPU that last woke this task up */ -#if defined(__ARCH_WANT_UNLOCKED_CTXSW) +#if defined(CONFIG_SMP ) && defined(__ARCH_WANT_UNLOCKED_CTXSW)int oncpu;#endif -#endif int prio, static_prio;struct list_head run_list;prio_array_t *array;
kernel/sched.c renamed from kernel/sched.c.orig +1 -9
@@ -1294,9 +1294,6 @@ static int try_to_wake_up(task_t *p, uns } } -if (p->last_waker_cpu != this_cpu) - goto out_set_cpu; -if (unlikely (!cpu_isset (this_cpu, p->cpus_allowed))) goto out_set_cpu;
@@ -1367,8 +1364,6 @@ out_set_cpu: cpu =task_cpu (p); } - p->last_waker_cpu = this_cpu; - out_activate:#endif /* CONFIG_SMP */ if (old_state ==TASK_UNINTERRUPTIBLE ) {
@@ -1450,12 +1445,9 @@ void fastcall sched_fork(task_t *p, int#ifdef CONFIG_SCHEDSTATS memset (&p->sched_info,0 ,sizeof (p->sched_info));#endif -#if defined(CONFIG_SMP ) - p->last_waker_cpu = cpu; -#if defined(__ARCH_WANT_UNLOCKED_CTXSW) +#if defined(CONFIG_SMP ) && defined(__ARCH_WANT_UNLOCKED_CTXSW) p->oncpu =0 ;#endif -#endif #ifdef CONFIG_PREEMPT /* Want to start with kernel preemption disabled. */ task_thread_info (p)->preempt_count =1 ;
Quoted 3 lines · Kenneth W
Revert commit
d7102e95b7b9c00277562c29aad421d2d521c5f6, which causes more than 10% performance regression with aim7.
Just to be sure, what kernel did you test with? In particular, did it have the smpnice patch reverted (as -rc3 does).
Signature · 2 lines
SUSE Labs, Novell Inc. Send instant messages to your online friends http://au.messenger.yahoo.com
Quoted 9 lines · Nick Piggin
Quoted 3 lines · Kenneth W
Revert commit
d7102e95b7b9c00277562c29aad421d2d521c5f6, which causes more than 10% performance regression with aim7.Just to be sure, what kernel did you test with? In particular, did it have the smpnice patch reverted (as -rc3 does).
Analysis of the smpnice code indicates that it could cause anomalous cpu selection decisions in try_to_wake_up() if there is a skew in the distribution of nice among the tasks on the cpus under consideration. Attached for review is a proposed patch to address problem. In particular, I request comments on the following issues:
1. Is this potential problem worth worrying about?
2. Do you agree with my decision to replace SCHED_LOAD_SCALE with the average load per task for this_cpu in the if statement in try_to_wake_up() or should I be using the average load per task for the tasks current cpu in one or both places?
Peter
Signature · 4 lines
Peter Williams [email protected] "Learning, n. The kind of ignorance distinguishing the studious." -- Ambrose Bierce
kernel/sched.c +15 -2
@@ -1061,6 +1061,18 @@ static inline unsigned long target_load( }/* +* Return the average load per task on the cpu's run queue +*/ +static inline unsigned long cpu_avg_load_per_task (int cpu) +{ +runqueue_t *rq =cpu_rq (cpu); +unsigned long n = rq->nr_running; +unsigned long load =weighted_load (rq->prio_bias); + +return n ? load / n : load; +} + +/* * find_idlest_group finds and returns the least busy CPU group within the * domain. */
@@ -1309,6 +1321,7 @@ static int try_to_wake_up(task_t *p, unsif (this_sd->flags &SD_WAKE_AFFINE ) {unsigned long tl = this_load; +unsigned long tl_per_task =cpu_avg_load_per_task (this_cpu);/* * If sync wakeup then subtract the (maximum possible) * effect of the currently running task from the load
@@ -1318,8 +1331,8 @@ static int try_to_wake_up(task_t *p, uns tl -=weighted_load (p->bias_prio);if ((tl <= load && - tl +target_load (cpu, idx) <=SCHED_LOAD_SCALE ) || -100 *(tl +SCHED_LOAD_SCALE ) <= imbalance*load) { + tl +target_load (cpu, idx) <= tl_per_task) || +100 *(tl + tl_per_task) <= imbalance*load) {/* * This domain has SD_WAKE_AFFINE and * p is cache cold in this domain, and