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>

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-cpumap.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/

block/blk-core.c

@@ -2464,6 +2464,11 @@ void blk_start_request(struct request *req)
 {
 	blk_dequeue_request(req);
 
+	if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
+		blk_stat_set_issue_time(&req->issue_stat);
+		req->rq_flags |= RQF_STATS;
+	}
+
 	/*
 	 * We are now handing the request to the hardware, initialize
 	 * resid_len to full count and add the timeout handler.
@@ -2683,8 +2688,13 @@ EXPORT_SYMBOL_GPL(blk_unprep_request);
  */
 void blk_finish_request(struct request *req, int error)
 {
+	struct request_queue *q = req->q;
+
+	if (req->rq_flags & RQF_STATS)
+		blk_stat_add(&q->rq_stats[rq_data_dir(req)], req);
+
 	if (req->rq_flags & RQF_QUEUED)
-		blk_queue_end_tag(req->q, req);
+		blk_queue_end_tag(q, req);
 
 	BUG_ON(blk_queued_rq(req));
 
@@ -2704,7 +2714,7 @@ void blk_finish_request(struct request *req, int error)
 		if (blk_bidi_rq(req))
 			__blk_put_request(req->next_rq->q, req->next_rq);
 
-		__blk_put_request(req->q, req);
+		__blk_put_request(q, req);
 	}
 }
 EXPORT_SYMBOL(blk_finish_request);

block/blk-mq-sysfs.c

@@ -259,6 +259,47 @@ 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[BLK_STAT_READ]);
+		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
+	}
+}
+
+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[BLK_STAT_READ]);
+	blk_stat_init(&stat[BLK_STAT_WRITE]);
+
+	blk_hctx_stat_get(hctx, stat);
+
+	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
+	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "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,
@@ -317,6 +358,11 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = {
 	.show = blk_mq_hw_sysfs_poll_show,
 	.store = blk_mq_hw_sysfs_poll_store,
 };
+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,
@@ -327,6 +373,7 @@ 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,
 };
 

block/blk-mq.c

@@ -30,6 +30,7 @@
 #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);
@@ -403,10 +404,27 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 	put_cpu();
 }
 
+static void blk_mq_stat_add(struct request *rq)
+{
+	if (rq->rq_flags & RQF_STATS) {
+		/*
+		 * We could rq->mq_ctx here, but there's less of a risk
+		 * of races if we have the completion event add the stats
+		 * to the local software queue.
+		 */
+		struct blk_mq_ctx *ctx;
+
+		ctx = __blk_mq_get_ctx(rq->q, raw_smp_processor_id());
+		blk_stat_add(&ctx->stat[rq_data_dir(rq)], 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
@@ -450,6 +468,11 @@ 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);
 
+	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
+		blk_stat_set_issue_time(&rq->issue_stat);
+		rq->rq_flags |= RQF_STATS;
+	}
+
 	blk_add_timer(rq);
 
 	/*
@@ -1784,6 +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[BLK_STAT_READ]);
+		blk_stat_init(&__ctx->stat[BLK_STAT_WRITE]);
 
 		/* If the cpu isn't online, the cpu is mapped to first hctx */
 		if (!cpu_online(i))

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 {
@@ -18,6 +20,7 @@ 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;