#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
+#define BYPASS_THRESHOLD 1
#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
might_sleep();
+ set_bit(STRIPE_IO_STARTED, &sh->state);
for (i = disks; i--; ) {
int rw;
struct bio *bi;
bi->bi_bdev = rdev->bdev;
pr_debug("%s: for %llu schedule op %ld on disc %d\n",
- __FUNCTION__, (unsigned long long)sh->sector,
+ __func__, (unsigned long long)sh->sector,
bi->bi_rw, i);
atomic_inc(&sh->count);
bi->bi_sector = sh->sector + rdev->data_offset;
raid5_conf_t *conf = sh->raid_conf;
int i;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* clear completed biofills */
raid5_conf_t *conf = sh->raid_conf;
int i;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = sh->disks; i--; ) {
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
set_bit(R5_UPTODATE, &tgt->flags);
int i;
pr_debug("%s: stripe %llu block: %d\n",
- __FUNCTION__, (unsigned long long)sh->sector, target);
+ __func__, (unsigned long long)sh->sector, target);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
for (i = disks; i--; )
{
struct stripe_head *sh = stripe_head_ref;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
set_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
/* existing parity data subtracted */
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
*/
int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
{
struct stripe_head *sh = stripe_head_ref;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
struct stripe_head *sh = stripe_head_ref;
int disks = sh->disks, i, pd_idx = sh->pd_idx;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
unsigned long flags;
dma_async_tx_callback callback;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* check if prexor is active which means only process blocks
struct stripe_head *sh = stripe_head_ref;
int pd_idx = sh->pd_idx;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) &&
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
rdev = conf->disks[i].rdev;
printk(KERN_INFO "raid5:%s: read error corrected (%lu sectors at %llu on %s)\n",
mdname(conf->mddev), STRIPE_SECTORS,
- (unsigned long long)sh->sector + rdev->data_offset,
+ (unsigned long long)(sh->sector + rdev->data_offset),
bdevname(rdev->bdev, b));
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
if (conf->mddev->degraded)
printk(KERN_WARNING "raid5:%s: read error not correctable (sector %llu on %s).\n",
mdname(conf->mddev),
- (unsigned long long)sh->sector + rdev->data_offset,
+ (unsigned long long)(sh->sector + rdev->data_offset),
bdn);
else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
/* Oh, no!!! */
printk(KERN_WARNING "raid5:%s: read error NOT corrected!! (sector %llu on %s).\n",
mdname(conf->mddev),
- (unsigned long long)sh->sector + rdev->data_offset,
+ (unsigned long long)(sh->sector + rdev->data_offset),
bdn);
else if (atomic_read(&rdev->read_errors)
> conf->max_nr_stripes)
}
set_bit(Faulty, &rdev->flags);
printk (KERN_ALERT
- "raid5: Disk failure on %s, disabling device."
- " Operation continuing on %d devices\n",
+ "raid5: Disk failure on %s, disabling device.\n"
+ "raid5: Operation continuing on %d devices.\n",
bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
}
}
locked++;
}
}
+ if (locked + 1 == disks)
+ if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+ atomic_inc(&sh->raid_conf->pending_full_writes);
} else {
BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
locked++;
pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
- __FUNCTION__, (unsigned long long)sh->sector,
+ __func__, (unsigned long long)sh->sector,
locked, sh->ops.pending);
return locked;
STRIPE_SECTORS, 0, 0);
}
+ if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
+ if (atomic_dec_and_test(&conf->pending_full_writes))
+ md_wakeup_thread(conf->mddev->thread);
}
/* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks
0);
}
}
+
+ if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
+ if (atomic_dec_and_test(&conf->pending_full_writes))
+ md_wakeup_thread(conf->mddev->thread);
}
static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
s->locked++;
set_bit(R5_Wantwrite, &sh->dev[i].flags);
}
+ if (s->locked == disks)
+ if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+ atomic_inc(&conf->pending_full_writes);
/* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
set_bit(STRIPE_INSYNC, &sh->state);
static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
struct stripe_head_state *s, int disks)
{
+ int canceled_check = 0;
+
set_bit(STRIPE_HANDLE, &sh->state);
- /* Take one of the following actions:
- * 1/ start a check parity operation if (uptodate == disks)
- * 2/ finish a check parity operation and act on the result
- * 3/ skip to the writeback section if we previously
- * initiated a recovery operation
- */
