* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/blkdev.h>
#include <linux/seq_file.h>
/* 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;
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;
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++) {
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
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;
}
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);
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) {
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 &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, 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;
break;
}
+ md_integrity_add_rdev(rdev, mddev);
print_conf(conf);
return err;
}
/* lost the race, try later */
err = -EBUSY;
p->rdev = rdev;
+ goto abort;
}
+ md_integrity_register(mddev);
}
abort:
/*
+ * 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
+ "raid10: %s: Raid device exceeded "
+ "read_error threshold "
+ "[cur %d:max %d]\n",
+ b, cur_read_error_count, max_read_errors);
+ printk(KERN_NOTICE
+ "raid10: %s: Failing raid "
+ "device\n", 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
+ "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 "raid10:%s: failing "
+ "drive\n",
+ 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
+ "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 "raid10:%s: failing drive\n",
+ bdevname(rdev->bdev, b));
+
md_error(mddev, rdev);
- else
+ } else {
printk(KERN_INFO
"raid10:%s: read error corrected"
" (%d sectors at %llu on %s)\n",
(unsigned long long)(sect+
rdev->data_offset),
bdevname(rdev->bdev, b));
+ }
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
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())
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);
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++)
static int run(mddev_t *mddev)
{
conf_t *conf;
- int i, disk_idx;
+ int i, disk_idx, chunk_size;
mirror_info_t *disk;
mdk_rdev_t *rdev;
int nc, fc, fo;
sector_t stride, size;
- if (mddev->chunk_size < PAGE_SIZE) {
+ if (mddev->chunk_sectors < (PAGE_SIZE >> 9) ||
+ !is_power_of_2(mddev->chunk_sectors)) {
printk(KERN_ERR "md/raid10: chunk size must be "
- "at least PAGE_SIZE(%ld).\n", PAGE_SIZE);
+ "at least PAGE_SIZE(%ld) and be a power of 2.\n", PAGE_SIZE);
return -EINVAL;
}
if (!conf->tmppage)
goto out_free_conf;
- 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;
+ conf->chunk_mask = mddev->chunk_sectors - 1;
+ conf->chunk_shift = ffz(~mddev->chunk_sectors);
size = mddev->dev_sectors >> conf->chunk_shift;
sector_div(size, fc);
size = size * conf->raid_disks;
goto out_free_conf;
}
+ conf->mddev = mddev;
spin_lock_init(&conf->device_lock);
mddev->queue->queue_lock = &conf->device_lock;
+ 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
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 &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, 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;
}
}
- mddev->thread = md_register_thread(raid10d, mddev, "%s_raid10");
+ mddev->thread = md_register_thread(raid10d, mddev, NULL);
if (!mddev->thread) {
printk(KERN_ERR
"raid10: couldn't allocate thread for %s\n",
goto out_free_conf;
}
+ if (mddev->recovery_cp != MaxSector)
+ printk(KERN_NOTICE "raid10: %s is not clean"
+ " -- starting background reconstruction\n",
+ mdname(mddev));
printk(KERN_INFO
"raid10: raid set %s active with %d out of %d devices\n",
mdname(mddev), mddev->raid_disks - mddev->degraded,
* 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)
blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
+ md_integrity_register(mddev);
return 0;
out_free_conf:
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 struct mdk_personality raid10_personality =
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");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff