[md-6.9,v2,09/10] md/raid1: factor out the code to manage sequential IO

Message ID 20240227120327.1432511-10-yukuai1@huaweicloud.com
State New
Headers
Series md/raid1: refactor read_balance() and some minor fix |

Commit Message

Yu Kuai Feb. 27, 2024, 12:03 p.m. UTC
  From: Yu Kuai <yukuai3@huawei.com>

There is no functional change for now, make read_balance() cleaner and
prepare to fix problems and refactor the handler of sequential IO.

Co-developed-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Paul Luse <paul.e.luse@linux.intel.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/raid1.c | 71 ++++++++++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 34 deletions(-)
  

Comments

Xiao Ni Feb. 28, 2024, 2:27 a.m. UTC | #1
On Tue, Feb 27, 2024 at 8:09 PM Yu Kuai <yukuai1@huaweicloud.com> wrote:
>
> From: Yu Kuai <yukuai3@huawei.com>
>
> There is no functional change for now, make read_balance() cleaner and
> prepare to fix problems and refactor the handler of sequential IO.
>
> Co-developed-by: Paul Luse <paul.e.luse@linux.intel.com>
> Signed-off-by: Paul Luse <paul.e.luse@linux.intel.com>
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> ---
>  drivers/md/raid1.c | 71 ++++++++++++++++++++++++----------------------
>  1 file changed, 37 insertions(+), 34 deletions(-)
>
> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index 76bb59ad1485..d3e9a0157437 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -705,6 +705,31 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
>         return bb_disk;
>  }
>
> +static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio)
> +{
> +       /* TODO: address issues with this check and concurrency. */
> +       return conf->mirrors[disk].next_seq_sect == r1_bio->sector ||
> +              conf->mirrors[disk].head_position == r1_bio->sector;
> +}
> +
> +/*
> + * If buffered sequential IO size exceeds optimal iosize, check if there is idle
> + * disk. If yes, choose the idle disk.
> + */
> +static bool should_choose_next(struct r1conf *conf, int disk)
> +{
> +       struct raid1_info *mirror = &conf->mirrors[disk];
> +       int opt_iosize;
> +
> +       if (!test_bit(Nonrot, &mirror->rdev->flags))
> +               return false;
> +
> +       opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9;
> +       return opt_iosize > 0 && mirror->seq_start != MaxSector &&
> +              mirror->next_seq_sect > opt_iosize &&
> +              mirror->next_seq_sect - opt_iosize >= mirror->seq_start;
> +}
> +
>  /*
>   * This routine returns the disk from which the requested read should
>   * be done. There is a per-array 'next expected sequential IO' sector
> @@ -768,43 +793,21 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
>                 pending = atomic_read(&rdev->nr_pending);
>                 dist = abs(this_sector - conf->mirrors[disk].head_position);
>                 /* Don't change to another disk for sequential reads */
> -               if (conf->mirrors[disk].next_seq_sect == this_sector
> -                   || dist == 0) {
> -                       int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
> -                       struct raid1_info *mirror = &conf->mirrors[disk];
> -
> -                       /*
> -                        * If buffered sequential IO size exceeds optimal
> -                        * iosize, check if there is idle disk. If yes, choose
> -                        * the idle disk. read_balance could already choose an
> -                        * idle disk before noticing it's a sequential IO in
> -                        * this disk. This doesn't matter because this disk
> -                        * will idle, next time it will be utilized after the
> -                        * first disk has IO size exceeds optimal iosize. In
> -                        * this way, iosize of the first disk will be optimal
> -                        * iosize at least. iosize of the second disk might be
> -                        * small, but not a big deal since when the second disk
> -                        * starts IO, the first disk is likely still busy.
> -                        */
> -                       if (test_bit(Nonrot, &rdev->flags) && opt_iosize > 0 &&
> -                           mirror->seq_start != MaxSector &&
> -                           mirror->next_seq_sect > opt_iosize &&
> -                           mirror->next_seq_sect - opt_iosize >=
> -                           mirror->seq_start) {
> -                               /*
> -                                * Add 'pending' to avoid choosing this disk if
> -                                * there is other idle disk.
> -                                */
> -                               pending++;
> -                               /*
> -                                * If there is no other idle disk, this disk
> -                                * will be chosen.
> -                                */
> -                               sequential_disk = disk;
> -                       } else {
> +               if (is_sequential(conf, disk, r1_bio)) {
> +                       if (!should_choose_next(conf, disk)) {
>                                 best_disk = disk;
>                                 break;
>                         }
> +                       /*
> +                        * Add 'pending' to avoid choosing this disk if
> +                        * there is other idle disk.
> +                        */
> +                       pending++;
> +                       /*
> +                        * If there is no other idle disk, this disk
> +                        * will be chosen.
> +                        */
> +                       sequential_disk = disk;
>                 }
>
>                 if (min_pending > pending) {
> --
> 2.39.2
>
Hi all
This patch looks good to me.
Reviewed-by: Xiao Ni <xni@redhat.com>
  

