[RFC 1/3] block: estimate disk bandwidth

[Shaohua Li]

weight based blk-throttling can use the estimated bandwidth to calculate
cgroup bandwidth.

Signed-off-by: Shaohua Li <shli@xxxxxx>
---
 block/blk-core.c       | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 block/blk-sysfs.c      | 13 +++++++++++++
 include/linux/blkdev.h |  4 ++++
 3 files changed, 66 insertions(+)

diff --git a/block/blk-core.c b/block/blk-core.c
index 33e2f62..8c85bb0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -753,6 +753,12 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (blkcg_init_queue(q))
 		goto fail_ref;
 
+	/*
+	 * assign a big initial bandwidth (10GB/s), so blk-throte doesn't start
+	 * slowly
+	 */
+	q->avg_bw[READ] = 10 * 1024 * 1024 * 2;
+	q->avg_bw[WRITE] = 10 * 1024 * 1024 * 2;
 	return q;
 
 fail_ref:
@@ -1909,6 +1915,46 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
 	return 0;
 }
 
+static void blk_update_bandwidth(struct request_queue *q,
+	struct hd_struct *p)
+{
+	unsigned long now = jiffies;
+	unsigned long last = q->bw_timestamp;
+	sector_t bw;
+	sector_t read_sect, write_sect, tmp_sect;
+
+	if (time_before(now, last + HZ / 5))
+		return;
+
+	if (cmpxchg(&q->bw_timestamp, last, now) != last)
+		return;
+
+	tmp_sect = part_stat_read(p, sectors[READ]);
+	read_sect = tmp_sect - q->last_sects[READ];
+	q->last_sects[READ] = tmp_sect;
+	tmp_sect = part_stat_read(p, sectors[WRITE]);
+	write_sect = tmp_sect - q->last_sects[WRITE];
+	q->last_sects[WRITE] = tmp_sect;
+
+	if (now - last > HZ)
+		return;
+	if (now == last)
+		return;
+
+	bw = read_sect * HZ;
+	sector_div(bw, now - last);
+	if (q->avg_bw[READ] < bw)
+		q->avg_bw[READ] += (bw - q->avg_bw[READ]) >> 3;
+	if (q->avg_bw[READ] > bw)
+		q->avg_bw[READ] -= (q->avg_bw[READ] - bw) >> 3;
+	bw = write_sect * HZ;
+	sector_div(bw, now - last);
+	if (q->avg_bw[WRITE] < bw)
+		q->avg_bw[WRITE] += (bw - q->avg_bw[WRITE]) >> 3;
+	if (q->avg_bw[WRITE] > bw)
+		q->avg_bw[WRITE] -= (q->avg_bw[WRITE] - bw) >> 3;
+}
+
 static noinline_for_stack bool
 generic_make_request_checks(struct bio *bio)
 {
@@ -1981,6 +2027,9 @@ generic_make_request_checks(struct bio *bio)
 	 */
 	create_io_context(GFP_ATOMIC, q->node);
 
+	blk_update_bandwidth(q,
+		part->partno ? &part_to_disk(part)->part0 : part);
+
 	if (!blkcg_bio_issue_check(q, bio))
 		return false;
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e140cc4..419f6bd 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -348,6 +348,13 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 	return ret;
 }
 
+static ssize_t queue_avg_perf_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%llu %llu\n",
+		       (unsigned long long)q->avg_bw[READ] * 512,
+		       (unsigned long long)q->avg_bw[WRITE] * 512);
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -479,6 +486,11 @@ static struct queue_sysfs_entry queue_poll_entry = {
 	.store = queue_poll_store,
 };
 
+static struct queue_sysfs_entry queue_avg_perf_entry = {
+	.attr = {.name = "average_perf", .mode = S_IRUGO },
+	.show = queue_avg_perf_show,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -504,6 +516,7 @@ static struct attribute *default_attrs[] = {
 	&queue_iostats_entry.attr,
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
+	&queue_avg_perf_entry.attr,
 	NULL,
 };
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c70e358..7e6b8ed 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -464,6 +464,10 @@ struct request_queue {
 	struct bio_set		*bio_split;
 
 	bool			mq_sysfs_init_done;
+
+	unsigned long bw_timestamp;
+	sector_t avg_bw[2];
+	sector_t last_sects[2];
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
-- 
2.4.6