From e1d8aa9f1dd655a3534b22fcfbecb70cdb125766 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 12 Jan 2009 23:15:46 +0100 Subject: tracing: add a new workqueue tracer Impact: new tracer The workqueue tracer provides some statistical informations about each cpu workqueue thread such as the number of the works inserted and executed since their creation. It can help to evaluate the amount of work each of them have to perform. For example it can help a developer to decide whether he should choose a per cpu workqueue instead of a singlethreaded one. It only traces statistical informations for now but it will probably later provide event tracing too. Such a tracer could help too, and be improved, to help rt priority sorted workqueue development. To have a snapshot of the workqueues state at any time, just do cat /debugfs/tracing/trace_stat/workqueues Ie: 1 125 125 reiserfs/1 1 0 0 scsi_tgtd/1 1 0 0 aio/1 1 0 0 ata/1 1 114 114 kblockd/1 1 0 0 kintegrityd/1 1 2147 2147 events/1 0 0 0 kpsmoused 0 105 105 reiserfs/0 0 0 0 scsi_tgtd/0 0 0 0 aio/0 0 0 0 ata_aux 0 0 0 ata/0 0 0 0 cqueue 0 0 0 kacpi_notify 0 0 0 kacpid 0 149 149 kblockd/0 0 0 0 kintegrityd/0 0 1000 1000 khelper 0 2270 2270 events/0 Changes in V2: _ Drop the static array based on NR_CPU and dynamically allocate the stat array with num_possible_cpus() and other cpu mask facilities.... _ Trace workqueue insertion at a bit lower level (insert_work instead of queue_work) to handle even the workqueue barriers. Signed-off-by: Frederic Weisbecker Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/workqueue.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2f445833ae37..1fc2bc20603f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -33,6 +33,7 @@ #include #include #include +#include /* * The per-CPU workqueue (if single thread, we always use the first @@ -125,9 +126,13 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK); } +DEFINE_TRACE(workqueue_insertion); + static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head) { + trace_workqueue_insertion(cwq->thread, work); + set_wq_data(work, cwq); /* * Ensure that we get the right work->data if we see the @@ -259,6 +264,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_delayed_work_on); +DEFINE_TRACE(workqueue_execution); + static void run_workqueue(struct cpu_workqueue_struct *cwq) { spin_lock_irq(&cwq->lock); @@ -284,7 +291,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) */ struct lockdep_map lockdep_map = work->lockdep_map; #endif - + trace_workqueue_execution(cwq->thread, work); cwq->current_work = work; list_del_init(cwq->worklist.next); spin_unlock_irq(&cwq->lock); @@ -765,6 +772,8 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu) return cwq; } +DEFINE_TRACE(workqueue_creation); + static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; @@ -787,6 +796,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); cwq->thread = p; + trace_workqueue_creation(cwq->thread, cpu); + return 0; } @@ -868,6 +879,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name, } EXPORT_SYMBOL_GPL(__create_workqueue_key); +DEFINE_TRACE(workqueue_destruction); + static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) { /* @@ -891,6 +904,7 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) * checks list_empty(), and a "normal" queue_work() can't use * a dead CPU. */ + trace_workqueue_destruction(cwq->thread); kthread_stop(cwq->thread); cwq->thread = NULL; } -- cgit From 2355b70fd59cb5be7de2052a9edeee7afb7ff099 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 2 Apr 2009 16:58:24 -0700 Subject: workqueue: avoid recursion in run_workqueue() 1) lockdep will complain when run_workqueue() performs recursion. 2) The recursive implementation of run_workqueue() means that flush_workqueue() and its documentation are inconsistent. This may hide deadlocks and other bugs. 3) The recursion in run_workqueue() will poison cwq->current_work, but flush_work() and __cancel_work_timer(), etcetera need a reliable cwq->current_work. Signed-off-by: Lai Jiangshan Acked-by: Oleg Nesterov Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Frederic Weisbecker Cc: Eric Dumazet Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/workqueue.c | 41 +++++++++++------------------------------ 1 file changed, 11 insertions(+), 30 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9aedd9fd825b..32f8e0d2bf5a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -48,8 +48,6 @@ struct cpu_workqueue_struct { struct workqueue_struct *wq; struct task_struct *thread; - - int run_depth; /* Detect run_workqueue() recursion depth */ } ____cacheline_aligned; /* @@ -262,13 +260,6 @@ EXPORT_SYMBOL_GPL(queue_delayed_work_on); static void run_workqueue(struct cpu_workqueue_struct *cwq) { spin_lock_irq(&cwq->lock); - cwq->run_depth++; - if (cwq->run_depth > 3) { - /* morton gets to eat his hat */ - printk("%s: recursion depth exceeded: %d\n", - __func__, cwq->run_depth); - dump_stack(); - } while (!list_empty(&cwq->worklist)) { struct work_struct *work = list_entry(cwq->worklist.next, struct work_struct, entry); @@ -311,7 +302,6 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) spin_lock_irq(&cwq->lock); cwq->current_work = NULL; } - cwq->run_depth--; spin_unlock_irq(&cwq->lock); } @@ -368,29 +358,20 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) { - int active; + int active = 0; + struct wq_barrier barr; - if (cwq->thread == current) { - /* - * Probably keventd trying to flush its own queue. So simply run - * it by hand rather than deadlocking. - */ - run_workqueue(cwq); - active = 1; - } else { - struct wq_barrier barr; + WARN_ON(cwq->thread == current); - active = 0; - spin_lock_irq(&cwq->lock); - if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) { - insert_wq_barrier(cwq, &barr, &cwq->worklist); - active = 1; - } - spin_unlock_irq(&cwq->lock); - - if (active) - wait_for_completion(&barr.done); + spin_lock_irq(&cwq->lock); + if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) { + insert_wq_barrier(cwq, &barr, &cwq->worklist); + active = 1; } + spin_unlock_irq(&cwq->lock); + + if (active) + wait_for_completion(&barr.done); return active; } -- cgit