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, 8 insertions, 2 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5a7da60..1a7dc42 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -40,6 +40,8 @@ struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
 struct rq_wb;
+struct blk_queue_stats;
+struct blk_stat_callback;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -388,6 +390,7 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
+	struct blk_queue_stats	*stats;
 	struct rq_wb		*rq_wb;
 
 	/*
@@ -505,8 +508,6 @@ struct request_queue {
 	unsigned int		nr_sorted;
 	unsigned int		in_flight[2];
 
-	struct blk_rq_stat	rq_stats[2];
-
 	/*
 	 * Number of active block driver functions for which blk_drain_queue()
 	 * must wait. Must be incremented around functions that unlock the
@@ -516,6 +517,10 @@ struct request_queue {
 
 	unsigned int		rq_timeout;
 	int			poll_nsec;
+
+	struct blk_stat_callback	*poll_cb;
+	struct blk_rq_stat	poll_stat[2];
+
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 	struct list_head	timeout_list;
@@ -611,6 +616,7 @@ struct request_queue {
 #define QUEUE_FLAG_DAX         26	/* device supports DAX */
 #define QUEUE_FLAG_STATS       27	/* track rq completion times */
 #define QUEUE_FLAG_RESTART     28	/* queue needs restart at completion */
+#define QUEUE_FLAG_POLL_STATS  29	/* collecting stats for hybrid polling */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\