summaryrefslogtreecommitdiff
path: root/drivers/md/raid1.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid1.c')
-rw-r--r--drivers/md/raid1.c32
1 files changed, 22 insertions, 10 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index de6ea87d4d24..fa86d9fdb16f 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -598,13 +598,12 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
const sector_t this_sector = r1_bio->sector;
int sectors;
int best_good_sectors;
- int best_disk, best_dist_disk, best_pending_disk;
+ int best_disk, best_dist_disk, best_pending_disk, sequential_disk;
int disk;
sector_t best_dist;
unsigned int min_pending;
struct md_rdev *rdev;
int choose_first;
- int choose_next_idle;
/*
* Check if we can balance. We can balance on the whole
@@ -615,11 +614,11 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
sectors = r1_bio->sectors;
best_disk = -1;
best_dist_disk = -1;
+ sequential_disk = -1;
best_dist = MaxSector;
best_pending_disk = -1;
min_pending = UINT_MAX;
best_good_sectors = 0;
- choose_next_idle = 0;
clear_bit(R1BIO_FailFast, &r1_bio->state);
if ((conf->mddev->recovery_cp < this_sector + sectors) ||
@@ -712,7 +711,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
struct raid1_info *mirror = &conf->mirrors[disk];
- best_disk = disk;
/*
* If buffered sequential IO size exceeds optimal
* iosize, check if there is idle disk. If yes, choose
@@ -731,15 +729,22 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
mirror->next_seq_sect > opt_iosize &&
mirror->next_seq_sect - opt_iosize >=
mirror->seq_start) {
- choose_next_idle = 1;
- continue;
+ /*
+ * 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 {
+ best_disk = disk;
+ break;
}
- break;
}
- if (choose_next_idle)
- continue;
-
if (min_pending > pending) {
min_pending = pending;
best_pending_disk = disk;
@@ -752,6 +757,13 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
}
/*
+ * sequential IO size exceeds optimal iosize, however, there is no other
+ * idle disk, so choose the sequential disk.
+ */
+ if (best_disk == -1 && min_pending != 0)
+ best_disk = sequential_disk;
+
+ /*
* If all disks are rotational, choose the closest disk. If any disk is
* non-rotational, choose the disk with less pending request even the
* disk is rotational, which might/might not be optimal for raids with