If resync is in progress, read_balance() should find the first usable
disk, otherwise, data could be inconsistent after resync is done. raid1
and raid10 implement the same checking, hence factor out the checking
to make code cleaner.
Noted that raid1 is using 'mddev->recovery_cp', which is updated after
all resync IO is done, while raid10 is using 'conf->next_resync', which
is inaccurate because raid10 update it before submitting resync IO.
Fortunately, raid10 read IO can't concurrent with resync IO, hence there
is no problem. And this patch also switch raid10 to use
'mddev->recovery_cp'.
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>
Reviewed-by: Xiao Ni <xni@redhat.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240229095714.926789-7-yukuai1@huaweicloud.com
*len = first_bad + bad_sectors - this_sector;
return 0;
}
+
+/*
+ * Check if read should choose the first rdev.
+ *
+ * Balance on the whole device if no resync is going on (recovery is ok) or
+ * below the resync window. Otherwise, take the first readable disk.
+ */
+static inline bool raid1_should_read_first(struct mddev *mddev,
+ sector_t this_sector, int len)
+{
+ if ((mddev->recovery_cp < this_sector + len))
+ return true;
+
+ if (mddev_is_clustered(mddev) &&
+ md_cluster_ops->area_resyncing(mddev, READ, this_sector,
+ this_sector + len))
+ return true;
+
+ return false;
+}
struct md_rdev *rdev;
int choose_first;
- /*
- * Check if we can balance. We can balance on the whole
- * device if no resync is going on, or below the resync window.
- * We take the first readable disk when above the resync window.
- */
retry:
sectors = r1_bio->sectors;
best_disk = -1;
best_pending_disk = -1;
min_pending = UINT_MAX;
best_good_sectors = 0;
+ choose_first = raid1_should_read_first(conf->mddev, this_sector,
+ sectors);
clear_bit(R1BIO_FailFast, &r1_bio->state);
- if ((conf->mddev->recovery_cp < this_sector + sectors) ||
- (mddev_is_clustered(conf->mddev) &&
- md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
- this_sector + sectors)))
- choose_first = 1;
- else
- choose_first = 0;
-
for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
sector_t dist;
sector_t first_bad;
best_good_sectors = 0;
do_balance = 1;
clear_bit(R10BIO_FailFast, &r10_bio->state);
- /*
- * Check if we can balance. We can balance on the whole
- * device if no resync is going on (recovery is ok), or below
- * the resync window. We take the first readable disk when
- * above the resync window.
- */
- if ((conf->mddev->recovery_cp < MaxSector
- && (this_sector + sectors >= conf->next_resync)) ||
- (mddev_is_clustered(conf->mddev) &&
- md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
- this_sector + sectors)))
+
+ if (raid1_should_read_first(conf->mddev, this_sector, sectors))
do_balance = 0;
for (slot = 0; slot < conf->copies ; slot++) {