[PATCH 6/8] block: add scalable completion tracking of requests

[Jens Axboe <axboe@fb.com>]

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.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/Makefile            |   2 +-
 block/blk-core.c          |   4 +
 block/blk-mq-sysfs.c      |  47 +++++++++++
 block/blk-mq.c            |  14 ++++
 block/blk-mq.h            |   3 +
 block/blk-stat.c          | 204 ++++++++++++++++++++++++++++++++++++++++++++++
 block/blk-stat.h          |  17 ++++
 block/blk-sysfs.c         |  26 ++++++
 include/linux/blk_types.h |  12 +++
 include/linux/blkdev.h    |   4 +
 10 files changed, 332 insertions(+), 1 deletion(-)
 create mode 100644 block/blk-stat.c
 create mode 100644 block/blk-stat.h

diff --git a/block/Makefile b/block/Makefile
index 9eda2322b2d4..3446e0472df0 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			blk-lib.o blk-mq.o blk-mq-tag.o \
+			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
diff --git a/block/blk-core.c b/block/blk-core.c
index 36c7ac328d8c..4075cbeb720e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2475,6 +2475,8 @@ void blk_start_request(struct request *req)
 {
 	blk_dequeue_request(req);
 
+	req->issue_time = ktime_to_ns(ktime_get());
+
 	/*
 	 * We are now handing the request to the hardware, initialize
 	 * resid_len to full count and add the timeout handler.
@@ -2542,6 +2544,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 
 	trace_block_rq_complete(req->q, req, nr_bytes);
 
+	blk_stat_add(&req->q->rq_stats[rq_data_dir(req)], req);
+
 	if (!req->bio)
 		return false;
 
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index fe822aa5b8e4..b66bbf13cc12 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -247,6 +247,47 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 	return ret;
 }
 
+static void blk_mq_stat_clear(struct blk_mq_hw_ctx *hctx)
+{
+	struct blk_mq_ctx *ctx;
+	unsigned int i;
+
+	hctx_for_each_ctx(hctx, ctx, i) {
+		blk_stat_init(&ctx->stat[0]);
+		blk_stat_init(&ctx->stat[1]);
+	}
+}
+
+static ssize_t blk_mq_hw_sysfs_stat_store(struct blk_mq_hw_ctx *hctx,
+					  const char *page, size_t count)
+{
+	blk_mq_stat_clear(hctx);
+	return count;
+}
+
+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 blk_mq_hw_sysfs_stat_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	struct blk_rq_stat stat[2];
+	ssize_t ret;
+
+	blk_stat_init(&stat[0]);
+	blk_stat_init(&stat[1]);
+
+	blk_hctx_stat_get(hctx, stat);
+
+	ret = print_stat(page, &stat[0], "read :");
+	ret += print_stat(page + ret, &stat[1], "write:");
+	return ret;
+}
+
 static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
 	.attr = {.name = "dispatched", .mode = S_IRUGO },
 	.show = blk_mq_sysfs_dispatched_show,
@@ -304,6 +345,11 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = {
 	.attr = {.name = "io_poll", .mode = S_IRUGO },
 	.show = blk_mq_hw_sysfs_poll_show,
 };
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_stat = {
+	.attr = {.name = "stats", .mode = S_IRUGO | S_IWUSR },
+	.show = blk_mq_hw_sysfs_stat_show,
+	.store = blk_mq_hw_sysfs_stat_store,
+};
 
 static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_queued.attr,
@@ -314,6 +360,7 @@ static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_cpus.attr,
 	&blk_mq_hw_sysfs_active.attr,
 	&blk_mq_hw_sysfs_poll.attr,
+	&blk_mq_hw_sysfs_stat.attr,
 	NULL,
 };
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 13f5a6c1de76..712f141a6f1a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -29,6 +29,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
+#include "blk-stat.h"
 
 static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
@@ -400,10 +401,19 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 	put_cpu();
 }
 
+static void blk_mq_stat_add(struct request *rq)
+{
+	struct blk_rq_stat *stat = &rq->mq_ctx->stat[rq_data_dir(rq)];
+
+	blk_stat_add(stat, rq);
+}
+
 static void __blk_mq_complete_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	blk_mq_stat_add(rq);
+
 	if (!q->softirq_done_fn)
 		blk_mq_end_request(rq, rq->errors);
 	else
@@ -447,6 +457,8 @@ void blk_mq_start_request(struct request *rq)
 	if (unlikely(blk_bidi_rq(rq)))
 		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
 
