*/
#include "dm-bio-list.h"
+#include <linux/delay.h>
#include <linux/raid/raid10.h>
#include <linux/raid/bitmap.h>
kfree(r10_bio);
}
+/* Maximum size of each resync request */
#define RESYNC_BLOCK_SIZE (64*1024)
-//#define RESYNC_BLOCK_SIZE PAGE_SIZE
-#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
-#define RESYNC_WINDOW (2048*1024)
+/* amount of memory to reserve for resync requests */
+#define RESYNC_WINDOW (1024*1024)
+/* maximum number of concurrent requests, memory permitting */
+#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)
/*
* When performing a resync, we need to read and compare, so
conf->nr_queued ++;
spin_unlock_irqrestore(&conf->device_lock, flags);
+ /* wake up frozen array... */
+ wake_up(&conf->wait_barrier);
+
md_wakeup_thread(mddev->thread);
}
/**
* raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
* @q: request queue
- * @bio: the buffer head that's been built up so far
+ * @bvm: properties of new bio
* @biovec: the request that could be merged to it.
*
* Return amount of bytes we can accept at this offset
* If near_copies == raid_disk, there are no striping issues,
* but in that case, the function isn't called at all.
*/
-static int raid10_mergeable_bvec(struct request_queue *q, struct bio *bio,
- struct bio_vec *bio_vec)
+static int raid10_mergeable_bvec(struct request_queue *q,
+ struct bvec_merge_data *bvm,
+ struct bio_vec *biovec)
{
mddev_t *mddev = q->queuedata;
- sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+ sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
unsigned int chunk_sectors = mddev->chunk_size >> 9;
- unsigned int bio_sectors = bio->bi_size >> 9;
+ unsigned int bio_sectors = bvm->bi_size >> 9;
max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
if (max < 0) max = 0; /* bio_add cannot handle a negative return */
- if (max <= bio_vec->bv_len && bio_sectors == 0)
- return bio_vec->bv_len;
+ if (max <= biovec->bv_len && bio_sectors == 0)
+ return biovec->bv_len;
else
return max;
}
current_distance = abs(r10_bio->devs[slot].addr -
conf->mirrors[disk].head_position);
- /* Find the disk whose head is closest */
+ /* Find the disk whose head is closest,
+ * or - for far > 1 - find the closest to partition beginning */
for (nslot = slot; nslot < conf->copies; nslot++) {
int ndisk = r10_bio->devs[nslot].devnum;
slot = nslot;
break;
}
- new_distance = abs(r10_bio->devs[nslot].addr -
- conf->mirrors[ndisk].head_position);
+
+ /* for far > 1 always use the lowest address */
+ if (conf->far_copies > 1)
+ new_distance = r10_bio->devs[nslot].addr;
+ else
+ new_distance = abs(r10_bio->devs[nslot].addr -
+ conf->mirrors[ndisk].head_position);
if (new_distance < current_distance) {
current_distance = new_distance;
disk = ndisk;
return ret;
}
-
+static int flush_pending_writes(conf_t *conf)
+{
+ /* Any writes that have been queued but are awaiting
+ * bitmap updates get flushed here.
+ * We return 1 if any requests were actually submitted.
+ */
+ int rv = 0;
+
+ spin_lock_irq(&conf->device_lock);
+
+ if (conf->pending_bio_list.head) {
+ struct bio *bio;
+ bio = bio_list_get(&conf->pending_bio_list);
+ blk_remove_plug(conf->mddev->queue);
+ spin_unlock_irq(&conf->device_lock);
+ /* flush any pending bitmap writes to disk
+ * before proceeding w/ I/O */
+ bitmap_unplug(conf->mddev->bitmap);
+
+ while (bio) { /* submit pending writes */
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
+ generic_make_request(bio);
+ bio = next;
+ }
+ rv = 1;
+ } else
+ spin_unlock_irq(&conf->device_lock);
+ return rv;
+}
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
* there is no normal IO happeing. It must arrange to call
* lower_barrier when the particular background IO completes.
*/
-#define RESYNC_DEPTH 32
static void raise_barrier(conf_t *conf, int force)
{
/* stop syncio and normal IO and wait for everything to
* go quiet.
* We increment barrier and nr_waiting, and then
- * wait until barrier+nr_pending match nr_queued+2
+ * wait until nr_pending match nr_queued+1
+ * This is called in the context of one normal IO request
+ * that has failed. Thus any sync request that might be pending
+ * will be blocked by nr_pending, and we need to wait for
+ * pending IO requests to complete or be queued for re-try.
