list_add_tail(&sh->lru, &conf->inactive_list);
atomic_dec(&conf->active_stripes);
if (!conf->inactive_blocked ||
- atomic_read(&conf->active_stripes) < (NR_STRIPES*3/4))
+ atomic_read(&conf->active_stripes) < (conf->max_nr_stripes*3/4))
wake_up(&conf->wait_for_stripe);
}
}
conf->inactive_blocked = 1;
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list) &&
- (atomic_read(&conf->active_stripes) < (NR_STRIPES *3/4)
+ (atomic_read(&conf->active_stripes)
+ < (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
conf->device_lock,
unplug_slaves(conf->mddev);
return sh;
}
-static int grow_stripes(raid5_conf_t *conf, int num)
+static int grow_one_stripe(raid5_conf_t *conf)
{
struct stripe_head *sh;
+ sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
+ if (!sh)
+ return 0;
+ memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev));
+ sh->raid_conf = conf;
+ spin_lock_init(&sh->lock);
+
+ if (grow_buffers(sh, conf->raid_disks)) {
+ shrink_buffers(sh, conf->raid_disks);
+ kmem_cache_free(conf->slab_cache, sh);
+ return 0;
+ }
+ /* we just created an active stripe so... */
+ atomic_set(&sh->count, 1);
+ atomic_inc(&conf->active_stripes);
+ INIT_LIST_HEAD(&sh->lru);
+ release_stripe(sh);
+ return 1;
+}
+
+static int grow_stripes(raid5_conf_t *conf, int num)
+{
kmem_cache_t *sc;
int devs = conf->raid_disks;
return 1;
conf->slab_cache = sc;
while (num--) {
- sh = kmem_cache_alloc(sc, GFP_KERNEL);
- if (!sh)
- return 1;
- memset(sh, 0, sizeof(*sh) + (devs-1)*sizeof(struct r5dev));
- sh->raid_conf = conf;
- spin_lock_init(&sh->lock);
-
- if (grow_buffers(sh, conf->raid_disks)) {
- shrink_buffers(sh, conf->raid_disks);
- kmem_cache_free(sc, sh);
+ if (!grow_one_stripe(conf))
return 1;
- }
- /* we just created an active stripe so... */
- atomic_set(&sh->count, 1);
- atomic_inc(&conf->active_stripes);
- INIT_LIST_HEAD(&sh->lru);
- release_stripe(sh);
}
return 0;
}
-static void shrink_stripes(raid5_conf_t *conf)
+static int drop_one_stripe(raid5_conf_t *conf)
{
struct stripe_head *sh;
- while (1) {
- spin_lock_irq(&conf->device_lock);
- sh = get_free_stripe(conf);
- spin_unlock_irq(&conf->device_lock);
- if (!sh)
- break;
- if (atomic_read(&sh->count))
- BUG();
- shrink_buffers(sh, conf->raid_disks);
- kmem_cache_free(conf->slab_cache, sh);
- atomic_dec(&conf->active_stripes);
- }
+ spin_lock_irq(&conf->device_lock);
+ sh = get_free_stripe(conf);
+ spin_unlock_irq(&conf->device_lock);
+ if (!sh)
+ return 0;
+ if (atomic_read(&sh->count))
+ BUG();
+ shrink_buffers(sh, conf->raid_disks);
+ kmem_cache_free(conf->slab_cache, sh);
+ atomic_dec(&conf->active_stripes);
+ return 1;
+}
+
+static void shrink_stripes(raid5_conf_t *conf)
+{
+ while (drop_one_stripe(conf))
+ ;
+
kmem_cache_destroy(conf->slab_cache);
conf->slab_cache = NULL;
}
-static int raid5_end_read_request (struct bio * bi, unsigned int bytes_done,
+static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done,
int error)
{
struct stripe_head *sh = bi->bi_private;
}
#else
set_bit(R5_UPTODATE, &sh->dev[i].flags);
-#endif
+#endif
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ printk(KERN_INFO "raid5: read error corrected!!\n");
+ clear_bit(R5_ReadError, &sh->dev[i].flags);
+ clear_bit(R5_ReWrite, &sh->dev[i].flags);
+ }
+ if (atomic_read(&conf->disks[i].rdev->read_errors))
+ atomic_set(&conf->disks[i].rdev->read_errors, 0);
} else {
- md_error(conf->mddev, conf->disks[i].rdev);
+ int retry = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
+ atomic_inc(&conf->disks[i].rdev->read_errors);
+ if (conf->mddev->degraded)
+ printk(KERN_WARNING "raid5: read error not correctable.\n");
