*
* 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
}
+static int flush_pending_writes(conf_t *conf)
+{
+ /* Any writes that have been queued but are awaiting
+ * bitmap updates get flushed here.
+ * We return 1 if any requests were actually submitted.
+ */
+ int rv = 0;
+
+ spin_lock_irq(&conf->device_lock);
+
+ if (conf->pending_bio_list.head) {
+ struct bio *bio;
+ bio = bio_list_get(&conf->pending_bio_list);
+ blk_remove_plug(conf->mddev->queue);
+ spin_unlock_irq(&conf->device_lock);
+ /* flush any pending bitmap writes to
+ * disk before proceeding w/ I/O */
+ bitmap_unplug(conf->mddev->bitmap);
+
+ while (bio) { /* submit pending writes */
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
+ generic_make_request(bio);
+ bio = next;
+ }
+ rv = 1;
+ } else
+ spin_unlock_irq(&conf->device_lock);
+ return rv;
+}
+
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
/* stop syncio and normal IO and wait for everything to
* go quite.
* We increment barrier and nr_waiting, and then
- * wait until barrier+nr_pending match nr_queued+2
+ * wait until nr_pending match nr_queued+1
+ * This is called in the context of one normal IO request
+ * that has failed. Thus any sync request that might be pending
+ * will be blocked by nr_pending, and we need to wait for
+ * pending IO requests to complete or be queued for re-try.
+ * Thus the number queued (nr_queued) plus this request (1)
+ * must match the number of pending IOs (nr_pending) before
+ * we continue.
*/
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq(conf->wait_barrier,
- conf->barrier+conf->nr_pending == conf->nr_queued+2,
+ conf->nr_pending == conf->nr_queued+1,
conf->resync_lock,
- raid1_unplug(conf->mddev->queue));
+ ({ flush_pending_writes(conf);
+ raid1_unplug(conf->mddev->queue); }));
spin_unlock_irq(&conf->resync_lock);
}
static void unfreeze_array(conf_t *conf)
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);
r1bio_t *r1_bio;
struct bio *read_bio;
int i, targets = 0, disks;
- mdk_rdev_t *rdev;
struct bitmap *bitmap = mddev->bitmap;
unsigned long flags;
struct bio_list bl;
struct page **behind_pages = NULL;
const int rw = bio_data_dir(bio);
+ const int do_sync = bio_sync(bio);
int do_barriers;
+ mdk_rdev_t *blocked_rdev;
/*
* Register the new request and wait if the reconstruction
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;
}
read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
read_bio->bi_bdev = mirror->rdev->bdev;
read_bio->bi_end_io = raid1_end_read_request;
- read_bio->bi_rw = READ;
+ read_bio->bi_rw = READ | do_sync;
read_bio->bi_private = r1_bio;
generic_make_request(read_bio);
first = 0;
}
#endif
+ retry_write:
+ blocked_rdev = NULL;
rcu_read_lock();
for (i = 0; i < disks; i++) {
- if ((rdev=rcu_dereference(conf->mirrors[i].rdev)) != NULL &&
- !test_bit(Faulty, &rdev->flags)) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+ if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ atomic_inc(&rdev->nr_pending);
+ blocked_rdev = rdev;
+ break;
+ }
+ if (rdev && !test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
if (test_bit(Faulty, &rdev->flags)) {
rdev_dec_pending(rdev, mddev);
}
rcu_read_unlock();
+ if (unlikely(blocked_rdev)) {
+ /* Wait for this device to become unblocked */
+ int j;
+
+ for (j = 0; j < i; j++)
+ if (r1_bio->bios[j])
+ rdev_dec_pending(conf->mirrors[j].rdev, mddev);
+
+ allow_barrier(conf);
+ md_wait_for_blocked_rdev(blocked_rdev, mddev);
+ wait_barrier(conf);
+ goto retry_write;
