[PATCH 0/7] md: raid5,raid0,raid10: align bio to io_opt

[PATCH 0/7] md: raid5,raid0,raid10: align bio to io_opt

[Yu Kuai]

Yu Kuai (7):
  md/raid5: use mempool to allocate stripe_request_ctx
  md/raid5: make sure max_sectors is not less than io_opt
  md: support to align bio to limits
  md: add a helper md_config_align_limits()
  md/raid5: align bio to io_opt
  md/raid10: align bio to io_opt
  md/raid0: align bio to io_opt

 drivers/md/md.c       | 46 ++++++++++++++++++++++++
 drivers/md/md.h       | 16 +++++++++
 drivers/md/raid0.c    |  2 ++
 drivers/md/raid1-10.c |  5 ---
 drivers/md/raid10.c   |  2 ++
 drivers/md/raid5.c    | 82 +++++++++++++++++++++++++++++--------------
 drivers/md/raid5.h    |  2 ++
 7 files changed, 124 insertions(+), 31 deletions(-)

-- 
2.51.0

[PATCH 1/7] md/raid5: use mempool to allocate stripe_request_ctx

[Yu Kuai]

On the one hand, stripe_request_ctx is 72 bytes, and it's a bit huge for
a stack variable.

On the other hand, the bitmap sectors_to_do is a fixed size, result in
max_hw_sector_kb of raid5 array is at most 256 * 4k = 1Mb, and this will
make full stripe IO impossible for the array that chunk_size * data_disks
is bigger. Allocate ctx during runtime will make it possible to get rid
of this limit.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/md.h       |  4 +++
 drivers/md/raid1-10.c |  5 ----
 drivers/md/raid5.c    | 58 +++++++++++++++++++++++++++----------------
 drivers/md/raid5.h    |  2 ++
 4 files changed, 42 insertions(+), 27 deletions(-)

diff --git a/drivers/md/md.h b/drivers/md/md.h
index 6985f2829bbd..75fd8c873b6f 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -22,6 +22,10 @@
 #include <trace/events/block.h>
 
 #define MaxSector (~(sector_t)0)
+/*
+ * Number of guaranteed raid bios in case of extreme VM load:
+ */
+#define	NR_RAID_BIOS 256
 
 enum md_submodule_type {
 	MD_PERSONALITY = 0,
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index 521625756128..c33099925f23 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -3,11 +3,6 @@
 #define RESYNC_BLOCK_SIZE (64*1024)
 #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
 
-/*
- * Number of guaranteed raid bios in case of extreme VM load:
- */
-#define	NR_RAID_BIOS 256
-
 /* when we get a read error on a read-only array, we redirect to another
  * device without failing the first device, or trying to over-write to
  * correct the read error.  To keep track of bad blocks on a per-bio
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index cdbc7eba5c54..0ccb5907cd20 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6079,13 +6079,13 @@ static sector_t raid5_bio_lowest_chunk_sector(struct r5conf *conf,
 static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	bool on_wq;
 	struct r5conf *conf = mddev->private;
-	sector_t logical_sector;
-	struct stripe_request_ctx ctx = {};
 	const int rw = bio_data_dir(bi);
+	struct stripe_request_ctx *ctx;
+	sector_t logical_sector;
 	enum stripe_result res;
 	int s, stripe_cnt;
+	bool on_wq;
 
 	if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
 		int ret = log_handle_flush_request(conf, bi);
@@ -6097,11 +6097,6 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 				return true;
 		}
 		/* ret == -EAGAIN, fallback */
-		/*
-		 * if r5l_handle_flush_request() didn't clear REQ_PREFLUSH,
-		 * we need to flush journal device
-		 */
-		ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
 	}
 
 	md_write_start(mddev, bi);
@@ -6124,16 +6119,24 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	}
 
