summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2006-03-27 01:18:08 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-03-27 08:45:01 -0800
commit7ecaa1e6a1ad69862e9980b6c777e11f26c4782d (patch)
tree3cbd64ebc2a45f6b5ac45b0305fd3cf2c6916070 /drivers/md
parentad01c9e3752f4ba4f3d99c89b7370fa4983a25b5 (diff)
downloadop-kernel-dev-7ecaa1e6a1ad69862e9980b6c777e11f26c4782d.zip
op-kernel-dev-7ecaa1e6a1ad69862e9980b6c777e11f26c4782d.tar.gz
[PATCH] md: Infrastructure to allow normal IO to continue while array is expanding
We need to allow that different stripes are of different effective sizes, and use the appropriate size. Also, when a stripe is being expanded, we must block any IO attempts until the stripe is stable again. Key elements in this change are: - each stripe_head gets a 'disk' field which is part of the key, thus there can sometimes be two stripe heads of the same area of the array, but covering different numbers of devices. One of these will be marked STRIPE_EXPANDING and so won't accept new requests. - conf->expand_progress tracks how the expansion is progressing and is used to determine whether the target part of the array has been expanded yet or not. Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/raid5.c88
1 files changed, 58 insertions, 30 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 6c20b44..7a6df51 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -178,10 +178,10 @@ static int grow_buffers(struct stripe_head *sh, int num)
static void raid5_build_block (struct stripe_head *sh, int i);
-static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
+static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks)
{
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks, i;
+ int i;
if (atomic_read(&sh->count) != 0)
BUG();
@@ -198,7 +198,9 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
sh->pd_idx = pd_idx;
sh->state = 0;
- for (i=disks; i--; ) {
+ sh->disks = disks;
+
+ for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->toread || dev->towrite || dev->written ||
@@ -215,7 +217,7 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
insert_hash(conf, sh);
}
-static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector)
+static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, int disks)
{
struct stripe_head *sh;
struct hlist_node *hn;
@@ -223,7 +225,7 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector)
CHECK_DEVLOCK();
PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
- if (sh->sector == sector)
+ if (sh->sector == sector && sh->disks == disks)
return sh;
PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector);
return NULL;
@@ -232,8 +234,8 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector)
static void unplug_slaves(mddev_t *mddev);
static void raid5_unplug_device(request_queue_t *q);
-static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector,
- int pd_idx, int noblock)
+static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks,
+ int pd_idx, int noblock)
{
struct stripe_head *sh;
@@ -245,7 +247,7 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0,
conf->device_lock, /* nothing */);
- sh = __find_stripe(conf, sector);
+ sh = __find_stripe(conf, sector, disks);
if (!sh) {
if (!conf->inactive_blocked)
sh = get_free_stripe(conf);
@@ -263,7 +265,7 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector
);
conf->inactive_blocked = 0;
} else
- init_stripe(sh, sector, pd_idx);
+ init_stripe(sh, sector, pd_idx, disks);
} else {
if (atomic_read(&sh->count)) {
if (!list_empty(&sh->lru))
@@ -300,6 +302,7 @@ static int grow_one_stripe(raid5_conf_t *conf)
kmem_cache_free(conf->slab_cache, sh);
return 0;
}
+ sh->disks = conf->raid_disks;
/* we just created an active stripe so... */
atomic_set(&sh->count, 1);
atomic_inc(&conf->active_stripes);
@@ -483,7 +486,7 @@ static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done,
{
struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks, i;
+ int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
if (bi->bi_size)
@@ -581,7 +584,7 @@ static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done,
{
struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks, i;
+ int disks = sh->disks, i;
unsigned long flags;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -735,7 +738,7 @@ static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
static sector_t compute_blocknr(struct stripe_head *sh, int i)
{
raid5_conf_t *conf = sh->raid_conf;
- int raid_disks = conf->raid_disks, data_disks = raid_disks - 1;
+ int raid_disks = sh->disks, data_disks = raid_disks - 1;
sector_t new_sector = sh->sector, check;
int sectors_per_chunk = conf->chunk_size >> 9;
sector_t stripe;
