* Fixes to reconstruction by Jakob Østergaard" <jakob@ostenfeld.dk>
* Various fixes by Neil Brown <neilb@cse.unsw.edu.au>
*
+ * Changes by Peter T. Breuer <ptb@it.uc3m.es> 31/1/2003 to support
+ * bitmapped intelligence in resync:
+ *
+ * - bitmap marked during normal i/o
+ * - bitmap used to skip nondirty blocks during sync
+ *
+ * Additions to bitmap code, (C) 2003-2004 Paul Clements, SteelEye Technology:
+ * - persistent bitmap code
+ *
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+#include "dm-bio-list.h"
#include <linux/raid/raid1.h>
+#include <linux/raid/bitmap.h>
+
+#define DEBUG 0
+#if DEBUG
+#define PRINTK(x...) printk(x)
+#else
+#define PRINTK(x...)
+#endif
/*
* Number of guaranteed r1bios in case of extreme VM load:
{
struct bio *bio = r1_bio->master_bio;
- bio_endio(bio, bio->bi_size,
- test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
+ /* if nobody has done the final endio yet, do it now */
+ if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
+ PRINTK(KERN_DEBUG "raid1: sync end %s on sectors %llu-%llu\n",
+ (bio_data_dir(bio) == WRITE) ? "write" : "read",
+ (unsigned long long) bio->bi_sector,
+ (unsigned long long) bio->bi_sector +
+ (bio->bi_size >> 9) - 1);
+
+ bio_endio(bio, bio->bi_size,
+ test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
+ }
free_r1bio(r1_bio);
}
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
- int mirror;
+ int mirror, behind;
conf_t *conf = mddev_to_conf(r1_bio->mddev);
if (bio->bi_size)
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
- if (!uptodate)
+ if (!uptodate) {
md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
- else
+ /* an I/O failed, we can't clear the bitmap */
+ set_bit(R1BIO_Degraded, &r1_bio->state);
+ } else
/*
* Set R1BIO_Uptodate in our master bio, so that
* we will return a good error code for to the higher
update_head_pos(mirror, r1_bio);
+ behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
+ if (behind) {
+ if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
+ atomic_dec(&r1_bio->behind_remaining);
+
+ /* In behind mode, we ACK the master bio once the I/O has safely
+ * reached all non-writemostly disks. Setting the Returned bit
+ * ensures that this gets done only once -- we don't ever want to
+ * return -EIO here, instead we'll wait */
+
+ if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
+ test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+ /* Maybe we can return now */
+ if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
+ struct bio *mbio = r1_bio->master_bio;
+ PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
+ (unsigned long long) mbio->bi_sector,
+ (unsigned long long) mbio->bi_sector +
+ (mbio->bi_size >> 9) - 1);
+ bio_endio(mbio, mbio->bi_size, 0);
+ }
+ }
+ }
/*
*
* Let's see if all mirrored write operations have finished
* already.
*/
if (atomic_dec_and_test(&r1_bio->remaining)) {
+ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+ /* free extra copy of the data pages */
+ int i = bio->bi_vcnt;
+ while (i--)
+ __free_page(bio->bi_io_vec[i].bv_page);
+ }
+ /* clear the bitmap if all writes complete successfully */
+ bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
+ r1_bio->sectors,
+ !test_bit(R1BIO_Degraded, &r1_bio->state),
+ behind);
md_write_end(r1_bio->mddev);
raid_end_bio_io(r1_bio);
}
{
const unsigned long this_sector = r1_bio->sector;
int new_disk = conf->last_used, disk = new_disk;
+ int wonly_disk = -1;
const int sectors = r1_bio->sectors;
sector_t new_distance, current_distance;
- mdk_rdev_t *new_rdev, *rdev;
+ mdk_rdev_t *rdev;
rcu_read_lock();
/*
- * Check if it if we can balance. We can balance on the whole
+ * Check if we can balance. We can balance on the whole
* device if no resync is going on, or below the resync window.
* We take the first readable disk when above the resync window.