 	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)RAID5_STRIPE_SECTORS(conf)-1);
-	ctx.first_sector = logical_sector;
-	ctx.last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 
-	stripe_cnt = DIV_ROUND_UP_SECTOR_T(ctx.last_sector - logical_sector,
+	ctx = mempool_alloc(conf->ctx_pool, GFP_NOIO | __GFP_ZERO);
+	ctx->first_sector = logical_sector;
+	ctx->last_sector = bio_end_sector(bi);
+	/*
+	 * if r5l_handle_flush_request() didn't clear REQ_PREFLUSH,
+	 * we need to flush journal device
+	 */
+	if (unlikely(bi->bi_opf & REQ_PREFLUSH))
+		ctx->do_flush = true;
+
+	stripe_cnt = DIV_ROUND_UP_SECTOR_T(ctx->last_sector - logical_sector,
 					   RAID5_STRIPE_SECTORS(conf));
-	bitmap_set(ctx.sectors_to_do, 0, stripe_cnt);
+	bitmap_set(ctx->sectors_to_do, 0, stripe_cnt);
 
 	pr_debug("raid456: %s, logical %llu to %llu\n", __func__,
-		 bi->bi_iter.bi_sector, ctx.last_sector);
+		 bi->bi_iter.bi_sector, ctx->last_sector);
 
 	/* Bail out if conflicts with reshape and REQ_NOWAIT is set */
 	if ((bi->bi_opf & REQ_NOWAIT) &&
@@ -6141,6 +6144,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		bio_wouldblock_error(bi);
 		if (rw == WRITE)
 			md_write_end(mddev);
+		mempool_free(ctx, conf->ctx_pool);
 		return true;
 	}
 	md_account_bio(mddev, &bi);
@@ -6159,10 +6163,10 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		add_wait_queue(&conf->wait_for_reshape, &wait);
 		on_wq = true;
 	}
-	s = (logical_sector - ctx.first_sector) >> RAID5_STRIPE_SHIFT(conf);
+	s = (logical_sector - ctx->first_sector) >> RAID5_STRIPE_SHIFT(conf);
 
 	while (1) {
-		res = make_stripe_request(mddev, conf, &ctx, logical_sector,
+		res = make_stripe_request(mddev, conf, ctx, logical_sector,
 					  bi);
 		if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE)
 			break;
@@ -6179,9 +6183,9 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 			 * raid5_activate_delayed() from making progress
 			 * and thus deadlocking.
 			 */
-			if (ctx.batch_last) {
-				raid5_release_stripe(ctx.batch_last);
-				ctx.batch_last = NULL;
+			if (ctx->batch_last) {
+				raid5_release_stripe(ctx->batch_last);
+				ctx->batch_last = NULL;
 			}
 
 			wait_woken(&wait, TASK_UNINTERRUPTIBLE,
@@ -6189,21 +6193,23 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 			continue;
 		}
 
-		s = find_next_bit_wrap(ctx.sectors_to_do, stripe_cnt, s);
+		s = find_next_bit_wrap(ctx->sectors_to_do, stripe_cnt, s);
 		if (s == stripe_cnt)
 			break;
 
-		logical_sector = ctx.first_sector +
+		logical_sector = ctx->first_sector +
 			(s << RAID5_STRIPE_SHIFT(conf));
 	}
 	if (unlikely(on_wq))
 		remove_wait_queue(&conf->wait_for_reshape, &wait);
 
-	if (ctx.batch_last)
-		raid5_release_stripe(ctx.batch_last);
+	if (ctx->batch_last)
+		raid5_release_stripe(ctx->batch_last);
 
 	if (rw == WRITE)
 		md_write_end(mddev);
+
+	mempool_free(ctx, conf->ctx_pool);
 	if (res == STRIPE_WAIT_RESHAPE) {
 		md_free_cloned_bio(bi);
 		return false;
@@ -7370,6 +7376,7 @@ static void free_conf(struct r5conf *conf)
 	bioset_exit(&conf->bio_split);
 	kfree(conf->stripe_hashtbl);
 	kfree(conf->pending_data);
+	mempool_destroy(conf->ctx_pool);
 	kfree(conf);
 }
 
@@ -8053,6 +8060,13 @@ static int raid5_run(struct mddev *mddev)
 			goto abort;
 	}
 
