[PATCH V2 0/3] Improve handling raid10 discard request

[PATCH V2 0/3] Improve handling raid10 discard request

[Xiao Ni]

Hi all

Now mkfs on raid10 which is combined with ssd/nvme disks takes a long time.
This patch set tries to resolve this problem.

Xiao Ni (3):
  Move codes related with submitting discard bio into one function
  extend r10bio devs to raid disks
  improve raid10 discard request

 drivers/md/md.c     |  22 ++++
 drivers/md/md.h     |   3 +
 drivers/md/raid0.c  |  15 +--
 drivers/md/raid10.c | 297 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 318 insertions(+), 19 deletions(-)

-- 
2.7.5

[PATCH V2 1/3] Move codes related with submitting discard bio into one function

[Xiao Ni]

These codes can be used in raid10. So we can move these codes into
md.c. raid0 and raid10 can share these codes.

Reviewed-by: Coly Li <colyli@suse.de>
Signed-off-by: Xiao Ni <xni@redhat.com>
---
 drivers/md/md.c    | 22 ++++++++++++++++++++++
 drivers/md/md.h    |  3 +++
 drivers/md/raid0.c | 15 ++-------------
 3 files changed, 27 insertions(+), 13 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 07e5b67..2b8f654 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8559,6 +8559,28 @@ void md_write_end(struct mddev *mddev)
 
 EXPORT_SYMBOL(md_write_end);
 
+void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
+				struct bio *bio,
+				sector_t dev_start, sector_t dev_end)
+{
+	struct bio *discard_bio = NULL;
+
+	if (__blkdev_issue_discard(rdev->bdev,
+	    dev_start + rdev->data_offset,
+	    dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
+	    !discard_bio)
+		return;
+
+	bio_chain(discard_bio, bio);
+	bio_clone_blkg_association(discard_bio, bio);
+	if (mddev->gendisk)
+		trace_block_bio_remap(bdev_get_queue(rdev->bdev),
+			discard_bio, disk_devt(mddev->gendisk),
+			bio->bi_iter.bi_sector);
+	submit_bio_noacct(discard_bio);
+}
+EXPORT_SYMBOL(md_submit_discard_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before
diff --git a/drivers/md/md.h b/drivers/md/md.h
index c26fa8b..83ae77e 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -710,6 +710,9 @@ extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
+extern void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
+				struct bio *bio,
+				sector_t dev_start, sector_t dev_end);
 
 extern int mddev_congested(struct mddev *mddev, int bits);
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index e9e91c8..e37fe8a 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -525,7 +525,6 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 	for (disk = 0; disk < zone->nb_dev; disk++) {
 		sector_t dev_start, dev_end;
-		struct bio *discard_bio = NULL;
 		struct md_rdev *rdev;
 
 		if (disk < start_disk_index)
@@ -548,18 +547,8 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 		rdev = conf->devlist[(zone - conf->strip_zone) *
 			conf->strip_zone[0].nb_dev + disk];
-		if (__blkdev_issue_discard(rdev->bdev,
-			dev_start + zone->dev_start + rdev->data_offset,
-			dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
-		    !discard_bio)
-			continue;
-		bio_chain(discard_bio, bio);
-		bio_clone_blkg_association(discard_bio, bio);
-		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
-				discard_bio, disk_devt(mddev->gendisk),
-				bio->bi_iter.bi_sector);
-		submit_bio_noacct(discard_bio);
+		dev_start += zone->dev_start;
+		md_submit_discard_bio(mddev, rdev, bio, dev_start, dev_end);
 	}
 	bio_endio(bio);
 }
-- 
2.7.5

[PATCH V2 2/3] extend r10bio devs to raid disks

[Xiao Ni]

Now it allocs r10bio->devs[conf->copies]. Discard bio needs to submit
to all member disks and it needs to use r10bio. So extend to
r10bio->devs[geo.raid_disks].

