* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include "dm-bio-list.h"
-#include <linux/raid/raid10.h>
-#include <linux/raid/bitmap.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid10.h"
+#include "raid0.h"
+#include "bitmap.h"
/*
* RAID10 provides a combination of RAID0 and RAID1 functionality.
/* allocate a r10bio with room for raid_disks entries in the bios array */
r10_bio = kzalloc(size, gfp_flags);
- if (!r10_bio)
+ if (!r10_bio && conf->mddev)
unplug_slaves(conf->mddev);
return r10_bio;
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
static void free_r10bio(r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
/*
* Wake up any possible resync thread that waits for the device
static void put_buf(r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
mempool_free(r10_bio, conf->r10buf_pool);
{
unsigned long flags;
mddev_t *mddev = r10_bio->mddev;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&r10_bio->retry_list, &conf->retry_list);
conf->nr_queued ++;
spin_unlock_irqrestore(&conf->device_lock, flags);
+ /* wake up frozen array... */
+ wake_up(&conf->wait_barrier);
+
md_wakeup_thread(mddev->thread);
}
*/
static inline void update_head_pos(int slot, r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
conf->mirrors[r10_bio->devs[slot].devnum].head_position =
r10_bio->devs[slot].addr + (r10_bio->sectors);
static void raid10_end_read_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
+ r10bio_t *r10_bio = bio->bi_private;
int slot, dev;
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
slot = r10_bio->read_slot;
*/
char b[BDEVNAME_SIZE];
if (printk_ratelimit())
- printk(KERN_ERR "raid10: %s: rescheduling sector %llu\n",
+ printk(KERN_ERR "md/raid10:%s: %s: rescheduling sector %llu\n",
+ mdname(conf->mddev),
bdevname(conf->mirrors[dev].rdev->bdev,b), (unsigned long long)r10_bio->sector);
reschedule_retry(r10_bio);
}
static void raid10_end_write_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
+ r10bio_t *r10_bio = bio->bi_private;
int slot, dev;
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
for (slot = 0; slot < conf->copies; slot++)
if (r10_bio->devs[slot].bio == bio)
mddev_t *mddev = q->queuedata;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
- unsigned int chunk_sectors = mddev->chunk_size >> 9;
+ unsigned int chunk_sectors = mddev->chunk_sectors;
unsigned int bio_sectors = bvm->bi_size >> 9;
max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
*/
static int read_balance(conf_t *conf, r10bio_t *r10_bio)
{
- const unsigned long this_sector = r10_bio->sector;
+ const sector_t this_sector = r10_bio->sector;
int disk, slot, nslot;
const int sectors = r10_bio->sectors;
sector_t new_distance, current_distance;
static void unplug_slaves(mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
rcu_read_lock();
- for (i=0; i<mddev->raid_disks; i++) {
+ for (i=0; i < conf->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
static int raid10_congested(void *data, int bits)
{
mddev_t *mddev = data;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i, ret = 0;
+ if (mddev_congested(mddev, bits))
+ return 1;
rcu_read_lock();
- for (i = 0; i < mddev->raid_disks && ret == 0; i++) {
+ for (i = 0; i < conf->raid_disks && ret == 0; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q = bdev_get_queue(rdev->bdev);
* 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)
{
spin_unlock_irq(&conf->resync_lock);
}
-static int make_request(struct request_queue *q, struct bio * bio)
+static int make_request(mddev_t *mddev, struct bio * bio)
{
- mddev_t *mddev = q->queuedata;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
mirror_info_t *mirror;
r10bio_t *r10_bio;
struct bio *read_bio;
int i;
int chunk_sects = conf->chunk_mask + 1;
const int rw = bio_data_dir(bio);
- const int do_sync = bio_sync(bio);
+ const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
struct bio_list bl;
unsigned long flags;
mdk_rdev_t *blocked_rdev;
- if (unlikely(bio_barrier(bio))) {
- bio_endio(bio, -EOPNOTSUPP);
+ if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
+ md_barrier_request(mddev, bio);
