#include <linux/delay.h>
#include <linux/blkdev.h>
#include <linux/seq_file.h>
+#include <linux/ratelimit.h>
#include "md.h"
#include "raid1.h"
#include "bitmap.h"
#define DEBUG 0
-#if DEBUG
-#define PRINTK(x...) printk(x)
-#else
-#define PRINTK(x...)
-#endif
+#define PRINTK(x...) do { if (DEBUG) printk(x); } while (0)
/*
* Number of guaranteed r1bios in case of extreme VM load:
for (i = 0; i < conf->raid_disks; i++) {
struct bio **bio = r1_bio->bios + i;
- if (*bio && *bio != IO_BLOCKED)
+ if (!BIO_SPECIAL(*bio))
bio_put(*bio);
*bio = NULL;
}
{
conf_t *conf = r1_bio->mddev->private;
- /*
- * Wake up any possible resync thread that waits for the device
- * to go idle.
- */
- allow_barrier(conf);
-
put_all_bios(conf, r1_bio);
mempool_free(r1_bio, conf->r1bio_pool);
}
* operation and are ready to return a success/failure code to the buffer
* cache layer.
*/
+static void call_bio_endio(r1bio_t *r1_bio)
+{
+ struct bio *bio = r1_bio->master_bio;
+ int done;
+ conf_t *conf = r1_bio->mddev->private;
+
+ if (bio->bi_phys_segments) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
+ bio->bi_phys_segments--;
+ done = (bio->bi_phys_segments == 0);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ } else
+ done = 1;
+
+ if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ if (done) {
+ bio_endio(bio, 0);
+ /*
+ * Wake up any possible resync thread that waits for the device
+ * to go idle.
+ */
+ allow_barrier(conf);
+ }
+}
+
static void raid_end_bio_io(r1bio_t *r1_bio)
{
struct bio *bio = r1_bio->master_bio;
(unsigned long long) bio->bi_sector +
(bio->bi_size >> 9) - 1);
- bio_endio(bio,
- test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
+ call_bio_endio(r1_bio);
}
free_r1bio(r1_bio);
}
* oops, read error:
*/
char b[BDEVNAME_SIZE];
- if (printk_ratelimit())
- printk(KERN_ERR "md/raid1:%s: %s: rescheduling sector %llu\n",
- mdname(conf->mddev),
- bdevname(conf->mirrors[mirror].rdev->bdev,b), (unsigned long long)r1_bio->sector);
+ printk_ratelimited(
+ KERN_ERR "md/raid1:%s: %s: "
+ "rescheduling sector %llu\n",
+ mdname(conf->mddev),
+ bdevname(conf->mirrors[mirror].rdev->bdev,
+ b),
+ (unsigned long long)r1_bio->sector);
+ set_bit(R1BIO_ReadError, &r1_bio->state);
reschedule_retry(r1_bio);
}
/* free extra copy of the data pages */
int i = r1_bio->behind_page_count;
while (i--)
- safe_put_page(r1_bio->behind_pages[i]);
- kfree(r1_bio->behind_pages);
- r1_bio->behind_pages = NULL;
+ safe_put_page(r1_bio->behind_bvecs[i].bv_page);
+ kfree(r1_bio->behind_bvecs);
+ r1_bio->behind_bvecs = NULL;
}
/* clear the bitmap if all writes complete successfully */
bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
!test_bit(R1BIO_Degraded, &r1_bio->state),
test_bit(R1BIO_BehindIO, &r1_bio->state));
md_write_end(r1_bio->mddev);
- raid_end_bio_io(r1_bio);
+ if (test_bit(R1BIO_MadeGood, &r1_bio->state))
+ reschedule_retry(r1_bio);
+ else
+ raid_end_bio_io(r1_bio);
}
}
md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
/* an I/O failed, we can't clear the bitmap */
set_bit(R1BIO_Degraded, &r1_bio->state);
- } else
+ } else {
/*
* Set R1BIO_Uptodate in our master bio, so that we
* will return a good error code for to the higher
* to user-side. So if something waits for IO, then it
* will wait for the 'master' bio.
*/
+ sector_t first_bad;
+ int bad_sectors;
+
set_bit(R1BIO_Uptodate, &r1_bio->state);
+ /* Maybe we can clear some bad blocks. */
+ if (is_badblock(conf->mirrors[mirror].rdev,
+ r1_bio->sector, r1_bio->sectors,
+ &first_bad, &bad_sectors)) {
+ r1_bio->bios[mirror] = IO_MADE_GOOD;
+ set_bit(R1BIO_MadeGood, &r1_bio->state);
+ }
+ }
+
update_head_pos(mirror, r1_bio);
if (behind) {
(unsigned long long) mbio->bi_sector,
(unsigned long long) mbio->bi_sector +
(mbio->bi_size >> 9) - 1);
- bio_endio(mbio, 0);
+ call_bio_endio(r1_bio);
}
}
}
- rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+ if (r1_bio->bios[mirror] == NULL)
+ rdev_dec_pending(conf->mirrors[mirror].rdev,
+ conf->mddev);
/*
* Let's see if all mirrored write operations have finished
*
* The rdev for the device selected will have nr_pending incremented.
*/
-static int read_balance(conf_t *conf, r1bio_t *r1_bio)
+static int read_balance(conf_t *conf, r1bio_t *r1_bio, int *max_sectors)
{
const sector_t this_sector = r1_bio->sector;
- const int sectors = r1_bio->sectors;
+ int sectors;
+ int best_good_sectors;
int start_disk;
int best_disk;
int i;
* We take the first readable disk when above the resync window.
*/
retry:
+ sectors = r1_bio->sectors;
best_disk = -1;
best_dist = MaxSector;
+ best_good_sectors = 0;
+
if (conf->mddev->recovery_cp < MaxSector &&
(this_sector + sectors >= conf->next_resync)) {
choose_first = 1;
for (i = 0 ; i < conf->raid_disks ; i++) {
sector_t dist;
+ sector_t first_bad;
+ int bad_sectors;
+
int disk = start_disk + i;
if (disk >= conf->raid_disks)
disk -= conf->raid_disks;
/* This is a reasonable device to use. It might
* even be best.
*/
+ if (is_badblock(rdev, this_sector, sectors,
+ &first_bad, &bad_sectors)) {
+ if (best_dist < MaxSector)
+ /* already have a better device */
+ continue;
+ if (first_bad <= this_sector) {
+ /* cannot read here. If this is the 'primary'
+ * device, then we must not read beyond
+ * bad_sectors from another device..
+ */
+ bad_sectors -= (this_sector - first_bad);
+ if (choose_first && sectors > bad_sectors)
+ sectors = bad_sectors;
+ if (best_good_sectors > sectors)
+ best_good_sectors = sectors;
+
+ } else {
+ sector_t good_sectors = first_bad - this_sector;
+ if (good_sectors > best_good_sectors) {
+ best_good_sectors = good_sectors;
+ best_disk = disk;
+ }
+ if (choose_first)
+ break;
+ }
+ continue;
+ } else
+ best_good_sectors = sectors;
+
dist = abs(this_sector - conf->mirrors[disk].head_position);
if (choose_first
/* Don't change to another disk for sequential reads */
rdev_dec_pending(rdev, conf->mddev);
goto retry;
}
+ sectors = best_good_sectors;
conf->next_seq_sect = this_sector + sectors;
conf->last_used = best_disk;
}
rcu_read_unlock();
+ *max_sectors = sectors;
return best_disk;
}
{
int i;
struct bio_vec *bvec;
- struct page **pages = kzalloc(bio->bi_vcnt * sizeof(struct page*),
+ struct bio_vec *bvecs = kzalloc(bio->bi_vcnt * sizeof(struct bio_vec),
GFP_NOIO);
- if (unlikely(!pages))
+ if (unlikely(!bvecs))
return;
bio_for_each_segment(bvec, bio, i) {
- pages[i] = alloc_page(GFP_NOIO);
- if (unlikely(!pages[i]))
+ bvecs[i] = *bvec;
+ bvecs[i].bv_page = alloc_page(GFP_NOIO);
+ if (unlikely(!bvecs[i].bv_page))
goto do_sync_io;
- memcpy(kmap(pages[i]) + bvec->bv_offset,
- kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len);
