mirror of
https://github.com/torvalds/linux.git
synced 2024-11-30 08:01:59 +00:00
1b69ac6b40
psi has provisions to shut off the periodic aggregation worker when
there is a period of no task activity - and thus no data that needs
aggregating. However, while developing psi monitoring, Suren noticed
that the aggregation clock currently won't stay shut off for good.
Debugging this revealed a flaw in the idle design: an aggregation run
will see no task activity and decide to go to sleep; shortly thereafter,
the kworker thread that executed the aggregation will go idle and cause
a scheduling change, during which the psi callback will kick the
!pending worker again. This will ping-pong forever, and is equivalent
to having no shut-off logic at all (but with more code!)
Fix this by exempting aggregation workers from psi's clock waking logic
when the state change is them going to sleep. To do this, tag workers
with the last work function they executed, and if in psi we see a worker
going to sleep after aggregating psi data, we will not reschedule the
aggregation work item.
What if the worker is also executing other items before or after?
Any psi state times that were incurred by work items preceding the
aggregation work will have been collected from the per-cpu buckets
during the aggregation itself. If there are work items following the
aggregation work, the worker's last_func tag will be overwritten and the
aggregator will be kept alive to process this genuine new activity.
If the aggregation work is the last thing the worker does, and we decide
to go idle, the brief period of non-idle time incurred between the
aggregation run and the kworker's dequeue will be stranded in the
per-cpu buckets until the clock is woken by later activity. But that
should not be a problem. The buckets can hold 4s worth of time, and
future activity will wake the clock with a 2s delay, giving us 2s worth
of data we can leave behind when disabling aggregation. If it takes a
worker more than two seconds to go idle after it finishes its last work
item, we likely have bigger problems in the system, and won't notice one
sample that was averaged with a bogus per-CPU weight.
Link: http://lkml.kernel.org/r/20190116193501.1910-1-hannes@cmpxchg.org
Fixes: eb414681d5 ("psi: pressure stall information for CPU, memory, and IO")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
80 lines
2.4 KiB
C
80 lines
2.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* kernel/workqueue_internal.h
|
|
*
|
|
* Workqueue internal header file. Only to be included by workqueue and
|
|
* core kernel subsystems.
|
|
*/
|
|
#ifndef _KERNEL_WORKQUEUE_INTERNAL_H
|
|
#define _KERNEL_WORKQUEUE_INTERNAL_H
|
|
|
|
#include <linux/workqueue.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/preempt.h>
|
|
|
|
struct worker_pool;
|
|
|
|
/*
|
|
* The poor guys doing the actual heavy lifting. All on-duty workers are
|
|
* either serving the manager role, on idle list or on busy hash. For
|
|
* details on the locking annotation (L, I, X...), refer to workqueue.c.
|
|
*
|
|
* Only to be used in workqueue and async.
|
|
*/
|
|
struct worker {
|
|
/* on idle list while idle, on busy hash table while busy */
|
|
union {
|
|
struct list_head entry; /* L: while idle */
|
|
struct hlist_node hentry; /* L: while busy */
|
|
};
|
|
|
|
struct work_struct *current_work; /* L: work being processed */
|
|
work_func_t current_func; /* L: current_work's fn */
|
|
struct pool_workqueue *current_pwq; /* L: current_work's pwq */
|
|
struct list_head scheduled; /* L: scheduled works */
|
|
|
|
/* 64 bytes boundary on 64bit, 32 on 32bit */
|
|
|
|
struct task_struct *task; /* I: worker task */
|
|
struct worker_pool *pool; /* A: the associated pool */
|
|
/* L: for rescuers */
|
|
struct list_head node; /* A: anchored at pool->workers */
|
|
/* A: runs through worker->node */
|
|
|
|
unsigned long last_active; /* L: last active timestamp */
|
|
unsigned int flags; /* X: flags */
|
|
int id; /* I: worker id */
|
|
|
|
/*
|
|
* Opaque string set with work_set_desc(). Printed out with task
|
|
* dump for debugging - WARN, BUG, panic or sysrq.
|
|
*/
|
|
char desc[WORKER_DESC_LEN];
|
|
|
|
/* used only by rescuers to point to the target workqueue */
|
|
struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */
|
|
|
|
/* used by the scheduler to determine a worker's last known identity */
|
|
work_func_t last_func;
|
|
};
|
|
|
|
/**
|
|
* current_wq_worker - return struct worker if %current is a workqueue worker
|
|
*/
|
|
static inline struct worker *current_wq_worker(void)
|
|
{
|
|
if (in_task() && (current->flags & PF_WQ_WORKER))
|
|
return kthread_data(current);
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Scheduler hooks for concurrency managed workqueue. Only to be used from
|
|
* sched/ and workqueue.c.
|
|
*/
|
|
void wq_worker_waking_up(struct task_struct *task, int cpu);
|
|
struct task_struct *wq_worker_sleeping(struct task_struct *task);
|
|
work_func_t wq_worker_last_func(struct task_struct *task);
|
|
|
|
#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
|