*(conf->hash_locks + hash));
sh = __find_stripe(conf, sector, conf->generation - previous);
if (!sh) {
- if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state))
+ if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) {
sh = get_free_stripe(conf, hash);
+ if (!sh && llist_empty(&conf->released_stripes) &&
+ !test_bit(R5_DID_ALLOC, &conf->cache_state))
+ set_bit(R5_ALLOC_MORE,
+ &conf->cache_state);
+ }
if (noblock && sh == NULL)
break;
if (!sh) {
static bool stripe_can_batch(struct stripe_head *sh)
{
return test_bit(STRIPE_BATCH_READY, &sh->state) &&
+ !test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
is_full_stripe_write(sh);
}
< IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
+ if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
+ int seq = sh->bm_seq;
+ if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
+ sh->batch_head->bm_seq > seq)
+ seq = sh->batch_head->bm_seq;
+ set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
+ sh->batch_head->bm_seq = seq;
+ }
+
atomic_inc(&sh->count);
unlock_out:
unlock_two_stripes(head, sh);
pr_debug("skip op %ld on disc %d for sector %llu\n",
bi->bi_rw, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
- if (sh->batch_head)
- set_bit(STRIPE_BATCH_ERR,
- &sh->batch_head->state);
set_bit(STRIPE_HANDLE, &sh->state);
}
} else
init_async_submit(&submit, 0, tx, NULL, NULL,
to_addr_conv(sh, percpu, j));
- async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
+ tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
put_cpu();
}
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+{
+ struct stripe_head *sh;
+
+ sh = kmem_cache_zalloc(sc, gfp);
+ if (sh) {
+ spin_lock_init(&sh->stripe_lock);
+ spin_lock_init(&sh->batch_lock);
+ INIT_LIST_HEAD(&sh->batch_list);
+ INIT_LIST_HEAD(&sh->lru);
+ atomic_set(&sh->count, 1);
+ }
+ return sh;
+}
static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
{
struct stripe_head *sh;
- sh = kmem_cache_zalloc(conf->slab_cache, gfp);
+
+ sh = alloc_stripe(conf->slab_cache, gfp);
if (!sh)
return 0;
sh->raid_conf = conf;
- spin_lock_init(&sh->stripe_lock);
-
if (grow_buffers(sh, gfp)) {
shrink_buffers(sh);
kmem_cache_free(conf->slab_cache, sh);
sh->hash_lock_index =
conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS;
/* we just created an active stripe so... */
- atomic_set(&sh->count, 1);
atomic_inc(&conf->active_stripes);
- INIT_LIST_HEAD(&sh->lru);
- spin_lock_init(&sh->batch_lock);
- INIT_LIST_HEAD(&sh->batch_list);
- sh->batch_head = NULL;
release_stripe(sh);
conf->max_nr_stripes++;
return 1;
return ret;
}
+static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
+{
+ unsigned long cpu;
+ int err = 0;
+
+ mddev_suspend(conf->mddev);
+ get_online_cpus();
+ for_each_present_cpu(cpu) {
+ struct raid5_percpu *percpu;
+ struct flex_array *scribble;
+
+ percpu = per_cpu_ptr(conf->percpu, cpu);
+ scribble = scribble_alloc(new_disks,
+ new_sectors / STRIPE_SECTORS,
+ GFP_NOIO);
+
+ if (scribble) {
+ flex_array_free(percpu->scribble);
+ percpu->scribble = scribble;
+ } else {
+ err = -ENOMEM;
+ break;
+ }
+ }
+ put_online_cpus();
+ mddev_resume(conf->mddev);
+ return err;
+}
+
static int resize_stripes(struct r5conf *conf, int newsize)
{
/* Make all the stripes able to hold 'newsize' devices.
