*/
update_head_pos(mirror, r1_bio);
- if (uptodate || conf->working_disks <= 1) {
+ 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
* already.
*/
if (atomic_dec_and_test(&r1_bio->remaining)) {
- if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
+ if (test_bit(R1BIO_BarrierRetry, &r1_bio->state))
reschedule_retry(r1_bio);
- goto out;
- }
- /* it really is the end of this request */
- if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
- /* free extra copy of the data pages */
- int i = bio->bi_vcnt;
- while (i--)
- safe_put_page(bio->bi_io_vec[i].bv_page);
+ else {
+ /* it really is the end of this request */
+ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+ /* free extra copy of the data pages */
+ int i = bio->bi_vcnt;
+ while (i--)
+ safe_put_page(bio->bi_io_vec[i].bv_page);
+ }
+ /* clear the bitmap if all writes complete successfully */
+ bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
+ r1_bio->sectors,
+ !test_bit(R1BIO_Degraded, &r1_bio->state),
+ behind);
+ md_write_end(r1_bio->mddev);
+ raid_end_bio_io(r1_bio);
}
- /* clear the bitmap if all writes complete successfully */
- bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
- r1_bio->sectors,
- !test_bit(R1BIO_Degraded, &r1_bio->state),
- behind);
- md_write_end(r1_bio->mddev);
- raid_end_bio_io(r1_bio);
}
- out:
+
if (to_put)
bio_put(to_put);
return ret;
}
+static int raid1_congested(void *data, int bits)
+{
+ mddev_t *mddev = data;
+ conf_t *conf = mddev_to_conf(mddev);
+ int i, ret = 0;
+
+ rcu_read_lock();
+ 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);
+
+ /* Note the '|| 1' - when read_balance prefers
+ * non-congested targets, it can be removed
+ */
+ if ((bits & (1<<BDI_write_congested)) || 1)
+ ret |= bdi_congested(&q->backing_dev_info, bits);
+ else
+ ret &= bdi_congested(&q->backing_dev_info, bits);
+ }
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
int i;
seq_printf(seq, " [%d/%d] [", conf->raid_disks,
- conf->working_disks);
- for (i = 0; i < conf->raid_disks; i++)
+ conf->raid_disks - mddev->degraded);
+ rcu_read_lock();
+ for (i = 0; i < conf->raid_disks; i++) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
seq_printf(seq, "%s",
- conf->mirrors[i].rdev &&
- test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_");
+ rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+ }
+ rcu_read_unlock();
seq_printf(seq, "]");
}
* else mark the drive as failed
*/
if (test_bit(In_sync, &rdev->flags)
- && conf->working_disks == 1)
+ && (conf->raid_disks - mddev->degraded) == 1)
/*
* Don't fail the drive, act as though we were just a
* normal single drive
*/
return;
- if (test_bit(In_sync, &rdev->flags)) {
+ if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
- conf->working_disks--;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery is running, make sure it aborts.
*/
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
}
- clear_bit(In_sync, &rdev->flags);
set_bit(Faulty, &rdev->flags);
- mddev->sb_dirty = 1;
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT "raid1: Disk failure on %s, disabling device. \n"
" Operation continuing on %d devices\n",
- bdevname(rdev->bdev,b), conf->working_disks);
+ bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
}
static void print_conf(conf_t *conf)
{
int i;
- mirror_info_t *tmp;
printk("RAID1 conf printout:\n");
if (!conf) {
printk("(!conf)\n");
return;
}
- printk(" --- wd:%d rd:%d\n", conf->working_disks,
+ printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
conf->raid_disks);
+ rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
char b[BDEVNAME_SIZE];
- tmp = conf->mirrors + i;
- if (tmp->rdev)
+ mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+ if (rdev)
printk(" disk %d, wo:%d, o:%d, dev:%s\n",
- i, !test_bit(In_sync, &tmp->rdev->flags), !test_bit(Faulty, &tmp->rdev->flags),
- bdevname(tmp->rdev->bdev,b));
+ i, !test_bit(In_sync, &rdev->flags),
+ !test_bit(Faulty, &rdev->flags),
+ bdevname(rdev->bdev,b));
}
+ rcu_read_unlock();
}
static void close_sync(conf_t *conf)
{
int i;
conf_t *conf = mddev->private;
- mirror_info_t *tmp;
/*
* Find all failed disks within the RAID1 configuration
- * and mark them readable
+ * and mark them readable.
+ * Called under mddev lock, so rcu protection not needed.
