#include "raid0.h"
#include "bitmap.h"
+#define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED)
+
#define cpu_to_group(cpu) cpu_to_node(cpu)
#define ANY_GROUP NUMA_NO_NODE
atomic_dec(&conf->r5c_cached_partial_stripes);
list_add_tail(&sh->lru, &conf->r5c_full_stripe_list);
r5c_check_cached_full_stripe(conf);
- } else {
- /* partial stripe */
- if (!test_and_set_bit(STRIPE_R5C_PARTIAL_STRIPE,
- &sh->state))
- atomic_inc(&conf->r5c_cached_partial_stripes);
+ } else
+ /*
+ * STRIPE_R5C_PARTIAL_STRIPE is set in
+ * r5c_try_caching_write(). No need to
+ * set it again.
+ */
list_add_tail(&sh->lru, &conf->r5c_partial_stripe_list);
- }
}
}
}
static int release_stripe_list(struct r5conf *conf,
struct list_head *temp_inactive_list)
{
- struct stripe_head *sh;
+ struct stripe_head *sh, *t;
int count = 0;
struct llist_node *head;
head = llist_del_all(&conf->released_stripes);
head = llist_reverse_order(head);
- while (head) {
+ llist_for_each_entry_safe(sh, t, head, release_list) {
int hash;
- sh = llist_entry(head, struct stripe_head, release_list);
- head = llist_next(head);
/* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */
smp_mb();
clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state);
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
*/
-static int calc_degraded(struct r5conf *conf)
+int raid5_calc_degraded(struct r5conf *conf)
{
int degraded, degraded2;
int i;
if (conf->mddev->reshape_position == MaxSector)
return conf->mddev->degraded > conf->max_degraded;
- degraded = calc_degraded(conf);
+ degraded = raid5_calc_degraded(conf);
if (degraded > conf->max_degraded)
return 1;
return 0;
return 1;
}
+static void flush_deferred_bios(struct r5conf *conf)
+{
+ struct bio_list tmp;
+ struct bio *bio;
+
+ if (!conf->batch_bio_dispatch || !conf->group_cnt)
+ return;
+
+ bio_list_init(&tmp);
+ spin_lock(&conf->pending_bios_lock);
+ bio_list_merge(&tmp, &conf->pending_bios);
+ bio_list_init(&conf->pending_bios);
+ spin_unlock(&conf->pending_bios_lock);
+
+ while ((bio = bio_list_pop(&tmp)))
+ generic_make_request(bio);
+}
+
+static void defer_bio_issue(struct r5conf *conf, struct bio *bio)
+{
+ /*
+ * change group_cnt will drain all bios, so this is safe
+ *
+ * A read generally means a read-modify-write, which usually means a
+ * randwrite, so we don't delay it
+ */
+ if (!conf->batch_bio_dispatch || !conf->group_cnt ||
+ bio_op(bio) == REQ_OP_READ) {
+ generic_make_request(bio);
+ return;
+ }
+ spin_lock(&conf->pending_bios_lock);
+ bio_list_add(&conf->pending_bios, bio);
+ spin_unlock(&conf->pending_bios_lock);
+ md_wakeup_thread(conf->mddev->thread);
+}
+
static void
raid5_end_read_request(struct bio *bi);
static void
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
- sh->dev[i].vec.bv_page = sh->dev[i].page;
+
+ if (!op_is_write(op) &&
+ test_bit(R5_InJournal, &sh->dev[i].flags))
+ /*
+ * issuing read for a page in journal, this
+ * must be preparing for prexor in rmw; read
+ * the data into orig_page
+ */
+ sh->dev[i].vec.bv_page = sh->dev[i].orig_page;
+ else
+ sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
bi, disk_devt(conf->mddev->gendisk),
sh->dev[i].sector);
- generic_make_request(bi);
+ defer_bio_issue(conf, bi);
}
if (rrdev) {
if (s->syncing || s->expanding || s->expanded
trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
rbi, disk_devt(conf->mddev->gendisk),
sh->dev[i].sector);
- generic_make_request(rbi);
+ defer_bio_issue(conf, rbi);
}
if (!rdev && !rrdev) {
if (op_is_write(op))
} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
+ if (test_bit(R5_InJournal, &sh->dev[i].flags))
+ /*
+ * end read for a page in journal, this
+ * must be preparing for prexor in rmw
+ */
+ set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
if (atomic_read(&rdev->read_errors))
atomic_set(&rdev->read_errors, 0);
} else {
spin_lock_irqsave(&conf->device_lock, flags);
clear_bit(In_sync, &rdev->flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
bdevname(rdev->bdev, b),
mdname(mddev),
conf->raid_disks - mddev->degraded);
+ r5c_update_on_rdev_error(mddev);
}
/*
return r_sector;
}
+/*
+ * There are cases where we want handle_stripe_dirtying() and
+ * schedule_reconstruction() to delay towrite to some dev of a stripe.