- if (s->failed == 0 &&
- !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
- if (!test_and_set_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
- BUG_ON(s->uptodate != disks);
- clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
- sh->ops.count++;
- s->uptodate--;
- } else if (
- test_and_clear_bit(STRIPE_OP_CHECK, &sh->ops.complete)) {
- clear_bit(STRIPE_OP_CHECK, &sh->ops.ack);
- clear_bit(STRIPE_OP_CHECK, &sh->ops.pending);
+ /* complete a check operation */
+ if (test_and_clear_bit(STRIPE_OP_CHECK, &sh->ops.complete)) {
+ clear_bit(STRIPE_OP_CHECK, &sh->ops.ack);
+ clear_bit(STRIPE_OP_CHECK, &sh->ops.pending);
+ if (s->failed == 0) {
if (sh->ops.zero_sum_result == 0)
/* parity is correct (on disc,
* not in buffer any more)
s->uptodate++;
}
}
- }
+ } else
+ canceled_check = 1; /* STRIPE_INSYNC is not set */
}
/* check if we can clear a parity disk reconstruct */
clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
}
+ /* start a new check operation if there are no failures, the stripe is
+ * not insync, and a repair is not in flight
+ */
+ if (s->failed == 0 &&
+ !test_bit(STRIPE_INSYNC, &sh->state) &&
+ !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
+ if (!test_and_set_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
+ BUG_ON(s->uptodate != disks);
+ clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
+ sh->ops.count++;
+ s->uptodate--;
+ }
+ }
+
/* Wait for check parity and compute block operations to complete
- * before write-back
+ * before write-back. If a failure occurred while the check operation
+ * was in flight we need to cycle this stripe through handle_stripe
+ * since the parity block may not be uptodate
*/
- if (!test_bit(STRIPE_INSYNC, &sh->state) &&
- !test_bit(STRIPE_OP_CHECK, &sh->ops.pending) &&
- !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) {
+ if (!canceled_check && !test_bit(STRIPE_INSYNC, &sh->state) &&
+ !test_bit(STRIPE_OP_CHECK, &sh->ops.pending) &&
+ !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) {
struct r5dev *dev;
/* either failed parity check, or recovery is happening */
if (s->failed == 0)
else
continue;
+ set_bit(STRIPE_IO_STARTED, &sh->state);
+
bi = &sh->dev[i].req;
bi->bi_rw = rw;
clear_bit(STRIPE_DELAYED, &sh->state);
if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
- list_add_tail(&sh->lru, &conf->handle_list);
+ list_add_tail(&sh->lru, &conf->hold_list);
}
- }
+ } else
+ blk_plug_device(conf->mddev->queue);
}
static void activate_bit_delay(raid5_conf_t *conf)
}
}
+/* __get_priority_stripe - get the next stripe to process
+ *
+ * Full stripe writes are allowed to pass preread active stripes up until
+ * the bypass_threshold is exceeded. In general the bypass_count
+ * increments when the handle_list is handled before the hold_list; however, it
+ * will not be incremented when STRIPE_IO_STARTED is sampled set signifying a
+ * stripe with in flight i/o. The bypass_count will be reset when the
+ * head of the hold_list has changed, i.e. the head was promoted to the
+ * handle_list.
+ */
+static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf)
+{
+ struct stripe_head *sh;
+
+ pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n",
+ __func__,
+ list_empty(&conf->handle_list) ? "empty" : "busy",
+ list_empty(&conf->hold_list) ? "empty" : "busy",
+ atomic_read(&conf->pending_full_writes), conf->bypass_count);
+
+ if (!list_empty(&conf->handle_list)) {
+ sh = list_entry(conf->handle_list.next, typeof(*sh), lru);
+
+ if (list_empty(&conf->hold_list))
+ conf->bypass_count = 0;
+ else if (!test_bit(STRIPE_IO_STARTED, &sh->state)) {
+ if (conf->hold_list.next == conf->last_hold)
+ conf->bypass_count++;
+ else {
+ conf->last_hold = conf->hold_list.next;
+ conf->bypass_count -= conf->bypass_threshold;
+ if (conf->bypass_count < 0)
+ conf->bypass_count = 0;
+ }
+ }
+ } else if (!list_empty(&conf->hold_list) &&
+ ((conf->bypass_threshold &&
+ conf->bypass_count > conf->bypass_threshold) ||
+ atomic_read(&conf->pending_full_writes) == 0)) {
+ sh = list_entry(conf->hold_list.next,
+ typeof(*sh), lru);
+ conf->bypass_count -= conf->bypass_threshold;
+ if (conf->bypass_count < 0)
+ conf->bypass_count = 0;
+ } else
+ return NULL;
+
+ list_del_init(&sh->lru);
+ atomic_inc(&sh->count);
+ BUG_ON(atomic_read(&sh->count) != 1);
+ return sh;
+}
static int make_request(struct request_queue *q, struct bio * bi)
{
goto retry;
}
finish_wait(&conf->wait_for_overlap, &w);
- handle_stripe(sh, NULL);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ clear_bit(STRIPE_DELAYED, &sh->state);
release_stripe(sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
release_stripe(sh);
first_sector += STRIPE_SECTORS;
}
+ /* If this takes us to the resync_max point where we have to pause,
+ * then we need to write out the superblock.
