for (i = disks; i--; ) {
int rw;
+ int replace_only = 0;
struct bio *bi, *rbi;
struct md_rdev *rdev, *rrdev = NULL;
if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
rw = WRITE;
} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
rw = READ;
- else
+ else if (test_and_clear_bit(R5_WantReplace,
+ &sh->dev[i].flags)) {
+ rw = WRITE;
+ replace_only = 1;
+ } else
continue;
bi = &sh->dev[i].req;
bi->bi_end_io = raid5_end_read_request;
rcu_read_lock();
+ rrdev = rcu_dereference(conf->disks[i].replacement);
+ smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
rdev = rcu_dereference(conf->disks[i].rdev);
- if (rw & WRITE)
- rrdev = rcu_dereference(conf->disks[i].replacement);
- else if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
- rdev = rcu_dereference(conf->disks[i].replacement);
+ if (!rdev) {
+ rdev = rrdev;
+ rrdev = NULL;
+ }
+ if (rw & WRITE) {
+ if (replace_only)
+ rdev = NULL;
+ if (rdev == rrdev)
+ /* We raced and saw duplicates */
+ rrdev = NULL;
+ } else {
+ if (test_bit(R5_ReadRepl, &sh->dev[i].flags) && rrdev)
+ rdev = rrdev;
+ rrdev = NULL;
+ }
if (rdev && test_bit(Faulty, &rdev->flags))
rdev = NULL;
}
if (rdev) {
- if (s->syncing || s->expanding || s->expanded)
+ if (s->syncing || s->expanding || s->expanded
+ || s->replacing)
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
set_bit(STRIPE_IO_STARTED, &sh->state);
generic_make_request(bi);
}
if (rrdev) {
- if (s->syncing || s->expanding || s->expanded)
+ if (s->syncing || s->expanding || s->expanded
+ || s->replacing)
md_sync_acct(rrdev->bdev, STRIPE_SECTORS);
set_bit(STRIPE_IO_STARTED, &sh->state);
int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
char b[BDEVNAME_SIZE];
- struct md_rdev *rdev;
+ struct md_rdev *rdev = NULL;
for (i=0 ; i<disks; i++)
return;
}
if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
+ /* If replacement finished while this request was outstanding,
+ * 'replacement' might be NULL already.
+ * In that case it moved down to 'rdev'.
+ * rdev is not removed until all requests are finished.
+ */
rdev = conf->disks[i].replacement;
- else
+ if (!rdev)
rdev = conf->disks[i].rdev;
if (uptodate) {
}
if (bi == &sh->dev[i].rreq) {
rdev = conf->disks[i].replacement;
- replacement = 1;
+ if (rdev)
+ replacement = 1;
+ else
+ /* rdev was removed and 'replacement'
+ * replaced it. rdev is not removed
+ * until all requests are finished.
+ */
+ rdev = conf->disks[i].rdev;
break;
}
}
md_done_sync(conf->mddev, STRIPE_SECTORS, 0);
clear_bit(STRIPE_SYNCING, &sh->state);
s->syncing = 0;
+ s->replacing = 0;
/* There is nothing more to do for sync/check/repair.
- * For recover we need to record a bad block on all
+ * For recover/replace we need to record a bad block on all
* non-sync devices, or abort the recovery
*/
if (!test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery))
*/
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = conf->disks[i].rdev;
- if (!rdev
- || test_bit(Faulty, &rdev->flags)
- || test_bit(In_sync, &rdev->flags))
- continue;
- if (!rdev_set_badblocks(rdev, sh->sector,
- STRIPE_SECTORS, 0))
+ if (rdev
+ && !test_bit(Faulty, &rdev->flags)
+ && !test_bit(In_sync, &rdev->flags)
+ && !rdev_set_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS, 0))
+ abort = 1;
+ rdev = conf->disks[i].replacement;
+ if (rdev
+ && !test_bit(Faulty, &rdev->flags)
+ && !test_bit(In_sync, &rdev->flags)
+ && !rdev_set_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS, 0))
abort = 1;
}
if (abort) {
}
}
+static int want_replace(struct stripe_head *sh, int disk_idx)
+{
+ struct md_rdev *rdev;
+ int rv = 0;
+ /* Doing recovery so rcu locking not required */
+ rdev = sh->raid_conf->disks[disk_idx].replacement;
+ if (rdev
+ && !test_bit(Faulty, &rdev->flags)
+ && !test_bit(In_sync, &rdev->flags)
+ && (rdev->recovery_offset <= sh->sector
+ || rdev->mddev->recovery_cp <= sh->sector))
+ rv = 1;
+
+ return rv;
+}
+
/* fetch_block - checks the given member device to see if its data needs
* to be read or computed to satisfy a request.