@@ -836,8 +839,7 @@ static void copy_data(int frombio, struct bio *bio,
static void compute_block(struct stripe_head *sh, int dd_idx)
{
- raid5_conf_t *conf = sh->raid_conf;
- int i, count, disks = conf->raid_disks;
+ int i, count, disks = sh->disks;
void *ptr[MAX_XOR_BLOCKS], *p;
PRINTK("compute_block, stripe %llu, idx %d\n",
@@ -867,7 +869,7 @@ static void compute_block(struct stripe_head *sh, int dd_idx)
static void compute_parity(struct stripe_head *sh, int method)
{
raid5_conf_t *conf = sh->raid_conf;
- int i, pd_idx = sh->pd_idx, disks = conf->raid_disks, count;
+ int i, pd_idx = sh->pd_idx, disks = sh->disks, count;
void *ptr[MAX_XOR_BLOCKS];
struct bio *chosen;
@@ -1055,7 +1057,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
static void handle_stripe(struct stripe_head *sh)
{
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks;
+ int disks = sh->disks;
struct bio *return_bi= NULL;
struct bio *bi;
int i;
@@ -1649,12 +1651,10 @@ static inline void raid5_plug_device(raid5_conf_t *conf)
spin_unlock_irq(&conf->device_lock);
}
-static int make_request (request_queue_t *q, struct bio * bi)
+static int make_request(request_queue_t *q, struct bio * bi)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
- const unsigned int raid_disks = conf->raid_disks;
- const unsigned int data_disks = raid_disks - 1;
unsigned int dd_idx, pd_idx;
sector_t new_sector;
sector_t logical_sector, last_sector;
@@ -1678,20 +1678,48 @@ static int make_request (request_queue_t *q, struct bio * bi)
for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
DEFINE_WAIT(w);
+ int disks;
- new_sector = raid5_compute_sector(logical_sector,
- raid_disks, data_disks, &dd_idx, &pd_idx, conf);
-
+ retry:
+ if (likely(conf->expand_progress == MaxSector))
+ disks = conf->raid_disks;
+ else {
+ spin_lock_irq(&conf->device_lock);
+ disks = conf->raid_disks;
+ if (logical_sector >= conf->expand_progress)
+ disks = conf->previous_raid_disks;
+ spin_unlock_irq(&conf->device_lock);
+ }
+ new_sector = raid5_compute_sector(logical_sector, disks, disks - 1,
+ &dd_idx, &pd_idx, conf);
PRINTK("raid5: make_request, sector %llu logical %llu\n",
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
- retry:
prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
- sh = get_active_stripe(conf, new_sector, pd_idx, (bi->bi_rw&RWA_MASK));
+ sh = get_active_stripe(conf, new_sector, disks, pd_idx, (bi->bi_rw&RWA_MASK));
if (sh) {
- if (!add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
- /* Add failed due to overlap. Flush everything
+ if (unlikely(conf->expand_progress != MaxSector)) {
+ /* expansion might have moved on while waiting for a
+ * stripe, so we much do the range check again.
+ */
+ int must_retry = 0;
+ spin_lock_irq(&conf->device_lock);
+ if (logical_sector < conf->expand_progress &&
+ disks == conf->previous_raid_disks)
+ /* mismatch, need to try again */
+ must_retry = 1;
+ spin_unlock_irq(&conf->device_lock);
+ if (must_retry) {
+ release_stripe(sh);
+ goto retry;
+ }
+ }
+
+ if (test_bit(STRIPE_EXPANDING, &sh->state) ||
+ !add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
+ /* Stripe is busy expanding or
+ * add failed due to overlap. Flush everything
* and wait a while
*/
raid5_unplug_device(mddev->queue);
@@ -1703,7 +1731,6 @@ static int make_request (request_queue_t *q, struct bio * bi)
raid5_plug_device(conf);
handle_stripe(sh);
release_stripe(sh);
-
} else {
/* cannot get stripe for read-ahead, just give-up */
clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -1779,9 +1806,9 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
first_sector = raid5_compute_sector((sector_t)stripe*data_disks*sectors_per_chunk
+ chunk_offset, raid_disks, data_disks, &dd_idx, &pd_idx, conf);
- sh = get_active_stripe(conf, sector_nr, pd_idx, 1);
+ sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
if (sh == NULL) {
- sh = get_active_stripe(conf, sector_nr, pd_idx, 0);
+ sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 0);
/* make sure we don't swamp the stripe cache if someone else
* is trying to get access
*/
@@ -1998,6 +2025,7 @@ static int run(mddev_t *mddev)
conf->level = mddev->level;
conf->algorithm = mddev->layout;
conf->max_nr_stripes = NR_STRIPES;
+ conf->expand_progress = MaxSector;
/* device size must be a multiple of chunk size */
mddev->size &= ~(mddev->chunk_size/1024 -1);
@@ -2128,7 +2156,7 @@ static void print_sh (struct stripe_head *sh)
printk("sh %llu, count %d.\n",
(unsigned long long)sh->sector, atomic_read(&sh->count));
printk("sh %llu, ", (unsigned long long)sh->sector);
- for (i = 0; i < sh->raid_conf->raid_disks; i++) {
+ for (i = 0; i < sh->disks; i++) {
printk("(cache%d: %p %ld) ",
i, sh->dev[i].page, sh->dev[i].flags);
}
OpenPOWER on IntegriCloud