*/
/* Choose the first operation device, for consistancy */
new_disk = 0;
- while ((new_rdev=conf->mirrors[new_disk].rdev) == NULL ||
- !new_rdev->in_sync) {
- new_disk++;
- if (new_disk == conf->raid_disks) {
- new_disk = -1;
+ for (rdev = conf->mirrors[new_disk].rdev;
+ !rdev || !rdev->in_sync
+ || test_bit(WriteMostly, &rdev->flags);
+ rdev = conf->mirrors[++new_disk].rdev) {
+
+ if (rdev && rdev->in_sync)
+ wonly_disk = new_disk;
+
+ if (new_disk == conf->raid_disks - 1) {
+ new_disk = wonly_disk;
break;
}
}
/* make sure the disk is operational */
- while ((new_rdev=conf->mirrors[new_disk].rdev) == NULL ||
- !new_rdev->in_sync) {
+ for (rdev = conf->mirrors[new_disk].rdev;
+ !rdev || !rdev->in_sync ||
+ test_bit(WriteMostly, &rdev->flags);
+ rdev = conf->mirrors[new_disk].rdev) {
+
+ if (rdev && rdev->in_sync)
+ wonly_disk = new_disk;
+
if (new_disk <= 0)
new_disk = conf->raid_disks;
new_disk--;
if (new_disk == disk) {
- new_disk = -1;
- goto rb_out;
+ new_disk = wonly_disk;
+ break;
}
}
+
+ if (new_disk < 0)
+ goto rb_out;
+
disk = new_disk;
/* now disk == new_disk == starting point for search */
disk = conf->raid_disks;
disk--;
- if ((rdev=conf->mirrors[disk].rdev) == NULL ||
- !rdev->in_sync)
+ rdev = conf->mirrors[disk].rdev;
+
+ if (!rdev ||
+ !rdev->in_sync ||
+ test_bit(WriteMostly, &rdev->flags))
continue;
if (!atomic_read(&rdev->nr_pending)) {
new_disk = disk;
- new_rdev = rdev;
break;
}
new_distance = abs(this_sector - conf->mirrors[disk].head_position);
if (new_distance < current_distance) {
current_distance = new_distance;
new_disk = disk;
- new_rdev = rdev;
}
} while (disk != conf->last_used);
-rb_out:
+ rb_out:
if (new_disk >= 0) {
- conf->next_seq_sect = this_sector + sectors;
- conf->last_used = new_disk;
- atomic_inc(&new_rdev->nr_pending);
- if (!new_rdev->in_sync) {
+ rdev = conf->mirrors[new_disk].rdev;
+ if (!rdev)
+ goto retry;
+ atomic_inc(&rdev->nr_pending);
+ if (!rdev->in_sync) {
/* cannot risk returning a device that failed
* before we inc'ed nr_pending
*/
- atomic_dec(&new_rdev->nr_pending);
+ atomic_dec(&rdev->nr_pending);
goto retry;
}
+ conf->next_seq_sect = this_sector + sectors;
+ conf->last_used = new_disk;
}
rcu_read_unlock();
static void raid1_unplug(request_queue_t *q)
{
- unplug_slaves(q->queuedata);
+ mddev_t *mddev = q->queuedata;
+
+ unplug_slaves(mddev);
+ md_wakeup_thread(mddev->thread);
}
static int raid1_issue_flush(request_queue_t *q, struct gendisk *disk,
{
spin_lock_irq(&conf->resync_lock);
wait_event_lock_irq(conf->wait_idle, !waitqueue_active(&conf->wait_resume),
- conf->resync_lock, unplug_slaves(conf->mddev));
+ conf->resync_lock, raid1_unplug(conf->mddev->queue));
if (!conf->barrier++) {
wait_event_lock_irq(conf->wait_idle, !conf->nr_pending,
- conf->resync_lock, unplug_slaves(conf->mddev));
+ conf->resync_lock, raid1_unplug(conf->mddev->queue));
if (conf->nr_pending)
BUG();
}
wait_event_lock_irq(conf->wait_resume, conf->barrier < RESYNC_DEPTH,
- conf->resync_lock, unplug_slaves(conf->mddev));
+ conf->resync_lock, raid1_unplug(conf->mddev->queue));
conf->next_resync = sect;
spin_unlock_irq(&conf->resync_lock);
}
+/* duplicate the data pages for behind I/O */
+static struct page **alloc_behind_pages(struct bio *bio)
+{
+ int i;
+ struct bio_vec *bvec;