- kunmap(pages[i]);
+ memcpy(kmap(bvecs[i].bv_page) + bvec->bv_offset,
+ kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len);
+ kunmap(bvecs[i].bv_page);
kunmap(bvec->bv_page);
}
- r1_bio->behind_pages = pages;
+ r1_bio->behind_bvecs = bvecs;
r1_bio->behind_page_count = bio->bi_vcnt;
set_bit(R1BIO_BehindIO, &r1_bio->state);
return;
do_sync_io:
for (i = 0; i < bio->bi_vcnt; i++)
- if (pages[i])
- put_page(pages[i]);
- kfree(pages);
+ if (bvecs[i].bv_page)
+ put_page(bvecs[i].bv_page);
+ kfree(bvecs);
PRINTK("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
}
mirror_info_t *mirror;
r1bio_t *r1_bio;
struct bio *read_bio;
- int i, targets = 0, disks;
+ int i, disks;
struct bitmap *bitmap;
unsigned long flags;
const int rw = bio_data_dir(bio);
const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
mdk_rdev_t *blocked_rdev;
int plugged;
+ int first_clone;
+ int sectors_handled;
+ int max_sectors;
/*
* Register the new request and wait if the reconstruction
r1_bio->mddev = mddev;
r1_bio->sector = bio->bi_sector;
+ /* We might need to issue multiple reads to different
+ * devices if there are bad blocks around, so we keep
+ * track of the number of reads in bio->bi_phys_segments.
+ * If this is 0, there is only one r1_bio and no locking
+ * will be needed when requests complete. If it is
+ * non-zero, then it is the number of not-completed requests.
+ */
+ bio->bi_phys_segments = 0;
+ clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+
if (rw == READ) {
/*
* read balancing logic:
*/
- int rdisk = read_balance(conf, r1_bio);
+ int rdisk;
+
+read_again:
+ rdisk = read_balance(conf, r1_bio, &max_sectors);
if (rdisk < 0) {
/* couldn't find anywhere to read from */
r1_bio->read_disk = rdisk;
read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+ md_trim_bio(read_bio, r1_bio->sector - bio->bi_sector,
+ max_sectors);
r1_bio->bios[rdisk] = read_bio;
read_bio->bi_rw = READ | do_sync;
read_bio->bi_private = r1_bio;
- generic_make_request(read_bio);
+ if (max_sectors < r1_bio->sectors) {
+ /* could not read all from this device, so we will
+ * need another r1_bio.
+ */
+
+ sectors_handled = (r1_bio->sector + max_sectors
+ - bio->bi_sector);
+ r1_bio->sectors = max_sectors;
+ spin_lock_irq(&conf->device_lock);
+ if (bio->bi_phys_segments == 0)
+ bio->bi_phys_segments = 2;
+ else
+ bio->bi_phys_segments++;
+ spin_unlock_irq(&conf->device_lock);
+ /* Cannot call generic_make_request directly
+ * as that will be queued in __make_request
+ * and subsequent mempool_alloc might block waiting
+ * for it. So hand bio over to raid1d.
+ */
+ reschedule_retry(r1_bio);
+
+ r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+
+ r1_bio->master_bio = bio;
+ r1_bio->sectors = (bio->bi_size >> 9) - sectors_handled;
+ r1_bio->state = 0;
+ r1_bio->mddev = mddev;
+ r1_bio->sector = bio->bi_sector + sectors_handled;
+ goto read_again;
+ } else
+ generic_make_request(read_bio);
return 0;
}
/*
* 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
+ * If there are known/acknowledged bad blocks on any device on
+ * which we have seen a write error, we want to avoid writing those
+ * blocks.
+ * This potentially requires several writes to write around
+ * the bad blocks. Each set of writes gets it's own r1bio
+ * with a set of bios attached.