+	rq->issue_time = ktime_to_ns(ktime_get());
+
 	blk_add_timer(rq);
 
 	/*
@@ -1795,6 +1807,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		spin_lock_init(&__ctx->lock);
 		INIT_LIST_HEAD(&__ctx->rq_list);
 		__ctx->queue = q;
+		blk_stat_init(&__ctx->stat[0]);
+		blk_stat_init(&__ctx->stat[1]);
 
 		/* If the cpu isn't online, the cpu is mapped to first hctx */
 		if (!cpu_online(i))
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 9087b11037b7..e107f700ff17 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -1,6 +1,8 @@
 #ifndef INT_BLK_MQ_H
 #define INT_BLK_MQ_H
 
+#include "blk-stat.h"
+
 struct blk_mq_tag_set;
 
 struct blk_mq_ctx {
@@ -20,6 +22,7 @@ struct blk_mq_ctx {
 
 	/* incremented at completion time */
 	unsigned long		____cacheline_aligned_in_smp rq_completed[2];
+	struct blk_rq_stat	stat[2];
 
 	struct request_queue	*queue;
 	struct kobject		kobj;
diff --git a/block/blk-stat.c b/block/blk-stat.c
new file mode 100644
index 000000000000..76cf2e2092c1
--- /dev/null
+++ b/block/blk-stat.c
@@ -0,0 +1,204 @@
+/*
+ * Block stat tracking code
+ *
+ * Copyright (C) 2016 Jens Axboe
+ */
+#include <linux/kernel.h>
+#include <linux/blk-mq.h>
+
+#include "blk-stat.h"
+#include "blk-mq.h"
+
+static void blk_stat_flush_batch(struct blk_rq_stat *stat)
+{
+	if (!stat->nr_batch)
+		return;
+	if (!stat->nr_samples)
+		stat->mean = div64_s64(stat->batch, stat->nr_batch);
+	else {
+		stat->mean = div64_s64((stat->mean * stat->nr_samples) +
+					stat->batch,
+					stat->nr_samples + stat->nr_batch);
+	}
+
+	stat->nr_samples += stat->nr_batch;
+	stat->nr_batch = stat->batch = 0;
+}
+
+void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
+{
+	if (!src->nr_samples)
+		return;
+
+	blk_stat_flush_batch(src);
+
+	dst->min = min(dst->min, src->min);
+	dst->max = max(dst->max, src->max);
+
+	if (!dst->nr_samples)
+		dst->mean = src->mean;
+	else {
+		dst->mean = div64_s64((src->mean * src->nr_samples) +
+					(dst->mean * dst->nr_samples),
+					dst->nr_samples + src->nr_samples);
+	}
+	dst->nr_samples += src->nr_samples;
+}
+
+static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	int i, j, nr;
+
+	blk_stat_init(&dst[0]);
+	blk_stat_init(&dst[1]);
+
+	nr = 0;
+	do {
+		uint64_t newest = 0;
+
+		queue_for_each_hw_ctx(q, hctx, i) {
+			hctx_for_each_ctx(hctx, ctx, j) {
+				if (!ctx->stat[0].nr_samples &&
+				    !ctx->stat[1].nr_samples)
+					continue;
+				if (ctx->stat[0].time > newest)
+					newest = ctx->stat[0].time;
+				if (ctx->stat[1].time > newest)
+					newest = ctx->stat[1].time;
+			}
+		}
+
+		/*
+		 * No samples
+		 */
+		if (!newest)
+			break;
+
+		queue_for_each_hw_ctx(q, hctx, i) {
+			hctx_for_each_ctx(hctx, ctx, j) {
+				if (ctx->stat[0].time == newest) {
+					blk_stat_sum(&dst[0], &ctx->stat[0]);
+					nr++;
+				}
+				if (ctx->stat[1].time == newest) {
+					blk_stat_sum(&dst[1], &ctx->stat[1]);
+					nr++;
+				}
+			}
+		}
+		/*
+		 * If we race on finding an entry, just loop back again.
+		 * Should be very rare.
+		 */
+	} while (!nr);
+}
+
+void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+{
+	if (q->mq_ops)
+		blk_mq_stat_get(q, dst);
+	else {
+		memcpy(&dst[0], &q->rq_stats[0], sizeof(struct blk_rq_stat));
+		memcpy(&dst[1], &q->rq_stats[1], sizeof(struct blk_rq_stat));
+	}
+}
+
+void blk_hctx_stat_get(struct blk_mq_hw_ctx *hctx, struct blk_rq_stat *dst)
+{
+	struct blk_mq_ctx *ctx;
+	unsigned int i, nr;
+
+	nr = 0;
+	do {
+		uint64_t newest = 0;
+
+		hctx_for_each_ctx(hctx, ctx, i) {
+			if (!ctx->stat[0].nr_samples &&
+			    !ctx->stat[1].nr_samples)
+				continue;
+
+			if (ctx->stat[0].time > newest)
+				newest = ctx->stat[0].time;
+			if (ctx->stat[1].time > newest)