*
(dev->toread ||
(dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
s->syncing || s->expanding ||
+ (s->replacing && want_replace(sh, disk_idx)) ||
(s->failed >= 1 && fdev[0]->toread) ||
(s->failed >= 2 && fdev[1]->toread) ||
(sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
}
}
-
/*
* handle_stripe - do things to a stripe.
*
- * We lock the stripe and then examine the state of various bits
- * to see what needs to be done.
+ * We lock the stripe by setting STRIPE_ACTIVE and then examine the
+ * state of various bits to see what needs to be done.
* Possible results:
- * return some read request which now have data
- * return some write requests which are safely on disc
+ * return some read requests which now have data
+ * return some write requests which are safely on storage
* schedule a read on some buffers
* schedule a write of some buffers
* return confirmation of parity correctness
*
- * buffers are taken off read_list or write_list, and bh_cache buffers
- * get BH_Lock set before the stripe lock is released.
- *
*/
static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
int disks = sh->disks;
struct r5dev *dev;
int i;
+ int do_recovery = 0;
memset(s, 0, sizeof(*s));
- s->syncing = test_bit(STRIPE_SYNCING, &sh->state);
s->expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
s->failed_num[0] = -1;
dev = &sh->dev[i];
pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
- i, dev->flags, dev->toread, dev->towrite, dev->written);
+ i, dev->flags,
+ dev->toread, dev->towrite, dev->written);
/* maybe we can reply to a read
*
* new wantfill requests are only permitted while
&first_bad, &bad_sectors))
set_bit(R5_ReadRepl, &dev->flags);
else {
+ if (rdev)
+ set_bit(R5_NeedReplace, &dev->flags);
rdev = rcu_dereference(conf->disks[i].rdev);
clear_bit(R5_ReadRepl, &dev->flags);
}
if (s->failed < 2)
s->failed_num[s->failed] = i;
s->failed++;
+ if (rdev && !test_bit(Faulty, &rdev->flags))
+ do_recovery = 1;
}
}
spin_unlock_irq(&conf->device_lock);
+ if (test_bit(STRIPE_SYNCING, &sh->state)) {
+ /* If there is a failed device being replaced,
+ * we must be recovering.
+ * else if we are after recovery_cp, we must be syncing
+ * else we can only be replacing
+ * sync and recovery both need to read all devices, and so
+ * use the same flag.
+ */
+ if (do_recovery ||
+ sh->sector >= conf->mddev->recovery_cp)
+ s->syncing = 1;
+ else
+ s->replacing = 1;
+ }
rcu_read_unlock();
}
if (unlikely(s.blocked_rdev)) {
if (s.syncing || s.expanding || s.expanded ||
- s.to_write || s.written) {
+ s.replacing || s.to_write || s.written) {
set_bit(STRIPE_HANDLE, &sh->state);
goto finish;
}
sh->reconstruct_state = 0;
if (s.to_read+s.to_write+s.written)
handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
- if (s.syncing)
+ if (s.syncing + s.replacing)
handle_failed_sync(conf, sh, &s);
}
*/
if (s.to_read || s.non_overwrite
|| (conf->level == 6 && s.to_write && s.failed)
- || (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
+ || (s.syncing && (s.uptodate + s.compute < disks))
+ || s.replacing
+ || s.expanding)
handle_stripe_fill(sh, &s, disks);
/* Now we check to see if any write operations have recently
handle_parity_checks5(conf, sh, &s, disks);
}
- if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
+ if (s.replacing && s.locked == 0
+ && !test_bit(STRIPE_INSYNC, &sh->state)) {
+ /* Write out to replacement devices where possible */
+ for (i = 0; i < conf->raid_disks; i++)
+ if (test_bit(R5_UPTODATE, &sh->dev[i].flags) &&
+ test_bit(R5_NeedReplace, &sh->dev[i].flags)) {
+ set_bit(R5_WantReplace, &sh->dev[i].flags);
+ set_bit(R5_LOCKED, &sh->dev[i].flags);
+ s.locked++;
+ }
+ set_bit(STRIPE_INSYNC, &sh->state);
+ }
+ if ((s.syncing || s.replacing) && s.locked == 0 &&
+ test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
}
if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) {
rdev = conf->disks[i].replacement;
+ if (!rdev)
+ /* rdev have been moved down */
+ rdev = conf->disks[i].rdev;
rdev_clear_badblocks(rdev, sh->sector,
STRIPE_SECTORS);
rdev_dec_pending(rdev, conf->mddev);
return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
}
-
bitmap_cond_end_sync(mddev->bitmap, sector_nr);
sh = get_active_stripe(conf, sector_nr, 0, 1, 0);
continue;
disk = conf->disks + raid_disk;
- disk->rdev = rdev;
+ if (test_bit(Replacement, &rdev->flags)) {
+ if (disk->replacement)
+ goto abort;
+ disk->replacement = rdev;
+ } else {
+ if (disk->rdev)
+ goto abort;
+ disk->rdev = rdev;
+ }
if (test_bit(In_sync, &rdev->flags)) {
char b[BDEVNAME_SIZE];
int dirty_parity_disks = 0;
struct md_rdev *rdev;
sector_t reshape_offset = 0;
+ int i;
if (mddev->recovery_cp != MaxSector)
printk(KERN_NOTICE "md/raid:%s: not clean"
conf->thread = NULL;
mddev->private = conf;
- /*
- * 0 for a fully functional array, 1 or 2 for a degraded array.