return 0;
}
/* 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))
+ if (make_request(mddev, &bp->bio1))
generic_make_request(&bp->bio1);
- if (make_request(q, &bp->bio2))
+ if (make_request(mddev, &bp->bio2))
generic_make_request(&bp->bio2);
bio_pair_release(bp);
return 0;
bad_map:
- printk("raid10_make_request bug: can't convert block across chunks"
- " or bigger than %dk %llu %d\n", chunk_sects/2,
+ printk("md/raid10:%s: make_request bug: can't convert block across chunks"
+ " or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2,
(unsigned long long)bio->bi_sector, bio->bi_size >> 10);
bio_io_error(bio);
*/
wait_barrier(conf);
- disk_stat_inc(mddev->gendisk, ios[rw]);
- disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
-
r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
r10_bio->master_bio = bio;
mirror->rdev->data_offset;
read_bio->bi_bdev = mirror->rdev->bdev;
read_bio->bi_end_io = raid10_end_read_request;
- read_bio->bi_rw = READ | do_sync;
+ read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
read_bio->bi_private = r10_bio;
generic_make_request(read_bio);
conf->mirrors[d].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync;
+ mbio->bi_rw = WRITE | (do_sync << BIO_RW_SYNCIO);
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
static void status(struct seq_file *seq, mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
if (conf->near_copies < conf->raid_disks)
- seq_printf(seq, " %dK chunks", mddev->chunk_size/1024);
+ seq_printf(seq, " %dK chunks", mddev->chunk_sectors / 2);
if (conf->near_copies > 1)
seq_printf(seq, " %d near-copies", conf->near_copies);
if (conf->far_copies > 1) {
static void error(mddev_t *mddev, mdk_rdev_t *rdev)
{
char b[BDEVNAME_SIZE];
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
/*
* If it is not operational, then we have already marked it as dead
}
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
- 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);
+ printk(KERN_ALERT "md/raid10:%s: Disk failure on %s, disabling device.\n"
+ KERN_ALERT "md/raid10:%s: Operation continuing on %d devices.\n",
+ mdname(mddev), bdevname(rdev->bdev, b),
+ mdname(mddev), conf->raid_disks - mddev->degraded);
}
static void print_conf(conf_t *conf)
int i;
mirror_info_t *tmp;
- printk("RAID10 conf printout:\n");
+ printk(KERN_DEBUG "RAID10 conf printout:\n");
if (!conf) {
- printk("(!conf)\n");
+ printk(KERN_DEBUG "(!conf)\n");
return;
}
- printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
+ printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
conf->raid_disks);
for (i = 0; i < conf->raid_disks; i++) {
char b[BDEVNAME_SIZE];
tmp = conf->mirrors + i;
if (tmp->rdev)
- printk(" disk %d, wo:%d, o:%d, dev:%s\n",
+ printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
i, !test_bit(In_sync, &tmp->rdev->flags),
!test_bit(Faulty, &tmp->rdev->flags),
bdevname(tmp->rdev->bdev,b));
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 = conf->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,
- rdev->bdev->bd_disk->queue);
- /* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
+ /* as we don't honour merge_bvec_fn, we must
+ * never risk violating it, so limit
+ * ->max_segments to one lying with a single
+ * page, as a one page request is never in
+ * violation.
*/
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- mddev->queue->max_sectors > (PAGE_SIZE>>9))
- mddev->queue->max_sectors = (PAGE_SIZE>>9);
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
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);
break;
}
+ md_integrity_add_rdev(rdev, mddev);
print_conf(conf);
- return found;
+ return err;
}
static int raid10_remove_disk(mddev_t *mddev, int number)
/* lost the race, try later */
err = -EBUSY;
p->rdev = rdev;
+ goto abort;
}
+ md_integrity_register(mddev);
}
abort:
static void end_sync_read(struct bio *bio, int error)
{
- r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ r10bio_t *r10_bio = bio->bi_private;
+ conf_t *conf = r10_bio->mddev->private;
int i,d;
for (i=0; i<conf->copies; i++)
/* for reconstruct, we always reschedule after a read.
