summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/btree.c2
-rw-r--r--drivers/md/bcache/super.c55
-rw-r--r--drivers/md/dm-raid.c6
-rw-r--r--drivers/md/md-bitmap.c35
-rw-r--r--drivers/md/md-bitmap.h17
-rw-r--r--drivers/md/md.c14
-rw-r--r--drivers/md/raid1-10.c10
-rw-r--r--drivers/md/raid1.c19
-rw-r--r--drivers/md/raid10.c11
9 files changed, 106 insertions, 63 deletions
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 2cc2eb24dc8a..1d0100677357 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -89,8 +89,6 @@
* Test module load/unload
*/
-#define MAX_NEED_GC 64
-#define MAX_SAVE_PRIO 72
#define MAX_GC_TIMES 100
#define MIN_GC_NODES 100
#define GC_SLEEP_MS 100
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 1a2ce1a4b456..1efb768b2890 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1733,7 +1733,12 @@ static CLOSURE_CALLBACK(cache_set_flush)
mutex_unlock(&b->write_lock);
}
- if (ca->alloc_thread)
+ /*
+ * If the register_cache_set() call to bch_cache_set_alloc() failed,
+ * ca has not been assigned a value and return error.
+ * So we need check ca is not NULL during bch_cache_set_unregister().
+ */
+ if (ca && ca->alloc_thread)
kthread_stop(ca->alloc_thread);
if (c->journal.cur) {
@@ -2233,15 +2238,47 @@ static int cache_alloc(struct cache *ca)
bio_init(&ca->journal.bio, NULL, ca->journal.bio.bi_inline_vecs, 8, 0);
/*
- * when ca->sb.njournal_buckets is not zero, journal exists,
- * and in bch_journal_replay(), tree node may split,
- * so bucket of RESERVE_BTREE type is needed,
- * the worst situation is all journal buckets are valid journal,
- * and all the keys need to replay,
- * so the number of RESERVE_BTREE type buckets should be as much
- * as journal buckets
+ * When the cache disk is first registered, ca->sb.njournal_buckets
+ * is zero, and it is assigned in run_cache_set().
+ *
+ * When ca->sb.njournal_buckets is not zero, journal exists,
+ * and in bch_journal_replay(), tree node may split.
+ * The worst situation is all journal buckets are valid journal,
+ * and all the keys need to replay, so the number of RESERVE_BTREE
+ * type buckets should be as much as journal buckets.
+ *
+ * If the number of RESERVE_BTREE type buckets is too few, the
+ * bch_allocator_thread() may hang up and unable to allocate
+ * bucket. The situation is roughly as follows:
+ *
+ * 1. In bch_data_insert_keys(), if the operation is not op->replace,
+ * it will call the bch_journal(), which increments the journal_ref
+ * counter. This counter is only decremented after bch_btree_insert
+ * completes.
+ *
+ * 2. When calling bch_btree_insert, if the btree needs to split,
+ * it will call btree_split() and btree_check_reserve() to check
+ * whether there are enough reserved buckets in the RESERVE_BTREE
+ * slot. If not enough, bcache_btree_root() will repeatedly retry.
+ *
+ * 3. Normally, the bch_allocator_thread is responsible for filling
+ * the reservation slots from the free_inc bucket list. When the
+ * free_inc bucket list is exhausted, the bch_allocator_thread
+ * will call invalidate_buckets() until free_inc is refilled.
+ * Then bch_allocator_thread calls bch_prio_write() once. and
+ * bch_prio_write() will call bch_journal_meta() and waits for
+ * the journal write to complete.
+ *
+ * 4. During journal_write, journal_write_unlocked() is be called.
+ * If journal full occurs, journal_reclaim() and btree_flush_write()
+ * will be called sequentially, then retry journal_write.
+ *
+ * 5. When 2 and 4 occur together, IO will hung up and cannot recover.
+ *
+ * Therefore, reserve more RESERVE_BTREE type buckets.
*/
- btree_buckets = ca->sb.njournal_buckets ?: 8;
+ btree_buckets = clamp_t(size_t, ca->sb.nbuckets >> 7,
+ 32, SB_JOURNAL_BUCKETS);
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
if (!free) {
ret = -EPERM;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 127138c61be5..d296770478b2 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1356,11 +1356,7 @@ static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
return -EINVAL;
}
- /*
- * In device-mapper, we specify things in sectors, but
- * MD records this value in kB
- */
- if (value < 0 || value / 2 > COUNTER_MAX) {
+ if (value < 0) {
rs->ti->error = "Max write-behind limit out of range";
return -EINVAL;
}
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 37b08f26c62f..bd694910b01b 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -105,9 +105,19 @@
*
*/
+typedef __u16 bitmap_counter_t;
+
#define PAGE_BITS (PAGE_SIZE << 3)
#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
+#define COUNTER_BITS 16
+#define COUNTER_BIT_SHIFT 4
+#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
+
+#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
+#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
+#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
+
#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
@@ -789,7 +799,7 @@ static int md_bitmap_new_disk_sb(struct bitmap *bitmap)
* is a good choice? We choose COUNTER_MAX / 2 arbitrarily.
