#include <linux/bitops.h>
#include <asm/atomic.h>
+#include <linux/raid/bitmap.h>
+
/*
* Stripe cache
*/
#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
-#define HASH_PAGES 1
-#define HASH_PAGES_ORDER 0
-#define NR_HASH (HASH_PAGES * PAGE_SIZE / sizeof(struct stripe_head *))
+#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
-#define stripe_hash(conf, sect) ((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK])
+#define stripe_hash(conf, sect) (&((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK]))
/* bio's attached to a stripe+device for I/O are linked together in bi_sector
* order without overlap. There may be several bio's per stripe+device, and
static void print_raid5_conf (raid5_conf_t *conf);
-static inline void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
+static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
if (!list_empty(&sh->lru))
if (test_bit(STRIPE_HANDLE, &sh->state)) {
if (test_bit(STRIPE_DELAYED, &sh->state))
list_add_tail(&sh->lru, &conf->delayed_list);
- else
+ else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+ conf->seq_write == sh->bm_seq)
+ list_add_tail(&sh->lru, &conf->bitmap_list);
+ else {
+ clear_bit(STRIPE_BIT_DELAY, &sh->state);
list_add_tail(&sh->lru, &conf->handle_list);
+ }
md_wakeup_thread(conf->mddev->thread);
} else {
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
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);
}
}
spin_unlock_irqrestore(&conf->device_lock, flags);
}
-static void remove_hash(struct stripe_head *sh)
+static inline void remove_hash(struct stripe_head *sh)
{
PRINTK("remove_hash(), stripe %llu\n", (unsigned long long)sh->sector);
- if (sh->hash_pprev) {
- if (sh->hash_next)
- sh->hash_next->hash_pprev = sh->hash_pprev;
- *sh->hash_pprev = sh->hash_next;
- sh->hash_pprev = NULL;
- }
+ hlist_del_init(&sh->hash);
}
-static __inline__ void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
+static void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
{
- struct stripe_head **shp = &stripe_hash(conf, sh->sector);
+ struct hlist_head *hp = stripe_hash(conf, sh->sector);
PRINTK("insert_hash(), stripe %llu\n", (unsigned long long)sh->sector);
CHECK_DEVLOCK();
- if ((sh->hash_next = *shp) != NULL)
- (*shp)->hash_pprev = &sh->hash_next;
- *shp = sh;
- sh->hash_pprev = shp;
+ hlist_add_head(&sh->hash, hp);
}
if (!p)
continue;
sh->dev[i].page = NULL;
- page_cache_release(p);
+ put_page(p);
}
}
static void raid5_build_block (struct stripe_head *sh, int i);
-static inline void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
+static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
{
raid5_conf_t *conf = sh->raid_conf;
int disks = conf->raid_disks, i;
static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector)
{
struct stripe_head *sh;
+ struct hlist_node *hn;
CHECK_DEVLOCK();
PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector);
- for (sh = stripe_hash(conf, sector); sh; sh = sh->hash_next)
+ hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
if (sh->sector == sector)
return sh;
PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector);
spin_lock_irq(&conf->device_lock);
do {
+ wait_event_lock_irq(conf->wait_for_stripe,
+ conf->quiesce == 0,
+ conf->device_lock, /* nothing */);
sh = __find_stripe(conf, sector);
if (!sh) {
if (!conf->inactive_blocked)
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);
- }
- kmem_cache_destroy(conf->slab_cache);
+ 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))
+ ;
+
+ if (conf->slab_cache)
+ 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);
{
struct bio **bip;
raid5_conf_t *conf = sh->raid_conf;
+ int firstwrite=0;
PRINTK("adding bh b#%llu to stripe s#%llu\n",
(unsigned long long)bi->bi_sector,
spin_lock(&sh->lock);
spin_lock_irq(&conf->device_lock);
- if (forwrite)
+ if (forwrite) {
bip = &sh->dev[dd_idx].towrite;
- else
+ if (*bip == NULL && sh->dev[dd_idx].written == NULL)
+ firstwrite = 1;
+ } else
bip = &sh->dev[dd_idx].toread;
while (*bip && (*bip)->bi_sector < bi->bi_sector) {
if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
(unsigned long long)bi->bi_sector,
(unsigned long long)sh->sector, dd_idx);
+ if (conf->mddev->bitmap && firstwrite) {
+ sh->bm_seq = conf->seq_write;
+ bitmap_startwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0);