+ struct page **pages = kmalloc(bio->bi_vcnt * sizeof(struct page *),
+ GFP_NOIO);
+ if (unlikely(!pages))
+ goto do_sync_io;
+
+ memset(pages, 0, bio->bi_vcnt * sizeof(struct page *));
+
+ bio_for_each_segment(bvec, bio, i) {
+ pages[i] = alloc_page(GFP_NOIO);
+ if (unlikely(!pages[i]))
+ goto do_sync_io;
+ memcpy(kmap(pages[i]) + bvec->bv_offset,
+ kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len);
+ kunmap(pages[i]);
+ kunmap(bvec->bv_page);
+ }
+
+ return pages;
+
+do_sync_io:
+ if (pages)
+ for (i = 0; i < bio->bi_vcnt && pages[i]; i++)
+ __free_page(pages[i]);
+ kfree(pages);
+ PRINTK("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
+ return NULL;
+}
+
static int make_request(request_queue_t *q, struct bio * bio)
{
mddev_t *mddev = q->queuedata;
mirror_info_t *mirror;
r1bio_t *r1_bio;
struct bio *read_bio;
- int i, disks;
+ int i, targets = 0, disks;
mdk_rdev_t *rdev;
+ struct bitmap *bitmap = mddev->bitmap;
+ unsigned long flags;
+ struct bio_list bl;
+ struct page **behind_pages = NULL;
+
+ if (unlikely(bio_barrier(bio))) {
+ bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+ return 0;
+ }
/*
* Register the new request and wait if the reconstruction
* thread has put up a bar for new requests.
* Continue immediately if no resync is active currently.
*/
+ md_write_start(mddev, bio); /* wait on superblock update early */
+
spin_lock_irq(&conf->resync_lock);
wait_event_lock_irq(conf->wait_resume, !conf->barrier, conf->resync_lock, );
conf->nr_pending++;
r1_bio->master_bio = bio;
r1_bio->sectors = bio->bi_size >> 9;
-
+ r1_bio->state = 0;
r1_bio->mddev = mddev;
r1_bio->sector = bio->bi_sector;
- r1_bio->state = 0;
-
if (bio_data_dir(bio) == READ) {
/*
* read balancing logic:
* bios[x] to bio
*/
disks = conf->raid_disks;
+#if 0
+ { static int first=1;
+ if (first) printk("First Write sector %llu disks %d\n",
+ (unsigned long long)r1_bio->sector, disks);
+ first = 0;
+ }
+#endif
rcu_read_lock();
for (i = 0; i < disks; i++) {
if ((rdev=conf->mirrors[i].rdev) != NULL &&
r1_bio->bios[i] = NULL;
} else
r1_bio->bios[i] = bio;
+ targets++;
} else
r1_bio->bios[i] = NULL;
}
rcu_read_unlock();
- atomic_set(&r1_bio->remaining, 1);
- md_write_start(mddev);
+ 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);
+ }
+
+ /* do behind I/O ? */
+ if (bitmap &&
+ atomic_read(&bitmap->behind_writes) < bitmap->max_write_behind &&
+ (behind_pages = alloc_behind_pages(bio)) != NULL)
+ set_bit(R1BIO_BehindIO, &r1_bio->state);
+
+ atomic_set(&r1_bio->remaining, 0);
+ atomic_set(&r1_bio->behind_remaining, 0);
+
+ bio_list_init(&bl);
for (i = 0; i < disks; i++) {
struct bio *mbio;
if (!r1_bio->bios[i])
mbio->bi_rw = WRITE;
mbio->bi_private = r1_bio;
+ if (behind_pages) {
+ struct bio_vec *bvec;
+ int j;
+
+ /* Yes, I really want the '__' version so that
+ * we clear any unused pointer in the io_vec, rather
+ * than leave them unchanged. This is important
+ * because when we come to free the pages, we won't
+ * know the originial bi_idx, so we just free
+ * them all
+ */
+ __bio_for_each_segment(bvec, mbio, j, 0)
+ bvec->bv_page = behind_pages[j];
+ if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
+ atomic_inc(&r1_bio->behind_remaining);
+ }
+
atomic_inc(&r1_bio->remaining);
- generic_make_request(mbio);
- }
- if (atomic_dec_and_test(&r1_bio->remaining)) {