*/
plugged = mddev_check_plugged(mddev);
retry_write:
blocked_rdev = NULL;
rcu_read_lock();
+ max_sectors = r1_bio->sectors;
for (i = 0; i < disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
blocked_rdev = rdev;
break;
}
- if (rdev && !test_bit(Faulty, &rdev->flags)) {
- atomic_inc(&rdev->nr_pending);
- if (test_bit(Faulty, &rdev->flags)) {
+ r1_bio->bios[i] = NULL;
+ if (!rdev || test_bit(Faulty, &rdev->flags)) {
+ set_bit(R1BIO_Degraded, &r1_bio->state);
+ continue;
+ }
+
+ atomic_inc(&rdev->nr_pending);
+ if (test_bit(WriteErrorSeen, &rdev->flags)) {
+ sector_t first_bad;
+ int bad_sectors;
+ int is_bad;
+
+ is_bad = is_badblock(rdev, r1_bio->sector,
+ max_sectors,
+ &first_bad, &bad_sectors);
+ if (is_bad < 0) {
+ /* mustn't write here until the bad block is
+ * acknowledged*/
+ set_bit(BlockedBadBlocks, &rdev->flags);
+ blocked_rdev = rdev;
+ break;
+ }
+ if (is_bad && first_bad <= r1_bio->sector) {
+ /* Cannot write here at all */
+ bad_sectors -= (r1_bio->sector - first_bad);
+ if (bad_sectors < max_sectors)
+ /* mustn't write more than bad_sectors
+ * to other devices yet
+ */
+ max_sectors = bad_sectors;
rdev_dec_pending(rdev, mddev);
- r1_bio->bios[i] = NULL;
- } else {
- r1_bio->bios[i] = bio;
- targets++;
+ /* We don't set R1BIO_Degraded as that
+ * only applies if the disk is
+ * missing, so it might be re-added,
+ * and we want to know to recover this
+ * chunk.
+ * In this case the device is here,
+ * and the fact that this chunk is not
+ * in-sync is recorded in the bad
+ * block log
+ */
+ continue;
}
- } else
- r1_bio->bios[i] = NULL;
+ if (is_bad) {
+ int good_sectors = first_bad - r1_bio->sector;
+ if (good_sectors < max_sectors)
+ max_sectors = good_sectors;
+ }
+ }
+ r1_bio->bios[i] = bio;
}
rcu_read_unlock();
for (j = 0; j < i; j++)
if (r1_bio->bios[j])
rdev_dec_pending(conf->mirrors[j].rdev, mddev);
-
+ r1_bio->state = 0;
allow_barrier(conf);
md_wait_for_blocked_rdev(blocked_rdev, mddev);
wait_barrier(conf);
goto retry_write;
}
- BUG_ON(targets == 0); /* we never fail the last device */
-
- if (targets < conf->raid_disks) {
- /* array is degraded, we will not clear the bitmap
- * on I/O completion (see raid1_end_write_request) */
- set_bit(R1BIO_Degraded, &r1_bio->state);
+ if (max_sectors < r1_bio->sectors) {
+ /* We are splitting this write into multiple parts, so
+ * we need to prepare for allocating another r1_bio.
+ */
+ r1_bio->sectors = max_sectors;
+ spin_lock_irq(&conf->device_lock);
+ if (bio->bi_phys_segments == 0)
+ bio->bi_phys_segments = 2;
+ else
+ bio->bi_phys_segments++;
+ spin_unlock_irq(&conf->device_lock);
}
-
- /* do behind I/O ?
- * Not if there are too many, or cannot allocate memory,
- * or a reader on WriteMostly is waiting for behind writes
- * to flush */
- if (bitmap &&
- (atomic_read(&bitmap->behind_writes)
- < mddev->bitmap_info.max_write_behind) &&
- !waitqueue_active(&bitmap->behind_wait))
- alloc_behind_pages(bio, r1_bio);
+ sectors_handled = r1_bio->sector + max_sectors - bio->bi_sector;
atomic_set(&r1_bio->remaining, 1);
atomic_set(&r1_bio->behind_remaining, 0);
- bitmap_startwrite(bitmap, bio->bi_sector, r1_bio->sectors,
- test_bit(R1BIO_BehindIO, &r1_bio->state));
+ first_clone = 1;
for (i = 0; i < disks; i++) {
struct bio *mbio;
if (!r1_bio->bios[i])
continue;
mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- r1_bio->bios[i] = mbio;
-
- mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset;
- mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
- mbio->bi_end_io = raid1_end_write_request;
- mbio->bi_rw = WRITE | do_flush_fua | do_sync;
- mbio->bi_private = r1_bio;
-
- if (r1_bio->behind_pages) {
+ md_trim_bio(mbio, r1_bio->sector - bio->bi_sector, max_sectors);
+
+ if (first_clone) {
+ /* do behind I/O ?
