Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit cdc1184c authored by Divyesh Shah's avatar Divyesh Shah Committed by Jens Axboe
Browse files

blkio: Add io_queued and avg_queue_size stats 



These stats are useful for getting a feel for the queue depth of the cgroup,
i.e., how filled up its queues are at a given instant and over the existence of
the cgroup. This ability is useful when debugging problems in the wild as it
helps understand the application's IO pattern w/o having to read through the
userspace code (coz its tedious or just not available) or w/o the ability
to run blktrace (since you may not have root access and/or not want to disturb
performance).

Signed-off-by: default avatarDivyesh <Shah&lt;dpshah@google.com>
Signed-off-by: default avatarJens Axboe <jens.axboe@oracle.com>
parent 812d4026

Documentation/cgroups/blkio-controller.txt

+11 −0
Original line number Diff line number Diff line
@@ -139,6 +139,17 @@ Details of cgroup files 
	  cgroup. This is further divided by the type of operation - read or

	  write, sync or async.



- blkio.io_queued

	- Total number of requests queued up at any given instant for this

	  cgroup. This is further divided by the type of operation - read or

	  write, sync or async.



- blkio.avg_queue_size

	- Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y.

	  The average queue size for this cgroup over the entire time of this

	  cgroup's existence. Queue size samples are taken each time one of the

	  queues of this cgroup gets a timeslice.



- blkio.dequeue

	- Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. This

	  gives the statistics about how many a times a group was dequeued

block/blk-cgroup.c

+93 −5
Original line number Diff line number Diff line
@@ -81,6 +81,71 @@ static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction, 
		stat[BLKIO_STAT_ASYNC] += add;

}



/*

 * Decrements the appropriate stat variable if non-zero depending on the

 * request type. Panics on value being zero.

 * This should be called with the blkg->stats_lock held.

 */

static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync)

{

	if (direction) {

		BUG_ON(stat[BLKIO_STAT_WRITE] == 0);

		stat[BLKIO_STAT_WRITE]--;

	} else {

		BUG_ON(stat[BLKIO_STAT_READ] == 0);

		stat[BLKIO_STAT_READ]--;

	}

	if (sync) {

		BUG_ON(stat[BLKIO_STAT_SYNC] == 0);

		stat[BLKIO_STAT_SYNC]--;

	} else {

		BUG_ON(stat[BLKIO_STAT_ASYNC] == 0);

		stat[BLKIO_STAT_ASYNC]--;

	}

}



#ifdef CONFIG_DEBUG_BLK_CGROUP

void blkiocg_update_set_active_queue_stats(struct blkio_group *blkg)

{

	unsigned long flags;

	struct blkio_group_stats *stats;



	spin_lock_irqsave(&blkg->stats_lock, flags);

	stats = &blkg->stats;

	stats->avg_queue_size_sum +=

			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] +

			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE];

	stats->avg_queue_size_samples++;

	spin_unlock_irqrestore(&blkg->stats_lock, flags);

}

EXPORT_SYMBOL_GPL(blkiocg_update_set_active_queue_stats);

#endif



void blkiocg_update_request_add_stats(struct blkio_group *blkg,

			struct blkio_group *curr_blkg, bool direction,

			bool sync)

{

	unsigned long flags;



	spin_lock_irqsave(&blkg->stats_lock, flags);

	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction,

			sync);

	spin_unlock_irqrestore(&blkg->stats_lock, flags);

}

EXPORT_SYMBOL_GPL(blkiocg_update_request_add_stats);



void blkiocg_update_request_remove_stats(struct blkio_group *blkg,

						bool direction, bool sync)

{

	unsigned long flags;



	spin_lock_irqsave(&blkg->stats_lock, flags);

	blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED],

					direction, sync);

	spin_unlock_irqrestore(&blkg->stats_lock, flags);

}

EXPORT_SYMBOL_GPL(blkiocg_update_request_remove_stats);



void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)