- md_write_end(mddev);
- raid_end_bio_io(r1_bio);
+ bio_list_add(&bl, mbio);
}
+ kfree(behind_pages); /* the behind pages are attached to the bios now */
+
+ bitmap_startwrite(bitmap, bio->bi_sector, r1_bio->sectors,
+ test_bit(R1BIO_BehindIO, &r1_bio->state));
+ spin_lock_irqsave(&conf->device_lock, flags);
+ bio_list_merge(&conf->pending_bio_list, &bl);
+ bio_list_init(&bl);
+
+ blk_plug_device(mddev->queue);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+
+#if 0
+ while ((bio = bio_list_pop(&bl)) != NULL)
+ generic_make_request(bio);
+#endif
return 0;
}
{
spin_lock_irq(&conf->resync_lock);
wait_event_lock_irq(conf->wait_resume, !conf->barrier,
- conf->resync_lock, unplug_slaves(conf->mddev));
+ conf->resync_lock, raid1_unplug(conf->mddev->queue));
spin_unlock_irq(&conf->resync_lock);
if (conf->barrier) BUG();
{
conf_t *conf = mddev->private;
int found = 0;
- int mirror;
+ int mirror = 0;
mirror_info_t *p;
+ if (rdev->saved_raid_disk >= 0 &&
+ conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
+ mirror = rdev->saved_raid_disk;
for (mirror=0; mirror < mddev->raid_disks; mirror++)
if ( !(p=conf->mirrors+mirror)->rdev) {
p->head_position = 0;
rdev->raid_disk = mirror;
found = 1;
+ if (rdev->saved_raid_disk != mirror)
+ conf->fullsync = 1;
p->rdev = rdev;
break;
}
* or re-read if the read failed.
* We don't do much here, just schedule handling by raid1d
*/
- if (!uptodate)
+ if (!uptodate) {
md_error(r1_bio->mddev,
conf->mirrors[r1_bio->read_disk].rdev);
- else
+ } else
set_bit(R1BIO_Uptodate, &r1_bio->state);
rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
reschedule_retry(r1_bio);
}
if (!uptodate)
md_error(mddev, conf->mirrors[mirror].rdev);
+
update_head_pos(mirror, r1_bio);
if (atomic_dec_and_test(&r1_bio->remaining)) {
bio = r1_bio->bios[r1_bio->read_disk];
+/*
+ if (r1_bio->sector == 0) printk("First sync write startss\n");
+*/
/*
* schedule writes
*/
atomic_inc(&conf->mirrors[i].rdev->nr_pending);
atomic_inc(&r1_bio->remaining);
md_sync_acct(conf->mirrors[i].rdev->bdev, wbio->bi_size >> 9);
+
generic_make_request(wbio);
}
if (atomic_dec_and_test(&r1_bio->remaining)) {
+ /* if we're here, all write(s) have completed, so clean up */
md_done_sync(mddev, r1_bio->sectors, 1);
put_buf(r1_bio);
}
mdk_rdev_t *rdev;
md_check_recovery(mddev);
- md_handle_safemode(mddev);
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 */
+ if (bitmap_unplug(mddev->bitmap) != 0)
+ printk("%s: bitmap file write failed!\n", mdname(mddev));
+
+ 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))
break;
r1_bio = list_entry(head->prev, r1bio_t, retry_list);
* that can be installed to exclude normal IO requests.
*/
-static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
+static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
conf_t *conf = mddev_to_conf(mddev);
mirror_info_t *mirror;
sector_t max_sector, nr_sectors;
int disk;
int i;
+ int wonly;
int write_targets = 0;
+ int sync_blocks;
+ int still_degraded = 0;
if (!conf->r1buf_pool)
+ {
+/*
+ printk("sync start - bitmap %p\n", mddev->bitmap);
+*/
if (init_resync(conf))
- return -ENOMEM;
+ return 0;
+ }
max_sector = mddev->size << 1;
if (sector_nr >= max_sector) {
+ /* If we aborted, we need to abort the
+ * sync on the 'current' bitmap chunk (there will
+ * only be one in raid1 resync.