* for resync, only after all reads
*/
+ rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
if (test_bit(R10BIO_IsRecover, &r10_bio->state) ||
atomic_dec_and_test(&r10_bio->remaining)) {
/* we have read all the blocks,
*/
reschedule_retry(r10_bio);
}
- rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
}
static void end_sync_write(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
+ r10bio_t *r10_bio = bio->bi_private;
mddev_t *mddev = r10_bio->mddev;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i,d;
for (i = 0; i < conf->copies; i++)
update_head_pos(i, r10_bio);
+ rdev_dec_pending(conf->mirrors[d].rdev, mddev);
while (atomic_dec_and_test(&r10_bio->remaining)) {
if (r10_bio->master_bio == NULL) {
/* the primary of several recovery bios */
- md_done_sync(mddev, r10_bio->sectors, 1);
+ sector_t s = r10_bio->sectors;
put_buf(r10_bio);
+ md_done_sync(mddev, s, 1);
break;
} else {
r10bio_t *r10_bio2 = (r10bio_t *)r10_bio->master_bio;
r10_bio = r10_bio2;
}
}
- rdev_dec_pending(conf->mirrors[d].rdev, mddev);
}
/*
*/
static void sync_request_write(mddev_t *mddev, r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i, first;
struct bio *tbio, *fbio;
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;
static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i, d;
struct bio *bio, *wbio;
/*
+ * Used by fix_read_error() to decay the per rdev read_errors.
+ * We halve the read error count for every hour that has elapsed
+ * since the last recorded read error.
+ *
+ */
+static void check_decay_read_errors(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+ struct timespec cur_time_mon;
+ unsigned long hours_since_last;
+ unsigned int read_errors = atomic_read(&rdev->read_errors);
+
+ ktime_get_ts(&cur_time_mon);
+
+ if (rdev->last_read_error.tv_sec == 0 &&
+ rdev->last_read_error.tv_nsec == 0) {
+ /* first time we've seen a read error */
+ rdev->last_read_error = cur_time_mon;
+ return;
+ }
+
+ hours_since_last = (cur_time_mon.tv_sec -
+ rdev->last_read_error.tv_sec) / 3600;
+
+ rdev->last_read_error = cur_time_mon;
+
+ /*
+ * if hours_since_last is > the number of bits in read_errors
+ * just set read errors to 0. We do this to avoid
+ * overflowing the shift of read_errors by hours_since_last.
+ */
+ if (hours_since_last >= 8 * sizeof(read_errors))
+ atomic_set(&rdev->read_errors, 0);
+ else
+ atomic_set(&rdev->read_errors, read_errors >> hours_since_last);
+}
+
+/*
* This is a kernel thread which:
*
* 1. Retries failed read operations on working mirrors.
