mirror of
https://github.com/torvalds/linux.git
synced 2025-10-31 08:38:45 +02:00
616db8779b
If a per-cpu work item hogs the CPU, it can prevent other work items from
starting through concurrency management. A per-cpu workqueue which intends
to host such CPU-hogging work items can choose to not participate in
concurrency management by setting %WQ_CPU_INTENSIVE; however, this can be
error-prone and difficult to debug when missed.
This patch adds an automatic CPU usage based detection. If a
concurrency-managed work item consumes more CPU time than the threshold
(10ms by default) continuously without intervening sleeps, wq_worker_tick()
which is called from scheduler_tick() will detect the condition and
automatically mark it CPU_INTENSIVE.
The mechanism isn't foolproof:
* Detection depends on tick hitting the work item. Getting preempted at the
right timings may allow a violating work item to evade detection at least
temporarily.
* nohz_full CPUs may not be running ticks and thus can fail detection.
* Even when detection is working, the 10ms detection delays can add up if
many CPU-hogging work items are queued at the same time.
However, in vast majority of cases, this should be able to detect violations
reliably and provide reasonable protection with a small increase in code
complexity.
If some work items trigger this condition repeatedly, the bigger problem
likely is the CPU being saturated with such per-cpu work items and the
solution would be making them UNBOUND. The next patch will add a debug
mechanism to help spot such cases.
v4: Documentation for workqueue.cpu_intensive_thresh_us added to
kernel-parameters.txt.
v3: Switch to use wq_worker_tick() instead of hooking into preemptions as
suggested by Peter.
v2: Lai pointed out that wq_worker_stopping() also needs to be called from
preemption and rtlock paths and an earlier patch was updated
accordingly. This patch adds a comment describing the risk of infinte
recursions and how they're avoided.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
83 lines
2.5 KiB
C
83 lines
2.5 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; /* K: work being processed and its */
|
|
work_func_t current_func; /* K: function */
|
|
struct pool_workqueue *current_pwq; /* K: pwq */
|
|
u64 current_at; /* K: runtime at start or last wakeup */
|
|
unsigned int current_color; /* K: color */
|
|
|
|
int sleeping; /* S: is worker sleeping? */
|
|
|
|
/* used by the scheduler to determine a worker's last known identity */
|
|
work_func_t last_func; /* K: last work's fn */
|
|
|
|
struct list_head scheduled; /* L: scheduled works */
|
|
|
|
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; /* K: 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 */
|
|
};
|
|
|
|
/**
|
|
* 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_running(struct task_struct *task);
|
|
void wq_worker_sleeping(struct task_struct *task);
|
|
void wq_worker_tick(struct task_struct *task);
|
|
work_func_t wq_worker_last_func(struct task_struct *task);
|
|
|
|
#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
|