+				newest = ctx->stat[1].time;
+		}
+
+		if (!newest)
+			break;
+
+		hctx_for_each_ctx(hctx, ctx, i) {
+			if (ctx->stat[0].time == newest) {
+				blk_stat_sum(&dst[0], &ctx->stat[0]);
+				nr++;
+			}
+			if (ctx->stat[1].time == newest) {
+				blk_stat_sum(&dst[1], &ctx->stat[1]);
+				nr++;
+			}
+		}
+		/*
+		 * If we race on finding an entry, just loop back again.
+		 * Should be very rare, as the window is only updated
+		 * occasionally
+		 */
+	} while (!nr);
+}
+
+static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now)
+{
+	stat->min = -1ULL;
+	stat->max = stat->nr_samples = stat->mean = 0;
+	stat->batch = stat->nr_batch = 0;
+	stat->time = time_now & BLK_STAT_MASK;
+}
+
+void blk_stat_init(struct blk_rq_stat *stat)
+{
+	__blk_stat_init(stat, ktime_to_ns(ktime_get()));
+}
+
+void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
+{
+	s64 now, value;
+
+	now = ktime_to_ns(ktime_get());
+	if (now < rq->issue_time)
+		return;
+
+	if ((now & BLK_STAT_MASK) != (stat->time & BLK_STAT_MASK))
+		__blk_stat_init(stat, now);
+
+	value = now - rq->issue_time;
+	if (value > stat->max)
+		stat->max = value;
+	if (value < stat->min)
+		stat->min = value;
+
+	if (stat->batch + value < stat->batch ||
+	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
+		blk_stat_flush_batch(stat);
+
+	stat->batch += value;
+	stat->nr_batch++;
+}
+
+void blk_stat_clear(struct request_queue *q)
+{
+	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+		struct blk_mq_ctx *ctx;
+		int i, j;
+
+		queue_for_each_hw_ctx(q, hctx, i) {
+			hctx_for_each_ctx(hctx, ctx, j) {
+				blk_stat_init(&ctx->stat[0]);
+				blk_stat_init(&ctx->stat[1]);
+			}
+		}
+	} else {
+		blk_stat_init(&q->rq_stats[0]);
+		blk_stat_init(&q->rq_stats[1]);
+	}
+}
diff --git a/block/blk-stat.h b/block/blk-stat.h
new file mode 100644
index 000000000000..d77548dbf196
--- /dev/null
+++ b/block/blk-stat.h
@@ -0,0 +1,17 @@
+#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_MASK	~(BLK_STAT_NSEC - 1)
+
+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 *q);
+void blk_stat_init(struct blk_rq_stat *);
+void blk_stat_sum(struct blk_rq_stat *, struct blk_rq_stat *);
+
+#endif
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index f87a7e747d36..0b9e435fec97 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -384,6 +384,26 @@ 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[0], "read :");
+	ret += print_stat(page + ret, &stat[1], "write:");
+	return ret;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -526,6 +546,11 @@ 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 attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -553,6 +578,7 @@ static struct attribute *default_attrs[] = {
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_dax_entry.attr,
+	&queue_stats_entry.attr,
 	NULL,
 };
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index be4409b6ae4f..95fbfa1fe010 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -266,4 +266,16 @@ static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
 	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
 }
 
+#define BLK_RQ_STAT_BATCH	64
+
+struct blk_rq_stat {
+	s64 mean;
+	u64 min;
+	u64 max;
+	s32 nr_samples;
+	s32 nr_batch;
+	u64 batch;
+	s64 time;
+};
+
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1d12aa664112..259eba88f991 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -151,6 +151,7 @@ struct request {
 	struct gendisk *rq_disk;
 	struct hd_struct *part;
 	unsigned long start_time;
+	s64 issue_time;
 #ifdef CONFIG_BLK_CGROUP
 	struct request_list *rl;		/* rl this rq is alloced from */
 	unsigned long long start_time_ns;
@@ -414,6 +415,9 @@ 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
-- 
2.7.4