+ */
+ sector_nr += conf->chunk_size>>9;
+ if (sector_nr >= mddev->resync_max) {
+ /* Cannot proceed until we've updated the superblock... */
+ wait_event(conf->wait_for_overlap,
+ atomic_read(&conf->reshape_stripes) == 0);
+ mddev->reshape_position = conf->expand_progress;
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ md_wakeup_thread(mddev->thread);
+ wait_event(mddev->sb_wait,
+ !test_bit(MD_CHANGE_DEVS, &mddev->flags)
+ || kthread_should_stop());
+ spin_lock_irq(&conf->device_lock);
+ conf->expand_lo = mddev->reshape_position;
+ spin_unlock_irq(&conf->device_lock);
+ wake_up(&conf->wait_for_overlap);
+ }
return conf->chunk_size>>9;
}
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
return reshape_request(mddev, sector_nr, skipped);
+ /* No need to check resync_max as we never do more than one
+ * stripe, and as resync_max will always be on a chunk boundary,
+ * if the check in md_do_sync didn't fire, there is no chance
+ * of overstepping resync_max here
+ */
+
/* if there is too many failed drives and we are trying
* to resync, then assert that we are finished, because there is
* nothing we can do.
* During the scan, completed stripes are saved for us by the interrupt
* handler, so that they will not have to wait for our next wakeup.
*/
-static void raid5d (mddev_t *mddev)
+static void raid5d(mddev_t *mddev)
{
struct stripe_head *sh;
raid5_conf_t *conf = mddev_to_conf(mddev);
handled = 0;
spin_lock_irq(&conf->device_lock);
while (1) {
- struct list_head *first;
struct bio *bio;
if (conf->seq_flush != conf->seq_write) {
activate_bit_delay(conf);
}
- if (list_empty(&conf->handle_list) &&
- atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
- !blk_queue_plugged(mddev->queue) &&
- !list_empty(&conf->delayed_list))
- raid5_activate_delayed(conf);
-
while ((bio = remove_bio_from_retry(conf))) {
int ok;
spin_unlock_irq(&conf->device_lock);
handled++;
}
- if (list_empty(&conf->handle_list)) {
+ sh = __get_priority_stripe(conf);
+
+ if (!sh) {
async_tx_issue_pending_all();
break;
}
-
- first = conf->handle_list.next;
- sh = list_entry(first, struct stripe_head, lru);
-
- list_del_init(first);
- atomic_inc(&sh->count);
- BUG_ON(atomic_read(&sh->count)!= 1);
spin_unlock_irq(&conf->device_lock);
handled++;
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;
+ unsigned long new;
if (len >= PAGE_SIZE)
return -EINVAL;
if (!conf)
return -ENODEV;
- new = simple_strtoul(page, &end, 10);
- if (!*page || (*end && *end != '\n') )
+ if (strict_strtoul(page, 10, &new))
return -EINVAL;
if (new <= 16 || new > 32768)
return -EINVAL;
raid5_show_stripe_cache_size,
raid5_store_stripe_cache_size);
+static ssize_t
+raid5_show_preread_threshold(mddev_t *mddev, char *page)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ if (conf)
+ return sprintf(page, "%d\n", conf->bypass_threshold);
+ else
+ return 0;
+}
+
+static ssize_t
+raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ unsigned long new;
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (!conf)
+ return -ENODEV;
+
+ if (strict_strtoul(page, 10, &new))
+ return -EINVAL;
+ if (new > conf->max_nr_stripes)
+ return -EINVAL;
+ conf->bypass_threshold = new;
+ return len;
+}
+
+static struct md_sysfs_entry
+raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
+ S_IRUGO | S_IWUSR,
+ raid5_show_preread_threshold,
+ raid5_store_preread_threshold);
+
static ssize_t
stripe_cache_active_show(mddev_t *mddev, char *page)
{
static struct attribute *raid5_attrs[] = {
&raid5_stripecache_size.attr,
&raid5_stripecache_active.attr,
+ &raid5_preread_bypass_threshold.attr,
NULL,
};
static struct attribute_group raid5_attrs_group = {
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
INIT_LIST_HEAD(&conf->handle_list);
+ INIT_LIST_HEAD(&conf->hold_list);
INIT_LIST_HEAD(&conf->delayed_list);
INIT_LIST_HEAD(&conf->bitmap_list);
INIT_LIST_HEAD(&conf->inactive_list);
atomic_set(&conf->active_stripes, 0);
atomic_set(&conf->preread_active_stripes, 0);
atomic_set(&conf->active_aligned_reads, 0);
+ conf->bypass_threshold = BYPASS_THRESHOLD;
pr_debug("raid5: run(%s) called.\n", mdname(mddev));
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
raid_disk = rdev->raid_disk;
if (raid_disk >= conf->raid_disks
|| raid_disk < 0)
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
- ITERATE_RDEV(mddev, rdev, rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags))
spares++;
/* Add some new drives, as many as will fit.
* We know there are enough to make the newly sized array work.
*/
- ITERATE_RDEV(mddev, rdev, rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags)) {
if (raid5_add_disk(mddev, rdev)) {