*
* Better read-balancing code written by Mika Kuoppala <miku@iki.fi>, 2000
*
- * Fixes to reconstruction by Jakob Østergaard" <jakob@ostenfeld.dk>
+ * Fixes to reconstruction by Jakob Østergaard" <jakob@ostenfeld.dk>
* Various fixes by Neil Brown <neilb@cse.unsw.edu.au>
*
* Changes by Peter T. Breuer <ptb@it.uc3m.es> 31/1/2003 to support
(unsigned long long) bio->bi_sector +
(bio->bi_size >> 9) - 1);
- bio_endio(bio, bio->bi_size,
+ bio_endio(bio,
test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
}
free_r1bio(r1_bio);
r1_bio->sector + (r1_bio->sectors);
}
-static int raid1_end_read_request(struct bio *bio, unsigned int bytes_done, int error)
+static void raid1_end_read_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
int mirror;
conf_t *conf = mddev_to_conf(r1_bio->mddev);
- if (bio->bi_size)
- return 1;
-
mirror = r1_bio->read_disk;
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
update_head_pos(mirror, r1_bio);
- if (uptodate || (conf->raid_disks - conf->mddev->degraded) <= 1) {
- /*
- * Set R1BIO_Uptodate in our master bio, so that
- * we will return a good error code for to the higher
- * levels even if IO on some other mirrored buffer fails.
- *
- * The 'master' represents the composite IO operation to
- * user-side. So if something waits for IO, then it will
- * wait for the 'master' bio.
+ if (uptodate)
+ set_bit(R1BIO_Uptodate, &r1_bio->state);
+ else {
+ /* If all other devices have failed, we want to return
+ * the error upwards rather than fail the last device.
+ * Here we redefine "uptodate" to mean "Don't want to retry"
*/
- if (uptodate)
- set_bit(R1BIO_Uptodate, &r1_bio->state);
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
+ if (r1_bio->mddev->degraded == conf->raid_disks ||
+ (r1_bio->mddev->degraded == conf->raid_disks-1 &&
+ !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+ uptodate = 1;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ }
+ if (uptodate)
raid_end_bio_io(r1_bio);
- } else {
+ else {
/*
* oops, read error:
*/
}
rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
- return 0;
}
-static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int error)
+static void raid1_end_write_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
conf_t *conf = mddev_to_conf(r1_bio->mddev);
struct bio *to_put = NULL;
- if (bio->bi_size)
- return 1;
for (mirror = 0; mirror < conf->raid_disks; mirror++)
if (r1_bio->bios[mirror] == bio)
(unsigned long long) mbio->bi_sector,
(unsigned long long) mbio->bi_sector +
(mbio->bi_size >> 9) - 1);
- bio_endio(mbio, mbio->bi_size, 0);
+ bio_endio(mbio, 0);
}
}
}
if (to_put)
bio_put(to_put);
-
- return 0;
}
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
- request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
+ struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- if (r_queue->unplug_fn)
- r_queue->unplug_fn(r_queue);
+ blk_unplug(r_queue);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
rcu_read_unlock();
}
-static void raid1_unplug(request_queue_t *q)
+static void raid1_unplug(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
md_wakeup_thread(mddev->thread);
}
-static int raid1_issue_flush(request_queue_t *q, struct gendisk *disk,
- sector_t *error_sector)
-{
- mddev_t *mddev = q->queuedata;
- conf_t *conf = mddev_to_conf(mddev);
- int i, ret = 0;
-
- rcu_read_lock();
- for (i=0; i<mddev->raid_disks && ret == 0; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags)) {
- struct block_device *bdev = rdev->bdev;
- request_queue_t *r_queue = bdev_get_queue(bdev);
-
- if (!r_queue->issue_flush_fn)
- ret = -EOPNOTSUPP;
- else {
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
- ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk,
- error_sector);
- rdev_dec_pending(rdev, mddev);
- rcu_read_lock();
- }
- }
- }
- rcu_read_unlock();
- return ret;
-}
-
static int raid1_congested(void *data, int bits)
{
mddev_t *mddev = data;
for (i = 0; i < mddev->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
- request_queue_t *q = bdev_get_queue(rdev->bdev);
+ struct request_queue *q = bdev_get_queue(rdev->bdev);
/* Note the '|| 1' - when read_balance prefers
* non-congested targets, it can be removed
return NULL;
}
-static int make_request(request_queue_t *q, struct bio * bio)
+static int make_request(struct request_queue *q, struct bio * bio)
{
mddev_t *mddev = q->queuedata;
conf_t *conf = mddev_to_conf(mddev);
if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
if (rw == WRITE)
md_write_end(mddev);
- bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+ bio_endio(bio, -EOPNOTSUPP);
return 0;
}
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
+ set_bit(Faulty, &rdev->flags);
spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery is running, make sure it aborts.