- */
- list_for_each_entry(rdev, &mddev->disks, same_set) {
- if (rdev->raid_disk < 0)
+ for (i = 0; i < conf->raid_disks && conf->previous_raid_disks;
+ i++) {
+ rdev = conf->disks[i].rdev;
+ if (!rdev && conf->disks[i].replacement) {
+ /* The replacement is all we have yet */
+ rdev = conf->disks[i].replacement;
+ conf->disks[i].replacement = NULL;
+ clear_bit(Replacement, &rdev->flags);
+ conf->disks[i].rdev = rdev;
+ }
+ if (!rdev)
continue;
+ if (conf->disks[i].replacement &&
+ conf->reshape_progress != MaxSector) {
+ /* replacements and reshape simply do not mix. */
+ printk(KERN_ERR "md: cannot handle concurrent "
+ "replacement and reshape.\n");
+ goto abort;
+ }
if (test_bit(In_sync, &rdev->flags)) {
working_disks++;
continue;
dirty_parity_disks++;
}
+ /*
+ * 0 for a fully functional array, 1 or 2 for a degraded array.
+ */
mddev->degraded = calc_degraded(conf);
if (has_failed(conf)) {
for (i = 0; i < conf->raid_disks; i++) {
tmp = conf->disks + i;
- if (tmp->rdev
+ if (tmp->replacement
+ && tmp->replacement->recovery_offset == MaxSector
+ && !test_bit(Faulty, &tmp->replacement->flags)
+ && !test_and_set_bit(In_sync, &tmp->replacement->flags)) {
+ /* Replacement has just become active. */
+ if (!tmp->rdev
+ || !test_and_clear_bit(In_sync, &tmp->rdev->flags))
+ count++;
+ if (tmp->rdev) {
+ /* Replaced device not technically faulty,
+ * but we need to be sure it gets removed
+ * and never re-added.
+ */
+ set_bit(Faulty, &tmp->rdev->flags);
+ sysfs_notify_dirent_safe(
+ tmp->rdev->sysfs_state);
+ }
+ sysfs_notify_dirent_safe(tmp->replacement->sysfs_state);
+ } else if (tmp->rdev
&& tmp->rdev->recovery_offset == MaxSector
&& !test_bit(Faulty, &tmp->rdev->flags)
&& !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
if (!test_bit(Faulty, &rdev->flags) &&
mddev->recovery_disabled != conf->recovery_disabled &&
!has_failed(conf) &&
+ (!p->replacement || p->replacement == rdev) &&
number < conf->raid_disks) {
err = -EBUSY;
goto abort;
/* lost the race, try later */
err = -EBUSY;
*rdevp = rdev;
- }
+ } else if (p->replacement) {
+ /* We must have just cleared 'rdev' */
+ p->rdev = p->replacement;
+ clear_bit(Replacement, &p->replacement->flags);
+ smp_mb(); /* Make sure other CPUs may see both as identical
+ * but will never see neither - if they are careful
+ */
+ p->replacement = NULL;
+ clear_bit(WantReplacement, &rdev->flags);
+ } else
+ /* We might have just removed the Replacement as faulty-
+ * clear the bit just in case
+ */
+ clear_bit(WantReplacement, &rdev->flags);
abort:
print_raid5_conf(conf);
projects / deliverable / linux.git / blobdiff