workqueue: Add pwq->stats[] and a monitoring script

Currently, the only way to peer into workqueue operations is through
tracing. While possible, it isn't easy or convenient to monitor
per-workqueue behaviors over time this way. Let's add pwq->stats[] that
track relevant events and a drgn monitoring script -
tools/workqueue/wq_monitor.py.

It's arguable whether this needs to be configurable. However, it currently
only has several counters and the runtime overhead shouldn't be noticeable
given that they're on pwq's which are per-cpu on per-cpu workqueues and
per-numa-node on unbound ones. Let's keep it simple for the time being.

v2: Patch reordered to earlier with fewer fields. Field will be added back
    gradually. Help message improved.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>

1 files changed, 23 insertions, 1 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 36bccc1285b3..60d5b84cccb2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -200,6 +200,20 @@ struct worker_pool {
 };
 
 /*
+ * Per-pool_workqueue statistics. These can be monitored using
+ * tools/workqueue/wq_monitor.py.
+ */
+enum pool_workqueue_stats {
+	PWQ_STAT_STARTED,	/* work items started execution */
+	PWQ_STAT_COMPLETED,	/* work items completed execution */
+	PWQ_STAT_CM_WAKEUP,	/* concurrency-management worker wakeups */
+	PWQ_STAT_MAYDAY,	/* maydays to rescuer */
+	PWQ_STAT_RESCUED,	/* linked work items executed by rescuer */
+
+	PWQ_NR_STATS,
+};
+
+/*
  * The per-pool workqueue.  While queued, the lower WORK_STRUCT_FLAG_BITS
  * of work_struct->data are used for flags and the remaining high bits
  * point to the pwq; thus, pwqs need to be aligned at two's power of the
@@ -236,6 +250,8 @@ struct pool_workqueue {
 	struct list_head	pwqs_node;	/* WR: node on wq->pwqs */
 	struct list_head	mayday_node;	/* MD: node on wq->maydays */
 
+	u64			stats[PWQ_NR_STATS];
+
 	/*
 	 * Release of unbound pwq is punted to system_wq.  See put_pwq()
 	 * and pwq_unbound_release_workfn() for details.  pool_workqueue
@@ -929,8 +945,10 @@ void wq_worker_sleeping(struct task_struct *task)
 	}
 
 	pool->nr_running--;
-	if (need_more_worker(pool))
+	if (need_more_worker(pool)) {
+		worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++;
 		wake_up_worker(pool);
+	}
 	raw_spin_unlock_irq(&pool->lock);
 }
 
@@ -2165,6 +2183,7 @@ static void send_mayday(struct work_struct *work)
 		get_pwq(pwq);
 		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
+		pwq->stats[PWQ_STAT_MAYDAY]++;
 	}
 }
 
@@ -2403,6 +2422,7 @@ __acquires(&pool->lock)
 	 * workqueues), so hiding them isn't a problem.
 	 */
 	lockdep_invariant_state(true);
+	pwq->stats[PWQ_STAT_STARTED]++;
 	trace_workqueue_execute_start(work);
 	worker->current_func(work);
 	/*
@@ -2410,6 +2430,7 @@ __acquires(&pool->lock)
 	 * point will only record its address.
 	 */
 	trace_workqueue_execute_end(work, worker->current_func);
+	pwq->stats[PWQ_STAT_COMPLETED]++;
 	lock_map_release(&lockdep_map);
 	lock_map_release(&pwq->wq->lockdep_map);
 
@@ -2653,6 +2674,7 @@ repeat:
 				if (first)
 					pool->watchdog_ts = jiffies;
 				move_linked_works(work, scheduled, &n);
+				pwq->stats[PWQ_STAT_RESCUED]++;
 			}
 			first = false;
 		}