+ * Thus the number queued (nr_queued) plus this request (1)
+ * must match the number of pending IOs (nr_pending) before
+ * we continue.
*/
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq(conf->wait_barrier,
- conf->barrier+conf->nr_pending == conf->nr_queued+2,
+ conf->nr_pending == conf->nr_queued+1,
conf->resync_lock,
- raid10_unplug(conf->mddev->queue));
+ ({ flush_pending_writes(conf);
+ raid10_unplug(conf->mddev->queue); }));
spin_unlock_irq(&conf->resync_lock);
}
mirror_info_t *mirror;
r10bio_t *r10_bio;
struct bio *read_bio;
+ int cpu;
int i;
int chunk_sects = conf->chunk_mask + 1;
const int rw = bio_data_dir(bio);
const int do_sync = bio_sync(bio);
struct bio_list bl;
unsigned long flags;
+ mdk_rdev_t *blocked_rdev;
if (unlikely(bio_barrier(bio))) {
bio_endio(bio, -EOPNOTSUPP);
/* This is a one page bio that upper layers
* refuse to split for us, so we need to split it.
*/
- bp = bio_split(bio, bio_split_pool,
+ bp = bio_split(bio,
chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
if (make_request(q, &bp->bio1))
generic_make_request(&bp->bio1);
*/
wait_barrier(conf);
- disk_stat_inc(mddev->gendisk, ios[rw]);
- disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
+ cpu = part_stat_lock();
+ part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
+ part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
+ bio_sectors(bio));
+ part_stat_unlock();
r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
/*
* WRITE:
*/
- /* first select target devices under spinlock and
+ /* first select target devices under rcu_lock and
* inc refcount on their rdev. Record them by setting
* bios[x] to bio
*/
raid10_find_phys(conf, r10_bio);
+ retry_write:
+ blocked_rdev = NULL;
rcu_read_lock();
for (i = 0; i < conf->copies; i++) {
int d = r10_bio->devs[i].devnum;
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[d].rdev);
- if (rdev &&
- !test_bit(Faulty, &rdev->flags)) {
+ if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ atomic_inc(&rdev->nr_pending);
+ blocked_rdev = rdev;
+ break;
+ }
+ if (rdev && !test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
r10_bio->devs[i].bio = bio;
} else {
}
rcu_read_unlock();
+ if (unlikely(blocked_rdev)) {
+ /* Have to wait for this device to get unblocked, then retry */
+ int j;
+ int d;
+
+ for (j = 0; j < i; j++)
+ if (r10_bio->devs[j].bio) {
+ d = r10_bio->devs[j].devnum;
+ rdev_dec_pending(conf->mirrors[d].rdev, mddev);
+ }
+ allow_barrier(conf);
+ md_wait_for_blocked_rdev(blocked_rdev, mddev);
+ wait_barrier(conf);
+ goto retry_write;
+ }
+
atomic_set(&r10_bio->remaining, 0);
bio_list_init(&bl);
blk_plug_device(mddev->queue);
spin_unlock_irqrestore(&conf->device_lock, flags);
+ /* In case raid10d snuck in to freeze_array */
+ wake_up(&conf->wait_barrier);
+
if (do_sync)
md_wakeup_thread(mddev->thread);
/*
* if recovery is running, make sure it aborts.
*/
- set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
}
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
- printk(KERN_ALERT "raid10: Disk failure on %s, disabling device. \n"
- " Operation continuing on %d devices\n",
+ printk(KERN_ALERT "raid10: Disk failure on %s, disabling device.\n"
+ "raid10: Operation continuing on %d devices.\n",
bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
}
static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
{
conf_t *conf = mddev->private;
- int found = 0;
+ int err = -EEXIST;
int mirror;
mirror_info_t *p;
+ int first = 0;
+ int last = mddev->raid_disks - 1;
if (mddev->recovery_cp < MaxSector)
/* only hot-add to in-sync arrays, as recovery is
* very different from resync
*/
- return 0;
+ return -EBUSY;
if (!enough(conf))
- return 0;
+ return -EINVAL;
+
+ if (rdev->raid_disk >= 0)
+ first = last = rdev->raid_disk;
if (rdev->saved_raid_disk >= 0 &&
+ rdev->saved_raid_disk >= first &&
conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
mirror = rdev->saved_raid_disk;
else
- mirror = 0;
- for ( ; mirror < mddev->raid_disks; mirror++)
+ mirror = first;
+ for ( ; mirror <= last ; mirror++)
if ( !(p=conf->mirrors+mirror)->rdev) {
blk_queue_stack_limits(mddev->queue,
p->head_position = 0;
rdev->raid_disk = mirror;
- found = 1;
+ err = 0;
if (rdev->saved_raid_disk != mirror)
conf->fullsync = 1;
rcu_assign_pointer(p->rdev, rdev);
}
print_conf(conf);
- return found;
+ return err;
}
static int raid10_remove_disk(mddev_t *mddev, int number)
err = -EBUSY;
goto abort;
}
+ /* Only remove faulty devices in recovery
+ * is not possible.
