blk-stat: convert to callback-based statistics reporting

Currently, statistics are gathered in ~0.13s windows, and users grab the
statistics whenever they need them. This is not ideal for both in-tree
users:

1. Writeback throttling wants its own dynamically sized window of
   statistics. Since the blk-stats statistics are reset after every
   window and the wbt windows don't line up with the blk-stats windows,
   wbt doesn't see every I/O.
2. Polling currently grabs the statistics on every I/O. Again, depending
   on how the window lines up, we may miss some I/Os. It's also
   unnecessary overhead to get the statistics on every I/O; the hybrid
   polling heuristic would be just as happy with the statistics from the
   previous full window.

This reworks the blk-stats infrastructure to be callback-based: users
register a callback that they want called at a given time with all of
the statistics from the window during which the callback was active.
Users can dynamically bucketize the statistics. wbt and polling both
currently use read vs. write, but polling can be extended to further
subdivide based on request size.

The callbacks are kept on an RCU list, and each callback has percpu
stats buffers. There will only be a few users, so the overhead on the
I/O completion side is low. The stats flushing is also simplified
considerably: since the timer function is responsible for clearing the
statistics, we don't have to worry about stale statistics.

wbt is a trivial conversion. After the conversion, the windowing problem
mentioned above is fixed.

For polling, we register an extra callback that caches the previous
window's statistics in the struct request_queue for the hybrid polling
heuristic to use.

Since we no longer have a single stats buffer for the request queue,
this also removes the sysfs and debugfs stats entries. To replace those,
we add a debugfs entry for the poll statistics.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 5 insertions, 26 deletions

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index fdb45fd0db0b..fa831cb2fc30 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -503,26 +503,6 @@ static ssize_t queue_dax_show(struct request_queue *q, char *page)
 	return queue_var_show(blk_queue_dax(q), page);
 }
 
-static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
-{
-	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
-			pre, (long long) stat->nr_samples,
-			(long long) stat->mean, (long long) stat->min,
-			(long long) stat->max);
-}
-
-static ssize_t queue_stats_show(struct request_queue *q, char *page)
-{
-	struct blk_rq_stat stat[2];
-	ssize_t ret;
-
-	blk_queue_stat_get(q, stat);
-
-	ret = print_stat(page, &stat[READ], "read :");
-	ret += print_stat(page + ret, &stat[WRITE], "write:");
-	return ret;
-}
-
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -691,11 +671,6 @@ static struct queue_sysfs_entry queue_dax_entry = {
 	.show = queue_dax_show,
 };
 
-static struct queue_sysfs_entry queue_stats_entry = {
-	.attr = {.name = "stats", .mode = S_IRUGO },
-	.show = queue_stats_show,
-};
-
 static struct queue_sysfs_entry queue_wb_lat_entry = {
 	.attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_wb_lat_show,
@@ -733,7 +708,6 @@ static struct attribute *default_attrs[] = {
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_dax_entry.attr,
-	&queue_stats_entry.attr,
 	&queue_wb_lat_entry.attr,
 	&queue_poll_delay_entry.attr,
 	NULL,
@@ -811,6 +785,9 @@ static void blk_release_queue(struct kobject *kobj)
 		container_of(kobj, struct request_queue, kobj);
 
 	wbt_exit(q);
+	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+		blk_stat_remove_callback(q, q->poll_cb);
+	blk_stat_free_callback(q->poll_cb);
 	bdi_put(q->backing_dev_info);
 	blkcg_exit_queue(q);
 
@@ -819,6 +796,8 @@ static void blk_release_queue(struct kobject *kobj)
 		elevator_exit(q->elevator);
 	}
 
+	blk_free_queue_stats(q->stats);
+
 	blk_exit_rl(&q->root_rl);
 
 	if (q->queue_tags)