summaryrefslogtreecommitdiff
path: root/drivers/md/raid1.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid1.c')
-rw-r--r--drivers/md/raid1.c249
1 files changed, 197 insertions, 52 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 83380b5d6593..ff1dbec864af 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -12,6 +12,15 @@
* 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)
@@ -22,7 +31,16 @@
* 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:
@@ -287,9 +305,11 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
/*
* 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
@@ -309,6 +329,10 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
* already.
*/
if (atomic_dec_and_test(&r1_bio->remaining)) {
+ /* 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));
md_write_end(r1_bio->mddev);
raid_end_bio_io(r1_bio);
}
@@ -458,7 +482,10 @@ static void unplug_slaves(mddev_t *mddev)
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,
@@ -501,16 +528,16 @@ static void device_barrier(conf_t *conf, sector_t sect)
{
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);
}
@@ -522,14 +549,20 @@ static int make_request(request_queue_t *q, struct bio * bio)
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;
+
/*
* 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++;
@@ -552,7 +585,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
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;
@@ -595,6 +628,13 @@ static int make_request(request_queue_t *q, struct bio * bio)
* 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 &&
@@ -605,13 +645,21 @@ static int make_request(request_queue_t *q, struct bio * bio)
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);
+ 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);
+ }
+
+ atomic_set(&r1_bio->remaining, 0);
+
+ bio_list_init(&bl);
for (i = 0; i < disks; i++) {
struct bio *mbio;
if (!r1_bio->bios[i])
@@ -627,14 +675,23 @@ static int make_request(request_queue_t *q, struct bio * bio)
mbio->bi_private = r1_bio;
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);
}
+ bitmap_startwrite(bitmap, bio->bi_sector, r1_bio->sectors);
+ 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;
}
@@ -714,7 +771,7 @@ static void close_sync(conf_t *conf)
{
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();
@@ -754,9 +811,12 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
{
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) {
@@ -773,6 +833,8 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
p->head_position = 0;
rdev->raid_disk = mirror;
found = 1;
+ if (rdev->saved_raid_disk != mirror)
+ conf->fullsync = 1;
p->rdev = rdev;
break;
}
@@ -828,10 +890,11 @@ static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
* 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
+ set_bit(R1BIO_Degraded, &r1_bio->state);
+ } else
set_bit(R1BIO_Uptodate, &r1_bio->state);
rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
reschedule_retry(r1_bio);
@@ -855,8 +918,10 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
mirror = i;
break;
}
- if (!uptodate)
+ if (!uptodate) {
md_error(mddev, conf->mirrors[mirror].rdev);
+ set_bit(R1BIO_Degraded, &r1_bio->state);
+ }
update_head_pos(mirror, r1_bio);
if (atomic_dec_and_test(&r1_bio->remaining)) {
@@ -876,6 +941,9 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
bio = r1_bio->bios[r1_bio->read_disk];
+/*
+ if (r1_bio->sector == 0) printk("First sync write startss\n");
+*/
/*
* schedule writes
*/
@@ -903,10 +971,12 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
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);
}
@@ -931,11 +1001,30 @@ static void raid1d(mddev_t *mddev)
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);
@@ -1009,7 +1098,7 @@ static int init_resync(conf_t *conf)
* 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;
@@ -1019,17 +1108,43 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
int disk;
int i;
int write_targets = 0;
+ int sync_blocks;
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 (!conf->fullsync) {
+ if (mddev->curr_resync < max_sector)
+ bitmap_end_sync(mddev->bitmap,
+ mddev->curr_resync,
+ &sync_blocks, 1);
+ bitmap_close_sync(mddev->bitmap);
+ }
+ if (mddev->curr_resync >= max_sector)
+ conf->fullsync = 0;
close_sync(conf);
return 0;
}
+ if (!conf->fullsync &&
+ !bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks)) {
+ /* 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.