int sect = 0; /* Offset from r10_bio->sector */
int sectors = r10_bio->sectors;
mdk_rdev_t*rdev;
+ int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
+
+ rcu_read_lock();
+ {
+ int d = r10_bio->devs[r10_bio->read_slot].devnum;
+ char b[BDEVNAME_SIZE];
+ int cur_read_error_count = 0;
+
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
+ bdevname(rdev->bdev, b);
+
+ if (test_bit(Faulty, &rdev->flags)) {
+ rcu_read_unlock();
+ /* drive has already been failed, just ignore any
+ more fix_read_error() attempts */
+ return;
+ }
+
+ check_decay_read_errors(mddev, rdev);
+ atomic_inc(&rdev->read_errors);
+ cur_read_error_count = atomic_read(&rdev->read_errors);
+ if (cur_read_error_count > max_read_errors) {
+ rcu_read_unlock();
+ printk(KERN_NOTICE
+ "md/raid10:%s: %s: Raid device exceeded "
+ "read_error threshold "
+ "[cur %d:max %d]\n",
+ mdname(mddev),
+ b, cur_read_error_count, max_read_errors);
+ printk(KERN_NOTICE
+ "md/raid10:%s: %s: Failing raid "
+ "device\n", mdname(mddev), b);
+ md_error(mddev, conf->mirrors[d].rdev);
+ return;
+ }
+ }
+ rcu_read_unlock();
+
while(sectors) {
int s = sectors;
int sl = r10_bio->read_slot;
/* write it back and re-read */
rcu_read_lock();
while (sl != r10_bio->read_slot) {
+ char b[BDEVNAME_SIZE];
int d;
if (sl==0)
sl = conf->copies;
r10_bio->devs[sl].addr +
sect + rdev->data_offset,
s<<9, conf->tmppage, WRITE)
- == 0)
+ == 0) {
/* Well, this device is dead */
+ printk(KERN_NOTICE
+ "md/raid10:%s: read correction "
+ "write failed"
+ " (%d sectors at %llu on %s)\n",
+ mdname(mddev), s,
+ (unsigned long long)(sect+
+ rdev->data_offset),
+ bdevname(rdev->bdev, b));
+ printk(KERN_NOTICE "md/raid10:%s: %s: failing "
+ "drive\n",
+ mdname(mddev),
+ bdevname(rdev->bdev, b));
md_error(mddev, rdev);
+ }
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
}
if (sync_page_io(rdev->bdev,
r10_bio->devs[sl].addr +
sect + rdev->data_offset,
- s<<9, conf->tmppage, READ) == 0)
+ s<<9, conf->tmppage,
+ READ) == 0) {
/* Well, this device is dead */
+ printk(KERN_NOTICE
+ "md/raid10:%s: unable to read back "
+ "corrected sectors"
+ " (%d sectors at %llu on %s)\n",
+ mdname(mddev), s,
+ (unsigned long long)(sect+
+ rdev->data_offset),
+ bdevname(rdev->bdev, b));
+ printk(KERN_NOTICE "md/raid10:%s: %s: failing drive\n",
+ mdname(mddev),
+ bdevname(rdev->bdev, b));
+
md_error(mddev, rdev);
- else
+ } else {
printk(KERN_INFO
- "raid10:%s: read error corrected"
+ "md/raid10:%s: read error corrected"
" (%d sectors at %llu on %s)\n",
mdname(mddev), s,
(unsigned long long)(sect+
rdev->data_offset),
bdevname(rdev->bdev, b));
+ }
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
r10bio_t *r10_bio;
struct bio *bio;
unsigned long flags;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
struct list_head *head = &conf->retry_list;
int unplug=0;
mdk_rdev_t *rdev;
spin_unlock_irqrestore(&conf->device_lock, flags);
mddev = r10_bio->mddev;
- conf = mddev_to_conf(mddev);
+ conf = mddev->private;
if (test_bit(R10BIO_IsSync, &r10_bio->state)) {
sync_request_write(mddev, r10_bio);
unplug = 1;
mddev->ro ? IO_BLOCKED : NULL;
mirror = read_balance(conf, r10_bio);
if (mirror == -1) {
- printk(KERN_ALERT "raid10: %s: unrecoverable I/O"