Reviewed-by: Coly Li <colyli@suse.de>
Signed-off-by: Xiao Ni <xni@redhat.com>
---
 drivers/md/raid10.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index e45fd56..2a7423e 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -91,7 +91,7 @@ static inline struct r10bio *get_resync_r10bio(struct bio *bio)
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct r10conf *conf = data;
-	int size = offsetof(struct r10bio, devs[conf->copies]);
+	int size = offsetof(struct r10bio, devs[conf->geo.raid_disks]);
 
 	/* allocate a r10bio with room for raid_disks entries in the
 	 * bios array */
@@ -238,7 +238,7 @@ static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio)
 {
 	int i;
 
-	for (i = 0; i < conf->copies; i++) {
+	for (i = 0; i < conf->geo.raid_disks; i++) {
 		struct bio **bio = & r10_bio->devs[i].bio;
 		if (!BIO_SPECIAL(*bio))
 			bio_put(*bio);
@@ -327,7 +327,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 	int slot;
 	int repl = 0;
 
-	for (slot = 0; slot < conf->copies; slot++) {
+	for (slot = 0; slot < conf->geo.raid_disks; slot++) {
 		if (r10_bio->devs[slot].bio == bio)
 			break;
 		if (r10_bio->devs[slot].repl_bio == bio) {
@@ -336,7 +336,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 		}
 	}
 
-	BUG_ON(slot == conf->copies);
+	BUG_ON(slot == conf->geo.raid_disks);
 	update_head_pos(slot, r10_bio);
 
 	if (slotp)
@@ -1510,7 +1510,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 	r10_bio->mddev = mddev;
 	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
-	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies);
+	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->geo.raid_disks);
 
 	if (bio_data_dir(bio) == READ)
 		raid10_read_request(mddev, bio, r10_bio);
-- 
2.7.5

[PATCH V2 3/3] improve raid10 discard request

[Xiao Ni]

Now the discard request is split by chunk size. So it takes a long time
to finish mkfs on disks which support discard function. This patch improve
handling raid10 discard request. It uses the similar way with patch
29efc390b (md/md0: optimize raid0 discard handling).

But it's a little complex than raid0. Because raid10 has different layout.
If raid10 is offset layout and the discard request is smaller than stripe
size. There are some holes when we submit discard bio to underlayer disks.

For example: five disks (disk1 - disk5)
D01 D02 D03 D04 D05
D05 D01 D02 D03 D04
D06 D07 D08 D09 D10
D10 D06 D07 D08 D09
The discard bio just wants to discard from D03 to D10. For disk3, there is
a hole between D03 and D08. For disk4, there is a hole between D04 and D09.
D03 is a chunk, raid10_write_request can handle one chunk perfectly. So
the part that is not aligned with stripe size is still handled by
raid10_write_request.

If reshape is running when discard bio comes and the discard bio spans the
reshape position, raid10_write_request is responsible to handle this
discard bio.

I did a test with this patch set.
Without patch:
time mkfs.xfs /dev/md0
real4m39.775s
user0m0.000s
sys0m0.298s

With patch:
time mkfs.xfs /dev/md0
real0m0.105s
user0m0.000s
sys0m0.007s

nvme3n1           259:1    0   477G  0 disk
└─nvme3n1p1       259:10   0    50G  0 part
nvme4n1           259:2    0   477G  0 disk
└─nvme4n1p1       259:11   0    50G  0 part
nvme5n1           259:6    0   477G  0 disk
└─nvme5n1p1       259:12   0    50G  0 part
nvme2n1           259:9    0   477G  0 disk
└─nvme2n1p1       259:15   0    50G  0 part
nvme0n1           259:13   0   477G  0 disk
└─nvme0n1p1       259:14   0    50G  0 part

v1:
Coly helps to review these patches and give some suggestions:
One bug is found. If discard bio is across one stripe but bio size is bigger
than one stripe size. After spliting, the bio will be NULL. In this version,
it checks whether discard bio size is bigger than 2*stripe_size.
In raid10_end_discard_request, it's better to check R10BIO_Uptodate is set
or not. It can avoid write memory to improve performance.
Add more comments for calculating addresses.

v2:
Fix error by checkpatch.pl
Fix one bug for offset layout. v1 calculates wrongly split size
Add more comments to explain how the discard range of each component disk
is decided.