+ * We can find the current addess in mddev->curr_resync
+ */
+ if (mddev->curr_resync < max_sector) /* aborted */
+ bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
+ &sync_blocks, 1);
+ else /* completed sync */
+ conf->fullsync = 0;
+
+ bitmap_close_sync(mddev->bitmap);
close_sync(conf);
return 0;
}
+ /* before building a request, check if we can skip these blocks..
+ * This call the bitmap_start_sync doesn't actually record anything
+ */
+ if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+ !conf->fullsync) {
+ /* We can skip this block, and probably several more */
+ *skipped = 1;
+ return sync_blocks;
+ }
/*
* If there is non-resync activity waiting for us then
* put in a delay to throttle resync.
*/
disk = conf->last_used;
/* make sure disk is operational */
-
+ wonly = disk;
while (conf->mirrors[disk].rdev == NULL ||
- !conf->mirrors[disk].rdev->in_sync) {
+ !conf->mirrors[disk].rdev->in_sync ||
+ test_bit(WriteMostly, &conf->mirrors[disk].rdev->flags)
+ ) {
+ if (conf->mirrors[disk].rdev &&
+ conf->mirrors[disk].rdev->in_sync)
+ wonly = disk;
if (disk <= 0)
disk = conf->raid_disks;
disk--;
- if (disk == conf->last_used)
+ if (disk == conf->last_used) {
+ disk = wonly;
break;
+ }
}
conf->last_used = disk;
atomic_inc(&conf->mirrors[disk].rdev->nr_pending);
r1_bio->mddev = mddev;
r1_bio->sector = sector_nr;
+ r1_bio->state = 0;
set_bit(R1BIO_IsSync, &r1_bio->state);
r1_bio->read_disk = disk;
if (i == disk) {
bio->bi_rw = READ;
bio->bi_end_io = end_sync_read;
- } else if (conf->mirrors[i].rdev &&
- !conf->mirrors[i].rdev->faulty &&
- (!conf->mirrors[i].rdev->in_sync ||
- sector_nr + RESYNC_SECTORS > mddev->recovery_cp)) {
+ } else if (conf->mirrors[i].rdev == NULL ||
+ conf->mirrors[i].rdev->faulty) {
+ still_degraded = 1;
+ continue;
+ } else if (!conf->mirrors[i].rdev->in_sync ||
+ sector_nr + RESYNC_SECTORS > mddev->recovery_cp) {
bio->bi_rw = WRITE;
bio->bi_end_io = end_sync_write;
write_targets ++;
} else
+ /* no need to read or write here */
continue;
bio->bi_sector = sector_nr + conf->mirrors[i].rdev->data_offset;
bio->bi_bdev = conf->mirrors[i].rdev->bdev;
bio->bi_private = r1_bio;
}
+
if (write_targets == 0) {
/* There is nowhere to write, so all non-sync
* drives must be failed - so we are finished
*/
- int rv = max_sector - sector_nr;
- md_done_sync(mddev, rv, 1);
+ sector_t rv = max_sector - sector_nr;
+ *skipped = 1;
put_buf(r1_bio);
rdev_dec_pending(conf->mirrors[disk].rdev, mddev);
return rv;
}
nr_sectors = 0;
+ sync_blocks = 0;
do {
struct page *page;
int len = PAGE_SIZE;
len = (max_sector - sector_nr) << 9;
if (len == 0)
break;
+ if (sync_blocks == 0) {
+ if (!bitmap_start_sync(mddev->bitmap, sector_nr,
+ &sync_blocks, still_degraded) &&
+ !conf->fullsync)
+ break;
+ if (sync_blocks < (PAGE_SIZE>>9))
+ BUG();
+ if (len > (sync_blocks<<9))
+ len = sync_blocks<<9;
+ }
+
for (i=0 ; i < conf->raid_disks; i++) {
bio = r1_bio->bios[i];
if (bio->bi_end_io) {
while (i > 0) {
i--;
bio = r1_bio->bios[i];
- if (bio->bi_end_io==NULL) continue;
+ if (bio->bi_end_io==NULL)
+ continue;
/* remove last page from this bio */
bio->bi_vcnt--;
bio->bi_size -= len;
}
nr_sectors += len>>9;