+ printk(KERN_ALERT "md/raid10:%s: %s: unrecoverable I/O"
" read error for block %llu\n",
+ mdname(mddev),
bdevname(bio->bi_bdev,b),
(unsigned long long)r10_bio->sector);
raid_end_bio_io(r10_bio);
bio_put(bio);
} else {
- const int do_sync = bio_sync(r10_bio->master_bio);
+ const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO);
bio_put(bio);
rdev = conf->mirrors[mirror].rdev;
if (printk_ratelimit())
- printk(KERN_ERR "raid10: %s: redirecting sector %llu to"
+ printk(KERN_ERR "md/raid10:%s: %s: redirecting sector %llu to"
" another mirror\n",
+ mdname(mddev),
bdevname(rdev->bdev,b),
(unsigned long long)r10_bio->sector);
bio = bio_clone(r10_bio->master_bio, GFP_NOIO);
bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
+ rdev->data_offset;
bio->bi_bdev = rdev->bdev;
- bio->bi_rw = READ | do_sync;
+ bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
bio->bi_private = r10_bio;
bio->bi_end_io = raid10_end_read_request;
unplug = 1;
generic_make_request(bio);
}
}
+ cond_resched();
}
if (unplug)
unplug_slaves(mddev);
static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
r10bio_t *r10_bio;
struct bio *biolist = NULL, *bio;
sector_t max_sector, nr_sectors;
return 0;
skipped:
- max_sector = mddev->size << 1;
+ max_sector = mddev->dev_sectors;
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
max_sector = mddev->resync_max_sectors;
if (sector_nr >= max_sector) {
if (!go_faster && conf->nr_waiting)
msleep_interruptible(1000);
- bitmap_cond_end_sync(mddev->bitmap, sector_nr);
-
/* Again, very different code for resync and recovery.
* Both must result in an r10bio with a list of bios that
* have bi_end_io, bi_sector, bi_bdev set,
max_sync = RESYNC_PAGES << (PAGE_SHIFT-9);
if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
/* recovery... the complicated one */
- int i, j, k;
+ int j, k;
r10_bio = NULL;
for (i=0 ; i<conf->raid_disks; i++)
r10_bio->sector = sect;
raid10_find_phys(conf, r10_bio);
- /* Need to check if this section will still be
+
+ /* Need to check if the array will still be
* degraded
*/
- for (j=0; j<conf->copies;j++) {
- int d = r10_bio->devs[j].devnum;
- if (conf->mirrors[d].rdev == NULL ||
- test_bit(Faulty, &conf->mirrors[d].rdev->flags)) {
+ for (j=0; j<conf->raid_disks; j++)
+ if (conf->mirrors[j].rdev == NULL ||
+ test_bit(Faulty, &conf->mirrors[j].rdev->flags)) {
still_degraded = 1;
break;
}
- }
+
must_sync = bitmap_start_sync(mddev->bitmap, sect,
&sync_blocks, still_degraded);
r10_bio = rb2;
if (!test_and_set_bit(MD_RECOVERY_INTR,
&mddev->recovery))
- printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",
+ printk(KERN_INFO "md/raid10:%s: insufficient "
+ "working devices for recovery.\n",
mdname(mddev));
break;
}
/* resync. Schedule a read for every block at this virt offset */
int count = 0;
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
if (!bitmap_start_sync(mddev->bitmap, sector_nr,
&sync_blocks, mddev->degraded) &&
!conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
bio->bi_vcnt = 0;
bio->bi_idx = 0;
bio->bi_phys_segments = 0;
- bio->bi_hw_segments = 0;
bio->bi_size = 0;
}
/* There is nowhere to write, so all non-sync
* drives must be failed, so try the next chunk...
