* 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/delay.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid10.h"
+#include "bitmap.h"
/*
* RAID10 provides a combination of RAID0 and RAID1 functionality.
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;
}
* 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)
{
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);
/* 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);
if (!enough(conf))
return -EINVAL;
- if (rdev->raid_disk)
+ if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
if (rdev->saved_raid_disk >= 0 &&
/* 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)
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);
}
/*
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;
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,
/* 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 sector_t
+raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+ sector_t size;
+ conf_t *conf = mddev_to_conf(mddev);
+
+ if (!raid_disks)
+ raid_disks = mddev->raid_disks;
+ if (!sectors)
+ sectors = mddev->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 int run(mddev_t *mddev)
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;
}
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);
+ 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);
+ mddev->dev_sectors = stride << conf->chunk_shift;
if (fo)
stride = 1;
spin_lock_init(&conf->device_lock);
mddev->queue->queue_lock = &conf->device_lock;
- rdev_for_each(rdev, tmp, mddev) {
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
/*
* Ok, everything is just fine now
*/
- mddev->array_size = size << (conf->chunk_shift-1);
- mddev->resync_max_sectors = size << conf->chunk_shift;
+ md_set_array_sectors(mddev, raid10_size(mddev, 0, 0));
+ mddev->resync_max_sectors = raid10_size(mddev, 0, 0);
mddev->queue->unplug_fn = raid10_unplug;
mddev->queue->backing_dev_info.congested_fn = raid10_congested;
{
conf_t *conf = mddev_to_conf(mddev);
+ raise_barrier(conf, 0);
+ lower_barrier(conf);
+
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
.spare_active = raid10_spare_active,
.sync_request = sync_request,
.quiesce = raid10_quiesce,
+ .size = raid10_size,
};
static int __init raid_init(void)