md/raid5: sort bios

Previous patch (raid5: only dispatch IO from raid5d for harddisk raid)
defers IO dispatching. The goal is to create better IO pattern. At that
time, we don't sort the deffered IO and hope the block layer can do IO
merge and sort. Now the raid5-cache writeback could create large amount
of bios. And if we enable muti-thread for stripe handling, we can't
control when to dispatch IO to raid disks. In a lot of time, we are
dispatching IO which block layer can't do merge effectively.

This patch moves further for the IO dispatching defer. We accumulate
bios, but we don't dispatch all the bios after a threshold is met. This
'dispatch partial portion of bios' stragety allows bios coming in a
large time window are sent to disks together. At the dispatching time,
there is large chance the block layer can merge the bios. To make this
more effective, we dispatch IO in ascending order. This increases
request merge chance and reduces disk seek.

Signed-off-by: Shaohua Li <shli@fb.com>

1 files changed, 113 insertions, 25 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5a28bd9b5b5f..013398ce2080 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -58,6 +58,7 @@
 #include <linux/sched/signal.h>
 
 #include <trace/events/block.h>
+#include <linux/list_sort.h>
 
 #include "md.h"
 #include "raid5.h"
@@ -878,41 +879,107 @@ static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
 	return 1;
 }
 
-static void flush_deferred_bios(struct r5conf *conf)
+static void dispatch_bio_list(struct bio_list *tmp)
 {
-	struct bio_list tmp;
 	struct bio *bio;
 
-	if (!conf->batch_bio_dispatch || !conf->group_cnt)
+	while ((bio = bio_list_pop(tmp)))
+		generic_make_request(bio);
+}
+
+static int cmp_stripe(void *priv, struct list_head *a, struct list_head *b)
+{
+	const struct r5pending_data *da = list_entry(a,
+				struct r5pending_data, sibling);
+	const struct r5pending_data *db = list_entry(b,
+				struct r5pending_data, sibling);
+	if (da->sector > db->sector)
+		return 1;
+	if (da->sector < db->sector)
+		return -1;
+	return 0;
+}
+
+static void dispatch_defer_bios(struct r5conf *conf, int target,
+				struct bio_list *list)
+{
+	struct r5pending_data *data;
+	struct list_head *first, *next = NULL;
+	int cnt = 0;
+
+	if (conf->pending_data_cnt == 0)
+		return;
+
+	list_sort(NULL, &conf->pending_list, cmp_stripe);
+
+	first = conf->pending_list.next;
+
+	/* temporarily move the head */
+	if (conf->next_pending_data)
+		list_move_tail(&conf->pending_list,
+				&conf->next_pending_data->sibling);
+
+	while (!list_empty(&conf->pending_list)) {
+		data = list_first_entry(&conf->pending_list,
+			struct r5pending_data, sibling);
+		if (&data->sibling == first)
+			first = data->sibling.next;
+		next = data->sibling.next;
+
+		bio_list_merge(list, &data->bios);
+		list_move(&data->sibling, &conf->free_list);
+		cnt++;
+		if (cnt >= target)
+			break;
+	}
+	conf->pending_data_cnt -= cnt;
+	BUG_ON(conf->pending_data_cnt < 0 || cnt < target);
+
+	if (next != &conf->pending_list)
+		conf->next_pending_data = list_entry(next,
+				struct r5pending_data, sibling);
+	else
+		conf->next_pending_data = NULL;
+	/* list isn't empty */
+	if (first != &conf->pending_list)
+		list_move_tail(&conf->pending_list, first);
+}
+
+static void flush_deferred_bios(struct r5conf *conf)
+{
+	struct bio_list tmp = BIO_EMPTY_LIST;
+
+	if (conf->pending_data_cnt == 0)
 		return;
 
-	bio_list_init(&tmp);
 	spin_lock(&conf->pending_bios_lock);
-	bio_list_merge(&tmp, &conf->pending_bios);
-	bio_list_init(&conf->pending_bios);
+	dispatch_defer_bios(conf, conf->pending_data_cnt, &tmp);
+	BUG_ON(conf->pending_data_cnt != 0);
 	spin_unlock(&conf->pending_bios_lock);
 
-	while ((bio = bio_list_pop(&tmp)))
-		generic_make_request(bio);
+	dispatch_bio_list(&tmp);
 }
 