+ *
+ * This function checks whether we want to delay the towrite. Specifically,
+ * we delay the towrite when:
+ *
+ * 1. degraded stripe has a non-overwrite to the missing dev, AND this
+ * stripe has data in journal (for other devices).
+ *
+ * In this case, when reading data for the non-overwrite dev, it is
+ * necessary to handle complex rmw of write back cache (prexor with
+ * orig_page, and xor with page). To keep read path simple, we would
+ * like to flush data in journal to RAID disks first, so complex rmw
+ * is handled in the write patch (handle_stripe_dirtying).
+ *
+ * 2. when journal space is critical (R5C_LOG_CRITICAL=1)
+ *
+ * It is important to be able to flush all stripes in raid5-cache.
+ * Therefore, we need reserve some space on the journal device for
+ * these flushes. If flush operation includes pending writes to the
+ * stripe, we need to reserve (conf->raid_disk + 1) pages per stripe
+ * for the flush out. If we exclude these pending writes from flush
+ * operation, we only need (conf->max_degraded + 1) pages per stripe.
+ * Therefore, excluding pending writes in these cases enables more
+ * efficient use of the journal device.
+ *
+ * Note: To make sure the stripe makes progress, we only delay
+ * towrite for stripes with data already in journal (injournal > 0).
+ * When LOG_CRITICAL, stripes with injournal == 0 will be sent to
+ * no_space_stripes list.
+ *
+ */
+static inline bool delay_towrite(struct r5conf *conf,
+ struct r5dev *dev,
+ struct stripe_head_state *s)
+{
+ /* case 1 above */
+ if (!test_bit(R5_OVERWRITE, &dev->flags) &&
+ !test_bit(R5_Insync, &dev->flags) && s->injournal)
+ return true;
+ /* case 2 above */
+ if (test_bit(R5C_LOG_CRITICAL, &conf->cache_state) &&
+ s->injournal > 0)
+ return true;
+ return false;
+}
+
static void
schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
int rcw, int expand)
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (dev->towrite) {
+ if (dev->towrite && !delay_towrite(conf, dev, s)) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantdrain, &dev->flags);
if (!expand)
return rv;
}
-/* fetch_block - checks the given member device to see if its data needs
- * to be read or computed to satisfy a request.
- *
- * Returns 1 when no more member devices need to be checked, otherwise returns
- * 0 to tell the loop in handle_stripe_fill to continue
- */
-
static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
int disk_idx, int disks)
{
return 0;
}
+/* fetch_block - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill to continue
+ */
static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
int disk_idx, int disks)
{
* midst of changing due to a write
*/
if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
- !sh->reconstruct_state)
+ !sh->reconstruct_state) {
+
+ /*
+ * For degraded stripe with data in journal, do not handle
+ * read requests yet, instead, flush the stripe to raid
+ * disks first, this avoids handling complex rmw of write
+ * back cache (prexor with orig_page, and then xor with
+ * page) in the read path
+ */
+ if (s->injournal && s->failed) {
+ if (test_bit(STRIPE_R5C_CACHING, &sh->state))
+ r5c_make_stripe_write_out(sh);
+ goto out;
+ }
+
for (i = disks; i--; )
if (fetch_block(sh, s, i, disks))
break;
+ }
+out:
set_bit(STRIPE_HANDLE, &sh->state);
}
break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
}
+/*
+ * For RMW in write back cache, we need extra page in prexor to store the
+ * old data. This page is stored in dev->orig_page.
+ *
+ * This function checks whether we have data for prexor. The exact logic
+ * is:
+ * R5_UPTODATE && (!R5_InJournal || R5_OrigPageUPTDODATE)
+ */
+static inline bool uptodate_for_rmw(struct r5dev *dev)
+{
+ return (test_bit(R5_UPTODATE, &dev->flags)) &&
+ (!test_bit(R5_InJournal, &dev->flags) ||
+ test_bit(R5_OrigPageUPTDODATE, &dev->flags));
+}
+
static int handle_stripe_dirtying(struct r5conf *conf,
struct stripe_head *sh,
struct stripe_head_state *s,
} else for (i = disks; i--; ) {
/* would I have to read this buffer for read_modify_write */
struct r5dev *dev = &sh->dev[i];
- if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx ||
+ if (((dev->towrite && !delay_towrite(conf, dev, s)) ||
+ i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rmw++;
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rcw++;
}
}
- pr_debug("for sector %llu, rmw=%d rcw=%d\n",
- (unsigned long long)sh->sector, rmw, rcw);
+ pr_debug("for sector %llu state 0x%lx, rmw=%d rcw=%d\n",
+ (unsigned long long)sh->sector, sh->state, rmw, rcw);
set_bit(STRIPE_HANDLE, &sh->state);
if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) {
/* prefer read-modify-write, but need to get some data */
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if ((dev->towrite ||
+ if (((dev->towrite && !delay_towrite(conf, dev, s)) ||
i == sh->pd_idx || i == sh->qd_idx ||
test_bit(R5_InJournal, &dev->flags)) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !((test_bit(R5_UPTODATE, &dev->flags) &&
- (!test_bit(R5_InJournal, &dev->flags) ||
- dev->page != dev->orig_page)) ||
+ !(uptodate_for_rmw(dev) ||
test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
if (test_bit(STRIPE_PREREAD_ACTIVE,
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_InJournal, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
rcw++;
if (test_bit(R5_Insync, &dev->flags) &&
return 0;
}
/*
- * use bio_clone_mddev to make a copy of the bio
+ * use bio_clone_fast to make a copy of the bio
*/
- align_bi = bio_clone_mddev(raid_bio, GFP_NOIO, mddev);
+ align_bi = bio_clone_fast(raid_bio, GFP_NOIO, mddev->bio_set);
if (!align_bi)
return 0;
/*
rdev->recovery_offset >= end_sector)))
rdev = NULL;
}
+
+ if (r5c_big_stripe_cached(conf, align_bi->bi_iter.bi_sector)) {
+ rcu_read_unlock();
+ bio_put(align_bi);
+ return 0;
+ }
+
if (rdev) {
sector_t first_bad;
int bad_sectors;
* data on failed drives.