+ set_bit(STRIPE_BIT_DELAY, &sh->state);
+ }
+
if (forwrite) {
/* check if page is covered */
sector_t sector = sh->dev[dd_idx].sector;
syncing = test_bit(STRIPE_SYNCING, &sh->state);
/* Now to look around and see what can be done */
+ rcu_read_lock();
for (i=disks; i--; ) {
mdk_rdev_t *rdev;
dev = &sh->dev[i];
clear_bit(R5_Insync, &dev->flags);
- clear_bit(R5_Syncio, &dev->flags);
PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
i, dev->flags, dev->toread, dev->towrite, dev->written);
non_overwrite++;
}
if (dev->written) written++;
- rdev = conf->disks[i].rdev; /* FIXME, should I be looking rdev */
- if (!rdev || !rdev->in_sync) {
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ 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
set_bit(R5_Insync, &dev->flags);
}
+ rcu_read_unlock();
PRINTK("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d\n",
locked, uptodate, to_read, to_write, failed, failed_num);
* need to be failed
*/
if (failed > 1 && to_read+to_write+written) {
- spin_lock_irq(&conf->device_lock);
for (i=disks; i--; ) {
+ int bitmap_end = 0;
+
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ mdk_rdev_t *rdev;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(In_sync, &rdev->flags))
+ /* multiple read failures in one stripe */
+ md_error(conf->mddev, rdev);
+ rcu_read_unlock();
+ }
+
+ spin_lock_irq(&conf->device_lock);
/* fail all writes first */
bi = sh->dev[i].towrite;
sh->dev[i].towrite = NULL;
- if (bi) to_write--;
+ if (bi) { to_write--; bitmap_end = 1; }
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
/* and fail all 'written' */
bi = sh->dev[i].written;
sh->dev[i].written = NULL;
+ if (bi) bitmap_end = 1;
while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
}
/* 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))
bi = nextbi;
}
}
+ spin_unlock_irq(&conf->device_lock);
+ if (bitmap_end)
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0, 0);
}
- spin_unlock_irq(&conf->device_lock);
}
if (failed > 1 && syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
test_bit(R5_UPTODATE, &dev->flags) ) {
/* We can return any write requests */
struct bio *wbi, *wbi2;
+ int bitmap_end = 0;
PRINTK("Return write for disc %d\n", i);
spin_lock_irq(&conf->device_lock);
wbi = dev->written;
}
wbi = wbi2;
}
+ if (dev->towrite == NULL)
+ bitmap_end = 1;
spin_unlock_irq(&conf->device_lock);
+ if (bitmap_end)
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS,
+ !test_bit(STRIPE_DEGRADED, &sh->state), 0);
}
}
}
locked++;
PRINTK("Reading block %d (sync=%d)\n",
i, syncing);
- if (syncing)
- md_sync_acct(conf->disks[i].rdev->bdev,
- STRIPE_SECTORS);
}
}
}
}
}
/* now if nothing is locked, and if we have enough data, we can start a write request */
- if (locked == 0 && (rcw == 0 ||rmw == 0)) {
+ if (locked == 0 && (rcw == 0 ||rmw == 0) &&
+ !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
PRINTK("Computing parity...\n");
compute_parity(sh, rcw==0 ? RECONSTRUCT_WRITE : READ_MODIFY_WRITE);
/* now every locked buffer is ready to be written */
* 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);
locked++;
set_bit(STRIPE_INSYNC, &sh->state);
- set_bit(R5_Syncio, &dev->flags);
}
}
if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &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_unlock();
if (rdev) {
- if (test_bit(R5_Syncio, &sh->dev[i].flags))
+ if (syncing)
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
bi->bi_bdev = rdev->bdev;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
bi->bi_next = NULL;
+ if (rw == WRITE &&
+ test_bit(R5_ReWrite, &sh->dev[i].flags))
+ atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
generic_make_request(bi);
} else {
+ if (rw == 1)
+ set_bit(STRIPE_DEGRADED, &sh->state);
PRINTK("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);
}
}
-static inline void raid5_activate_delayed(raid5_conf_t *conf)
+static void raid5_activate_delayed(raid5_conf_t *conf)
{
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
while (!list_empty(&conf->delayed_list)) {
}
}
+static void activate_bit_delay(raid5_conf_t *conf)
+{
+ /* device_lock is held */
+ struct list_head head;
+ list_add(&head, &conf->bitmap_list);
+ list_del_init(&conf->bitmap_list);
+ while (!list_empty(&head)) {
+ struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