struct stripe_head *osh, *nsh;
LIST_HEAD(newstripes);
struct disk_info *ndisks;
- unsigned long cpu;
int err;
struct kmem_cache *sc;
int i;
return -ENOMEM;
for (i = conf->max_nr_stripes; i; i--) {
- nsh = kmem_cache_zalloc(sc, GFP_KERNEL);
+ nsh = alloc_stripe(sc, GFP_KERNEL);
if (!nsh)
break;
nsh->raid_conf = conf;
- spin_lock_init(&nsh->stripe_lock);
-
list_add(&nsh->lru, &newstripes);
}
if (i) {
lock_device_hash_lock(conf, hash));
osh = get_free_stripe(conf, hash);
unlock_device_hash_lock(conf, hash);
- atomic_set(&nsh->count, 1);
+
for(i=0; i<conf->pool_size; i++) {
nsh->dev[i].page = osh->dev[i].page;
nsh->dev[i].orig_page = osh->dev[i].page;
}
- for( ; i<newsize; i++)
- nsh->dev[i].page = NULL;
nsh->hash_lock_index = hash;
kmem_cache_free(conf->slab_cache, osh);
cnt++;
} else
err = -ENOMEM;
- get_online_cpus();
- for_each_present_cpu(cpu) {
- struct raid5_percpu *percpu;
- struct flex_array *scribble;
-
- percpu = per_cpu_ptr(conf->percpu, cpu);
- scribble = scribble_alloc(newsize, conf->chunk_sectors /
- STRIPE_SECTORS, GFP_NOIO);
-
- if (scribble) {
- flex_array_free(percpu->scribble);
- percpu->scribble = scribble;
- } else {
- err = -ENOMEM;
- break;
- }
- }
- put_online_cpus();
-
/* Step 4, return new stripes to service */
while(!list_empty(&newstripes)) {
nsh = list_entry(newstripes.next, struct stripe_head, lru);
conf->slab_cache = sc;
conf->active_name = 1-conf->active_name;
- conf->pool_size = newsize;
+ if (!err)
+ conf->pool_size = newsize;
return err;
}
}
rdev_dec_pending(rdev, conf->mddev);
- if (sh->batch_head && !uptodate)
+ if (sh->batch_head && !uptodate && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
(unsigned long long)(*bip)->bi_iter.bi_sector,
(unsigned long long)sh->sector, dd_idx);
- spin_unlock_irq(&sh->stripe_lock);
if (conf->mddev->bitmap && firstwrite) {
+ /* Cannot hold spinlock over bitmap_startwrite,
+ * but must ensure this isn't added to a batch until
+ * we have added to the bitmap and set bm_seq.
+ * So set STRIPE_BITMAP_PENDING to prevent
+ * batching.
+ * If multiple add_stripe_bio() calls race here they
+ * much all set STRIPE_BITMAP_PENDING. So only the first one
+ * to complete "bitmap_startwrite" gets to set
+ * STRIPE_BIT_DELAY. This is important as once a stripe
+ * is added to a batch, STRIPE_BIT_DELAY cannot be changed
+ * any more.
+ */
+ set_bit(STRIPE_BITMAP_PENDING, &sh->state);
+ spin_unlock_irq(&sh->stripe_lock);
bitmap_startwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0);
- sh->bm_seq = conf->seq_flush+1;
- set_bit(STRIPE_BIT_DELAY, &sh->state);
+ spin_lock_irq(&sh->stripe_lock);
+ clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
+ if (!sh->batch_head) {
+ sh->bm_seq = conf->seq_flush+1;
+ set_bit(STRIPE_BIT_DELAY, &sh->state);
+ }
}
+ spin_unlock_irq(&sh->stripe_lock);
if (stripe_can_batch(sh))
stripe_add_to_batch_list(conf, sh);
/* reconstruct-write isn't being forced */
return 0;
for (i = 0; i < s->failed; i++) {
- if (!test_bit(R5_UPTODATE, &fdev[i]->flags) &&
+ if (s->failed_num[i] != sh->pd_idx &&