+ * Not if there are too many, or cannot
+ * allocate memory, or a reader on WriteMostly
+ * is waiting for behind writes to flush */
+ if (bitmap &&
+ (atomic_read(&bitmap->behind_writes)
+ < mddev->bitmap_info.max_write_behind) &&
+ !waitqueue_active(&bitmap->behind_wait))
+ alloc_behind_pages(mbio, r1_bio);
+
+ bitmap_startwrite(bitmap, r1_bio->sector,
+ r1_bio->sectors,
+ test_bit(R1BIO_BehindIO,
+ &r1_bio->state));
+ first_clone = 0;
+ }
+ if (r1_bio->behind_bvecs) {
struct bio_vec *bvec;
int j;
* them all
*/
__bio_for_each_segment(bvec, mbio, j, 0)
- bvec->bv_page = r1_bio->behind_pages[j];
+ bvec->bv_page = r1_bio->behind_bvecs[j].bv_page;
if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
atomic_inc(&r1_bio->behind_remaining);
}
+ r1_bio->bios[i] = mbio;
+
+ mbio->bi_sector = (r1_bio->sector +
+ conf->mirrors[i].rdev->data_offset);
+ mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
+ mbio->bi_end_io = raid1_end_write_request;
+ mbio->bi_rw = WRITE | do_flush_fua | do_sync;
+ mbio->bi_private = r1_bio;
+
atomic_inc(&r1_bio->remaining);
spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
/* In case raid1d snuck in to freeze_array */
wake_up(&conf->wait_barrier);
+ if (sectors_handled < (bio->bi_size >> 9)) {
+ /* We need another r1_bio. It has already been counted
+ * in bio->bi_phys_segments
+ */
+ r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+ r1_bio->master_bio = bio;
+ r1_bio->sectors = (bio->bi_size >> 9) - sectors_handled;
+ r1_bio->state = 0;
+ r1_bio->mddev = mddev;
+ r1_bio->sector = bio->bi_sector + sectors_handled;
+ goto retry_write;
+ }
+
if (do_sync || !bitmap || !plugged)
md_wakeup_thread(mddev->thread);
* However don't try a recovery from this drive as
* it is very likely to fail.
*/
- mddev->recovery_disabled = 1;
+ conf->recovery_disabled = mddev->recovery_disabled;
return;
}
+ set_bit(Blocked, &rdev->flags);
if (test_and_clear_bit(In_sync, &rdev->flags)) {
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
&& !test_bit(Faulty, &rdev->flags)
&& !test_and_set_bit(In_sync, &rdev->flags)) {
count++;
- sysfs_notify_dirent(rdev->sysfs_state);
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
}
}
spin_lock_irqsave(&conf->device_lock, flags);
int first = 0;
int last = mddev->raid_disks - 1;
+ if (mddev->recovery_disabled == conf->recovery_disabled)
+ return -EBUSY;
+
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
* is not possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
- !mddev->recovery_disabled &&
+ mddev->recovery_disabled != conf->recovery_disabled &&
mddev->degraded < conf->raid_disks) {
err = -EBUSY;
goto abort;
conf_t *conf = mddev->private;
int i;
int mirror=0;
+ sector_t first_bad;
+ int bad_sectors;
for (i = 0; i < conf->raid_disks; i++)
if (r1_bio->bios[i] == bio) {
sectors_to_go -= sync_blocks;
} while (sectors_to_go > 0);
md_error(mddev, conf->mirrors[mirror].rdev);
- }
+ } else if (is_badblock(conf->mirrors[mirror].rdev,
+ r1_bio->sector,
+ r1_bio->sectors,
+ &first_bad, &bad_sectors))
+ set_bit(R1BIO_MadeGood, &r1_bio->state);
update_head_pos(mirror, r1_bio);
if (atomic_dec_and_test(&r1_bio->remaining)) {
- sector_t s = r1_bio->sectors;
- put_buf(r1_bio);
- md_done_sync(mddev, s, uptodate);
+ int s = r1_bio->sectors;
+ if (test_bit(R1BIO_MadeGood, &r1_bio->state))
+ reschedule_retry(r1_bio);
+ else {
+ put_buf(r1_bio);
+ md_done_sync(mddev, s, uptodate);
+ }
}
}
* We don't need to freeze the array, because being in an
* active sync request, there is no normal IO, and
* no overlapping syncs.