*/
for (i = 0; i < conf->raid_disks; i++) {
- tmp = conf->mirrors + i;
- if (tmp->rdev
- && !test_bit(Faulty, &tmp->rdev->flags)
- && !test_bit(In_sync, &tmp->rdev->flags)) {
- conf->working_disks++;
+ mdk_rdev_t *rdev = conf->mirrors[i].rdev;
+ if (rdev
+ && !test_bit(Faulty, &rdev->flags)
+ && !test_and_set_bit(In_sync, &rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded--;
- set_bit(In_sync, &tmp->rdev->flags);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
}
}
long sectors_to_go = r1_bio->sectors;
/* make sure these bits doesn't get cleared. */
do {
- bitmap_end_sync(mddev->bitmap, r1_bio->sector,
+ bitmap_end_sync(mddev->bitmap, s,
&sync_blocks, 1);
s += sync_blocks;
sectors_to_go -= sync_blocks;
/* ouch - failed to read all of that.
* Try some synchronous reads of other devices to get
* good data, much like with normal read errors. Only
- * read into the pages we already have so they we don't
+ * read into the pages we already have so we don't
* need to re-issue the read request.
* We don't need to freeze the array, because being in an
* active sync request, there is no normal IO, and
s = PAGE_SIZE >> 9;
do {
if (r1_bio->bios[d]->bi_end_io == end_sync_read) {
+ /* No rcu protection needed here devices
+ * can only be removed when no resync is
+ * active, and resync is currently active
+ */
rdev = conf->mirrors[d].rdev;
if (sync_page_io(rdev->bdev,
sect + rdev->data_offset,
* 3. Performs writes following reads for array syncronising.
*/
+static void fix_read_error(conf_t *conf, int read_disk,
+ sector_t sect, int sectors)
+{
+ mddev_t *mddev = conf->mddev;
+ while(sectors) {
+ int s = sectors;
+ int d = read_disk;
+ int success = 0;
+ int start;
+ mdk_rdev_t *rdev;
+
+ if (s > (PAGE_SIZE>>9))
+ s = PAGE_SIZE >> 9;
+
+ do {
+ /* Note: no rcu protection needed here
+ * as this is synchronous in the raid1d thread
+ * which is the thread that might remove
+ * a device. If raid1d ever becomes multi-threaded....
+ */
+ rdev = conf->mirrors[d].rdev;
+ if (rdev &&
+ test_bit(In_sync, &rdev->flags) &&
+ sync_page_io(rdev->bdev,
+ sect + rdev->data_offset,
+ s<<9,
+ conf->tmppage, READ))
+ success = 1;
+ else {
+ d++;
+ if (d == conf->raid_disks)
+ d = 0;
+ }
+ } while (!success && d != read_disk);
+
+ if (!success) {
+ /* Cannot read from anywhere -- bye bye array */
+ md_error(mddev, conf->mirrors[read_disk].rdev);
+ break;
+ }
+ /* write it back and re-read */
+ start = d;
+ while (d != read_disk) {
+ if (d==0)
+ d = conf->raid_disks;
+ d--;
+ rdev = conf->mirrors[d].rdev;
+ if (rdev &&
+ test_bit(In_sync, &rdev->flags)) {
+ if (sync_page_io(rdev->bdev,
+ sect + rdev->data_offset,
+ s<<9, conf->tmppage, WRITE)
+ == 0)
+ /* Well, this device is dead */
+ md_error(mddev, rdev);
+ }
+ }
+ d = start;
+ while (d != read_disk) {
+ char b[BDEVNAME_SIZE];
+ if (d==0)
+ d = conf->raid_disks;
+ d--;
+ rdev = conf->mirrors[d].rdev;
+ if (rdev &&
+ test_bit(In_sync, &rdev->flags)) {
+ if (sync_page_io(rdev->bdev,
+ sect + rdev->data_offset,
+ s<<9, conf->tmppage, READ)
+ == 0)
+ /* Well, this device is dead */
+ md_error(mddev, rdev);
+ else {
+ atomic_add(s, &rdev->corrected_errors);
+ printk(KERN_INFO
+ "raid1:%s: read error corrected "
+ "(%d sectors at %llu on %s)\n",
+ mdname(mddev), s,
+ (unsigned long long)(sect +
+ rdev->data_offset),
+ bdevname(rdev->bdev, b));
+ }
+ }
+ }
+ sectors -= s;
+ sect += s;
+ }
+}
+
static void raid1d(mddev_t *mddev)
{
r1bio_t *r1_bio;
* This is all done synchronously while the array is
* frozen
*/
- sector_t sect = r1_bio->sector;
- int sectors = r1_bio->sectors;
- freeze_array(conf);
- if (mddev->ro == 0) while(sectors) {
- int s = sectors;
- int d = r1_bio->read_disk;
- int success = 0;
-
- if (s > (PAGE_SIZE>>9))
- s = PAGE_SIZE >> 9;
-
- do {
- rdev = conf->mirrors[d].rdev;
- if (rdev &&
- test_bit(In_sync, &rdev->flags) &&
- sync_page_io(rdev->bdev,
- sect + rdev->data_offset,
- s<<9,
- conf->tmppage, READ))