@@ -1068,6 +1183,7 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
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;
@@ -1102,18 +1218,24 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
bio->bi_bdev = conf->mirrors[i].rdev->bdev;
bio->bi_private = r1_bio;
}
+
+ if (write_targets + 1 < conf->raid_disks)
+ /* array degraded, can't clear bitmap */
+ set_bit(R1BIO_Degraded, &r1_bio->state);
+
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;
@@ -1121,6 +1243,17 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
len = (max_sector - sector_nr) << 9;
if (len == 0)
break;
+ if (!conf->fullsync) {
+ if (sync_blocks == 0) {
+ if (!bitmap_start_sync(mddev->bitmap,
+ sector_nr, &sync_blocks))
+ 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) {
@@ -1143,6 +1276,7 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
}
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];
@@ -1197,10 +1331,6 @@ static int run(mddev_t *mddev)
if (!conf->r1bio_pool)
goto out_no_mem;
- mddev->queue->unplug_fn = raid1_unplug;
-
- mddev->queue->issue_flush_fn = raid1_issue_flush;
-
ITERATE_RDEV(mddev, rdev, tmp) {
disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
@@ -1235,6 +1365,9 @@ static int run(mddev_t *mddev)
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));
@@ -1263,16 +1396,15 @@ static int run(mddev_t *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,
@@ -1282,6 +1414,9 @@ static int run(mddev_t *mddev)
*/
mddev->array_size = mddev->size;
+ mddev->queue->unplug_fn = raid1_unplug;
+ mddev->queue->issue_flush_fn = raid1_issue_flush;
+
return 0;
out_no_mem:
@@ -1292,10 +1427,8 @@ out_free_conf:
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;
}
@@ -1312,10 +1445,8 @@ static int stop(mddev_t *mddev)
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;
@@ -1350,17 +1481,26 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
* We allocate a new r1bio_pool if we can.
* Then raise a device barrier and wait until all IO stops.
* Then resize conf->mirrors and swap in the new r1bio pool.
+ *
+ * At the same time, we "pack" the devices so that all the missing
+ * devices have the higher raid_disk numbers.
*/
mempool_t *newpool, *oldpool;
struct pool_info *newpoolinfo;
mirror_info_t *newmirrors;
conf_t *conf = mddev_to_conf(mddev);
+ int cnt;
- int d;
+ int d, d2;
- for (d= raid_disks; d < conf->raid_disks; d++)
- if (conf->mirrors[d].rdev)
+ if (raid_disks < conf->raid_disks) {
+ cnt=0;
+ for (d= 0; d < conf->raid_disks; d++)
+ if (conf->mirrors[d].rdev)
+ cnt++;
+ if (cnt > raid_disks)
return -EBUSY;
+ }
newpoolinfo = kmalloc(sizeof(*newpoolinfo), GFP_KERNEL);
if (!newpoolinfo)
@@ -1385,14 +1525,18 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
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 */
oldpool = conf->r1bio_pool;
conf->r1bio_pool = newpool;
- for (d=0; d < raid_disks && d < conf->raid_disks; d++)
- newmirrors[d] = conf->mirrors[d];
+
+ for (d=d2=0; d < conf->raid_disks; d++)
+ if (conf->mirrors[d].rdev) {
+ conf->mirrors[d].rdev->raid_disk = d2;
+ newmirrors[d2++].rdev = conf->mirrors[d].rdev;
+ }
kfree(conf->mirrors);
conf->mirrors = newmirrors;
kfree(conf->poolinfo);
@@ -1401,6 +1545,7 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
mddev->degraded += (raid_disks - conf->raid_disks);
conf->raid_disks = mddev->raid_disks = raid_disks;
+ conf->last_used = 0; /* just make sure it is in-range */
spin_lock_irq(&conf->resync_lock);
conf->barrier--;
spin_unlock_irq(&conf->resync_lock);
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-05 00:18:24 +0000