*/
- {
- sector_t sec = max_sector - sector_nr;
- sectors_skipped += sec;
+ if (sector_nr + max_sync < max_sector)
+ max_sector = sector_nr + max_sync;
+
+ sectors_skipped += (max_sector - sector_nr);
chunks_skipped ++;
sector_nr = max_sector;
goto skipped;
- }
}
-static int run(mddev_t *mddev)
+static sector_t
+raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
{
- conf_t *conf;
- int i, disk_idx;
- mirror_info_t *disk;
- mdk_rdev_t *rdev;
- struct list_head *tmp;
+ sector_t size;
+ conf_t *conf = mddev->private;
+
+ if (!raid_disks)
+ raid_disks = conf->raid_disks;
+ if (!sectors)
+ sectors = conf->dev_sectors;
+
+ size = sectors >> conf->chunk_shift;
+ sector_div(size, conf->far_copies);
+ size = size * raid_disks;
+ sector_div(size, conf->near_copies);
+
+ return size << conf->chunk_shift;
+}
+
+
+static conf_t *setup_conf(mddev_t *mddev)
+{
+ conf_t *conf = NULL;
int nc, fc, fo;
sector_t stride, size;
+ int err = -EINVAL;
- if (mddev->chunk_size == 0) {
- printk(KERN_ERR "md/raid10: non-zero chunk size required.\n");
- return -EINVAL;
+ if (mddev->chunk_sectors < (PAGE_SIZE >> 9) ||
+ !is_power_of_2(mddev->chunk_sectors)) {
+ printk(KERN_ERR "md/raid10:%s: chunk size must be "
+ "at least PAGE_SIZE(%ld) and be a power of 2.\n",
+ mdname(mddev), PAGE_SIZE);
+ goto out;
}
nc = mddev->layout & 255;
fc = (mddev->layout >> 8) & 255;
fo = mddev->layout & (1<<16);
+
if ((nc*fc) <2 || (nc*fc) > mddev->raid_disks ||
(mddev->layout >> 17)) {
- printk(KERN_ERR "raid10: %s: unsupported raid10 layout: 0x%8x\n",
+ printk(KERN_ERR "md/raid10:%s: unsupported raid10 layout: 0x%8x\n",
mdname(mddev), mddev->layout);
goto out;
}
- /*
- * copy the already verified devices into our private RAID10
- * bookkeeping area. [whatever we allocate in run(),
- * should be freed in stop()]
- */
+
+ err = -ENOMEM;
conf = kzalloc(sizeof(conf_t), GFP_KERNEL);
- mddev->private = conf;
- if (!conf) {
- printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
- mdname(mddev));
+ if (!conf)
goto out;
- }
+
conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks,
- GFP_KERNEL);
- if (!conf->mirrors) {
- printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
- mdname(mddev));
- goto out_free_conf;
- }
+ GFP_KERNEL);
+ if (!conf->mirrors)
+ goto out;
conf->tmppage = alloc_page(GFP_KERNEL);
if (!conf->tmppage)
- goto out_free_conf;
+ goto out;
+
- conf->mddev = mddev;
conf->raid_disks = mddev->raid_disks;
conf->near_copies = nc;
conf->far_copies = fc;
conf->copies = nc*fc;
conf->far_offset = fo;
- conf->chunk_mask = (sector_t)(mddev->chunk_size>>9)-1;
- conf->chunk_shift = ffz(~mddev->chunk_size) - 9;
- size = mddev->size >> (conf->chunk_shift-1);
+ conf->chunk_mask = mddev->new_chunk_sectors - 1;
+ conf->chunk_shift = ffz(~mddev->new_chunk_sectors);
+
+ conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
+ r10bio_pool_free, conf);
+ if (!conf->r10bio_pool)
+ goto out;
+
+ size = mddev->dev_sectors >> conf->chunk_shift;
sector_div(size, fc);
size = size * conf->raid_disks;
sector_div(size, nc);
*/
stride += conf->raid_disks - 1;
sector_div(stride, conf->raid_disks);
- mddev->size = stride << (conf->chunk_shift-1);
+
+ conf->dev_sectors = stride << conf->chunk_shift;
if (fo)
stride = 1;
sector_div(stride, fc);
conf->stride = stride << conf->chunk_shift;
- conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
- r10bio_pool_free, conf);
- if (!conf->r10bio_pool) {
- printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
- mdname(mddev));
- goto out_free_conf;
- }
spin_lock_init(&conf->device_lock);
+ INIT_LIST_HEAD(&conf->retry_list);
+
+ spin_lock_init(&conf->resync_lock);