{

	unsigned long flags;
@@ -253,14 +318,18 @@ blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val) 
	struct blkio_cgroup *blkcg;

	struct blkio_group *blkg;

	struct hlist_node *n;

	struct blkio_group_stats *stats;

	uint64_t queued[BLKIO_STAT_TOTAL];

	int i;



	blkcg = cgroup_to_blkio_cgroup(cgroup);

	spin_lock_irq(&blkcg->lock);

	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {

		spin_lock(&blkg->stats_lock);

		stats = &blkg->stats;

		memset(stats, 0, sizeof(struct blkio_group_stats));

		for (i = 0; i < BLKIO_STAT_TOTAL; i++)

			queued[i] = blkg->stats.stat_arr[BLKIO_STAT_QUEUED][i];

		memset(&blkg->stats, 0, sizeof(struct blkio_group_stats));

		for (i = 0; i < BLKIO_STAT_TOTAL; i++)

			blkg->stats.stat_arr[BLKIO_STAT_QUEUED][i] = queued[i];

		spin_unlock(&blkg->stats_lock);

	}

	spin_unlock_irq(&blkcg->lock);
@@ -323,6 +392,15 @@ static uint64_t blkio_get_stat(struct blkio_group *blkg, 
		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,

					blkg->stats.sectors, cb, dev);

#ifdef CONFIG_DEBUG_BLK_CGROUP

	if (type == BLKIO_STAT_AVG_QUEUE_SIZE) {

		uint64_t sum = blkg->stats.avg_queue_size_sum;

		uint64_t samples = blkg->stats.avg_queue_size_samples;

		if (samples)

			do_div(sum, samples);

		else

			sum = 0;

		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev);

	}

	if (type == BLKIO_STAT_DEQUEUE)

		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,

					blkg->stats.dequeue, cb, dev);
@@ -376,8 +454,10 @@ SHOW_FUNCTION_PER_GROUP(io_serviced, BLKIO_STAT_SERVICED, 1); 
SHOW_FUNCTION_PER_GROUP(io_service_time, BLKIO_STAT_SERVICE_TIME, 1);

SHOW_FUNCTION_PER_GROUP(io_wait_time, BLKIO_STAT_WAIT_TIME, 1);

SHOW_FUNCTION_PER_GROUP(io_merged, BLKIO_STAT_MERGED, 1);

SHOW_FUNCTION_PER_GROUP(io_queued, BLKIO_STAT_QUEUED, 1);

#ifdef CONFIG_DEBUG_BLK_CGROUP

SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0);

SHOW_FUNCTION_PER_GROUP(avg_queue_size, BLKIO_STAT_AVG_QUEUE_SIZE, 0);

#endif

#undef SHOW_FUNCTION_PER_GROUP
@@ -424,11 +504,19 @@ struct cftype blkio_files[] = { 
		.name = "io_merged",

		.read_map = blkiocg_io_merged_read,

	},

	{

		.name = "io_queued",

		.read_map = blkiocg_io_queued_read,

	},

	{

		.name = "reset_stats",

		.write_u64 = blkiocg_reset_stats,

	},

#ifdef CONFIG_DEBUG_BLK_CGROUP

	{

		.name = "avg_queue_size",

		.read_map = blkiocg_avg_queue_size_read,

	},

	{

		.name = "dequeue",

		.read_map = blkiocg_dequeue_read,

block/blk-cgroup.h

+19 −1
Original line number Diff line number Diff line
@@ -36,10 +36,13 @@ enum stat_type { 
	BLKIO_STAT_WAIT_TIME,

	/* Number of IOs merged */

	BLKIO_STAT_MERGED,

	/* Number of IOs queued up */

	BLKIO_STAT_QUEUED,

	/* All the single valued stats go below this */

	BLKIO_STAT_TIME,

	BLKIO_STAT_SECTORS,

#ifdef CONFIG_DEBUG_BLK_CGROUP

	BLKIO_STAT_AVG_QUEUE_SIZE,

	BLKIO_STAT_DEQUEUE

#endif

};
@@ -63,8 +66,12 @@ struct blkio_group_stats { 
	/* total disk time and nr sectors dispatched by this group */

	uint64_t time;

	uint64_t sectors;

	uint64_t stat_arr[BLKIO_STAT_MERGED + 1][BLKIO_STAT_TOTAL];

	uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL];

