Re: [PATCH] md/raid0: optimize stripe mapping with bitwise shifts for power-of-2 devices
From: yu kuai
Date: Sat Nov 21 2026 - 05:58:24 EST
Hi,
在 2026/11/17 13:15, Herman Semenoff 写道:
> From 086678202572260393864f72c06f4d67032a4b76 Mon Sep 17 00:00:00 2001
> From: Herman Semenoff <GermanAizek@xxxxxxxxx>
> Date: Sun, 8 Nov 2026 22:43:29 +0300
> Subject: [PATCH] md/raid0: optimize stripe mapping with bitwise shifts
> for power-of-2 devices
>
> In drivers/md/raid0.c, map_sector() performs two 64-bit integer divisions
> (sector_div) on every submitted bio:
> 1. sector_div(chunk, zone->nb_dev << chunksect_bits) to compute the chunk
> offset within the member device.
> 2. sector_div(sector, zone->nb_dev) to select the target member disk.
>
> For ultra-low latency solid-state storage devices, such as Intel Optane
> (3D XPoint NVMe SSDs) capable of sub-10us latencies and multi-million IOPS,
> these un-pipelined 64-bit division instructions create unnecessary CPU
> pipeline stalls and latency overhead in the I/O submission hot path.
>
> When the number of member devices in a strip zone is a power of two
> (e.g., 2, 4, 8, 16 disks, which is the predominant configuration for
> NVMe arrays), both divisions can be replaced with bitwise shifts and
> masks:
> - chunk >>= (zone->nb_dev_shift + chunksect_bits)
> - disk_idx = sector & (zone->nb_dev - 1)
> - *sector_offset = (chunk << chunksect_bits) + sect_in_chunk
>
> Store nb_dev_shift (ilog2(zone->nb_dev)) in struct strip_zone during zone
> initialization when is_power_of_2(zone->nb_dev) is true, or -1 otherwise.
> If nb_dev_shift is non-negative and chunk_sects is a power of two, fast
> bitwise math is used with zero divisions. Arrays with non-power-of-2 disk
> counts fall back to the existing sector_div() path without any behavior
> or compatibility change.
>
> In addition, annotate the bio split check in raid0_make_request() with
> unlikely(), as standard MD devices already enforce chunk_sectors limits
> via bio_split_to_limits() in md_submit_bio().
>
> Tested on an 8-disk Intel Optane Memory M10 (MEMPEK1J016GAD) RAID0 array:
> - Random 4K read QD1 latency: avg lat 22.06 us -> 21.10 us (-4.4%)
> - Random 4K read QD1 IOPS: 42.6k IOPS -> 44.6k IOPS (+4.7%)
> - Random 4K read QD32x8 IOPS: 1.11M IOPS -> 1.72M IOPS (+54.5%)
> - Non-power-of-2 disk arrays: unaffected, identical fallback path
>
> Signed-off-by: Herman Semenoff <GermanAizek@xxxxxxxxx>
> Signed-off-by: Herman Semenoff <GermanAizek@xxxxxxxxxxxxx>
> ---
> drivers/md/raid0.c | 26 +++++++++++++++++++-------
> drivers/md/raid0.h | 1 +
> 2 files changed, 20 insertions(+), 7 deletions(-)
This patch is unacceptable, you need to regenerate it with correct format.
>
> diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
> index 35e103f0c2c3..993df48eaa4c 100644
> --- a/drivers/md/raid0.c
> +++ b/drivers/md/raid0.c
> @@ -207,6 +207,8 @@ static int create_strip_zones(struct mddev *mddev,
> struct r0conf **private_conf)
> }
> zone->nb_dev = cnt;
> zone->zone_end = smallest->sectors * cnt;
> + zone->nb_dev_shift = is_power_of_2(zone->nb_dev) ?
> + ilog2(zone->nb_dev) : -1;
>
> curr_zone_end = zone->zone_end;
>
> @@ -246,6 +248,8 @@ static int create_strip_zones(struct mddev *mddev,
> struct r0conf **private_conf)
> }
>
> zone->nb_dev = c;
> + zone->nb_dev_shift = is_power_of_2(zone->nb_dev) ?
> + ilog2(zone->nb_dev) : -1;
> sectors = (smallest->sectors - zone->dev_start) * c;
> pr_debug("md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n",
> mdname(mddev),
> @@ -330,6 +334,7 @@ static struct md_rdev *map_sector(struct mddev
> *mddev, struct strip_zone *zone,
> struct r0conf *conf = mddev->private;
> int raid_disks = conf->strip_zone[0].nb_dev;
> unsigned int chunk_sects = mddev->chunk_sectors;
> + unsigned int disk_idx;
>
> if (is_power_of_2(chunk_sects)) {
> int chunksect_bits = ffz(~chunk_sects);
> @@ -338,21 +343,28 @@ static struct md_rdev *map_sector(struct mddev
> *mddev, struct strip_zone *zone,
> sector >>= chunksect_bits;
> /* chunk in zone */
> chunk = *sector_offset;
> - /* quotient is the chunk in real device*/
> - sector_div(chunk, zone->nb_dev << chunksect_bits);
> - } else{
> + if (zone->nb_dev_shift >= 0) {
> + chunk >>= (zone->nb_dev_shift + chunksect_bits);
> + disk_idx = sector & (zone->nb_dev - 1);
> + } else {
> + /* quotient is the chunk in real device*/
> + sector_div(chunk, zone->nb_dev << chunksect_bits);
> + disk_idx = sector_div(sector, zone->nb_dev);
> + }
> + *sector_offset = (chunk << chunksect_bits) + sect_in_chunk;
> + } else {
> sect_in_chunk = sector_div(sector, chunk_sects);
> chunk = *sector_offset;
> sector_div(chunk, chunk_sects * zone->nb_dev);
> + disk_idx = sector_div(sector, zone->nb_dev);
> + *sector_offset = (chunk * chunk_sects) + sect_in_chunk;
> }
> /*
> * position the bio over the real device
> * real sector = chunk in device + starting of zone
> * + the position in the chunk
> */
> - *sector_offset = (chunk * chunk_sects) + sect_in_chunk;
> - return conf->devlist[(zone - conf->strip_zone)*raid_disks
> - + sector_div(sector, zone->nb_dev)];
> + return conf->devlist[(zone - conf->strip_zone) * raid_disks + disk_idx];
> }
>
> static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int
> raid_disks)
> @@ -616,7 +628,7 @@ static bool raid0_make_request(struct mddev
> *mddev, struct bio *bio)
> ? (sector & (chunk_sects-1))
> : sector_div(sector, chunk_sects));
>
> - if (sectors < bio_sectors(bio)) {
> + if (unlikely(sectors < bio_sectors(bio))) {
> bio = bio_submit_split_bioset(bio, sectors,
> &mddev->bio_set);
> if (!bio)
> diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h
> index 8cc761ca7423..70b73511fb14 100644
> --- a/drivers/md/raid0.h
> +++ b/drivers/md/raid0.h
> @@ -7,6 +7,7 @@ struct strip_zone {
> sector_t dev_start; /* Zone offset in real dev (in sectors) */
> int nb_dev; /* # of devices attached to the zone */
> int disk_shift; /* start disk for the original layout */
> + int nb_dev_shift; /* log2(nb_dev) if power of 2, else -1 */
> };
>
> /* Linux 3.14 (20d0189b101) made an unintended change to
--
Thanks,
Kuai