block: add scalable completion tracking of requests

For legacy block, we simply track them in the request queue. For
blk-mq, we track them on a per-sw queue basis, which we can then
sum up through the hardware queues and finally to a per device
state.

The stats are tracked in, roughly, 0.1s interval windows.

Add sysfs files to display the stats.

The feature is off by default, to avoid any extra overhead. In-kernel
users of it can turn it on by setting QUEUE_FLAG_STATS in the queue
flags. We currently don't turn it on if someone just reads any of
the stats files, that is something we could add as well.

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

1 files changed, 42 insertions, 0 deletions

diff --git a/block/blk-stat.h b/block/blk-stat.h
new file mode 100644
index 0000000000000..a2050a0a5314b
--- /dev/null
+++ b/block/blk-stat.h
@@ -0,0 +1,42 @@
+#ifndef BLK_STAT_H
+#define BLK_STAT_H
+
+/*
+ * ~0.13s window as a power-of-2 (2^27 nsecs)
+ */
+#define BLK_STAT_NSEC		134217728ULL
+#define BLK_STAT_NSEC_MASK	~(BLK_STAT_NSEC - 1)
+
+/*
+ * Upper 3 bits can be used elsewhere
+ */
+#define BLK_STAT_RES_BITS	3
+#define BLK_STAT_SHIFT		(64 - BLK_STAT_RES_BITS)
+#define BLK_STAT_TIME_MASK	((1ULL << BLK_STAT_SHIFT) - 1)
+#define BLK_STAT_MASK		~BLK_STAT_TIME_MASK
+
+enum {
+	BLK_STAT_READ	= 0,
+	BLK_STAT_WRITE,
+};
+
+void blk_stat_add(struct blk_rq_stat *, struct request *);
+void blk_hctx_stat_get(struct blk_mq_hw_ctx *, struct blk_rq_stat *);
+void blk_queue_stat_get(struct request_queue *, struct blk_rq_stat *);
+void blk_stat_clear(struct request_queue *);
+void blk_stat_init(struct blk_rq_stat *);
+bool blk_stat_is_current(struct blk_rq_stat *);
+void blk_stat_set_issue_time(struct blk_issue_stat *);
+bool blk_stat_enable(struct request_queue *);
+
+static inline u64 __blk_stat_time(u64 time)
+{
+	return time & BLK_STAT_TIME_MASK;
+}
+
+static inline u64 blk_stat_time(struct blk_issue_stat *stat)
+{
+	return __blk_stat_time(stat->time);
+}
+
+#endif