*/
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
- }
- set_bit(Faulty, &rdev->flags);
+ } else
+ set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT "raid1: Disk failure on %s, disabling device. \n"
" Operation continuing on %d devices\n",
}
-static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
+static void end_sync_read(struct bio *bio, int error)
{
r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
int i;
- if (bio->bi_size)
- return 1;
-
for (i=r1_bio->mddev->raid_disks; i--; )
if (r1_bio->bios[i] == bio)
break;
if (atomic_dec_and_test(&r1_bio->remaining))
reschedule_retry(r1_bio);
- return 0;
}
-static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
+static void end_sync_write(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
int i;
int mirror=0;
- if (bio->bi_size)
- return 1;
-
for (i = 0; i < conf->raid_disks; i++)
if (r1_bio->bios[i] == bio) {
mirror = i;
md_done_sync(mddev, r1_bio->sectors, uptodate);
put_buf(r1_bio);
}
- return 0;
}
static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
}
r1_bio->read_disk = primary;
for (i=0; i<mddev->raid_disks; i++)
- if (r1_bio->bios[i]->bi_end_io == end_sync_read &&
- test_bit(BIO_UPTODATE, &r1_bio->bios[i]->bi_flags)) {
+ if (r1_bio->bios[i]->bi_end_io == end_sync_read) {
int j;
int vcnt = r1_bio->sectors >> (PAGE_SHIFT- 9);
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
- for (j = vcnt; j-- ; )
- if (memcmp(page_address(pbio->bi_io_vec[j].bv_page),
- page_address(sbio->bi_io_vec[j].bv_page),
- PAGE_SIZE))
- break;
+
+ if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+ for (j = vcnt; j-- ; ) {
+ struct page *p, *s;
+ p = pbio->bi_io_vec[j].bv_page;
+ s = sbio->bi_io_vec[j].bv_page;
+ if (memcmp(page_address(p),
+ page_address(s),
+ PAGE_SIZE))
+ break;
+ }
+ } else
+ j = 0;
if (j >= 0)
mddev->resync_mismatches += r1_bio->sectors;
- if (j < 0 || test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
+ if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
+ && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
} else {
sbio->bi_sector = r1_bio->sector +
conf->mirrors[i].rdev->data_offset;
sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
+ for (j = 0; j < vcnt ; j++)
+ memcpy(page_address(sbio->bi_io_vec[j].bv_page),
+ page_address(pbio->bi_io_vec[j].bv_page),
+ PAGE_SIZE);
+
}
}
}
blk_remove_plug(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
/* flush any pending bitmap writes to disk before proceeding w/ I/O */
- if (bitmap_unplug(mddev->bitmap) != 0)
- printk("%s: bitmap file write failed!\n", mdname(mddev));
+ bitmap_unplug(mddev->bitmap);
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
!test_bit(In_sync, &disk->rdev->flags)) {
disk->head_position = 0;
mddev->degraded++;
- conf->fullsync = 1;
+ if (disk->rdev)
+ conf->fullsync = 1;
}
}
if (mddev->degraded == conf->raid_disks) {
mddev->array_size = mddev->size;
mddev->queue->unplug_fn = raid1_unplug;
- mddev->queue->issue_flush_fn = raid1_issue_flush;
mddev->queue->backing_dev_info.congested_fn = raid1_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
return -EINVAL;
}
+ md_allow_write(mddev);
+
raid_disks = mddev->raid_disks + mddev->delta_disks;
if (raid_disks < conf->raid_disks) {
oldpool = conf->r1bio_pool;
conf->r1bio_pool = newpool;
- for (d=d2=0; d < conf->raid_disks; d++)
- if (conf->mirrors[d].rdev) {
- conf->mirrors[d].rdev->raid_disk = d2;
- newmirrors[d2++].rdev = conf->mirrors[d].rdev;
+ for (d = d2 = 0; d < conf->raid_disks; d++) {
+ mdk_rdev_t *rdev = conf->mirrors[d].rdev;
+ if (rdev && rdev->raid_disk != d2) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ rdev->raid_disk = d2;
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ if (sysfs_create_link(&mddev->kobj,
+ &rdev->kobj, nm))
+ printk(KERN_WARNING
+ "md/raid1: cannot register "
+ "%s for %s\n",
+ nm, mdname(mddev));
}
+ if (rdev)
+ newmirrors[d2++].rdev = rdev;
+ }
kfree(conf->mirrors);
conf->mirrors = newmirrors;
kfree(conf->poolinfo);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff