const sector_t this_sector = r1_bio->sector;
int sectors;
int best_good_sectors;
- int best_disk;
+ int best_disk, best_dist_disk, best_pending_disk;
+ int has_nonrot_disk;
int disk;
sector_t best_dist;
+ unsigned int min_pending;
struct md_rdev *rdev;
int choose_first;
+ int choose_next_idle;
rcu_read_lock();
/*
retry:
sectors = r1_bio->sectors;
best_disk = -1;
+ best_dist_disk = -1;
best_dist = MaxSector;
+ best_pending_disk = -1;
+ min_pending = UINT_MAX;
best_good_sectors = 0;
+ has_nonrot_disk = 0;
+ choose_next_idle = 0;
if (conf->mddev->recovery_cp < MaxSector &&
(this_sector + sectors >= conf->next_resync))
sector_t dist;
sector_t first_bad;
int bad_sectors;
+ unsigned int pending;
+ bool nonrot;
rdev = rcu_dereference(conf->mirrors[disk].rdev);
if (r1_bio->bios[disk] == IO_BLOCKED
} else
best_good_sectors = sectors;
+ nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
+ has_nonrot_disk |= nonrot;
+ pending = atomic_read(&rdev->nr_pending);
dist = abs(this_sector - conf->mirrors[disk].head_position);
- if (choose_first
- /* Don't change to another disk for sequential reads */
- || conf->mirrors[disk].next_seq_sect == this_sector
- || dist == 0
- /* If device is idle, use it */
- || atomic_read(&rdev->nr_pending) == 0) {
+ if (choose_first) {
best_disk = disk;
break;
}
+ /* 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];
+
+ best_disk = 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 (nonrot && opt_iosize > 0 &&
+ mirror->seq_start != MaxSector &&
+ mirror->next_seq_sect > opt_iosize &&
+ mirror->next_seq_sect - opt_iosize >=
+ mirror->seq_start) {
+ choose_next_idle = 1;
+ continue;
+ }
+ break;
+ }
+ /* If device is idle, use it */
+ if (pending == 0) {
+ best_disk = disk;
+ break;
+ }
+
+ if (choose_next_idle)
+ continue;
+
+ if (min_pending > pending) {
+ min_pending = pending;
+ best_pending_disk = disk;
+ }
+
if (dist < best_dist) {
best_dist = dist;
- best_disk = disk;
+ best_dist_disk = 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
+ * mixed ratation/non-rotational disks depending on workload.
+ */
+ if (best_disk == -1) {
+ if (has_nonrot_disk)
+ best_disk = best_pending_disk;
+ else
+ best_disk = best_dist_disk;
+ }
+
if (best_disk >= 0) {
rdev = rcu_dereference(conf->mirrors[best_disk].rdev);
if (!rdev)
goto retry;
}
sectors = best_good_sectors;
+
+ if (conf->mirrors[best_disk].next_seq_sect != this_sector)
+ conf->mirrors[best_disk].seq_start = this_sector;
+
conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
}
rcu_read_unlock();
pr_debug("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
}
+struct raid1_plug_cb {
+ struct blk_plug_cb cb;
+ struct bio_list pending;
+ int pending_cnt;
+};
+
+static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+ struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb,
+ cb);
+ struct mddev *mddev = plug->cb.data;
+ struct r1conf *conf = mddev->private;
+ struct bio *bio;
+
+ if (from_schedule) {
+ spin_lock_irq(&conf->device_lock);
+ bio_list_merge(&conf->pending_bio_list, &plug->pending);
+ conf->pending_count += plug->pending_cnt;
+ spin_unlock_irq(&conf->device_lock);
+ md_wakeup_thread(mddev->thread);
+ kfree(plug);
+ return;
+ }
+
+ /* we aren't scheduling, so we can do the write-out directly. */
+ bio = bio_list_get(&plug->pending);
+ bitmap_unplug(mddev->bitmap);
+ wake_up(&conf->wait_barrier);
+
+ while (bio) { /* submit pending writes */
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
+ generic_make_request(bio);
+ bio = next;
+ }
+ kfree(plug);
+}
+
static void make_request(struct mddev *mddev, struct bio * bio)
{
struct r1conf *conf = mddev->private;
const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
struct md_rdev *blocked_rdev;
+ struct blk_plug_cb *cb;
+ struct raid1_plug_cb *plug = NULL;
int first_clone;
int sectors_handled;
int max_sectors;
mbio->bi_private = r1_bio;
atomic_inc(&r1_bio->remaining);
+
+ cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
+ if (cb)
+ plug = container_of(cb, struct raid1_plug_cb, cb);
+ else
+ plug = NULL;
spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_add(&conf->pending_bio_list, mbio);
- conf->pending_count++;
+ if (plug) {
+ bio_list_add(&plug->pending, mbio);
+ plug->pending_cnt++;
+ } else {
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ }
spin_unlock_irqrestore(&conf->device_lock, flags);
- if (!mddev_check_plugged(mddev))
+ if (!plug)
md_wakeup_thread(mddev->thread);
}
/* Mustn't call r1_bio_write_done before this next test,
blk_start_plug(&plug);
for (;;) {
- if (atomic_read(&mddev->plug_cnt) == 0)
- flush_pending_writes(conf);
+ flush_pending_writes(conf);
spin_lock_irqsave(&conf->device_lock, flags);
if (list_empty(head)) {
bio->bi_rw = READ;
bio->bi_end_io = end_sync_read;
read_targets++;
+ } else if (!test_bit(WriteErrorSeen, &rdev->flags) &&
+ test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
+ !test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
+ /*
+ * The device is suitable for reading (InSync),
+ * but has bad block(s) here. Let's try to correct them,
+ * if we are doing resync or repair. Otherwise, leave
+ * this device alone for this sync request.
+ */
+ bio->bi_rw = WRITE;
+ bio->bi_end_io = end_sync_write;
+ write_targets++;
}
}
if (bio->bi_end_io) {
/* There is nowhere to write, so all non-sync
* drives must be failed - so we are finished
*/
- sector_t rv = max_sector - sector_nr;
+ sector_t rv;
+ if (min_bad > 0)
+ max_sector = sector_nr + min_bad;
+ rv = max_sector - sector_nr;
*skipped = 1;
put_buf(r1_bio);
return rv;
mddev->merge_check_needed = 1;
disk->head_position = 0;
+ disk->seq_start = MaxSector;
}
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
projects / ~andy / linux / blobdiff