+ list_del_init(&sh->lru);
+ atomic_inc(&sh->count);
+ __release_stripe(conf, sh);
+ }
+}
+
static void unplug_slaves(mddev_t *mddev)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
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);
raid5_conf_t *conf = mddev_to_conf(mddev);
unsigned long flags;
- if (!conf) return;
-
spin_lock_irqsave(&conf->device_lock, flags);
- if (blk_remove_plug(q))
+ if (blk_remove_plug(q)) {
+ conf->seq_flush++;
raid5_activate_delayed(conf);
+ }
md_wakeup_thread(mddev->thread);
spin_unlock_irqrestore(&conf->device_lock, flags);
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);
sector_t new_sector;
sector_t logical_sector, last_sector;
struct stripe_head *sh;
+ const int rw = bio_data_dir(bi);
- if (bio_data_dir(bi)==WRITE) {
- disk_stat_inc(mddev->gendisk, writes);
- disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bi));
- } else {
- disk_stat_inc(mddev->gendisk, reads);
- disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bi));
+ if (unlikely(bio_barrier(bi))) {
+ bio_endio(bi, bi->bi_size, -EOPNOTSUPP);
+ return 0;
}
+ md_write_start(mddev, bi);
+
+ disk_stat_inc(mddev->gendisk, ios[rw]);
+ disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bi));
+
logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
last_sector = bi->bi_sector + (bi->bi_size>>9);
bi->bi_next = NULL;
bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
- if ( bio_data_dir(bi) == WRITE )
- md_write_start(mddev);
+
for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
DEFINE_WAIT(w);
}
/* FIXME go_faster isn't used */
-static int sync_request (mddev_t *mddev, sector_t sector_nr, int go_faster)
+static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
struct stripe_head *sh;
sector_t first_sector;
int raid_disks = conf->raid_disks;
int data_disks = raid_disks-1;
+ sector_t max_sector = mddev->size << 1;
+ int sync_blocks;
- if (sector_nr >= mddev->size <<1) {
+ if (sector_nr >= max_sector) {
/* just being told to finish up .. nothing much to do */
unplug_slaves(mddev);
+
+ if (mddev->curr_resync < max_sector) /* aborted */
+ bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
+ &sync_blocks, 1);
+ else /* compelted sync */
+ conf->fullsync = 0;
+ bitmap_close_sync(mddev->bitmap);
+
return 0;
}
/* if there is 1 or more failed drives and we are trying
* nothing we can do.
*/
if (mddev->degraded >= 1 && test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
- int rv = (mddev->size << 1) - sector_nr;
- md_done_sync(mddev, rv, 1);
+ sector_t rv = (mddev->size << 1) - sector_nr;
+ *skipped = 1;
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;
+ *skipped = 1;
+ return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
+ }
x = sector_nr;
chunk_offset = sector_div(x, sectors_per_chunk);
/* 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);
set_bit(STRIPE_SYNCING, &sh->state);
clear_bit(STRIPE_INSYNC, &sh->state);
PRINTK("+++ raid5d active\n");
md_check_recovery(mddev);
- md_handle_safemode(mddev);
handled = 0;
spin_lock_irq(&conf->device_lock);
while (1) {
struct list_head *first;
+ 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);
+ }
+
if (list_empty(&conf->handle_list) &&
atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
!blk_queue_plugged(mddev->queue) &&
PRINTK("--- raid5d inactive\n");
}
-static int run (mddev_t *mddev)
+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;
int raid_disk, memory;
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;
}
- mddev->private = kmalloc (sizeof (raid5_conf_t)
- + mddev->raid_disks * sizeof(struct disk_info),
- GFP_KERNEL);
+ mddev->private = kzalloc(sizeof (raid5_conf_t)
+ + mddev->raid_disks * sizeof(struct disk_info),
+ GFP_KERNEL);
if ((conf = mddev->private) == NULL)
goto abort;
- memset (conf, 0, sizeof (*conf) + mddev->raid_disks * sizeof(struct disk_info) );
+
conf->mddev = mddev;
- if ((conf->stripe_hashtbl = (struct stripe_head **) __get_free_pages(GFP_ATOMIC, HASH_PAGES_ORDER)) == NULL)
+ if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
goto abort;
- memset(conf->stripe_hashtbl, 0, HASH_PAGES * PAGE_SIZE);
spin_lock_init(&conf->device_lock);
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
INIT_LIST_HEAD(&conf->handle_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);
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),