+ s->failed_num[i] != sh->qd_idx &&
+ !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
!test_bit(R5_OVERWRITE, &fdev[i]->flags))
return 1;
}
*/
BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
BUG_ON(test_bit(R5_Wantread, &dev->flags));
+ BUG_ON(sh->batch_head);
if ((s->uptodate == disks - 1) &&
(s->failed && (disk_idx == s->failed_num[0] ||
disk_idx == s->failed_num[1]))) {
{
int i;
- BUG_ON(sh->batch_head);
/* look for blocks to read/compute, skip this if a compute
* is already in flight, or if the stripe contents are in the
* midst of changing due to a write
struct stripe_head, batch_list);
list_del_init(&sh->batch_list);
- set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
- head_sh->state & ~((1 << STRIPE_ACTIVE) |
- (1 << STRIPE_PREREAD_ACTIVE) |
- STRIPE_EXPAND_SYNC_FLAG));
+ WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
+ (1 << STRIPE_SYNCING) |
+ (1 << STRIPE_REPLACED) |
+ (1 << STRIPE_PREREAD_ACTIVE) |
+ (1 << STRIPE_DELAYED) |
+ (1 << STRIPE_BIT_DELAY) |
+ (1 << STRIPE_FULL_WRITE) |
+ (1 << STRIPE_BIOFILL_RUN) |
+ (1 << STRIPE_COMPUTE_RUN) |
+ (1 << STRIPE_OPS_REQ_PENDING) |
+ (1 << STRIPE_DISCARD) |
+ (1 << STRIPE_BATCH_READY) |
+ (1 << STRIPE_BATCH_ERR) |
+ (1 << STRIPE_BITMAP_PENDING)));
+ WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
+ (1 << STRIPE_REPLACED)));
+
+ set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+ (1 << STRIPE_DEGRADED)),
+ head_sh->state & (1 << STRIPE_INSYNC));
+
sh->check_state = head_sh->check_state;
sh->reconstruct_state = head_sh->reconstruct_state;
for (i = 0; i < sh->disks; i++) {
spin_lock_irq(&sh->stripe_lock);
sh->batch_head = NULL;
spin_unlock_irq(&sh->stripe_lock);
- if (sh->state & STRIPE_EXPAND_SYNC_FLAG)
+ if (sh->state & STRIPE_EXPAND_SYNC_FLAGS)
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
spin_lock_irq(&head_sh->stripe_lock);
head_sh->batch_head = NULL;
spin_unlock_irq(&head_sh->stripe_lock);
- wake_up_nr(&conf->wait_for_overlap, wakeup_nr);
- if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG)
+ if (wakeup_nr)
+ wake_up(&conf->wait_for_overlap);
+ if (head_sh->state & STRIPE_EXPAND_SYNC_FLAGS)
set_bit(STRIPE_HANDLE, &head_sh->state);
}
static int clear_batch_ready(struct stripe_head *sh)
{
+ /* Return '1' if this is a member of batch, or
+ * '0' if it is a lone stripe or a head which can now be
+ * handled.
+ */
struct stripe_head *tmp;
if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state))
- return 0;
+ return (sh->batch_head && sh->batch_head != sh);
spin_lock(&sh->stripe_lock);
if (!sh->batch_head) {
spin_unlock(&sh->stripe_lock);
return 0;
}
-static void check_break_stripe_batch_list(struct stripe_head *sh)
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+ unsigned long handle_flags)
{
- struct stripe_head *head_sh, *next;
+ struct stripe_head *sh, *next;
int i;
+ int do_wakeup = 0;
- if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
- return;
-
- head_sh = sh;
- do {
- sh = list_first_entry(&sh->batch_list,
- struct stripe_head, batch_list);
- BUG_ON(sh == head_sh);