+ init_waitqueue_head(&conf->wait_barrier);
+
+ conf->thread = md_register_thread(raid10d, mddev, NULL);
+ if (!conf->thread)
+ goto out;
+
+ conf->scale_disks = 0;
+ conf->mddev = mddev;
+ return conf;
+
+ out:
+ printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n",
+ mdname(mddev));
+ if (conf) {
+ if (conf->r10bio_pool)
+ mempool_destroy(conf->r10bio_pool);
+ kfree(conf->mirrors);
+ safe_put_page(conf->tmppage);
+ kfree(conf);
+ }
+ return ERR_PTR(err);
+}
+
+static int run(mddev_t *mddev)
+{
+ conf_t *conf;
+ int i, disk_idx, chunk_size;
+ mirror_info_t *disk;
+ mdk_rdev_t *rdev;
+ sector_t size;
+
+ /*
+ * copy the already verified devices into our private RAID10
+ * bookkeeping area. [whatever we allocate in run(),
+ * should be freed in stop()]
+ */
+
+ if (mddev->private == NULL) {
+ conf = setup_conf(mddev);
+ if (IS_ERR(conf))
+ return PTR_ERR(conf);
+ mddev->private = conf;
+ }
+ conf = mddev->private;
+ if (!conf)
+ goto out;
+
mddev->queue->queue_lock = &conf->device_lock;
- rdev_for_each(rdev, tmp, mddev) {
+ mddev->thread = conf->thread;
+ conf->thread = NULL;
+
+ chunk_size = mddev->chunk_sectors << 9;
+ blk_queue_io_min(mddev->queue, chunk_size);
+ if (conf->raid_disks % conf->near_copies)
+ blk_queue_io_opt(mddev->queue, chunk_size * conf->raid_disks);
+ else
+ blk_queue_io_opt(mddev->queue, chunk_size *
+ (conf->raid_disks / conf->near_copies));
+
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
disk_idx = rdev->raid_disk;
- if (disk_idx >= mddev->raid_disks
+ if (disk_idx >= conf->raid_disks
|| disk_idx < 0)
continue;
+ if (conf->scale_disks) {
+ disk_idx *= conf->scale_disks;
+ rdev->raid_disk = disk_idx;
+ /* MOVE 'rd%d' link !! */
+ }
disk = conf->mirrors + disk_idx;
disk->rdev = rdev;
-
- blk_queue_stack_limits(mddev->queue,
- rdev->bdev->bd_disk->queue);
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
/* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ * violating it, so limit max_segments to 1 lying
+ * within a single page.
*/
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- mddev->queue->max_sectors > (PAGE_SIZE>>9))
- mddev->queue->max_sectors = (PAGE_SIZE>>9);
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
disk->head_position = 0;
}
- INIT_LIST_HEAD(&conf->retry_list);
-
- spin_lock_init(&conf->resync_lock);
- init_waitqueue_head(&conf->wait_barrier);
-
/* need to check that every block has at least one working mirror */
if (!enough(conf)) {
- printk(KERN_ERR "raid10: not enough operational mirrors for %s\n",
+ printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",
mdname(mddev));
goto out_free_conf;
}
}
}
-
- mddev->thread = md_register_thread(raid10d, mddev, "%s_raid10");
- if (!mddev->thread) {
- printk(KERN_ERR
- "raid10: couldn't allocate thread for %s\n",
+ if (mddev->recovery_cp != MaxSector)
+ printk(KERN_NOTICE "md/raid10:%s: not clean"
+ " -- starting background reconstruction\n",
mdname(mddev));
- goto out_free_conf;
- }
-
printk(KERN_INFO
- "raid10: raid set %s active with %d out of %d devices\n",
- mdname(mddev), mddev->raid_disks - mddev->degraded,
- mddev->raid_disks);
+ "md/raid10:%s: active with %d out of %d devices\n",
+ mdname(mddev), conf->raid_disks - mddev->degraded,
+ conf->raid_disks);
/*
* Ok, everything is just fine now
*/
- mddev->array_size = size << (conf->chunk_shift-1);
- mddev->resync_max_sectors = size << conf->chunk_shift;
+ mddev->dev_sectors = conf->dev_sectors;
+ size = raid10_size(mddev, 0, 0);
+ md_set_array_sectors(mddev, size);
+ mddev->resync_max_sectors = size;
mddev->queue->unplug_fn = raid10_unplug;
mddev->queue->backing_dev_info.congested_fn = raid10_congested;
* maybe...