Reviewed-by: Coly Li <colyli@suse.de>
Signed-off-by: Xiao Ni <xni@redhat.com>
---
 drivers/md/raid10.c | 287 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 286 insertions(+), 1 deletion(-)

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 2a7423e..ad56563 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1518,6 +1518,287 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 		raid10_write_request(mddev, bio, r10_bio);
 }
 
+static void wait_blocked_dev(struct mddev *mddev, int cnt)
+{
+	int i;
+	struct r10conf *conf = mddev->private;
+	struct md_rdev *blocked_rdev = NULL;
+
+retry_wait:
+	rcu_read_lock();
+	for (i = 0; i < cnt; i++) {
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[i].replacement);
+		if (rdev == rrdev)
+			rrdev = NULL;
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			atomic_inc(&rdev->nr_pending);
+			blocked_rdev = rdev;
+			break;
+		}
+		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
+			atomic_inc(&rrdev->nr_pending);
+			blocked_rdev = rrdev;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	if (unlikely(blocked_rdev)) {
+		/* Have to wait for this device to get unblocked, then retry */
+		allow_barrier(conf);
+		raid10_log(conf->mddev, "%s wait rdev %d blocked",
+				__func__, blocked_rdev->raid_disk);
+		md_wait_for_blocked_rdev(blocked_rdev, mddev);
+		wait_barrier(conf);
+		goto retry_wait;
+	}
+}
+
+static struct bio *raid10_split_bio(struct r10conf *conf,
+			struct bio *bio, sector_t sectors, bool want_first)
+{
+	struct bio *split;
+
+	split = bio_split(bio, sectors,	GFP_NOIO, &conf->bio_split);
+	bio_chain(split, bio);
+	allow_barrier(conf);
+	if (want_first) {
+		submit_bio_noacct(bio);
+		bio = split;
+	} else
+		submit_bio_noacct(split);
+	wait_barrier(conf);
+
+	return bio;
+}
+
+static void raid10_end_discard_request(struct bio *bio)
+{
+	struct r10bio *r10_bio = bio->bi_private;
+	struct r10conf *conf = r10_bio->mddev->private;
+	struct md_rdev *rdev = NULL;
+	int dev;
+	int slot, repl;
+
+	/*
+	 * We don't care the return value of discard bio
+	 */
+	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
+		set_bit(R10BIO_Uptodate, &r10_bio->state);
+
+	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
+	if (repl)
+		rdev = conf->mirrors[dev].replacement;
+	if (!rdev) {
+		smp_rmb();
+		repl = 0;
+		rdev = conf->mirrors[dev].rdev;
+	}
+
+	if (atomic_dec_and_test(&r10_bio->remaining)) {
+		md_write_end(r10_bio->mddev);
+		raid_end_bio_io(r10_bio);
+	}
+
+	rdev_dec_pending(rdev, conf->mddev);
+}
+
+/* There are some limitations to handle discard bio
+ * 1st, the discard size is bigger than stripe_size*2.
+ * 2st, if the discard bio spans reshape progress, we use the old way to
+ * handle discard bio
+ */
+static bool raid10_handle_discard(struct mddev *mddev, struct bio *bio)
+{
+	struct r10conf *conf = mddev->private;
+	struct geom geo = conf->geo;
+	struct r10bio *r10_bio;
+
+	int disk;
+	sector_t chunk;
+	int stripe_size, stripe_mask;
+
+	sector_t bio_start, bio_end;
+	sector_t first_stripe_index, last_stripe_index;
+	sector_t start_disk_offset;
+	unsigned int start_disk_index;
+	sector_t end_disk_offset;
+	unsigned int end_disk_index;
+
+	wait_barrier(conf);
+
+	if (conf->reshape_progress != MaxSector &&
+	    ((bio->bi_iter.bi_sector >= conf->reshape_progress) !=
+	     conf->mddev->reshape_backwards))
+		geo = conf->prev;
+
+	stripe_size = (1<<geo.chunk_shift) * geo.raid_disks;
+	stripe_mask = stripe_size - 1;
+
+	bio_start = bio->bi_iter.bi_sector;
+	bio_end = bio_end_sector(bio);
+
+	/* Maybe one discard bio is smaller than strip size or across one stripe
+	 * and discard region is larger than one stripe size. For far offset layout,
+	 * if the discard region is not aligned with stripe size, there is hole
+	 * when we submit discard bio to member disk. For simplicity, we only
+	 * handle discard bio which discard region is bigger than stripe_size*2
+	 */
+	if (bio_sectors(bio) < stripe_size*2)
+		goto out;
+
+	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+		bio_start < conf->reshape_progress &&
+		bio_end > conf->reshape_progress)
+		goto out;
+
+	/* For far offset layout, if bio is not aligned with stripe size, it splits
+	 * the part that is not aligned with strip size.
+	 */
+	if (geo.far_offset && (bio_start & stripe_mask)) {
+		sector_t split_size;
+		split_size = round_up(bio_start, stripe_size) - bio_start;
+		bio = raid10_split_bio(conf, bio, split_size, false);
+	}
+	if (geo.far_offset && (bio_end & stripe_mask)) {