+ * We don't need to check is_badblock() again as we
+ * made sure that anything with a bad block in range
+ * will have bi_end_io clear.
*/
mddev_t *mddev = r1_bio->mddev;
conf_t *conf = mddev->private;
* active, and resync is currently active
*/
rdev = conf->mirrors[d].rdev;
- if (sync_page_io(rdev,
- sect,
- s<<9,
+ if (sync_page_io(rdev, sect, s<<9,
bio->bi_io_vec[idx].bv_page,
READ, false)) {
success = 1;
if (r1_bio->bios[d]->bi_end_io != end_sync_read)
continue;
rdev = conf->mirrors[d].rdev;
- if (sync_page_io(rdev,
- sect,
- s<<9,
+ if (sync_page_io(rdev, sect, s<<9,
bio->bi_io_vec[idx].bv_page,
WRITE, false) == 0) {
r1_bio->bios[d]->bi_end_io = NULL;
rdev_dec_pending(rdev, mddev);
md_error(mddev, rdev);
- } else
- atomic_add(s, &rdev->corrected_errors);
+ }
}
d = start;
while (d != r1_bio->read_disk) {
if (r1_bio->bios[d]->bi_end_io != end_sync_read)
continue;
rdev = conf->mirrors[d].rdev;
- if (sync_page_io(rdev,
- sect,
- s<<9,
+ if (sync_page_io(rdev, sect, s<<9,
bio->bi_io_vec[idx].bv_page,
READ, false) == 0)
md_error(mddev, rdev);
+ else
+ atomic_add(s, &rdev->corrected_errors);
}
sectors -= s;
sect += s;
*
* 1. Retries failed read operations on working mirrors.
* 2. Updates the raid superblock when problems encounter.
- * 3. Performs writes following reads for array syncronising.
+ * 3. Performs writes following reads for array synchronising.
*/
static void fix_read_error(conf_t *conf, int read_disk,
* which is the thread that might remove
* a device. If raid1d ever becomes multi-threaded....
*/
+ sector_t first_bad;
+ int bad_sectors;
+
rdev = conf->mirrors[d].rdev;
if (rdev &&
test_bit(In_sync, &rdev->flags) &&
+ is_badblock(rdev, sect, s,
+ &first_bad, &bad_sectors) == 0 &&
sync_page_io(rdev, sect, s<<9,
conf->tmppage, READ, false))
success = 1;
mddev = r1_bio->mddev;
conf = mddev->private;
- if (test_bit(R1BIO_IsSync, &r1_bio->state))
- sync_request_write(mddev, r1_bio);
- else {
+ if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
+ if (test_bit(R1BIO_MadeGood, &r1_bio->state)) {
+ int m;
+ int s = r1_bio->sectors;
+ for (m = 0; m < conf->raid_disks ; m++) {
+ struct bio *bio = r1_bio->bios[m];
+ if (bio->bi_end_io != NULL &&
+ test_bit(BIO_UPTODATE,
+ &bio->bi_flags)) {
+ rdev = conf->mirrors[m].rdev;
+ rdev_clear_badblocks(
+ rdev,
+ r1_bio->sector,
+ r1_bio->sectors);
+ }
+ }
+ put_buf(r1_bio);
+ md_done_sync(mddev, s, 1);
+ } else
+ sync_request_write(mddev, r1_bio);
+ } else if (test_bit(R1BIO_MadeGood, &r1_bio->state)) {
+ int m;
+ for (m = 0; m < conf->raid_disks ; m++)
+ if (r1_bio->bios[m] == IO_MADE_GOOD) {
+ rdev = conf->mirrors[m].rdev;
+ rdev_clear_badblocks(
+ rdev,
+ r1_bio->sector,
+ r1_bio->sectors);
+ rdev_dec_pending(rdev, mddev);
+ }
+ raid_end_bio_io(r1_bio);
+ } else if (test_bit(R1BIO_ReadError, &r1_bio->state)) {
int disk;
+ int max_sectors;
+ clear_bit(R1BIO_ReadError, &r1_bio->state);
/* we got a read error. Maybe the drive is bad. Maybe just
* the block and we can fix it.