- } while (!test_bit(STRIPE_DEGRADED, &sh->state));
+ list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {
- while (sh != head_sh) {
- next = list_first_entry(&sh->batch_list,
- struct stripe_head, batch_list);
list_del_init(&sh->batch_list);
- set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
- head_sh->state & ~((1 << STRIPE_ACTIVE) |
- (1 << STRIPE_PREREAD_ACTIVE) |
- (1 << STRIPE_DEGRADED) |
- STRIPE_EXPAND_SYNC_FLAG));
+ WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
+ (1 << STRIPE_SYNCING) |
+ (1 << STRIPE_REPLACED) |
+ (1 << STRIPE_PREREAD_ACTIVE) |
+ (1 << STRIPE_DELAYED) |
+ (1 << STRIPE_BIT_DELAY) |
+ (1 << STRIPE_FULL_WRITE) |
+ (1 << STRIPE_BIOFILL_RUN) |
+ (1 << STRIPE_COMPUTE_RUN) |
+ (1 << STRIPE_OPS_REQ_PENDING) |
+ (1 << STRIPE_DISCARD) |
+ (1 << STRIPE_BATCH_READY) |
+ (1 << STRIPE_BATCH_ERR) |
+ (1 << STRIPE_BITMAP_PENDING)));
+ WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
+ (1 << STRIPE_REPLACED)));
+
+ set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+ (1 << STRIPE_DEGRADED)),
+ head_sh->state & (1 << STRIPE_INSYNC));
+
sh->check_state = head_sh->check_state;
sh->reconstruct_state = head_sh->reconstruct_state;
- for (i = 0; i < sh->disks; i++)
+ for (i = 0; i < sh->disks; i++) {
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+ do_wakeup = 1;
sh->dev[i].flags = head_sh->dev[i].flags &
(~((1 << R5_WriteError) | (1 << R5_Overlap)));
-
+ }
spin_lock_irq(&sh->stripe_lock);
sh->batch_head = NULL;
spin_unlock_irq(&sh->stripe_lock);
-
- set_bit(STRIPE_HANDLE, &sh->state);
+ if (handle_flags == 0 ||
+ sh->state & handle_flags)
+ set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
-
- sh = next;
}
+ spin_lock_irq(&head_sh->stripe_lock);
+ head_sh->batch_head = NULL;
+ spin_unlock_irq(&head_sh->stripe_lock);
+ for (i = 0; i < head_sh->disks; i++)
+ if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
+ do_wakeup = 1;
+ if (head_sh->state & handle_flags)
+ set_bit(STRIPE_HANDLE, &head_sh->state);
+
+ if (do_wakeup)
+ wake_up(&head_sh->raid_conf->wait_for_overlap);
}
static void handle_stripe(struct stripe_head *sh)
return;
}
- check_break_stripe_batch_list(sh);
+ if (test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
+ break_stripe_batch_list(sh, 0);
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
spin_lock(&sh->stripe_lock);
unsigned int chunk_sectors = mddev->chunk_sectors;
unsigned int bio_sectors = bvm->bi_size >> 9;
- if ((bvm->bi_rw & 1) == WRITE)
- return biovec->bv_len; /* always allow writes to be mergeable */
+ /*
+ * always allow writes to be mergeable, read as well if array
+ * is degraded as we'll go through stripe cache anyway.
+ */
+ if ((bvm->bi_rw & 1) == WRITE || mddev->degraded)
+ return biovec->bv_len;
if (mddev->new_chunk_sectors < mddev->chunk_sectors)
chunk_sectors = mddev->new_chunk_sectors;
md_write_start(mddev, bi);
- if (rw == READ &&
+ /*
+ * If array is degraded, better not do chunk aligned read because
+ * later we might have to read it again in order to reconstruct
+ * data on failed drives.