/* device size must be a multiple of chunk size */
mddev->size &= ~(mddev->chunk_size/1024 -1);
+ mddev->resync_max_sectors = mddev->size << 1;
if (!conf->chunk_size || conf->chunk_size % 4) {
printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
if (mddev->degraded == 1 &&
mddev->recovery_cp != MaxSector) {
- printk(KERN_ERR
- "raid5: cannot start dirty degraded array for %s\n",
- mdname(mddev));
- goto abort;
+ if (mddev->ok_start_degraded)
+ printk(KERN_WARNING
+ "raid5: starting dirty degraded array: %s"
+ "- data corruption possible.\n",
+ mdname(mddev));
+ else {
+ printk(KERN_ERR
+ "raid5: cannot start dirty degraded array for %s\n",
+ mdname(mddev));
+ goto abort;
+ }
}
{
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
*/
{
int stripe = (mddev->raid_disks-1) * mddev->chunk_size
- / PAGE_CACHE_SIZE;
+ / PAGE_SIZE;
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
}
/* Ok, everything is just fine now */
+ sysfs_create_group(&mddev->kobj, &raid5_attrs_group);
mddev->queue->unplug_fn = raid5_unplug_device;
mddev->queue->issue_flush_fn = raid5_issue_flush;
abort:
if (conf) {
print_raid5_conf(conf);
- if (conf->stripe_hashtbl)
- free_pages((unsigned long) conf->stripe_hashtbl,
- HASH_PAGES_ORDER);
+ kfree(conf->stripe_hashtbl);
kfree(conf);
}
mddev->private = NULL;
-static int stop (mddev_t *mddev)
+static int stop(mddev_t *mddev)
{
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
shrink_stripes(conf);
- free_pages((unsigned long) conf->stripe_hashtbl, HASH_PAGES_ORDER);
+ kfree(conf->stripe_hashtbl);
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;
static void printall (raid5_conf_t *conf)
{
struct stripe_head *sh;
+ struct hlist_node *hn;
int i;
spin_lock_irq(&conf->device_lock);
for (i = 0; i < NR_HASH; i++) {
- sh = conf->stripe_hashtbl[i];
- for (; sh; sh = sh->hash_next) {
+ hlist_for_each_entry(sh, hn, &conf->stripe_hashtbl[i], hash) {
if (sh->raid_conf != conf)
continue;
print_sh(sh);
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;
- p->rdev = rdev;
+ if (rdev->saved_raid_disk != disk)
+ conf->fullsync = 1;
+ rcu_assign_pointer(p->rdev, rdev);
break;
}
print_raid5_conf(conf);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}
mddev->size = sectors /2;
+ mddev->resync_max_sectors = sectors;
return 0;
}
-static mdk_personality_t raid5_personality=
+static void raid5_quiesce(mddev_t *mddev, int state)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+
+ switch(state) {
+ case 1: /* stop all writes */
+ spin_lock_irq(&conf->device_lock);
+ conf->quiesce = 1;
+ wait_event_lock_irq(conf->wait_for_stripe,
+ atomic_read(&conf->active_stripes) == 0,
+ conf->device_lock, /* nothing */);
+ spin_unlock_irq(&conf->device_lock);
+ break;
+
+ case 0: /* re-enable writes */
+ spin_lock_irq(&conf->device_lock);
+ conf->quiesce = 0;
+ wake_up(&conf->wait_for_stripe);
+ spin_unlock_irq(&conf->device_lock);
+ break;
+ }
+}
+
+static struct mdk_personality raid5_personality =
{
.name = "raid5",
+ .level = 5,
+ .owner = THIS_MODULE,
+ .make_request = make_request,
+ .run = run,
+ .stop = stop,
+ .status = status,
+ .error_handler = error,
+ .hot_add_disk = raid5_add_disk,
+ .hot_remove_disk= raid5_remove_disk,
+ .spare_active = raid5_spare_active,
+ .sync_request = sync_request,
+ .resize = raid5_resize,
+ .quiesce = raid5_quiesce,
+};
+
+static struct mdk_personality raid4_personality =
+{
+ .name = "raid4",
+ .level = 4,
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
.spare_active = raid5_spare_active,
.sync_request = sync_request,
.resize = raid5_resize,
+ .quiesce = raid5_quiesce,
};
-static int __init raid5_init (void)
+static int __init raid5_init(void)
{
- return register_md_personality (RAID5, &raid5_personality);
+ register_md_personality(&raid5_personality);
+ register_md_personality(&raid4_personality);
+ return 0;
}
-static void raid5_exit (void)
+static void raid5_exit(void)
{
- unregister_md_personality (RAID5);
+ unregister_md_personality(&raid5_personality);
+ unregister_md_personality(&raid4_personality);
}
module_init(raid5_init);
module_exit(raid5_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-4"); /* RAID5 */
+MODULE_ALIAS("md-raid5");
+MODULE_ALIAS("md-raid4");
+MODULE_ALIAS("md-level-5");
+MODULE_ALIAS("md-level-4");
git://git.onelab.eu / linux-2.6.git / blobdiff