* We freeze all other IO, and try reading the block from
conf->mirrors[r1_bio->read_disk].rdev);
bio = r1_bio->bios[r1_bio->read_disk];
- if ((disk=read_balance(conf, r1_bio)) == -1) {
+ bdevname(bio->bi_bdev, b);
+read_more:
+ disk = read_balance(conf, r1_bio, &max_sectors);
+ if (disk == -1) {
printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O"
" read error for block %llu\n",
- mdname(mddev),
- bdevname(bio->bi_bdev,b),
+ mdname(mddev), b,
(unsigned long long)r1_bio->sector);
raid_end_bio_io(r1_bio);
} else {
const unsigned long do_sync = r1_bio->master_bio->bi_rw & REQ_SYNC;
- r1_bio->bios[r1_bio->read_disk] =
- mddev->ro ? IO_BLOCKED : NULL;
+ if (bio) {
+ r1_bio->bios[r1_bio->read_disk] =
+ mddev->ro ? IO_BLOCKED : NULL;
+ bio_put(bio);
+ }
r1_bio->read_disk = disk;
- bio_put(bio);
bio = bio_clone_mddev(r1_bio->master_bio,
GFP_NOIO, mddev);
+ md_trim_bio(bio,
+ r1_bio->sector - bio->bi_sector,
+ max_sectors);
r1_bio->bios[r1_bio->read_disk] = bio;
rdev = conf->mirrors[disk].rdev;
- if (printk_ratelimit())
- printk(KERN_ERR "md/raid1:%s: redirecting sector %llu to"
- " other mirror: %s\n",
- mdname(mddev),
- (unsigned long long)r1_bio->sector,
- bdevname(rdev->bdev,b));
+ printk_ratelimited(
+ KERN_ERR
+ "md/raid1:%s: redirecting sector %llu"
+ " to other mirror: %s\n",
+ mdname(mddev),
+ (unsigned long long)r1_bio->sector,
+ bdevname(rdev->bdev, b));
bio->bi_sector = r1_bio->sector + rdev->data_offset;
bio->bi_bdev = rdev->bdev;
bio->bi_end_io = raid1_end_read_request;
bio->bi_rw = READ | do_sync;
bio->bi_private = r1_bio;
- generic_make_request(bio);
+ if (max_sectors < r1_bio->sectors) {
+ /* Drat - have to split this up more */
+ struct bio *mbio = r1_bio->master_bio;
+ int sectors_handled =
+ r1_bio->sector + max_sectors
+ - mbio->bi_sector;
+ r1_bio->sectors = max_sectors;
+ spin_lock_irq(&conf->device_lock);
+ if (mbio->bi_phys_segments == 0)
+ mbio->bi_phys_segments = 2;
+ else
+ mbio->bi_phys_segments++;
+ spin_unlock_irq(&conf->device_lock);
+ generic_make_request(bio);
+ bio = NULL;
+
+ r1_bio = mempool_alloc(conf->r1bio_pool,
+ GFP_NOIO);
+
+ r1_bio->master_bio = mbio;
+ r1_bio->sectors = (mbio->bi_size >> 9)
+ - sectors_handled;
+ r1_bio->state = 0;
+ set_bit(R1BIO_ReadError,
+ &r1_bio->state);
+ r1_bio->mddev = mddev;
+ r1_bio->sector = mbio->bi_sector
+ + sectors_handled;
+
+ goto read_more;
+ } else
+ generic_make_request(bio);
}
+ } else {
+ /* just a partial read to be scheduled from separate
+ * context
+ */
+ generic_make_request(r1_bio->bios[r1_bio->read_disk]);
}
cond_resched();
+ if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+ md_check_recovery(mddev);
}
blk_finish_plug(&plug);
}
int write_targets = 0, read_targets = 0;
sector_t sync_blocks;
int still_degraded = 0;
+ int good_sectors = RESYNC_SECTORS;
+ int min_bad = 0; /* number of sectors that are bad in all devices */
if (!conf->r1buf_pool)
if (init_resync(conf))
rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev == NULL ||
- test_bit(Faulty, &rdev->flags)) {
+ test_bit(Faulty, &rdev->flags)) {
still_degraded = 1;
- continue;
} else if (!test_bit(In_sync, &rdev->flags)) {
bio->bi_rw = WRITE;
bio->bi_end_io = end_sync_write;
write_targets ++;