+ else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
+ /* Oh, no!!! */
+ printk(KERN_WARNING "raid5: read error NOT corrected!!\n");
+ else if (atomic_read(&conf->disks[i].rdev->read_errors)
+ > conf->max_nr_stripes)
+ printk(KERN_WARNING
+ "raid5: Too many read errors, failing device.\n");
+ else
+ retry = 1;
+ if (retry)
+ set_bit(R5_ReadError, &sh->dev[i].flags);
+ else {
+ clear_bit(R5_ReadError, &sh->dev[i].flags);
+ clear_bit(R5_ReWrite, &sh->dev[i].flags);
+ md_error(conf->mddev, conf->disks[i].rdev);
+ }
}
rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
#if 0
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
PRINTK("raid5: error called\n");
- if (!rdev->faulty) {
+ if (!test_bit(Faulty, &rdev->flags)) {
mddev->sb_dirty = 1;
- if (rdev->in_sync) {
+ if (test_bit(In_sync, &rdev->flags)) {
conf->working_disks--;
mddev->degraded++;
conf->failed_disks++;
- rdev->in_sync = 0;
+ clear_bit(In_sync, &rdev->flags);
/*
* if recovery was running, make sure it aborts.
*/
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
}
- rdev->faulty = 1;
+ set_bit(Faulty, &rdev->flags);
printk (KERN_ALERT
"raid5: Disk failure on %s, disabling device."
" Operation continuing on %d devices\n",
*dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
break;
default:
- printk("raid5: unsupported algorithm %d\n",
+ printk(KERN_ERR "raid5: unsupported algorithm %d\n",
conf->algorithm);
}
i -= (sh->pd_idx + 1);
break;
default:
- printk("raid5: unsupported algorithm %d\n",
+ printk(KERN_ERR "raid5: unsupported algorithm %d\n",
conf->algorithm);
}
check = raid5_compute_sector (r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf);
if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) {
- printk("compute_blocknr: map not correct\n");
+ printk(KERN_ERR "compute_blocknr: map not correct\n");
return 0;
}
return r_sector;
if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
ptr[count++] = p;
else
- printk("compute_block() %d, stripe %llu, %d"
+ printk(KERN_ERR "compute_block() %d, stripe %llu, %d"
" not present\n", dd_idx,
(unsigned long long)sh->sector, i);
}
if (dev->written) written++;
rdev = conf->disks[i].rdev; /* FIXME, should I be looking rdev */
- if (!rdev || !rdev->in_sync) {
+ if (!rdev || !test_bit(In_sync, &rdev->flags)) {
+ /* The ReadError flag will just be confusing now */
+ clear_bit(R5_ReadError, &dev->flags);
+ clear_bit(R5_ReWrite, &dev->flags);
+ }
+ if (!rdev || !test_bit(In_sync, &rdev->flags)
+ || test_bit(R5_ReadError, &dev->flags)) {
failed++;
failed_num = i;
} else
if (failed > 1 && to_read+to_write+written) {
for (i=disks; i--; ) {
int bitmap_end = 0;
+
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ mdk_rdev_t *rdev = conf->disks[i].rdev;
+ if (rdev && test_bit(In_sync, &rdev->flags))
+ /* multiple read failures in one stripe */
+ md_error(conf->mddev, rdev);
+ }
+
spin_lock_irq(&conf->device_lock);
/* fail all writes first */
bi = sh->dev[i].towrite;
}
/* fail any reads if this device is non-operational */
- if (!test_bit(R5_Insync, &sh->dev[i].flags)) {
+ if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
+ test_bit(R5_ReadError, &sh->dev[i].flags)) {
bi = sh->dev[i].toread;
sh->dev[i].toread = NULL;
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
* is available
*/
if (syncing && locked == 0 &&
- !test_bit(STRIPE_INSYNC, &sh->state) && failed <= 1) {
+ !test_bit(STRIPE_INSYNC, &sh->state)) {
set_bit(STRIPE_HANDLE, &sh->state);
if (failed == 0) {
char *pagea;
!memcmp(pagea, pagea+4, STRIPE_SIZE-4)) {
/* parity is correct (on disc, not in buffer any more) */
set_bit(STRIPE_INSYNC, &sh->state);
+ } else {
+ conf->mddev->resync_mismatches += STRIPE_SECTORS;
+ if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+ /* don't try to repair!! */
+ set_bit(STRIPE_INSYNC, &sh->state);
+ else {
+ compute_block(sh, sh->pd_idx);
+ uptodate++;
+ }
}
}
if (!test_bit(STRIPE_INSYNC, &sh->state)) {
+ /* either failed parity check, or recovery is happening */
if (failed==0)
failed_num = sh->pd_idx;
- /* should be able to compute the missing block and write it to spare */
- if (!test_bit(R5_UPTODATE, &sh->dev[failed_num].flags)) {
- if (uptodate+1 != disks)
- BUG();
- compute_block(sh, failed_num);
- uptodate++;
- }
- if (uptodate != disks)
- BUG();
dev = &sh->dev[failed_num];
+ BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
+ BUG_ON(uptodate != disks);
+
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
clear_bit(STRIPE_DEGRADED, &sh->state);
md_done_sync(conf->mddev, STRIPE_SECTORS,1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
-
+
+ /* If the failed drive is just a ReadError, then we might need to progress
+ * the repair/check process
+ */
+ if (failed == 1 && ! conf->mddev->ro &&
+ test_bit(R5_ReadError, &sh->dev[failed_num].flags)
+ && !test_bit(R5_LOCKED, &sh->dev[failed_num].flags)
+ && test_bit(R5_UPTODATE, &sh->dev[failed_num].flags)
+ ) {
+ dev = &sh->dev[failed_num];
+ if (!test_bit(R5_ReWrite, &dev->flags)) {
+ set_bit(R5_Wantwrite, &dev->flags);
+ set_bit(R5_ReWrite, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ } else {
+ /* let's read it back */
+ set_bit(R5_Wantread, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ }
+ }
+
spin_unlock(&sh->lock);
while ((bi=return_bi)) {
bi->bi_end_io = raid5_end_read_request;
rcu_read_lock();
- rdev = conf->disks[i].rdev;
- if (rdev && rdev->faulty)
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
rdev = NULL;
if (rdev)
atomic_inc(&rdev->nr_pending);
rcu_read_lock();
for (i=0; i<mddev->raid_disks; i++) {
- mdk_rdev_t *rdev = conf->disks[i].rdev;
- if (rdev && !rdev->faulty && atomic_read(&rdev->nr_pending)) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
rcu_read_lock();
for (i=0; i<mddev->raid_disks && ret == 0; i++) {
- mdk_rdev_t *rdev = conf->disks[i].rdev;
- if (rdev && !rdev->faulty) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct block_device *bdev = rdev->bdev;
request_queue_t *r_queue = bdev_get_queue(bdev);
return rv;
}
if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
!conf->fullsync && sync_blocks >= STRIPE_SECTORS) {
/* we can skip this block, and probably more */
sync_blocks /= STRIPE_SECTORS;
/* make sure we don't swamp the stripe cache if someone else
* is trying to get access
*/
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(1);
+ schedule_timeout_uninterruptible(1);
}
bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 0);
spin_lock(&sh->lock);
if (conf->seq_flush - conf->seq_write > 0) {
int seq = conf->seq_flush;
+ spin_unlock_irq(&conf->device_lock);
bitmap_unplug(mddev->bitmap);
+ spin_lock_irq(&conf->device_lock);
conf->seq_write = seq;
activate_bit_delay(conf);
}
PRINTK("--- raid5d inactive\n");
}
+static ssize_t
+raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ if (conf)
+ return sprintf(page, "%d\n", conf->max_nr_stripes);
+ else
+ return 0;
+}
+
+static ssize_t
+raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ char *end;
+ int new;
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (!conf)
+ return -ENODEV;
+
+ new = simple_strtoul(page, &end, 10);
+ if (!*page || (*end && *end != '\n') )
+ return -EINVAL;
+ if (new <= 16 || new > 32768)
