workqueues: shrink cpu_populated_map when CPU dies
PATCH 1/2 workqueues: shrink cpu_populated_map when CPU dies
When cpu_populated_map was introduced, it was supposed that cwq->thread can survive after CPU_DEAD, that is why we never shrink cpu_populated_map.
This is not very nice, we can safely remove the already dead CPU from the map. The only required change is that destroy_workqueue() must hold the hotplug lock until it destroys all cwq->thread's, to protect the cpu_populated_map. We could make the local copy of cpu mask and drop the lock, but sizeof(cpumask_t) may be very large.
Also, fix the comment near queue_work(). Unless _cpu_down() happens we do guarantee the cpu-affinity of the work_struct, and we have users which rely on this.
kernel/workqueue.c renamed from kernel/workqueue.c~2_WQ_CPU_MAP +9 -4
@@ -158,8 +158,8 @@ static void __queue_work(struct cpu_work* * Returns 0 if @work was already on a queue, non-zero otherwise. * -* We queue the work to the CPU it was submitted, but there is no -* guarantee that it will be processed by that CPU. +* We queue the work to the CPU it was submitted, but if CPU dies +* it can be processed by another CPU. */ int queue_work (struct workqueue_struct *wq,struct work_struct *work) {
@@ -813,12 +813,12 @@ void destroy_workqueue(struct workqueue_spin_lock (&workqueue_lock);list_del (&wq->list);spin_unlock (&workqueue_lock); -put_online_cpus ();for_each_cpu_mask (cpu, *cpu_map) { cwq =per_cpu_ptr (wq->cpu_wq, cpu);cleanup_workqueue_thread (cwq, cpu); } +put_online_cpus ();free_percpu (wq->cpu_wq);kfree (wq);
@@ -836,7 +836,6 @@ static int __devinit workqueue_cpu_callb action &= ~CPU_TASKS_FROZEN ;switch (action) { -case CPU_UP_PREPARE :cpu_set (cpu, cpu_populated_map); }
@@ -864,6 +863,12 @@ static int __devinit workqueue_cpu_callb } } +switch (action) { +case CPU_UP_CANCELED : +case CPU_DEAD : +cpu_clear (cpu, cpu_populated_map); + } +return NOTIFY_OK ; }
Hi Oleg,
This patch looks OK to me. But while reading this I got some doubts in nearby places, so BTW 2 small questions:
1) ... workqueue_cpu_callback(...)
{
...
list_for_each_entry(wq, &workqueues, list) {
cwq = per_cpu_ptr(wq->cpu_wq, cpu);
switch (action) {
case CPU_UP_PREPARE:
...It looks like not all CPU_ cases are served here: shouldn't list_for_each_entry() be omitted for them?
2) ... __create_workqueue_key(...)
{
...
if (singlethread) {
...
} else {
get_online_cpus();
spin_lock(&workqueue_lock);
list_add(&wq->list, &workqueues);Shouldn't this list_add() be done after all these inits below?
spin_unlock(&workqueue_lock);
for_each_possible_cpu(cpu) {
cwq = init_cpu_workqueue(wq, cpu);
...
}
...Thanks,
Jarek P.
Quoted 14 lines · Oleg Nesterov
When
cpu_populated_mapwas introduced, it was supposed thatcwq->threadcan survive afterCPU_DEAD, that is why we never shrinkcpu_populated_map.This is not very nice, we can safely remove the already dead CPU from the map. The only required change is that
destroy_workqueue()must hold the hotplug lock until it destroys all cwq->thread's, to protect thecpu_populated_map. We could make the local copy of cpu mask and drop the lock, butsizeof(cpumask_t)may be very large.Also, fix the comment near
queue_work(). Unless_cpu_down()happens we do guarantee the cpu-affinity of thework_struct, and we have users which rely on this.Signed-off-by Oleg Nesterov <[email protected]>
Quoted 2 lines · Jarek Poplawski
This patch looks OK to me.
Thanks for looking at this!
Quoted 13 lines
But while reading this I got some doubts
in nearby places, so BTW 2 small questions:1) ...
workqueue_cpu_callback(...){ ... list_for_each_entry(wq, &workqueues, list) { cwq = per_cpu_ptr(wq->cpu_wq, cpu); switch (action) { case CPU_UP_PREPARE: ...
Quoted 2 lines
It looks like not all
CPU_cases are served here: shouldn'tlist_for_each_entry()be omitted for them?
Yes, but this is harmless. cpu-hotplug callbacks are not time-critical, and cpu_down/cpu_up happens not often, and LIST_HEAD(workqueues) is not very long, so ...
Quoted 12 lines
2) ...
__create_workqueue_key(...){ ... if (singlethread) { ... } else { get_online_cpus(); spin_lock(&workqueue_lock); list_add(&wq->list, &workqueues);Shouldn't this
list_add()be done after all these inits below?
Quoted 7 lines
spin_unlock(&workqueue_lock);
for_each_possible_cpu(cpu) {
cwq = init_cpu_workqueue(wq, cpu);
...
}
...This doesn't matter. Please note that get_online_cpus() blocks cpu_up/cpu_down, they take cpu_hotplug_begin().
Oleg.
Quoted 1 line · Oleg Nesterov
On 02/17, Jarek Poplawski wrote:
...
Quoted 1 line
Quoted 1 line
1) ...
workqueue_cpu_callback(...)
...
Quoted 5 lines
Yes, but this is harmless. cpu-hotplug callbacks are not time-critical, and cpu_down/cpu_up happens not often, and
LIST_HEAD(workqueues)is not very long, so ...Quoted 1 line
2) ...
__create_workqueue_key(...)
...
Quoted 3 lines
Quoted 1 line
Shouldn't this
list_add()be done after all these inits below?This doesn't matter. Please note that
get_online_cpus()blocks cpu_up/cpu_down, they takecpu_hotplug_begin().
You are completely right. It looks like this was only about ..."look". (But adding only "default:" in 1) would make it look nicer to me...)
Regards,
Jarek P.