+	conf->ctx_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS,
+					sizeof(struct stripe_request_ctx));
+	if (!conf->ctx_pool) {
+		ret = -ENOMEM;
+		goto abort;
+	}
+
 	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
 		goto abort;
 
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index eafc6e9ed6ee..6e3f07119fa4 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -690,6 +690,8 @@ struct r5conf {
 	struct list_head	pending_list;
 	int			pending_data_cnt;
 	struct r5pending_data	*next_pending_data;
+
+	mempool_t		*ctx_pool;
 };
 
 #if PAGE_SIZE == DEFAULT_STRIPE_SIZE
-- 
2.51.0

[PATCH] md: support to align bio to limits

[Yu Kuai]

For personalities that report optimal IO size, it's indicate that users
can get the best IO bandwidth if they issue IO with this size. However
there is also an implicit condition that IO should also be aligned to the
optimal IO size.

Currently, bio will only be split by limits, if bio offset is not aligned
to limits, then all split bio will not be aligned. This patch add a new
feature to align bio to limits first, and following patches will support
this for each personality if necessary.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/md.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/md.h |  1 +
 2 files changed, 47 insertions(+)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 7b5c5967568f..b09f87b27807 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -427,6 +427,48 @@ bool md_handle_request(struct mddev *mddev, struct bio *bio)
 }
 EXPORT_SYMBOL(md_handle_request);
 
+static struct bio *__md_bio_align_to_limits(struct mddev *mddev,
+					    struct bio *bio)
+{
+	unsigned int max_sectors = mddev->gendisk->queue->limits.max_sectors;
+	sector_t start = bio->bi_iter.bi_sector;
+	sector_t align_start = roundup(start, max_sectors);
+	sector_t end;
+	sector_t align_end;
+
+	/* already aligned */
+	if (align_start == start)
+		return bio;
+
+	end = start + bio_sectors(bio);
+	align_end = rounddown(end, max_sectors);
+
+	/* bio is too small to split */
+	if (align_end <= align_start)
+		return bio;
+
+	return bio_submit_split_bioset(bio, align_start - start,
+				       &mddev->gendisk->bio_split);
+}
+
+static struct bio *md_bio_align_to_limits(struct mddev *mddev, struct bio *bio)
+{
+	if (!mddev->bio_align_to_limits)
+		return bio;
+
+	/* atomic write can't split */
+	if (bio->bi_opf & REQ_ATOMIC)
+		return bio;
+
+	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		return __md_bio_align_to_limits(mddev, bio);
+	default:
+		return bio;
+	}
+}
+
 static void md_submit_bio(struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
@@ -442,6 +484,10 @@ static void md_submit_bio(struct bio *bio)
 		return;
 	}
 
+	bio = md_bio_align_to_limits(mddev, bio);
+	if (!bio)
+		return;
+
 	bio = bio_split_to_limits(bio);
 	if (!bio)
 		return;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 75fd8c873b6f..1ed90fd85ac4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -630,6 +630,7 @@ struct mddev {
 	bool	has_superblocks:1;
 	bool	fail_last_dev:1;
 	bool	serialize_policy:1;
+	bool	bio_align_to_limits:1;
 };
 
 enum recovery_flags {
-- 
2.51.0

Re: [PATCH] md: support to align bio to limits

[Yu Kuai]

Hi,

I forgot to remove this patch, that is patch 3 in this set, before sending
to mail list, please ignore this one.