+		sector_t split_size;
+		split_size = bio_sectors(bio) - (bio_end & stripe_mask);
+		bio = raid10_split_bio(conf, bio, split_size, true);
+	}
+
+	r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
+	r10_bio->mddev = mddev;
+	r10_bio->state = 0;
+	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->geo.raid_disks);
+
+	wait_blocked_dev(mddev, geo.raid_disks);
+
+	r10_bio->master_bio = bio;
+
+	bio_start = bio->bi_iter.bi_sector;
+	bio_end = bio_end_sector(bio);
+
+	/* raid10 uses chunk as the unit to store data. It's similar like raid0.
+	 * One stripe contains the chunks from all member disk (one chunk from
+	 * one disk at the same HAB address). For layout detail, see 'man md 4'
+	 */
+	chunk = bio_start >> geo.chunk_shift;
+	chunk *= geo.near_copies;
+	first_stripe_index = chunk;
+	start_disk_index = sector_div(first_stripe_index, geo.raid_disks);
+	if (geo.far_offset)
+		first_stripe_index *= geo.far_copies;
+	start_disk_offset = (bio_start & geo.chunk_mask) +
+				(first_stripe_index << geo.chunk_shift);
+
+	chunk = bio_end >> geo.chunk_shift;
+	chunk *= geo.near_copies;
+	last_stripe_index = chunk;
+	end_disk_index = sector_div(last_stripe_index, geo.raid_disks);
+	if (geo.far_offset)
+		last_stripe_index *= geo.far_copies;
+	end_disk_offset = (bio_end & geo.chunk_mask) +
+				(last_stripe_index << geo.chunk_shift);
+
+	rcu_read_lock();
+	for (disk = 0; disk < geo.raid_disks; disk++) {
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[disk].replacement);
+
+		r10_bio->devs[disk].bio = NULL;
+		r10_bio->devs[disk].repl_bio = NULL;
+
+		if (rdev && (test_bit(Faulty, &rdev->flags)))
+			rdev = NULL;
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
+			rrdev = NULL;
+		if (!rdev && !rrdev)
+			continue;
+
+		if (rdev) {
+			r10_bio->devs[disk].bio = bio;
+			atomic_inc(&rdev->nr_pending);
+		}
+		if (rrdev) {
+			r10_bio->devs[disk].repl_bio = bio;
+			atomic_inc(&rrdev->nr_pending);
+		}
+	}
+	rcu_read_unlock();
+
+	atomic_set(&r10_bio->remaining, 1);
+	for (disk = 0; disk < geo.raid_disks; disk++) {
+		sector_t dev_start, dev_end;
+		struct bio *mbio, *rbio = NULL;
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[disk].replacement);
+
+		/*
+		 * Now start to calculate the start and end address for each disk.
+		 * The space between dev_start and dev_end is the discard region.
+		 *
+		 * For dev_start, it needs to consider three conditions:
+		 * 1st, the disk is before start_disk, you can imagine the disk in
+		 * the next stripe. So the dev_start is the start address of next
+		 * stripe.
+		 * 2st, the disk is after start_disk, it means the disk is at the
+		 * same stripe of first disk
+		 * 3st, the first disk itself, we can use start_disk_offset directly
+		 */
+		if (disk < start_disk_index)
+			dev_start = (first_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > start_disk_index)
+			dev_start = first_stripe_index * mddev->chunk_sectors;
+		else
+			dev_start = start_disk_offset;
+
+		if (disk < end_disk_index)
+			dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > end_disk_index)
+			dev_end = last_stripe_index * mddev->chunk_sectors;
+		else
+			dev_end = end_disk_offset;
+
+		/* It only handles discard bio which size is >= stripe size, so
+		 * dev_end > dev_start all the time
+		 */
+		if (r10_bio->devs[disk].bio) {
+			mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
+			mbio->bi_end_io = raid10_end_discard_request;
+			mbio->bi_private = r10_bio;
+			r10_bio->devs[disk].bio = mbio;
+			r10_bio->devs[disk].devnum = disk;
+			atomic_inc(&r10_bio->remaining);
+			md_submit_discard_bio(mddev, rdev, mbio, dev_start, dev_end);
+			bio_endio(mbio);
+		}
+		if (r10_bio->devs[disk].repl_bio) {
+			rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
+			rbio->bi_end_io = raid10_end_discard_request;
+			rbio->bi_private = r10_bio;
+			r10_bio->devs[disk].repl_bio = rbio;
+			r10_bio->devs[disk].devnum = disk;
+			atomic_inc(&r10_bio->remaining);
+			md_submit_discard_bio(mddev, rrdev, rbio, dev_start, dev_end);
+			bio_endio(rbio);
+		}
+	}
+
+	if (atomic_dec_and_test(&r10_bio->remaining)) {
+		md_write_end(r10_bio->mddev);
+		raid_end_bio_io(r10_bio);
+	}
+
+	return 0;
+out:
+	allow_barrier(conf);
+	return -EAGAIN;
+}
+
 static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct r10conf *conf = mddev->private;
@@ -1532,6 +1813,10 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	if (!md_write_start(mddev, bio))
 		return false;
 