+ }
+
BUG_ON(targets == 0); /* we never fail the last device */
if (targets < conf->raid_disks) {
mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
mbio->bi_end_io = raid1_end_write_request;
- mbio->bi_rw = WRITE | do_barriers;
+ mbio->bi_rw = WRITE | do_barriers | do_sync;
mbio->bi_private = r1_bio;
if (behind_pages) {
blk_plug_device(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
+ /* In case raid1d snuck into freeze_array */
+ wake_up(&conf->wait_barrier);
+
+ if (do_sync)
+ md_wakeup_thread(mddev->thread);
#if 0
while ((bio = bio_list_pop(&bl)) != NULL)
generic_make_request(bio);
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",
+ printk(KERN_ALERT "raid1: Disk failure on %s, disabling device.\n"
+ "raid1: Operation continuing on %d devices.\n",
bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
}
}
-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);
+
}
}
}
for (;;) {
char b[BDEVNAME_SIZE];
- spin_lock_irqsave(&conf->device_lock, flags);
- if (conf->pending_bio_list.head) {
- bio = bio_list_get(&conf->pending_bio_list);
- 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));
-
- while (bio) { /* submit pending writes */
- struct bio *next = bio->bi_next;
- bio->bi_next = NULL;
- generic_make_request(bio);
- bio = next;
- }
- unplug = 1;
-
- continue;
- }
+ unplug += flush_pending_writes(conf);
- if (list_empty(head))
+ spin_lock_irqsave(&conf->device_lock, flags);
+ if (list_empty(head)) {
+ spin_unlock_irqrestore(&conf->device_lock, flags);
break;
+ }
r1_bio = list_entry(head->prev, r1bio_t, retry_list);
list_del(head->prev);
conf->nr_queued--;
* We already have a nr_pending reference on these rdevs.
*/
int i;
+ const int do_sync = bio_sync(r1_bio->master_bio);
clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
clear_bit(R1BIO_Barrier, &r1_bio->state);
for (i=0; i < conf->raid_disks; i++)
conf->mirrors[i].rdev->data_offset;
bio->bi_bdev = conf->mirrors[i].rdev->bdev;
bio->bi_end_io = raid1_end_write_request;
- bio->bi_rw = WRITE;
+ bio->bi_rw = WRITE | do_sync;
bio->bi_private = r1_bio;
r1_bio->bios[i] = bio;
generic_make_request(bio);
(unsigned long long)r1_bio->sector);
raid_end_bio_io(r1_bio);
} else {
+ const int do_sync = bio_sync(r1_bio->master_bio);
r1_bio->bios[r1_bio->read_disk] =
mddev->ro ? IO_BLOCKED : NULL;
r1_bio->read_disk = disk;
bio->bi_sector = r1_bio->sector + rdev->data_offset;
bio->bi_bdev = rdev->bdev;
bio->bi_end_io = raid1_end_read_request;
- bio->bi_rw = READ;
+ bio->bi_rw = READ | do_sync;
bio->bi_private = r1_bio;
unplug = 1;
generic_make_request(bio);
}
}
}
- spin_unlock_irqrestore(&conf->device_lock, flags);
if (unplug)
unplug_slaves(mddev);
}
if (!go_faster && conf->nr_waiting)
msleep_interruptible(1000);
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr);
raise_barrier(conf);
conf->next_resync = sector_nr;
/* take from bio_init */
bio->bi_next = NULL;
bio->bi_flags |= 1 << BIO_UPTODATE;
- bio->bi_rw = 0;
+ bio->bi_rw = READ;
bio->bi_vcnt = 0;
bio->bi_idx = 0;
bio->bi_phys_segments = 0;
return rv;
}
+ if (max_sector > mddev->resync_max)
+ max_sector = mddev->resync_max; /* Don't do IO beyond here */
nr_sectors = 0;
sync_blocks = 0;
do {
if (!conf->r1bio_pool)
goto out_no_mem;
- ITERATE_RDEV(mddev, rdev, tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
!test_bit(In_sync, &disk->rdev->flags)) {
disk->head_position = 0;
mddev->degraded++;
+ 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);
Code Review / linux-2.6.git / blobdiff