在 2025/11/21 13:14, Yu Kuai 写道:
> For personalities that report optimal IO size, it's indicate that users
> can get the best IO bandwidth if they issue IO with this size. However
> there is also an implicit condition that IO should also be aligned to the
> optimal IO size.
>
> Currently, bio will only be split by limits, if bio offset is not aligned
> to limits, then all split bio will not be aligned. This patch add a new
> feature to align bio to limits first, and following patches will support
> this for each personality if necessary.
>
> Signed-off-by: Yu Kuai <yukuai@fnnas.com>
> ---
>   drivers/md/md.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
>   drivers/md/md.h |  1 +
>   2 files changed, 47 insertions(+)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 7b5c5967568f..b09f87b27807 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -427,6 +427,48 @@ bool md_handle_request(struct mddev *mddev, struct bio *bio)
>   }
>   EXPORT_SYMBOL(md_handle_request);
>   
> +static struct bio *__md_bio_align_to_limits(struct mddev *mddev,
> +					    struct bio *bio)
> +{
> +	unsigned int max_sectors = mddev->gendisk->queue->limits.max_sectors;
> +	sector_t start = bio->bi_iter.bi_sector;
> +	sector_t align_start = roundup(start, max_sectors);
> +	sector_t end;
> +	sector_t align_end;
> +
> +	/* already aligned */
> +	if (align_start == start)
> +		return bio;
> +
> +	end = start + bio_sectors(bio);
> +	align_end = rounddown(end, max_sectors);
> +
> +	/* bio is too small to split */
> +	if (align_end <= align_start)
> +		return bio;
> +
> +	return bio_submit_split_bioset(bio, align_start - start,
> +				       &mddev->gendisk->bio_split);
> +}
> +
> +static struct bio *md_bio_align_to_limits(struct mddev *mddev, struct bio *bio)
> +{
> +	if (!mddev->bio_align_to_limits)
> +		return bio;
> +
> +	/* atomic write can't split */
> +	if (bio->bi_opf & REQ_ATOMIC)
> +		return bio;
> +
> +	switch (bio_op(bio)) {
> +	case REQ_OP_READ:
> +	case REQ_OP_WRITE:
> +		return __md_bio_align_to_limits(mddev, bio);
> +	default:
> +		return bio;
> +	}
> +}
> +
>   static void md_submit_bio(struct bio *bio)
>   {
>   	const int rw = bio_data_dir(bio);
> @@ -442,6 +484,10 @@ static void md_submit_bio(struct bio *bio)
>   		return;
>   	}
>   
> +	bio = md_bio_align_to_limits(mddev, bio);
> +	if (!bio)
> +		return;
> +
>   	bio = bio_split_to_limits(bio);
>   	if (!bio)
>   		return;
> diff --git a/drivers/md/md.h b/drivers/md/md.h
> index 75fd8c873b6f..1ed90fd85ac4 100644
> --- a/drivers/md/md.h
> +++ b/drivers/md/md.h
> @@ -630,6 +630,7 @@ struct mddev {
>   	bool	has_superblocks:1;
>   	bool	fail_last_dev:1;
>   	bool	serialize_policy:1;
> +	bool	bio_align_to_limits:1;
>   };
>   
>   enum recovery_flags {

-- 
Thanks,
Kuai

Re: [PATCH] md: support to align bio to limits

[kernel test robot]

Hi Yu,

kernel test robot noticed the following build errors:

[auto build test ERROR on linus/master]
[also build test ERROR on v6.18-rc7 next-20251124]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Yu-Kuai/md-support-to-align-bio-to-limits/20251121-131703
base:   linus/master
patch link:    https://lore.kernel.org/r/20251121051406.1316884-3-yukuai%40fnnas.com
patch subject: [PATCH] md: support to align bio to limits
config: i386-randconfig-002-20251125 (https://download.01.org/0day-ci/archive/20251125/202511250848.gq6d7JeR-lkp@intel.com/config)
compiler: gcc-14 (Debian 14.2.0-19) 14.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251125/202511250848.gq6d7JeR-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511250848.gq6d7JeR-lkp@intel.com/

All errors (new ones prefixed by >>):

   ld: drivers/md/md.o: in function `__md_bio_align_to_limits':
>> drivers/md/md.c:434:(.text+0x68e4): undefined reference to `__umoddi3'
>> ld: drivers/md/md.c:443:(.text+0x693a): undefined reference to `__umoddi3'


vim +434 drivers/md/md.c

   428	
   429	static struct bio *__md_bio_align_to_limits(struct mddev *mddev,
   430						    struct bio *bio)
   431	{
   432		unsigned int max_sectors = mddev->gendisk->queue->limits.max_sectors;
   433		sector_t start = bio->bi_iter.bi_sector;
 > 434		sector_t align_start = roundup(start, max_sectors);
   435		sector_t end;
   436		sector_t align_end;
   437	
   438		/* already aligned */
   439		if (align_start == start)
   440			return bio;
   441	
   442		end = start + bio_sectors(bio);
 > 443		align_end = rounddown(end, max_sectors);
   444	
   445		/* bio is too small to split */
   446		if (align_end <= align_start)
   447			return bio;
   448	
   449		return bio_submit_split_bioset(bio, align_start - start,
   450					       &mddev->gendisk->bio_split);
   451	}
   452	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH] md: support to align bio to limits

[kernel test robot]

Hi Yu,

kernel test robot noticed the following build errors:

[auto build test ERROR on linus/master]
[also build test ERROR on v6.18-rc7 next-20251124]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Yu-Kuai/md-support-to-align-bio-to-limits/20251121-131703
base:   linus/master
patch link:    https://lore.kernel.org/r/20251121051406.1316884-3-yukuai%40fnnas.com
patch subject: [PATCH] md: support to align bio to limits
config: arm-randconfig-002-20251125 (https://download.01.org/0day-ci/archive/20251125/202511251523.ariD3O9E-lkp@intel.com/config)
compiler: arm-linux-gnueabi-gcc (GCC) 10.5.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251125/202511251523.ariD3O9E-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511251523.ariD3O9E-lkp@intel.com/

All errors (new ones prefixed by >>, old ones prefixed by <<):

>> ERROR: modpost: "__aeabi_uldivmod" [drivers/md/md-mod.ko] undefined!

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH 2/7] md/raid5: make sure max_sectors is not less than io_opt

[Yu Kuai]

Otherwise, even if user issue IO by io_opt, such IO will be split
by max_sectors before they are submitted to raid5. For consequence,
full stripe IO is impossible.

BTW, dm-raid5 is not affected and still have such problem.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/raid5.c | 35 ++++++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0ccb5907cd20..dc7bdbdb04b7 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -773,14 +773,14 @@ struct stripe_request_ctx {
 	/* last sector in the request */
 	sector_t last_sector;
 
+	/* the request had REQ_PREFLUSH, cleared after the first stripe_head */
+	bool do_flush;
+
 	/*
 	 * bitmap to track stripe sectors that have been added to stripes
 	 * add one to account for unaligned requests
 	 */
-	DECLARE_BITMAP(sectors_to_do, RAID5_MAX_REQ_STRIPES + 1);
-
-	/* the request had REQ_PREFLUSH, cleared after the first stripe_head */
-	bool do_flush;
+	unsigned long sectors_to_do[];
 };
 
 /*
@@ -7732,6 +7732,24 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 	return 0;
 }
 
+static int raid5_create_ctx_pool(struct r5conf *conf)
+{
+	struct stripe_request_ctx *ctx;
+	int size;
+
+	if (mddev_is_dm(conf->mddev))
+		size = BITS_TO_LONGS(RAID5_MAX_REQ_STRIPES);
+	else
+		size = BITS_TO_LONGS(
+			queue_max_hw_sectors(conf->mddev->gendisk->queue) >>
+			RAID5_STRIPE_SHIFT(conf));
+
+	conf->ctx_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS,
+				struct_size(ctx, sectors_to_do, size));
+
+	return conf->ctx_pool ? 0 : -ENOMEM;
+}
+
 static int raid5_set_limits(struct mddev *mddev)
 {
 	struct r5conf *conf = mddev->private;
@@ -7788,6 +7806,8 @@ static int raid5_set_limits(struct mddev *mddev)
 	 * Limit the max sectors based on this.
 	 */
 	lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
+	if ((lim.max_hw_sectors << 9) < lim.io_opt)
+		lim.max_hw_sectors = lim.io_opt >> 9;
 
 	/* No restrictions on the number of segments in the request */
 	lim.max_segments = USHRT_MAX;
@@ -8060,12 +8080,9 @@ static int raid5_run(struct mddev *mddev)
 			goto abort;
 	}
 
-	conf->ctx_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS,
-					sizeof(struct stripe_request_ctx));
-	if (!conf->ctx_pool) {
-		ret = -ENOMEM;
+	ret = raid5_create_ctx_pool(conf);
+	if (ret)
 		goto abort;
-	}
 
 	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
 		goto abort;
-- 
2.51.0

[PATCH 3/7] md: support to align bio to limits

[Yu Kuai]

For personalities that report optimal IO size, it's indicate that users
can get the best IO bandwidth if they issue IO with this size. However
there is also an implicit condition that IO should also be aligned to the
optimal IO size.

Currently, bio will only be split by limits, if bio offset is not aligned
to limits, then all split bio will not be aligned. This patch add a new
feature to align bio to limits first, and following patches will support
this for each personality if necessary.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/md.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/md.h |  1 +
 2 files changed, 47 insertions(+)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 7b5c5967568f..b09f87b27807 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -427,6 +427,48 @@ bool md_handle_request(struct mddev *mddev, struct bio *bio)
 }
 EXPORT_SYMBOL(md_handle_request);
 
+static struct bio *__md_bio_align_to_limits(struct mddev *mddev,
+					    struct bio *bio)
+{
+	unsigned int max_sectors = mddev->gendisk->queue->limits.max_sectors;
+	sector_t start = bio->bi_iter.bi_sector;
+	sector_t align_start = roundup(start, max_sectors);
+	sector_t end;
+	sector_t align_end;
+
+	/* already aligned */
+	if (align_start == start)
+		return bio;
+
+	end = start + bio_sectors(bio);
+	align_end = rounddown(end, max_sectors);
+
+	/* bio is too small to split */
+	if (align_end <= align_start)
+		return bio;
+
+	return bio_submit_split_bioset(bio, align_start - start,
+				       &mddev->gendisk->bio_split);
+}
+
+static struct bio *md_bio_align_to_limits(struct mddev *mddev, struct bio *bio)
+{
+	if (!mddev->bio_align_to_limits)
+		return bio;
+
+	/* atomic write can't split */
+	if (bio->bi_opf & REQ_ATOMIC)
+		return bio;
+
+	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		return __md_bio_align_to_limits(mddev, bio);
+	default:
+		return bio;
+	}
+}
+
 static void md_submit_bio(struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
@@ -442,6 +484,10 @@ static void md_submit_bio(struct bio *bio)
 		return;
 	}
 
+	bio = md_bio_align_to_limits(mddev, bio);
+	if (!bio)
+		return;
+
 	bio = bio_split_to_limits(bio);
 	if (!bio)
 		return;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 75fd8c873b6f..1ed90fd85ac4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -630,6 +630,7 @@ struct mddev {
 	bool	has_superblocks:1;
 	bool	fail_last_dev:1;
 	bool	serialize_policy:1;
+	bool	bio_align_to_limits:1;
 };
 
 enum recovery_flags {
-- 
2.51.0

Re: [PATCH 3/7] md: support to align bio to limits

[kernel test robot]

Hi Yu,

kernel test robot noticed the following build errors:

[auto build test ERROR on linus/master]
[also build test ERROR on v6.18-rc6 next-20251121]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Yu-Kuai/md-raid5-use-mempool-to-allocate-stripe_request_ctx/20251121-131818
base:   linus/master
patch link:    https://lore.kernel.org/r/20251121051406.1316884-5-yukuai%40fnnas.com
patch subject: [PATCH 3/7] md: support to align bio to limits
config: powerpc-randconfig-002-20251123 (https://download.01.org/0day-ci/archive/20251123/202511230429.aSwW3knO-lkp@intel.com/config)
compiler: powerpc-linux-gcc (GCC) 8.5.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251123/202511230429.aSwW3knO-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511230429.aSwW3knO-lkp@intel.com/

All errors (new ones prefixed by >>):

   powerpc-linux-ld: drivers/md/md.o: in function `md_submit_bio':
>> md.c:(.text+0xf8c4): undefined reference to `__udivdi3'
>> powerpc-linux-ld: md.c:(.text+0xf914): undefined reference to `__umoddi3'