sector_nr += len>>9;
+ sync_blocks -= (len>>9);
} while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES);
bio_full:
bio = r1_bio->bios[disk];
init_waitqueue_head(&conf->wait_idle);
init_waitqueue_head(&conf->wait_resume);
+ bio_list_init(&conf->pending_bio_list);
+ bio_list_init(&conf->flushing_bio_list);
+
if (!conf->working_disks) {
printk(KERN_ERR "raid1: no operational mirrors for %s\n",
mdname(mddev));
conf->last_used = j;
-
- {
- mddev->thread = md_register_thread(raid1d, mddev, "%s_raid1");
- if (!mddev->thread) {
- printk(KERN_ERR
- "raid1: couldn't allocate thread for %s\n",
- mdname(mddev));
- goto out_free_conf;
- }
+ mddev->thread = md_register_thread(raid1d, mddev, "%s_raid1");
+ if (!mddev->thread) {
+ printk(KERN_ERR
+ "raid1: couldn't allocate thread for %s\n",
+ mdname(mddev));
+ goto out_free_conf;
}
+ if (mddev->bitmap) mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
+
printk(KERN_INFO
"raid1: raid set %s active with %d out of %d mirrors\n",
mdname(mddev), mddev->raid_disks - mddev->degraded,
if (conf) {
if (conf->r1bio_pool)
mempool_destroy(conf->r1bio_pool);
- if (conf->mirrors)
- kfree(conf->mirrors);
- if (conf->poolinfo)
- kfree(conf->poolinfo);
+ kfree(conf->mirrors);
+ kfree(conf->poolinfo);
kfree(conf);
mddev->private = NULL;
}
static int stop(mddev_t *mddev)
{
conf_t *conf = mddev_to_conf(mddev);
+ struct bitmap *bitmap = mddev->bitmap;
+ int behind_wait = 0;
+
+ /* wait for behind writes to complete */
+ while (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+ behind_wait++;
+ printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(HZ); /* wait a second */
+ /* need to kick something here to make sure I/O goes? */
+ }
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
if (conf->r1bio_pool)
mempool_destroy(conf->r1bio_pool);
- if (conf->mirrors)
- kfree(conf->mirrors);
- if (conf->poolinfo)
- kfree(conf->poolinfo);
+ kfree(conf->mirrors);
+ kfree(conf->poolinfo);
kfree(conf);
mddev->private = NULL;
return 0;
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}
mddev->size = mddev->array_size;
+ mddev->resync_max_sectors = sectors;
return 0;
}
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
wait_event_lock_irq(conf->wait_idle, !conf->nr_pending,
- conf->resync_lock, unplug_slaves(mddev));
+ conf->resync_lock, raid1_unplug(mddev->queue));
spin_unlock_irq(&conf->resync_lock);
/* ok, everything is stopped */
return 0;
}
+static void raid1_quiesce(mddev_t *mddev, int state)
+{
+ conf_t *conf = mddev_to_conf(mddev);
+
+ switch(state) {
+ case 1:
+ spin_lock_irq(&conf->resync_lock);
+ conf->barrier++;
+ wait_event_lock_irq(conf->wait_idle, !conf->nr_pending,
+ conf->resync_lock, raid1_unplug(mddev->queue));
+ spin_unlock_irq(&conf->resync_lock);
+ break;
+ case 0:
+ spin_lock_irq(&conf->resync_lock);
+ conf->barrier--;
+ spin_unlock_irq(&conf->resync_lock);
+ wake_up(&conf->wait_resume);
+ wake_up(&conf->wait_idle);
+ 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 mdk_personality_t raid1_personality =
{
.sync_request = sync_request,
.resize = raid1_resize,
.reshape = raid1_reshape,
+ .quiesce = raid1_quiesce,
};
static int __init raid_init(void)