+ */
+ if (rw == READ && mddev->degraded == 0 &&
mddev->reshape_position == MaxSector &&
chunk_aligned_read(mddev,bi))
return;
int batch_size, released;
released = release_stripe_list(conf, conf->temp_inactive_list);
+ if (released)
+ clear_bit(R5_DID_ALLOC, &conf->cache_state);
if (
!list_empty(&conf->bitmap_list)) {
pr_debug("%d stripes handled\n", handled);
spin_unlock_irq(&conf->device_lock);
+ if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state)) {
+ grow_one_stripe(conf, __GFP_NOWARN);
+ /* Set flag even if allocation failed. This helps
+ * slow down allocation requests when mem is short
+ */
+ set_bit(R5_DID_ALLOC, &conf->cache_state);
+ }
async_tx_issue_pending_all();
blk_finish_plug(&plug);
spin_lock(&mddev->lock);
conf = mddev->private;
if (conf)
- ret = sprintf(page, "%d\n", conf->max_nr_stripes);
+ ret = sprintf(page, "%d\n", conf->min_nr_stripes);
spin_unlock(&mddev->lock);
return ret;
}
if (size <= 16 || size > 32768)
return -EINVAL;
+ conf->min_nr_stripes = size;
while (size < conf->max_nr_stripes &&
drop_one_stripe(conf))
;
+
err = md_allow_write(mddev);
if (err)
return err;
conf = mddev->private;
if (!conf)
err = -ENODEV;
- else if (new > conf->max_nr_stripes)
+ else if (new > conf->min_nr_stripes)
err = -EINVAL;
else
conf->bypass_threshold = new;
percpu->spare_page = alloc_page(GFP_KERNEL);
if (!percpu->scribble)
percpu->scribble = scribble_alloc(max(conf->raid_disks,
- conf->previous_raid_disks), conf->chunk_sectors /
- STRIPE_SECTORS, GFP_KERNEL);
+ conf->previous_raid_disks),
+ max(conf->chunk_sectors,
+ conf->prev_chunk_sectors)
+ / STRIPE_SECTORS,
+ GFP_KERNEL);
if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
free_scratch_buffer(conf, percpu);
static void free_conf(struct r5conf *conf)
{
+ if (conf->shrinker.seeks)
+ unregister_shrinker(&conf->shrinker);
free_thread_groups(conf);
shrink_stripes(conf);
raid5_free_percpu(conf);
return err;
}
+static unsigned long raid5_cache_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
+ int ret = 0;
+ while (ret < sc->nr_to_scan) {
+ if (drop_one_stripe(conf) == 0)
+ return SHRINK_STOP;
+ ret++;
+ }
+ return ret;
+}
+
+static unsigned long raid5_cache_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
+
+ if (conf->max_nr_stripes < conf->min_nr_stripes)
+ /* unlikely, but not impossible */
+ return 0;
+ return conf->max_nr_stripes - conf->min_nr_stripes;
+}
+
static struct r5conf *setup_conf(struct mddev *mddev)
{
struct r5conf *conf;
conf->prev_algo = mddev->layout;
}
- memory = NR_STRIPES * (sizeof(struct stripe_head) +
+ conf->min_nr_stripes = NR_STRIPES;
+ memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
- if (grow_stripes(conf, NR_STRIPES)) {
+ if (grow_stripes(conf, conf->min_nr_stripes)) {
printk(KERN_ERR
"md/raid:%s: couldn't allocate %dkB for buffers\n",
mdname(mddev), memory);
} else
printk(KERN_INFO "md/raid:%s: allocated %dkB\n",
mdname(mddev), memory);
+ /*
+ * Losing a stripe head costs more than the time to refill it,
+ * it reduces the queue depth and so can hurt throughput.
+ * So set it rather large, scaled by number of devices.
+ */
+ conf->shrinker.seeks = DEFAULT_SEEKS * conf->raid_disks * 4;
+ conf->shrinker.scan_objects = raid5_cache_scan;
+ conf->shrinker.count_objects = raid5_cache_count;
+ conf->shrinker.batch = 128;
+ conf->shrinker.flags = 0;
+ register_shrinker(&conf->shrinker);
sprintf(pers_name, "raid%d", mddev->new_level);
conf->thread = md_register_thread(raid5d, mddev, pers_name);
*/
struct r5conf *conf = mddev->private;
if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4
- > conf->max_nr_stripes ||
+ > conf->min_nr_stripes ||
((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4
- > conf->max_nr_stripes) {
+ > conf->min_nr_stripes) {
printk(KERN_WARNING "md/raid:%s: reshape: not enough stripes. Needed %lu\n",
mdname(mddev),
((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9)
if (!check_stripe_cache(mddev))
return -ENOSPC;
+ if (mddev->new_chunk_sectors > mddev->chunk_sectors ||
+ mddev->delta_disks > 0)
+ if (resize_chunks(conf,
+ conf->previous_raid_disks
+ + max(0, mddev->delta_disks),
+ max(mddev->new_chunk_sectors,
+ mddev->chunk_sectors)
+ ) < 0)
+ return -ENOMEM;
return resize_stripes(conf, (conf->previous_raid_disks
+ mddev->delta_disks));
}