} else {
/* may need to read from here */
- bio->bi_rw = READ;
- bio->bi_end_io = end_sync_read;
- if (test_bit(WriteMostly, &rdev->flags)) {
- if (wonly < 0)
- wonly = i;
- } else {
- if (disk < 0)
- disk = i;
+ sector_t first_bad = MaxSector;
+ int bad_sectors;
+
+ if (is_badblock(rdev, sector_nr, good_sectors,
+ &first_bad, &bad_sectors)) {
+ if (first_bad > sector_nr)
+ good_sectors = first_bad - sector_nr;
+ else {
+ bad_sectors -= (sector_nr - first_bad);
+ if (min_bad == 0 ||
+ min_bad > bad_sectors)
+ min_bad = bad_sectors;
+ }
+ }
+ if (sector_nr < first_bad) {
+ if (test_bit(WriteMostly, &rdev->flags)) {
+ if (wonly < 0)
+ wonly = i;
+ } else {
+ if (disk < 0)
+ disk = i;
+ }
+ bio->bi_rw = READ;
+ bio->bi_end_io = end_sync_read;
+ read_targets++;
}
- read_targets++;
}
- atomic_inc(&rdev->nr_pending);
- bio->bi_sector = sector_nr + rdev->data_offset;
- bio->bi_bdev = rdev->bdev;
- bio->bi_private = r1_bio;
+ if (bio->bi_end_io) {
+ atomic_inc(&rdev->nr_pending);
+ bio->bi_sector = sector_nr + rdev->data_offset;
+ bio->bi_bdev = rdev->bdev;
+ bio->bi_private = r1_bio;
+ }
}
rcu_read_unlock();
if (disk < 0)
disk = wonly;
r1_bio->read_disk = disk;
+ if (read_targets == 0 && min_bad > 0) {
+ /* These sectors are bad on all InSync devices, so we
+ * need to mark them bad on all write targets
+ */
+ int ok = 1;
+ for (i = 0 ; i < conf->raid_disks ; i++)
+ if (r1_bio->bios[i]->bi_end_io == end_sync_write) {
+ mdk_rdev_t *rdev =
+ rcu_dereference(conf->mirrors[i].rdev);
+ ok = rdev_set_badblocks(rdev, sector_nr,
+ min_bad, 0
+ ) && ok;
+ }
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ *skipped = 1;
+ put_buf(r1_bio);
+
+ if (!ok) {
+ /* Cannot record the badblocks, so need to
+ * abort the resync.
+ * If there are multiple read targets, could just
+ * fail the really bad ones ???
+ */
+ conf->recovery_disabled = mddev->recovery_disabled;
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ return 0;
+ } else
+ return min_bad;
+
+ }
+ if (min_bad > 0 && min_bad < good_sectors) {
+ /* only resync enough to reach the next bad->good
+ * transition */
+ good_sectors = min_bad;
+ }
+
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && read_targets > 0)
/* extra read targets are also write targets */
write_targets += read_targets-1;
if (max_sector > mddev->resync_max)
max_sector = mddev->resync_max; /* Don't do IO beyond here */
+ if (max_sector > sector_nr + good_sectors)
+ max_sector = sector_nr + good_sectors;
nr_sectors = 0;
sync_blocks = 0;
do {
for (d = d2 = 0; d < conf->raid_disks; d++) {
mdk_rdev_t *rdev = conf->mirrors[d].rdev;
if (rdev && rdev->raid_disk != d2) {
- char nm[20];
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
+ sysfs_unlink_rdev(mddev, rdev);
rdev->raid_disk = d2;
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
- if (sysfs_create_link(&mddev->kobj,
- &rdev->kobj, nm))
+ sysfs_unlink_rdev(mddev, rdev);
+ if (sysfs_link_rdev(mddev, rdev))
printk(KERN_WARNING
- "md/raid1:%s: cannot register "
- "%s\n",
- mdname(mddev), nm);
+ "md/raid1:%s: cannot register rd%d\n",
+ mdname(mddev), rdev->raid_disk);
}
if (rdev)
newmirrors[d2++].rdev = rdev;
projects / mirror_ubuntu-artful-kernel.git / blobdiff