#ifdef CONFIG_DEBUG_BLK_CGROUP

	/* Sum of number of IOs queued across all samples */

	uint64_t avg_queue_size_sum;

	/* Count of samples taken for average */

	uint64_t avg_queue_size_samples;

	/* How many times this group has been removed from service tree */

	unsigned long dequeue;

#endif
@@ -127,10 +134,13 @@ static inline char *blkg_path(struct blkio_group *blkg) 
{

	return blkg->path;

}

void blkiocg_update_set_active_queue_stats(struct blkio_group *blkg);

void blkiocg_update_dequeue_stats(struct blkio_group *blkg,

				unsigned long dequeue);

#else

static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }

static inline void blkiocg_update_set_active_queue_stats(

						struct blkio_group *blkg) {}

static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg,

						unsigned long dequeue) {}

#endif
@@ -152,6 +162,10 @@ void blkiocg_update_completion_stats(struct blkio_group *blkg, 
	uint64_t start_time, uint64_t io_start_time, bool direction, bool sync);

void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,

					bool sync);

void blkiocg_update_request_add_stats(struct blkio_group *blkg,

		struct blkio_group *curr_blkg, bool direction, bool sync);

void blkiocg_update_request_remove_stats(struct blkio_group *blkg,

					bool direction, bool sync);

#else

struct cgroup;

static inline struct blkio_cgroup *
@@ -175,5 +189,9 @@ static inline void blkiocg_update_completion_stats(struct blkio_group *blkg, 
		bool sync) {}

static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg,

						bool direction, bool sync) {}

static inline void blkiocg_update_request_add_stats(struct blkio_group *blkg,

		struct blkio_group *curr_blkg, bool direction, bool sync) {}

static inline void blkiocg_update_request_remove_stats(struct blkio_group *blkg,

						bool direction, bool sync) {}

#endif

#endif /* _BLK_CGROUP_H */

block/cfq-iosched.c

+11 −0
Original line number Diff line number Diff line
@@ -1380,7 +1380,12 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq) 
{

	elv_rb_del(&cfqq->sort_list, rq);

	cfqq->queued[rq_is_sync(rq)]--;

	blkiocg_update_request_remove_stats(&cfqq->cfqg->blkg, rq_data_dir(rq),

						rq_is_sync(rq));

	cfq_add_rq_rb(rq);

	blkiocg_update_request_add_stats(

			&cfqq->cfqg->blkg, &cfqq->cfqd->serving_group->blkg,

			rq_data_dir(rq), rq_is_sync(rq));

}



static struct request *
@@ -1436,6 +1441,8 @@ static void cfq_remove_request(struct request *rq) 
	cfq_del_rq_rb(rq);



	cfqq->cfqd->rq_queued--;

	blkiocg_update_request_remove_stats(&cfqq->cfqg->blkg, rq_data_dir(rq),

						rq_is_sync(rq));

	if (rq_is_meta(rq)) {

		WARN_ON(!cfqq->meta_pending);

		cfqq->meta_pending--;
@@ -1527,6 +1534,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, 
	if (cfqq) {

		cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",

				cfqd->serving_prio, cfqd->serving_type);

		blkiocg_update_set_active_queue_stats(&cfqq->cfqg->blkg);

		cfqq->slice_start = 0;

		cfqq->dispatch_start = jiffies;

		cfqq->allocated_slice = 0;
@@ -3213,6 +3221,9 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) 
	list_add_tail(&rq->queuelist, &cfqq->fifo);

	cfq_add_rq_rb(rq);



	blkiocg_update_request_add_stats(&cfqq->cfqg->blkg,

			&cfqd->serving_group->blkg, rq_data_dir(rq),

			rq_is_sync(rq));

	cfq_rq_enqueued(cfqd, cfqq, rq);

}