Patch

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 76bb59ad1485..d3e9a0157437 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -705,6 +705,31 @@  static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
 	return bb_disk;
 }
 
+static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio)
+{
+	/* TODO: address issues with this check and concurrency. */
+	return conf->mirrors[disk].next_seq_sect == r1_bio->sector ||
+	       conf->mirrors[disk].head_position == r1_bio->sector;
+}
+
+/*
+ * If buffered sequential IO size exceeds optimal iosize, check if there is idle
+ * disk. If yes, choose the idle disk.
+ */
+static bool should_choose_next(struct r1conf *conf, int disk)
+{
+	struct raid1_info *mirror = &conf->mirrors[disk];
+	int opt_iosize;
+
+	if (!test_bit(Nonrot, &mirror->rdev->flags))
+		return false;
+
+	opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9;
+	return opt_iosize > 0 && mirror->seq_start != MaxSector &&
+	       mirror->next_seq_sect > opt_iosize &&
+	       mirror->next_seq_sect - opt_iosize >= mirror->seq_start;
+}
+
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -768,43 +793,21 @@  static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		pending = atomic_read(&rdev->nr_pending);
 		dist = abs(this_sector - conf->mirrors[disk].head_position);
 		/* Don't change to another disk for sequential reads */
-		if (conf->mirrors[disk].next_seq_sect == this_sector
-		    || dist == 0) {
-			int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
-			struct raid1_info *mirror = &conf->mirrors[disk];
-
-			/*
-			 * If buffered sequential IO size exceeds optimal
-			 * iosize, check if there is idle disk. If yes, choose
-			 * the idle disk. read_balance could already choose an
-			 * idle disk before noticing it's a sequential IO in
-			 * this disk. This doesn't matter because this disk
-			 * will idle, next time it will be utilized after the
-			 * first disk has IO size exceeds optimal iosize. In
-			 * this way, iosize of the first disk will be optimal
-			 * iosize at least. iosize of the second disk might be
-			 * small, but not a big deal since when the second disk
-			 * starts IO, the first disk is likely still busy.
-			 */
-			if (test_bit(Nonrot, &rdev->flags) && opt_iosize > 0 &&
-			    mirror->seq_start != MaxSector &&
-			    mirror->next_seq_sect > opt_iosize &&
-			    mirror->next_seq_sect - opt_iosize >=
-			    mirror->seq_start) {
-				/*
-				 * Add 'pending' to avoid choosing this disk if
-				 * there is other idle disk.
-				 */
-				pending++;
-				/*
-				 * If there is no other idle disk, this disk
-				 * will be chosen.
-				 */
-				sequential_disk = disk;
-			} else {
+		if (is_sequential(conf, disk, r1_bio)) {
+			if (!should_choose_next(conf, disk)) {
 				best_disk = disk;
 				break;
 			}
+			/*
+			 * Add 'pending' to avoid choosing this disk if
+			 * there is other idle disk.
+			 */
+			pending++;
+			/*
+			 * If there is no other idle disk, this disk
+			 * will be chosen.
+			 */
+			sequential_disk = disk;
 		}
 
 		if (min_pending > pending) {