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
+		if (!raid10_handle_discard(mddev, bio))
+			return true;
+
 	/*
 	 * If this request crosses a chunk boundary, we need to split
 	 * it.
@@ -3762,7 +4047,7 @@ static int raid10_run(struct mddev *mddev)
 	chunk_size = mddev->chunk_sectors << 9;
 	if (mddev->queue) {
 		blk_queue_max_discard_sectors(mddev->queue,
-					      mddev->chunk_sectors);
+					      UINT_MAX);
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 		blk_queue_io_min(mddev->queue, chunk_size);
-- 
2.7.5

Re: [PATCH V2 1/3] Move codes related with submitting discard bio into one function

[Guoqing Jiang]

Hi Xiao,

Better to add a prefix before subject like "md" ...", the same to other 
patches.

On 7/28/20 9:18 AM, Xiao Ni wrote:
> These codes can be used in raid10. So we can move these codes into
> md.c. raid0 and raid10 can share these codes.
>
> Reviewed-by: Coly Li <colyli@suse.de>
> Signed-off-by: Xiao Ni <xni@redhat.com>
> ---
>   drivers/md/md.c    | 22 ++++++++++++++++++++++
>   drivers/md/md.h    |  3 +++
>   drivers/md/raid0.c | 15 ++-------------
>   3 files changed, 27 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 07e5b67..2b8f654 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -8559,6 +8559,28 @@ void md_write_end(struct mddev *mddev)
>   
>   EXPORT_SYMBOL(md_write_end);
>   

Could you add comment before the function to inform it is used by raid0 
and raid10?