*/
{
- int stripe = conf->raid_disks * (mddev->chunk_size / PAGE_SIZE);
+ int stripe = conf->raid_disks *
+ ((mddev->chunk_sectors << 9) / PAGE_SIZE);
stripe /= conf->near_copies;
if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
mddev->queue->backing_dev_info.ra_pages = 2* stripe;
}
- if (conf->near_copies < mddev->raid_disks)
+ if (conf->near_copies < conf->raid_disks)
blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
+ md_integrity_register(mddev);
return 0;
out_free_conf:
kfree(conf->mirrors);
kfree(conf);
mddev->private = NULL;
+ md_unregister_thread(mddev->thread);
out:
return -EIO;
}
static int stop(mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
+
+ raise_barrier(conf, 0);
+ lower_barrier(conf);
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
static void raid10_quiesce(mddev_t *mddev, int state)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
switch(state) {
case 1:
lower_barrier(conf);
break;
}
- if (mddev->thread) {
- if (mddev->bitmap)
- mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
- else
- mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
- md_wakeup_thread(mddev->thread);
+}
+
+static void *raid10_takeover_raid0(mddev_t *mddev)
+{
+ mdk_rdev_t *rdev;
+ conf_t *conf;
+
+ if (mddev->degraded > 0) {
+ printk(KERN_ERR "md/raid10:%s: Error: degraded raid0!\n",
+ mdname(mddev));
+ return ERR_PTR(-EINVAL);
+ }
+
+ /* Update slot numbers to obtain
+ * degraded raid10 with missing mirrors
+ */
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ rdev->raid_disk *= 2;
+ }
+
+ /* Set new parameters */
+ mddev->new_level = 10;
+ /* new layout: far_copies = 1, near_copies = 2 */
+ mddev->new_layout = (1<<8) + 2;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
+ mddev->delta_disks = mddev->raid_disks;
+ mddev->degraded = mddev->raid_disks;
+ mddev->raid_disks *= 2;
+ /* make sure it will be not marked as dirty */
+ mddev->recovery_cp = MaxSector;
+
+ conf = setup_conf(mddev);
+ conf->scale_disks = 2;
+ return conf;
+}
+
+static void *raid10_takeover(mddev_t *mddev)
+{
+ struct raid0_private_data *raid0_priv;
+
+ /* raid10 can take over:
+ * raid0 - providing it has only two drives
+ */
+ if (mddev->level == 0) {
+ /* for raid0 takeover only one zone is supported */
+ raid0_priv = mddev->private;
+ if (raid0_priv->nr_strip_zones > 1) {
+ printk(KERN_ERR "md/raid10:%s: cannot takeover raid 0"
+ " with more than one zone.\n",
+ mdname(mddev));
+ return ERR_PTR(-EINVAL);
+ }
+ return raid10_takeover_raid0(mddev);
}
+ return ERR_PTR(-EINVAL);
}
static struct mdk_personality raid10_personality =
.spare_active = raid10_spare_active,
.sync_request = sync_request,
.quiesce = raid10_quiesce,
+ .size = raid10_size,
+ .takeover = raid10_takeover,
};
static int __init raid_init(void)
module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD");
MODULE_ALIAS("md-personality-9"); /* RAID10 */
MODULE_ALIAS("md-raid10");
MODULE_ALIAS("md-level-10");