Re: [PATCH md-6.9 08/10] md/raid1: factor out choose_bb_rdev() from read_balance()

[Xiao Ni]

On Thu, Feb 22, 2024 at 4:06 PM Yu Kuai <yukuai1@xxxxxxxxxxxxxxx> wrote:
>
> From: Yu Kuai <yukuai3@xxxxxxxxxx>
>
> read_balance() is hard to understand because there are too many status
> and branches, and it's overlong.
>
> This patch factor out the case to read the rdev with bad blocks from
> read_balance(), there are no functional changes.
>
> Co-developed-by: Paul Luse <paul.e.luse@xxxxxxxxxxxxxxx>
> Signed-off-by: Paul Luse <paul.e.luse@xxxxxxxxxxxxxxx>
> Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
> ---
>  drivers/md/raid1.c | 79 ++++++++++++++++++++++++++++------------------
>  1 file changed, 48 insertions(+), 31 deletions(-)
>
> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index bc2f8fcbe5b3..4694e0e71e36 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -620,6 +620,44 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
>         return -1;
>  }
>
> +static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
> +                         int *max_sectors)
> +{
> +       sector_t this_sector = r1_bio->sector;
> +       int best_disk = -1;
> +       int best_len = 0;
> +       int disk;
> +
> +       for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
> +               struct md_rdev *rdev;
> +               int len;
> +               int read_len;
> +
> +               if (r1_bio->bios[disk] == IO_BLOCKED)
> +                       continue;
> +
> +               rdev = conf->mirrors[disk].rdev;
> +               if (!rdev || test_bit(Faulty, &rdev->flags) ||
> +                   test_bit(WriteMostly, &rdev->flags))
> +                       continue;
> +
> +               /* keep track of the disk with the most readable sectors. */
> +               len = r1_bio->sectors;
> +               read_len = raid1_check_read_range(rdev, this_sector, &len);
> +               if (read_len > best_len) {
> +                       best_disk = disk;
> +                       best_len = read_len;
> +               }
> +       }
> +
> +       if (best_disk != -1) {
> +               *max_sectors = best_len;
> +               update_read_sectors(conf, best_disk, this_sector, best_len);
> +       }
> +
> +       return best_disk;
> +}
> +
>  static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
>                             int *max_sectors)
>  {
> @@ -707,8 +745,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
>
>         for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
>                 sector_t dist;
> -               sector_t first_bad;
> -               int bad_sectors;
>                 unsigned int pending;
>
>                 rdev = conf->mirrors[disk].rdev;
> @@ -721,36 +757,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
>                         continue;
>                 if (test_bit(WriteMostly, &rdev->flags))
>                         continue;
> -               /* This is a reasonable device to use.  It might
> -                * even be best.
> -                */
> -               if (is_badblock(rdev, this_sector, sectors,
> -                               &first_bad, &bad_sectors)) {
> -                       if (best_dist < MaxSector)
> -                               /* already have a better device */
> -                               continue;
> -                       if (first_bad <= this_sector) {
> -                               /* cannot read here. If this is the 'primary'
> -                                * device, then we must not read beyond
> -                                * bad_sectors from another device..
> -                                */
> -                               bad_sectors -= (this_sector - first_bad);
> -                               if (best_good_sectors > sectors)
> -                                       best_good_sectors = sectors;
> -
> -                       } else {
> -                               sector_t good_sectors = first_bad - this_sector;
> -                               if (good_sectors > best_good_sectors) {
> -                                       best_good_sectors = good_sectors;
> -                                       best_disk = disk;
> -                               }
> -                       }
> +               if (rdev_has_badblock(rdev, this_sector, sectors))
>                         continue;
> -               } else {
> -                       if ((sectors > best_good_sectors) && (best_disk >= 0))
> -                               best_disk = -1;
> -                       best_good_sectors = sectors;
> -               }
>
>                 if (best_disk >= 0)
>                         /* At least two disks to choose from so failfast is OK */
> @@ -834,6 +842,15 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
>         if (best_disk >= 0)
>                 return best_disk;
>
> +       /*
> +        * If we are here it means we didn't find a perfectly good disk so
> +        * now spend a bit more time trying to find one with the most good
> +        * sectors.
> +        */
> +       disk = choose_bb_rdev(conf, r1_bio, max_sectors);
> +       if (disk >= 0)
> +               return disk;
> +
>         return choose_slow_rdev(conf, r1_bio, max_sectors);
>  }
>
> --
> 2.39.2
>
>
Hi
This patch looks good to me.
Reviewed-by: Xiao Ni <xni@xxxxxxxxxx>