*/
if (rw == READ && mddev->degraded == 0 &&
- !r5c_is_writeback(conf->log) &&
mddev->reshape_position == MaxSector) {
bi = chunk_aligned_read(mddev, bi);
if (!bi)
mutex_unlock(&conf->cache_size_mutex);
}
+ flush_deferred_bios(conf);
+
r5l_flush_stripe_to_raid(conf->log);
async_tx_issue_pending_all();
mddev_suspend(mddev);
conf->skip_copy = new;
if (new)
- mddev->queue->backing_dev_info.capabilities |=
+ mddev->queue->backing_dev_info->capabilities |=
BDI_CAP_STABLE_WRITES;
else
- mddev->queue->backing_dev_info.capabilities &=
+ mddev->queue->backing_dev_info->capabilities &=
~BDI_CAP_STABLE_WRITES;
mddev_resume(mddev);
}
atomic_set(&conf->active_stripes, 0);
atomic_set(&conf->preread_active_stripes, 0);
atomic_set(&conf->active_aligned_reads, 0);
+ bio_list_init(&conf->pending_bios);
+ spin_lock_init(&conf->pending_bios_lock);
+ conf->batch_bio_dispatch = true;
+ rdev_for_each(rdev, mddev) {
+ if (test_bit(Journal, &rdev->flags))
+ continue;
+ if (blk_queue_nonrot(bdev_get_queue(rdev->bdev))) {
+ conf->batch_bio_dispatch = false;
+ break;
+ }
+ }
+
conf->bypass_threshold = BYPASS_THRESHOLD;
conf->recovery_disabled = mddev->recovery_disabled - 1;
INIT_LIST_HEAD(&conf->r5c_full_stripe_list);
atomic_set(&conf->r5c_cached_partial_stripes, 0);
INIT_LIST_HEAD(&conf->r5c_partial_stripe_list);
+ atomic_set(&conf->r5c_flushing_full_stripes, 0);
+ atomic_set(&conf->r5c_flushing_partial_stripes, 0);
conf->level = mddev->new_level;
conf->chunk_sectors = mddev->new_chunk_sectors;
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
if (has_failed(conf)) {
pr_crit("md/raid:%s: not enough operational devices (%d/%d failed)\n",
int data_disks = conf->previous_raid_disks - conf->max_degraded;
int stripe = data_disks *
((mddev->chunk_sectors << 9) / PAGE_SIZE);
- if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
- mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+ if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
+ mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
chunk_size = mddev->chunk_sectors << 9;
blk_queue_io_min(mddev->queue, chunk_size);
}
}
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
print_raid5_conf(conf);
return count;
* pre and post number of devices.
*/
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
mddev->raid_disks = conf->raid_disks;
int data_disks = conf->raid_disks - conf->max_degraded;
int stripe = data_disks * ((conf->chunk_sectors << 9)
/ PAGE_SIZE);
- if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
- conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+ if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
+ conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
}
}
}
} else {
int d;
spin_lock_irq(&conf->device_lock);
- mddev->degraded = calc_degraded(conf);
+ mddev->degraded = raid5_calc_degraded(conf);
spin_unlock_irq(&conf->device_lock);
for (d = conf->raid_disks ;
d < conf->raid_disks - mddev->delta_disks;
mddev->new_chunk_sectors = chunksect;
ret = setup_conf(mddev);
- if (!IS_ERR_VALUE(ret))
- clear_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
+ if (!IS_ERR(ret))
+ mddev_clear_unsupported_flags(mddev,
+ UNSUPPORTED_MDDEV_FLAGS);
return ret;
}
projects / linux.git / blobdiff