> +void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
> +				struct bio *bio,
> +				sector_t dev_start, sector_t dev_end)

Thanks,
Guoqing

Re: [PATCH V2 3/3] improve raid10 discard request

[Guoqing Jiang]

On 7/28/20 9:18 AM, Xiao Ni wrote:
> Now the discard request is split by chunk size. So it takes a long time
> to finish mkfs on disks which support discard function. This patch improve
> handling raid10 discard request. It uses the similar way with patch
> 29efc390b (md/md0: optimize raid0 discard handling).
>
> But it's a little complex than raid0. Because raid10 has different layout.
> If raid10 is offset layout and the discard request is smaller than stripe
> size. There are some holes when we submit discard bio to underlayer disks.
>
> For example: five disks (disk1 - disk5)
> D01 D02 D03 D04 D05
> D05 D01 D02 D03 D04
> D06 D07 D08 D09 D10
> D10 D06 D07 D08 D09
> The discard bio just wants to discard from D03 to D10. For disk3, there is
> a hole between D03 and D08. For disk4, there is a hole between D04 and D09.
> D03 is a chunk, raid10_write_request can handle one chunk perfectly. So
> the part that is not aligned with stripe size is still handled by
> raid10_write_request.

One question, is far layout handled by raid10_write_request or the
discard request?

>
> If reshape is running when discard bio comes and the discard bio spans the
> reshape position, raid10_write_request is responsible to handle this
> discard bio.
>
> I did a test with this patch set.
> Without patch:
> time mkfs.xfs /dev/md0
> real4m39.775s
> user0m0.000s
> sys0m0.298s
>
> With patch:
> time mkfs.xfs /dev/md0
> real0m0.105s
> user0m0.000s
> sys0m0.007s
>
> nvme3n1           259:1    0   477G  0 disk
> └─nvme3n1p1       259:10   0    50G  0 part
> nvme4n1           259:2    0   477G  0 disk
> └─nvme4n1p1       259:11   0    50G  0 part
> nvme5n1           259:6    0   477G  0 disk
> └─nvme5n1p1       259:12   0    50G  0 part
> nvme2n1           259:9    0   477G  0 disk
> └─nvme2n1p1       259:15   0    50G  0 part
> nvme0n1           259:13   0   477G  0 disk
> └─nvme0n1p1       259:14   0    50G  0 part
>
> v1:
> Coly helps to review these patches and give some suggestions:
> One bug is found. If discard bio is across one stripe but bio size is bigger
> than one stripe size. After spliting, the bio will be NULL. In this version,
> it checks whether discard bio size is bigger than 2*stripe_size.
> In raid10_end_discard_request, it's better to check R10BIO_Uptodate is set
> or not. It can avoid write memory to improve performance.
> Add more comments for calculating addresses.
>
> v2:
> Fix error by checkpatch.pl
> Fix one bug for offset layout. v1 calculates wrongly split size
> Add more comments to explain how the discard range of each component disk
> is decided.

The above change log are usually put under "---".

> Reviewed-by: Coly Li <colyli@suse.de>
> Signed-off-by: Xiao Ni <xni@redhat.com>
> ---

[...]

> +
> +/* There are some limitations to handle discard bio
> + * 1st, the discard size is bigger than stripe_size*2.
> + * 2st, if the discard bio spans reshape progress, we use the old way to
> + * handle discard bio
> + */
> +static bool raid10_handle_discard(struct mddev *mddev, struct bio *bio)
> +{

[...]

> +	/* For far offset layout, if bio is not aligned with stripe size, it splits
> +	 * the part that is not aligned with strip size.
> +	 */
> +	if (geo.far_offset && (bio_start & stripe_mask)) {
> +		sector_t split_size;
> +		split_size = round_up(bio_start, stripe_size) - bio_start;
> +		bio = raid10_split_bio(conf, bio, split_size, false);
> +	}
> +	if (geo.far_offset && (bio_end & stripe_mask)) {
> +		sector_t split_size;
> +		split_size = bio_sectors(bio) - (bio_end & stripe_mask);
> +		bio = raid10_split_bio(conf, bio, split_size, true);
> +	}

So far layout is handled here. I think the hole issue is existed for far 
layout,
Just FYI.