*/
write_behind = bitmap->mddev->bitmap_info.max_write_behind;
- if (write_behind > COUNTER_MAX)
+ if (write_behind > COUNTER_MAX / 2)
write_behind = COUNTER_MAX / 2;
sb->write_behind = cpu_to_le32(write_behind);
bitmap->mddev->bitmap_info.max_write_behind = write_behind;
@@ -1672,13 +1682,13 @@ __acquires(bitmap->lock)
&(bitmap->bp[page].map[pageoff]);
}
-static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
- unsigned long sectors)
+static void bitmap_start_write(struct mddev *mddev, sector_t offset,
+ unsigned long sectors)
{
struct bitmap *bitmap = mddev->bitmap;
if (!bitmap)
- return 0;
+ return;
while (sectors) {
sector_t blocks;
@@ -1688,7 +1698,7 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
bmc = md_bitmap_get_counter(&bitmap->counts, offset, &blocks, 1);
if (!bmc) {
spin_unlock_irq(&bitmap->counts.lock);
- return 0;
+ return;
}
if (unlikely(COUNTER(*bmc) == COUNTER_MAX)) {
@@ -1724,11 +1734,10 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
else
sectors = 0;
}
- return 0;
}
-static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
- unsigned long sectors)
+static void bitmap_end_write(struct mddev *mddev, sector_t offset,
+ unsigned long sectors)
{
struct bitmap *bitmap = mddev->bitmap;
@@ -2205,9 +2214,9 @@ static struct bitmap *__bitmap_create(struct mddev *mddev, int slot)
return ERR_PTR(err);
}
-static int bitmap_create(struct mddev *mddev, int slot)
+static int bitmap_create(struct mddev *mddev)
{
- struct bitmap *bitmap = __bitmap_create(mddev, slot);
+ struct bitmap *bitmap = __bitmap_create(mddev, -1);
if (IS_ERR(bitmap))
return PTR_ERR(bitmap);
@@ -2670,7 +2679,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
}
mddev->bitmap_info.offset = offset;
- rv = bitmap_create(mddev, -1);
+ rv = bitmap_create(mddev);
if (rv)
goto out;
@@ -3003,8 +3012,8 @@ static struct bitmap_operations bitmap_ops = {
.end_behind_write = bitmap_end_behind_write,
.wait_behind_writes = bitmap_wait_behind_writes,
- .startwrite = bitmap_startwrite,
- .endwrite = bitmap_endwrite,
+ .start_write = bitmap_start_write,
+ .end_write = bitmap_end_write,
.start_sync = bitmap_start_sync,
.end_sync = bitmap_end_sync,
.cond_end_sync = bitmap_cond_end_sync,
diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h
index 31c93019c76b..59e9dd45cfde 100644
--- a/drivers/md/md-bitmap.h
+++ b/drivers/md/md-bitmap.h
@@ -9,15 +9,6 @@
#define BITMAP_MAGIC 0x6d746962
-typedef __u16 bitmap_counter_t;
-#define COUNTER_BITS 16
-#define COUNTER_BIT_SHIFT 4
-#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
-
-#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
-#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
-#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
-
/* use these for bitmap->flags and bitmap->sb->state bit-fields */
enum bitmap_state {
BITMAP_STALE = 1, /* the bitmap file is out of date or had -EIO */
@@ -72,7 +63,7 @@ struct md_bitmap_stats {
struct bitmap_operations {
bool (*enabled)(struct mddev *mddev);
- int (*create)(struct mddev *mddev, int slot);
+ int (*create)(struct mddev *mddev);
int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize,
bool init);
@@ -89,10 +80,10 @@ struct bitmap_operations {
void (*end_behind_write)(struct mddev *mddev);
void (*wait_behind_writes)(struct mddev *mddev);
- int (*startwrite)(struct mddev *mddev, sector_t offset,
+ void (*start_write)(struct mddev *mddev, sector_t offset,
+ unsigned long sectors);
+ void (*end_write)(struct mddev *mddev, sector_t offset,
unsigned long sectors);
- void (*endwrite)(struct mddev *mddev, sector_t offset,
- unsigned long sectors);
bool (*start_sync)(struct mddev *mddev, sector_t offset,
sector_t *blocks, bool degraded);
void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0fde115e921f..09042b060086 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -6225,7 +6225,7 @@ int md_run(struct mddev *mddev)
}
if (err == 0 && pers->sync_request &&
(mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
- err = mddev->bitmap_ops->create(mddev, -1);
+ err = mddev->bitmap_ops->create(mddev);
if (err)
pr_warn("%s: failed to create bitmap (%d)\n",
mdname(mddev), err);
@@ -7285,7 +7285,7 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
err = 0;
if (mddev->pers) {
if (fd >= 0) {
- err = mddev->bitmap_ops->create(mddev, -1);
+ err = mddev->bitmap_ops->create(mddev);
if (!err)
err = mddev->bitmap_ops->load(mddev);
@@ -7601,7 +7601,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
mddev->bitmap_info.default_offset;
mddev->bitmap_info.space =
mddev->bitmap_info.default_space;
- rv = mddev->bitmap_ops->create(mddev, -1);
+ rv = mddev->bitmap_ops->create(mddev);
if (!rv)
rv = mddev->bitmap_ops->load(mddev);
@@ -8799,14 +8799,14 @@ static void md_bitmap_start(struct mddev *mddev,
mddev->pers->bitmap_sector(mddev, &md_io_clone->offset,
&md_io_clone->sectors);
- mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset,
- md_io_clone->sectors);
+ mddev->bitmap_ops->start_write(mddev, md_io_clone->offset,
+ md_io_clone->sectors);
}
static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone)
{
- mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset,
- md_io_clone->sectors);
+ mddev->bitmap_ops->end_write(mddev, md_io_clone->offset,
+ md_io_clone->sectors);
}
static void md_end_clone_io(struct bio *bio)
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index c7efd8aab675..b8b3a9069701 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -293,3 +293,13 @@ static inline bool raid1_should_read_first(struct mddev *mddev,
return false;
}
+
+/*
+ * bio with REQ_RAHEAD or REQ_NOWAIT can fail at anytime, before such IO is
+ * submitted to the underlying disks, hence don't record badblocks or retry
+ * in this case.