-static void defer_bio_issue(struct r5conf *conf, struct bio *bio)
+static void defer_issue_bios(struct r5conf *conf, sector_t sector,
+				struct bio_list *bios)
 {
-	/*
-	 * change group_cnt will drain all bios, so this is safe
-	 *
-	 * A read generally means a read-modify-write, which usually means a
-	 * randwrite, so we don't delay it
-	 */
-	if (!conf->batch_bio_dispatch || !conf->group_cnt ||
-	    bio_op(bio) == REQ_OP_READ) {
-		generic_make_request(bio);
-		return;
-	}
+	struct bio_list tmp = BIO_EMPTY_LIST;
+	struct r5pending_data *ent;
+
 	spin_lock(&conf->pending_bios_lock);
-	bio_list_add(&conf->pending_bios, bio);
+	ent = list_first_entry(&conf->free_list, struct r5pending_data,
+							sibling);
+	list_move_tail(&ent->sibling, &conf->pending_list);
+	ent->sector = sector;
+	bio_list_init(&ent->bios);
+	bio_list_merge(&ent->bios, bios);
+	conf->pending_data_cnt++;
+	if (conf->pending_data_cnt >= PENDING_IO_MAX)
+		dispatch_defer_bios(conf, PENDING_IO_ONE_FLUSH, &tmp);
+
 	spin_unlock(&conf->pending_bios_lock);
-	md_wakeup_thread(conf->mddev->thread);
+
+	dispatch_bio_list(&tmp);
 }
 
 static void
@@ -925,6 +992,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 	struct r5conf *conf = sh->raid_conf;
 	int i, disks = sh->disks;
 	struct stripe_head *head_sh = sh;
+	struct bio_list pending_bios = BIO_EMPTY_LIST;
+	bool should_defer;
 
 	might_sleep();
 
@@ -941,6 +1010,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 		}
 	}
 
+	should_defer = conf->batch_bio_dispatch && conf->group_cnt;
+
 	for (i = disks; i--; ) {
 		int op, op_flags = 0;
 		int replace_only = 0;
@@ -1095,7 +1166,10 @@ again:
 				trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
 						      bi, disk_devt(conf->mddev->gendisk),
 						      sh->dev[i].sector);
-			defer_bio_issue(conf, bi);
+			if (should_defer && op_is_write(op))
+				bio_list_add(&pending_bios, bi);
+			else
+				generic_make_request(bi);
 		}
 		if (rrdev) {
 			if (s->syncing || s->expanding || s->expanded
@@ -1140,7 +1214,10 @@ again:
 				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
 						      rbi, disk_devt(conf->mddev->gendisk),
 						      sh->dev[i].sector);
-			defer_bio_issue(conf, rbi);
+			if (should_defer && op_is_write(op))
+				bio_list_add(&pending_bios, rbi);
+			else
+				generic_make_request(rbi);
 		}
 		if (!rdev && !rrdev) {
 			if (op_is_write(op))
@@ -1158,6 +1235,9 @@ again:
 		if (sh != head_sh)
 			goto again;
 	}
+
+	if (should_defer && !bio_list_empty(&pending_bios))
+		defer_issue_bios(conf, head_sh->sector, &pending_bios);
 }
 
 static struct dma_async_tx_descriptor *
@@ -6678,6 +6758,7 @@ static void free_conf(struct r5conf *conf)
 			put_page(conf->disks[i].extra_page);
 	kfree(conf->disks);
 	kfree(conf->stripe_hashtbl);
+	kfree(conf->pending_data);
 	kfree(conf);
 }
 
@@ -6787,6 +6868,14 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL);
 	if (conf == NULL)
 		goto abort;
+	INIT_LIST_HEAD(&conf->free_list);
+	INIT_LIST_HEAD(&conf->pending_list);
+	conf->pending_data = kzalloc(sizeof(struct r5pending_data) *
+		PENDING_IO_MAX, GFP_KERNEL);
+	if (!conf->pending_data)
+		goto abort;
+	for (i = 0; i < PENDING_IO_MAX; i++)
+		list_add(&conf->pending_data[i].sibling, &conf->free_list);
 	/* Don't enable multi-threading by default*/
 	if (!alloc_thread_groups(conf, 0, &group_cnt, &worker_cnt_per_group,
 				 &new_group)) {
@@ -6811,7 +6900,6 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	atomic_set(&conf->active_stripes, 0);
 	atomic_set(&conf->preread_active_stripes, 0);
 	atomic_set(&conf->active_aligned_reads, 0);
-	bio_list_init(&conf->pending_bios);
 	spin_lock_init(&conf->pending_bios_lock);
 	conf->batch_bio_dispatch = true;
 	rdev_for_each(rdev, mddev) {