+ */
+ if (!test_bit(Faulty, &rdev->flags) &&
+ enough(conf)) {
+ err = -EBUSY;
+ goto abort;
+ }
p->rdev = NULL;
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
if (!uptodate)
md_error(mddev, conf->mirrors[d].rdev);
+
update_head_pos(i, r10_bio);
while (atomic_dec_and_test(&r10_bio->remaining)) {
tbio->bi_size = r10_bio->sectors << 9;
tbio->bi_idx = 0;
tbio->bi_phys_segments = 0;
- tbio->bi_hw_segments = 0;
- tbio->bi_hw_front_size = 0;
- tbio->bi_hw_back_size = 0;
tbio->bi_flags &= ~(BIO_POOL_MASK - 1);
tbio->bi_flags |= 1 << BIO_UPTODATE;
tbio->bi_next = NULL;
for (;;) {
char b[BDEVNAME_SIZE];
- spin_lock_irqsave(&conf->device_lock, flags);
- if (conf->pending_bio_list.head) {
- bio = bio_list_get(&conf->pending_bio_list);
- blk_remove_plug(mddev->queue);
- spin_unlock_irqrestore(&conf->device_lock, flags);
- /* flush any pending bitmap writes to disk before proceeding w/ I/O */
- bitmap_unplug(mddev->bitmap);
+ unplug += flush_pending_writes(conf);
- while (bio) { /* submit pending writes */
- struct bio *next = bio->bi_next;
- bio->bi_next = NULL;
- generic_make_request(bio);
- bio = next;
- }
- unplug = 1;
-
- continue;
- }
-
- if (list_empty(head))
+ spin_lock_irqsave(&conf->device_lock, flags);
+ if (list_empty(head)) {
+ spin_unlock_irqrestore(&conf->device_lock, flags);
break;
+ }
r10_bio = list_entry(head->prev, r10bio_t, retry_list);
list_del(head->prev);
conf->nr_queued--;
}
}
}
- spin_unlock_irqrestore(&conf->device_lock, flags);
if (unplug)
unplug_slaves(mddev);
}
if (j == conf->copies) {
/* Cannot recover, so abort the recovery */
put_buf(r10_bio);
+ if (rb2)
+ atomic_dec(&rb2->remaining);
r10_bio = rb2;
- if (!test_and_set_bit(MD_RECOVERY_ERR, &mddev->recovery))
+ if (!test_and_set_bit(MD_RECOVERY_INTR,
+ &mddev->recovery))
printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",
mdname(mddev));
break;
bio->bi_vcnt = 0;
bio->bi_idx = 0;
bio->bi_phys_segments = 0;
- bio->bi_hw_segments = 0;
bio->bi_size = 0;
}
int i, disk_idx;
mirror_info_t *disk;
mdk_rdev_t *rdev;
- struct list_head *tmp;
int nc, fc, fo;
sector_t stride, size;
- if (mddev->chunk_size == 0) {
- printk(KERN_ERR "md/raid10: non-zero chunk size required.\n");
+ if (mddev->chunk_size < PAGE_SIZE) {
+ printk(KERN_ERR "md/raid10: chunk size must be "
+ "at least PAGE_SIZE(%ld).\n", PAGE_SIZE);
return -EINVAL;
}
goto out_free_conf;
}
- rdev_for_each(rdev, tmp, mddev) {
+ spin_lock_init(&conf->device_lock);
+ mddev->queue->queue_lock = &conf->device_lock;
+
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
disk->head_position = 0;
}
- spin_lock_init(&conf->device_lock);
INIT_LIST_HEAD(&conf->retry_list);
spin_lock_init(&conf->resync_lock);
!test_bit(In_sync, &disk->rdev->flags)) {
disk->head_position = 0;
mddev->degraded++;
+ if (disk->rdev)
+ conf->fullsync = 1;
}
}
/*
* Ok, everything is just fine now
*/
- mddev->array_size = size << (conf->chunk_shift-1);
+ mddev->array_sectors = size << conf->chunk_shift;
mddev->resync_max_sectors = size << conf->chunk_shift;
mddev->queue->unplug_fn = raid10_unplug;