| Message ID | 20240222075806.1816400-8-yukuai1@huaweicloud.com (mailing list archive) |
|---|---|
| State | Superseded, archived |
| Headers | show |
| Series | md/raid1: refactor read_balance() and some minor fix | expand |
On Thu, Feb 22, 2024 at 4:04 PM Yu Kuai <yukuai1@huaweicloud.com> wrote: > > From: Yu Kuai <yukuai3@huawei.com> > > 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 slow rdev from > read_balance(), there are no functional changes. > > 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 | 69 ++++++++++++++++++++++++++++++++++------------ > 1 file changed, 52 insertions(+), 17 deletions(-) > > diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c > index 08c45ca55a7e..bc2f8fcbe5b3 100644 > --- a/drivers/md/raid1.c > +++ b/drivers/md/raid1.c > @@ -620,6 +620,53 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio, > return -1; > } > > +static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio, > + int *max_sectors) > +{ > + sector_t this_sector = r1_bio->sector; > + int bb_disk = -1; > + int bb_read_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; > + > + /* there are no bad blocks, we can use this disk */ > + len = r1_bio->sectors; > + read_len = raid1_check_read_range(rdev, this_sector, &len); > + if (read_len == r1_bio->sectors) { > + update_read_sectors(conf, disk, this_sector, read_len); > + return disk; > + } > + > + /* > + * there are partial bad blocks, choose the rdev with largest > + * read length. > + */ > + if (read_len > bb_read_len) { > + bb_disk = disk; > + bb_read_len = read_len; > + } > + } > + > + if (bb_disk != -1) { > + *max_sectors = bb_read_len; > + update_read_sectors(conf, bb_disk, this_sector, bb_read_len); > + } > + > + return bb_disk; > +} > + > /* > * This routine returns the disk from which the requested read should > * be done. There is a per-array 'next expected sequential IO' sector > @@ -672,23 +719,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect > if (!test_bit(In_sync, &rdev->flags) && > rdev->recovery_offset < this_sector + sectors) > continue; > - if (test_bit(WriteMostly, &rdev->flags)) { > - /* Don't balance among write-mostly, just > - * use the first as a last resort */ > - if (best_dist_disk < 0) { > - if (is_badblock(rdev, this_sector, sectors, > - &first_bad, &bad_sectors)) { > - if (first_bad <= this_sector) > - /* Cannot use this */ > - continue; > - best_good_sectors = first_bad - this_sector; > - } else > - best_good_sectors = sectors; > - best_dist_disk = disk; > - best_pending_disk = disk; > - } > + if (test_bit(WriteMostly, &rdev->flags)) > continue; > - } > /* This is a reasonable device to use. It might > * even be best. > */ > @@ -799,7 +831,10 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect > } > *max_sectors = sectors; > > - return best_disk; > + if (best_disk >= 0) > + return best_disk; > + > + return choose_slow_rdev(conf, r1_bio, max_sectors); > } > > static void wake_up_barrier(struct r1conf *conf) > -- > 2.39.2 > > This patch looks good to me. Reviewed-by: Xiao Ni <xni@redhat.com>
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 08c45ca55a7e..bc2f8fcbe5b3 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -620,6 +620,53 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio, return -1; } +static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + sector_t this_sector = r1_bio->sector; + int bb_disk = -1; + int bb_read_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; + + /* there are no bad blocks, we can use this disk */ + len = r1_bio->sectors; + read_len = raid1_check_read_range(rdev, this_sector, &len); + if (read_len == r1_bio->sectors) { + update_read_sectors(conf, disk, this_sector, read_len); + return disk; + } + + /* + * there are partial bad blocks, choose the rdev with largest + * read length. + */ + if (read_len > bb_read_len) { + bb_disk = disk; + bb_read_len = read_len; + } + } + + if (bb_disk != -1) { + *max_sectors = bb_read_len; + update_read_sectors(conf, bb_disk, this_sector, bb_read_len); + } + + return bb_disk; +} + /* * This routine returns the disk from which the requested read should * be done. There is a per-array 'next expected sequential IO' sector @@ -672,23 +719,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect if (!test_bit(In_sync, &rdev->flags) && rdev->recovery_offset < this_sector + sectors) continue; - if (test_bit(WriteMostly, &rdev->flags)) { - /* Don't balance among write-mostly, just - * use the first as a last resort */ - if (best_dist_disk < 0) { - if (is_badblock(rdev, this_sector, sectors, - &first_bad, &bad_sectors)) { - if (first_bad <= this_sector) - /* Cannot use this */ - continue; - best_good_sectors = first_bad - this_sector; - } else - best_good_sectors = sectors; - best_dist_disk = disk; - best_pending_disk = disk; - } + if (test_bit(WriteMostly, &rdev->flags)) continue; - } /* This is a reasonable device to use. It might * even be best. */ @@ -799,7 +831,10 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect } *max_sectors = sectors; - return best_disk; + if (best_disk >= 0) + return best_disk; + + return choose_slow_rdev(conf, r1_bio, max_sectors); } static void wake_up_barrier(struct r1conf *conf)