+ */
+static inline bool raid1_should_handle_error(struct bio *bio)
+{
+ return !(bio->bi_opf & (REQ_RAHEAD | REQ_NOWAIT));
+}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 657d481525be..19c5a0ce5a40 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -373,14 +373,16 @@ static void raid1_end_read_request(struct bio *bio)
*/
update_head_pos(r1_bio->read_disk, r1_bio);
- if (uptodate)
+ if (uptodate) {
set_bit(R1BIO_Uptodate, &r1_bio->state);
- else if (test_bit(FailFast, &rdev->flags) &&
- test_bit(R1BIO_FailFast, &r1_bio->state))
+ } else if (test_bit(FailFast, &rdev->flags) &&
+ test_bit(R1BIO_FailFast, &r1_bio->state)) {
/* This was a fail-fast read so we definitely
* want to retry */
;
- else {
+ } else if (!raid1_should_handle_error(bio)) {
+ uptodate = 1;
+ } else {
/* If all other devices have failed, we want to return
* the error upwards rather than fail the last device.
* Here we redefine "uptodate" to mean "Don't want to retry"
@@ -451,16 +453,15 @@ static void raid1_end_write_request(struct bio *bio)
struct bio *to_put = NULL;
int mirror = find_bio_disk(r1_bio, bio);
struct md_rdev *rdev = conf->mirrors[mirror].rdev;
- bool discard_error;
sector_t lo = r1_bio->sector;
sector_t hi = r1_bio->sector + r1_bio->sectors;
-
- discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
+ bool ignore_error = !raid1_should_handle_error(bio) ||
+ (bio->bi_status && bio_op(bio) == REQ_OP_DISCARD);
/*
* 'one mirror IO has finished' event handler:
*/
- if (bio->bi_status && !discard_error) {
+ if (bio->bi_status && !ignore_error) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
@@ -511,7 +512,7 @@ static void raid1_end_write_request(struct bio *bio)
/* Maybe we can clear some bad blocks. */
if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
- !discard_error) {
+ !ignore_error) {
r1_bio->bios[mirror] = IO_MADE_GOOD;
set_bit(R1BIO_MadeGood, &r1_bio->state);
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index dce06bf65016..b74780af4c22 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -399,6 +399,8 @@ static void raid10_end_read_request(struct bio *bio)
* wait for the 'master' bio.
*/
set_bit(R10BIO_Uptodate, &r10_bio->state);
+ } else if (!raid1_should_handle_error(bio)) {
+ uptodate = 1;
} else {
/* If all other devices that store this block have
* failed, we want to return the error upwards rather
@@ -456,9 +458,8 @@ static void raid10_end_write_request(struct bio *bio)
int slot, repl;
struct md_rdev *rdev = NULL;
struct bio *to_put = NULL;
- bool discard_error;
-
- discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
+ bool ignore_error = !raid1_should_handle_error(bio) ||
+ (bio->bi_status && bio_op(bio) == REQ_OP_DISCARD);
dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
@@ -472,7 +473,7 @@ static void raid10_end_write_request(struct bio *bio)
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
- if (bio->bi_status && !discard_error) {
+ if (bio->bi_status && !ignore_error) {
if (repl)
/* Never record new bad blocks to replacement,
* just fail it.
@@ -527,7 +528,7 @@ static void raid10_end_write_request(struct bio *bio)
/* Maybe we can clear some bad blocks. */
if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
r10_bio->sectors) &&
- !discard_error) {
+ !ignore_error) {
bio_put(bio);
if (repl)
r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
generated by cgit (git 2.34.1) at 2025-06-07 17:16:21 +0000