+ return -EINVAL;
+ while (new < conf->max_nr_stripes) {
+ if (drop_one_stripe(conf))
+ conf->max_nr_stripes--;
+ else
+ break;
+ }
+ while (new > conf->max_nr_stripes) {
+ if (grow_one_stripe(conf))
+ conf->max_nr_stripes++;
+ else break;
+ }
+ return len;
+}
+
+static struct md_sysfs_entry
+raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR,
+ raid5_show_stripe_cache_size,
+ raid5_store_stripe_cache_size);
+
+static ssize_t
+stripe_cache_active_show(mddev_t *mddev, char *page)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ if (conf)
+ return sprintf(page, "%d\n", atomic_read(&conf->active_stripes));
+ else
+ return 0;
+}
+
+static struct md_sysfs_entry
+raid5_stripecache_active = __ATTR_RO(stripe_cache_active);
+
+static struct attribute *raid5_attrs[] = {
+ &raid5_stripecache_size.attr,
+ &raid5_stripecache_active.attr,
+ NULL,
+};
+static struct attribute_group raid5_attrs_group = {
+ .name = NULL,
+ .attrs = raid5_attrs,
+};
+
static int run(mddev_t *mddev)
{
raid5_conf_t *conf;
struct list_head *tmp;
if (mddev->level != 5 && mddev->level != 4) {
- printk("raid5: %s: raid level not set to 4/5 (%d)\n", mdname(mddev), mddev->level);
+ printk(KERN_ERR "raid5: %s: raid level not set to 4/5 (%d)\n",
+ mdname(mddev), mddev->level);
return -EIO;
}
disk->rdev = rdev;
- if (rdev->in_sync) {
+ if (test_bit(In_sync, &rdev->flags)) {
char b[BDEVNAME_SIZE];
printk(KERN_INFO "raid5: device %s operational as raid"
" disk %d\n", bdevname(rdev->bdev,b),
goto abort;
}
}
-memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
+ memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
conf->raid_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
if (grow_stripes(conf, conf->max_nr_stripes)) {
printk(KERN_ERR
}
/* Ok, everything is just fine now */
+ sysfs_create_group(&mddev->kobj, &raid5_attrs_group);
if (mddev->bitmap)
mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
-static int stop (mddev_t *mddev)
+static int stop(mddev_t *mddev)
{
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
shrink_stripes(conf);
free_pages((unsigned long) conf->stripe_hashtbl, HASH_PAGES_ORDER);
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+ sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
kfree(conf);
mddev->private = NULL;
return 0;
for (i = 0; i < conf->raid_disks; i++)
seq_printf (seq, "%s",
conf->disks[i].rdev &&
- conf->disks[i].rdev->in_sync ? "U" : "_");
+ test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
seq_printf (seq, "]");
#if RAID5_DEBUG
#define D(x) \
tmp = conf->disks + i;
if (tmp->rdev)
printk(" disk %d, o:%d, dev:%s\n",
- i, !tmp->rdev->faulty,
+ i, !test_bit(Faulty, &tmp->rdev->flags),
bdevname(tmp->rdev->bdev,b));
}
}
for (i = 0; i < conf->raid_disks; i++) {
tmp = conf->disks + i;
if (tmp->rdev
- && !tmp->rdev->faulty
- && !tmp->rdev->in_sync) {
+ && !test_bit(Faulty, &tmp->rdev->flags)
+ && !test_bit(In_sync, &tmp->rdev->flags)) {
mddev->degraded--;
conf->failed_disks--;
conf->working_disks++;
- tmp->rdev->in_sync = 1;
+ set_bit(In_sync, &tmp->rdev->flags);
}
}
print_raid5_conf(conf);
print_raid5_conf(conf);
rdev = p->rdev;
if (rdev) {
- if (rdev->in_sync ||
+ if (test_bit(In_sync, &rdev->flags) ||
atomic_read(&rdev->nr_pending)) {
err = -EBUSY;
goto abort;
*/
for (disk=0; disk < mddev->raid_disks; disk++)
if ((p=conf->disks + disk)->rdev == NULL) {
- rdev->in_sync = 0;
+ clear_bit(In_sync, &rdev->flags);
rdev->raid_disk = disk;
found = 1;
if (rdev->saved_raid_disk != disk)
conf->fullsync = 1;
- p->rdev = rdev;
+ rcu_assign_pointer(p->rdev, rdev);
break;
}
print_raid5_conf(conf);