- success = 1;
- else {
- d++;
- if (d == conf->raid_disks)
- d = 0;
- }
- } while (!success && d != r1_bio->read_disk);
-
- if (success) {
- /* write it back and re-read */
- int start = d;
- while (d != r1_bio->read_disk) {
- if (d==0)
- d = conf->raid_disks;
- d--;
- rdev = conf->mirrors[d].rdev;
- atomic_add(s, &rdev->corrected_errors);
- if (rdev &&
- test_bit(In_sync, &rdev->flags)) {
- if (sync_page_io(rdev->bdev,
- sect + rdev->data_offset,
- s<<9, conf->tmppage, WRITE) == 0)
- /* Well, this device is dead */
- md_error(mddev, rdev);
- }
- }
- d = start;
- while (d != r1_bio->read_disk) {
- if (d==0)
- d = conf->raid_disks;
- d--;
- rdev = conf->mirrors[d].rdev;
- if (rdev &&
- test_bit(In_sync, &rdev->flags)) {
- if (sync_page_io(rdev->bdev,
- sect + rdev->data_offset,
- s<<9, conf->tmppage, READ) == 0)
- /* Well, this device is dead */
- md_error(mddev, rdev);
- }
- }
- } else {
- /* Cannot read from anywhere -- bye bye array */
- md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
- break;
- }
- sectors -= s;
- sect += s;
+ if (mddev->ro == 0) {
+ freeze_array(conf);
+ fix_read_error(conf, r1_bio->read_disk,
+ r1_bio->sector,
+ r1_bio->sectors);
+ unfreeze_array(conf);
}
- unfreeze_array(conf);
-
bio = r1_bio->bios[r1_bio->read_disk];
if ((disk=read_balance(conf, r1_bio)) == -1) {
printk(KERN_ALERT "raid1: %s: unrecoverable I/O"
return 0;
}
+ if (mddev->bitmap == NULL &&
+ mddev->recovery_cp == MaxSector &&
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+ conf->fullsync == 0) {
+ *skipped = 1;
+ return max_sector - sector_nr;
+ }
/* before building a request, check if we can skip these blocks..
* This call the bitmap_start_sync doesn't actually record anything
*/
for (i=0; i<conf->raid_disks; i++) {
bio = r1_bio->bios[i];
if (bio->bi_end_io == end_sync_read) {
- md_sync_acct(conf->mirrors[i].rdev->bdev, nr_sectors);
+ md_sync_acct(bio->bi_bdev, nr_sectors);
generic_make_request(bio);
}
}
} else {
atomic_set(&r1_bio->remaining, 1);
bio = r1_bio->bios[r1_bio->read_disk];
- md_sync_acct(conf->mirrors[r1_bio->read_disk].rdev->bdev,
- nr_sectors);
+ md_sync_acct(bio->bi_bdev, nr_sectors);
generic_make_request(bio);
}
-
return nr_sectors;
}
blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
disk->head_position = 0;
- if (!test_bit(Faulty, &rdev->flags) && test_bit(In_sync, &rdev->flags))
- conf->working_disks++;
}
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
spin_lock_init(&conf->device_lock);
INIT_LIST_HEAD(&conf->retry_list);
- if (conf->working_disks == 1)
- mddev->recovery_cp = MaxSector;
spin_lock_init(&conf->resync_lock);
init_waitqueue_head(&conf->wait_barrier);
bio_list_init(&conf->pending_bio_list);
bio_list_init(&conf->flushing_bio_list);
- if (!conf->working_disks) {
- printk(KERN_ERR "raid1: no operational mirrors for %s\n",
- mdname(mddev));
- goto out_free_conf;
- }
mddev->degraded = 0;
for (i = 0; i < conf->raid_disks; i++) {
disk = conf->mirrors + i;
- if (!disk->rdev) {
+ if (!disk->rdev ||
+ !test_bit(In_sync, &disk->rdev->flags)) {
disk->head_position = 0;
mddev->degraded++;
}
}
+ if (mddev->degraded == conf->raid_disks) {
+ printk(KERN_ERR "raid1: no operational mirrors for %s\n",
+ mdname(mddev));
+ goto out_free_conf;
+ }
+ if (conf->raid_disks - mddev->degraded == 1)
+ mddev->recovery_cp = MaxSector;
/*
* find the first working one and use it as a starting point
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 0;
mirror_info_t *newmirrors;
conf_t *conf = mddev_to_conf(mddev);
int cnt, raid_disks;
-
+ unsigned long flags;
int d, d2;
/* Cannot change chunk_size, layout, or level */
kfree(conf->poolinfo);
conf->poolinfo = newpoolinfo;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded += (raid_disks - conf->raid_disks);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
conf->raid_disks = mddev->raid_disks = raid_disks;
mddev->delta_disks = 0;
projects / linux-2.6 / blobdiff