> +
> +	r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
> +	r10_bio->mddev = mddev;
> +	r10_bio->state = 0;
> +	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->geo.raid_disks);
> +
> +	wait_blocked_dev(mddev, geo.raid_disks);
> +
> +	r10_bio->master_bio = bio;
> +
> +	bio_start = bio->bi_iter.bi_sector;
> +	bio_end = bio_end_sector(bio);
> +
> +	/* raid10 uses chunk as the unit to store data. It's similar like raid0.
> +	 * One stripe contains the chunks from all member disk (one chunk from
> +	 * one disk at the same HAB address). For layout detail, see 'man md 4'
> +	 */

s/HAB/HBA/

Thanks,
Guoqing

Re: [PATCH V2 1/3] Move codes related with submitting discard bio into one function

[Xiao Ni]

Hi Guoqing

Thanks for reviewing this patch set.


On 07/28/2020 04:21 PM, Guoqing Jiang wrote:
> Hi Xiao,
>
> Better to add a prefix before subject like "md" ...", the same to 
> other patches.
Sure.
>
> On 7/28/20 9:18 AM, Xiao Ni wrote:
>> These codes can be used in raid10. So we can move these codes into
>> md.c. raid0 and raid10 can share these codes.
>>
>> Reviewed-by: Coly Li <colyli@suse.de>
>> Signed-off-by: Xiao Ni <xni@redhat.com>
>> ---
>>   drivers/md/md.c    | 22 ++++++++++++++++++++++
>>   drivers/md/md.h    |  3 +++
>>   drivers/md/raid0.c | 15 ++-------------
>>   3 files changed, 27 insertions(+), 13 deletions(-)
>>
>> diff --git a/drivers/md/md.c b/drivers/md/md.c
>> index 07e5b67..2b8f654 100644
>> --- a/drivers/md/md.c
>> +++ b/drivers/md/md.c
>> @@ -8559,6 +8559,28 @@ void md_write_end(struct mddev *mddev)
>>     EXPORT_SYMBOL(md_write_end);
>
> Could you add comment before the function to inform it is used by 
> raid0 and raid10?
I'll add comments in next version.

Regards
Xiao
>
>> +void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
>> +                struct bio *bio,
>> +                sector_t dev_start, sector_t dev_end)
>
> Thanks,
> Guoqing
>

Re: [PATCH V2 3/3] improve raid10 discard request

[Xiao Ni]

On 07/28/2020 04:38 PM, Guoqing Jiang wrote:
>
>
> On 7/28/20 9:18 AM, Xiao Ni wrote:
>> Now the discard request is split by chunk size. So it takes a long time
>> to finish mkfs on disks which support discard function. This patch 
>> improve
>> handling raid10 discard request. It uses the similar way with patch
>> 29efc390b (md/md0: optimize raid0 discard handling).
>>
>> But it's a little complex than raid0. Because raid10 has different 
>> layout.
>> If raid10 is offset layout and the discard request is smaller than 
>> stripe
>> size. There are some holes when we submit discard bio to underlayer 
>> disks.
>>
>> For example: five disks (disk1 - disk5)
>> D01 D02 D03 D04 D05
>> D05 D01 D02 D03 D04
>> D06 D07 D08 D09 D10
>> D10 D06 D07 D08 D09
>> The discard bio just wants to discard from D03 to D10. For disk3, 
>> there is
>> a hole between D03 and D08. For disk4, there is a hole between D04 
>> and D09.
>> D03 is a chunk, raid10_write_request can handle one chunk perfectly. So
>> the part that is not aligned with stripe size is still handled by
>> raid10_write_request.
>
> One question, is far layout handled by raid10_write_request or the
> discard request?
>
>>
>> If reshape is running when discard bio comes and the discard bio 
>> spans the
>> reshape position, raid10_write_request is responsible to handle this
>> discard bio.
>>
>> I did a test with this patch set.
>> Without patch:
>> time mkfs.xfs /dev/md0
>> real4m39.775s
>> user0m0.000s
>> sys0m0.298s
>>
>> With patch:
>> time mkfs.xfs /dev/md0
>> real0m0.105s
>> user0m0.000s
>> sys0m0.007s
>>
>> nvme3n1           259:1    0   477G  0 disk
>> └─nvme3n1p1       259:10   0    50G  0 part
>> nvme4n1           259:2    0   477G  0 disk
>> └─nvme4n1p1       259:11   0    50G  0 part
>> nvme5n1           259:6    0   477G  0 disk
>> └─nvme5n1p1       259:12   0    50G  0 part
>> nvme2n1           259:9    0   477G  0 disk
>> └─nvme2n1p1       259:15   0    50G  0 part
>> nvme0n1           259:13   0   477G  0 disk
>> └─nvme0n1p1       259:14   0    50G  0 part
>>
>> v1:
>> Coly helps to review these patches and give some suggestions:
>> One bug is found. If discard bio is across one stripe but bio size is 
>> bigger
>> than one stripe size. After spliting, the bio will be NULL. In this 
>> version,
>> it checks whether discard bio size is bigger than 2*stripe_size.
>> In raid10_end_discard_request, it's better to check R10BIO_Uptodate 
>> is set
>> or not. It can avoid write memory to improve performance.
>> Add more comments for calculating addresses.
>>
>> v2:
>> Fix error by checkpatch.pl
>> Fix one bug for offset layout. v1 calculates wrongly split size
>> Add more comments to explain how the discard range of each component 
>> disk
>> is decided.
>
> The above change log are usually put under "---".