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH 4/7] md: add a helper md_config_align_limits()

[Yu Kuai]

This helper will be used by personalities that want to align bio to
io_opt to get best IO bandwidth.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/md.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1ed90fd85ac4..c8190cf02701 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -1088,6 +1088,17 @@ static inline bool rdev_blocked(struct md_rdev *rdev)
 	return false;
 }
 
+static inline void md_config_align_limits(struct mddev *mddev,
+					  struct queue_limits *lim)
+{
+	if ((lim->max_hw_sectors << 9) < lim->io_opt)
+		lim->max_hw_sectors = lim->io_opt >> 9;
+	else
+		lim->max_hw_sectors = rounddown(lim->max_hw_sectors,
+						lim->io_opt >> 9);
+	mddev->bio_align_to_limits = true;
+}
+
 #define mddev_add_trace_msg(mddev, fmt, args...)			\
 do {									\
 	if (!mddev_is_dm(mddev))					\
-- 
2.51.0

[PATCH 5/7] md/raid5: align bio to io_opt

[Yu Kuai]

raid5 internal implementaion indicates that if write bio is aligned to
io_opt, then full stripe write will be used, which will be best for
bandwidth because there is no need to read extra data to build new
xor data.

Simple test in my VM, 32 disks raid5 with 64kb chunksize:
dd if=/dev/zero of=/dev/md0 bs=100M oflag=direct

Before this patch:  782 MB/s
With this patch:    1.1 GB/s

BTW, there are still other bottleneck related to stripe handler, and
require further optimization.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/raid5.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dc7bdbdb04b7..2db4e4fe913a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7806,8 +7806,7 @@ static int raid5_set_limits(struct mddev *mddev)
 	 * Limit the max sectors based on this.
 	 */
 	lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
-	if ((lim.max_hw_sectors << 9) < lim.io_opt)
-		lim.max_hw_sectors = lim.io_opt >> 9;
+	md_config_align_limits(mddev, &lim);
 
 	/* No restrictions on the number of segments in the request */
 	lim.max_segments = USHRT_MAX;
-- 
2.51.0

[PATCH 6/7] md/raid10: align bio to io_opt

[Yu Kuai]

The impact is not so significant for raid10 compared to raid5, however
it's still more appropriate to issue IOs evenly to underlying disks.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/raid10.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 84be4cc7e873..f6a4bb26fb4a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4008,6 +4008,8 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err)
 		return err;
+
+	md_config_align_limits(mddev, &lim);
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
-- 
2.51.0

[PATCH 7/7] md/raid0: align bio to io_opt

[Yu Kuai]

The impact is not so significant for raid0 compared to raid5, however
it's still more appropriate to issue IOs evenly to underlying disks.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
---
 drivers/md/raid0.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 47aee1b1d4d1..332f413bcf51 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -388,6 +388,8 @@ static int raid0_set_limits(struct mddev *mddev)
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err)
 		return err;
+
+	md_config_align_limits(mddev, &lim);
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
-- 
2.51.0

Re: [PATCH 7/7] md/raid0: align bio to io_opt

[Paul Menzel]

Dear Kuai,


Thank you for your patches.

Am 21.11.25 um 06:14 schrieb Yu Kuai:
> The impact is not so significant for raid0 compared to raid5, however
> it's still more appropriate to issue IOs evenly to underlying disks.

Could you please elaborate, what the problem is, and also share your 
benchmark results and test setups?

> Signed-off-by: Yu Kuai <yukuai@fnnas.com>
> ---
>   drivers/md/raid0.c | 2 ++
>   1 file changed, 2 insertions(+)
> 
> diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
> index 47aee1b1d4d1..332f413bcf51 100644
> --- a/drivers/md/raid0.c
> +++ b/drivers/md/raid0.c
> @@ -388,6 +388,8 @@ static int raid0_set_limits(struct mddev *mddev)
>   	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
>   	if (err)
>   		return err;
> +
> +	md_config_align_limits(mddev, &lim);
>   	return queue_limits_set(mddev->gendisk->queue, &lim);
>   }
>   


Kind regards,

Paul