Thanks for reminding me about this.
>
>> Reviewed-by: Coly Li <colyli@suse.de>
>> Signed-off-by: Xiao Ni <xni@redhat.com>
>> ---
>
> [...]
>
>> +
>> +/* There are some limitations to handle discard bio
>> + * 1st, the discard size is bigger than stripe_size*2.
>> + * 2st, if the discard bio spans reshape progress, we use the old 
>> way to
>> + * handle discard bio
>> + */
>> +static bool raid10_handle_discard(struct mddev *mddev, struct bio *bio)
>> +{
>
> [...]
>
>> +    /* For far offset layout, if bio is not aligned with stripe 
>> size, it splits
>> +     * the part that is not aligned with strip size.
>> +     */
>> +    if (geo.far_offset && (bio_start & stripe_mask)) {
>> +        sector_t split_size;
>> +        split_size = round_up(bio_start, stripe_size) - bio_start;
>> +        bio = raid10_split_bio(conf, bio, split_size, false);
>> +    }
>> +    if (geo.far_offset && (bio_end & stripe_mask)) {
>> +        sector_t split_size;
>> +        split_size = bio_sectors(bio) - (bio_end & stripe_mask);
>> +        bio = raid10_split_bio(conf, bio, split_size, true);
>> +    }
>
> So far layout is handled here. I think the hole issue is existed for 
> far layout,
> Just FYI.

It looks like I missed the far layout. Far layout is different with far 
offset layout.
It doesn't need to consider the write hole problem. This patch only 
consider the
write hole in one copy. For far layout, the discard region is 
sequential. So we just
need to find the start/end address of next copy. I'll fix this in next 
version.

Regards
Xiao

>
>> +
>> +    r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
>> +    r10_bio->mddev = mddev;
>> +    r10_bio->state = 0;
>> +    memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * 
>> conf->geo.raid_disks);
>> +
>> +    wait_blocked_dev(mddev, geo.raid_disks);
>> +
>> +    r10_bio->master_bio = bio;
>> +
>> +    bio_start = bio->bi_iter.bi_sector;
>> +    bio_end = bio_end_sector(bio);
>> +
>> +    /* raid10 uses chunk as the unit to store data. It's similar 
>> like raid0.
>> +     * One stripe contains the chunks from all member disk (one 
>> chunk from
>> +     * one disk at the same HAB address). For layout detail, see 
>> 'man md 4'
>> +     */
>
> s/HAB/HBA/
>
> Thanks,
> Guoqing
>