From: Mingzhe Zou <mingzhe.zou@xxxxxxxxxxxx>
If the bucket was reused while our bio was in flight, we might
have read the wrong data. Currently, we will reread the data from
the backing device. This not only reduces performance, but also
makes the process more complex.
When the bucket is in use, we hope not to reclaim it.
Signed-off-by: Mingzhe Zou <mingzhe.zou@xxxxxxxxxxxx>
---
drivers/md/bcache/alloc.c | 30 +++++++++++++++++++++---------
drivers/md/bcache/bcache.h | 3 ++-
2 files changed, 23 insertions(+), 10 deletions(-)
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index da50f6661bae..32f65d6fc906 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -134,25 +134,39 @@ bool bch_can_invalidate_bucket(struct cache *ca, struct bucket *b)
!atomic_read(&b->pin) && can_inc_bucket_gen(b));
}
-void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
+bool __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
{
lockdep_assert_held(&ca->set->bucket_lock);
BUG_ON(GC_MARK(b) && GC_MARK(b) != GC_MARK_RECLAIMABLE);
+ /*
+ * If the bucket was reused while read bio was in flight, it will
+ * reread the data from the backing device. This will increase latency
+ * and cause other errors. When b->pin is not 0, do not invalidate
+ * the bucket.
+ */
+
+ b->invalidating = 1;
+
+ if (atomic_inc_return(&b->pin) > 1) {
+ atomic_dec(&b->pin);
+ return false;
+ }
+
if (GC_SECTORS_USED(b))
trace_bcache_invalidate(ca, b - ca->buckets);
bch_inc_gen(ca, b);
b->prio = INITIAL_PRIO;
- atomic_inc(&b->pin);
b->reclaimable_in_gc = 0;
+ b->invalidating = 0;
+ return true;
}
static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
{
- __bch_invalidate_one_bucket(ca, b);
-
- fifo_push(&ca->free_inc, b - ca->buckets);
+ if (bch_can_invalidate_bucket(ca, b) && __bch_invalidate_one_bucket(ca, b))
+ fifo_push(&ca->free_inc, b - ca->buckets);
}
/*
@@ -253,8 +267,7 @@ static void invalidate_buckets_fifo(struct cache *ca)
b = ca->buckets + ca->fifo_last_bucket++;
- if (bch_can_invalidate_bucket(ca, b))
- bch_invalidate_one_bucket(ca, b);
+ bch_invalidate_one_bucket(ca, b);
if (++checked >= ca->sb.nbuckets) {
ca->invalidate_needs_gc = 1;
@@ -279,8 +292,7 @@ static void invalidate_buckets_random(struct cache *ca)
b = ca->buckets + n;
- if (bch_can_invalidate_bucket(ca, b))
- bch_invalidate_one_bucket(ca, b);
+ bch_invalidate_one_bucket(ca, b);
if (++checked >= ca->sb.nbuckets / 2) {
ca->invalidate_needs_gc = 1;
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 785b0d9008fa..2777d72e1038 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -201,6 +201,7 @@ struct bucket {
uint8_t last_gc; /* Most out of date gen in the btree */
uint16_t gc_mark; /* Bitfield used by GC. See below for field */
uint16_t reclaimable_in_gc:1;
+ uint16_t invalidating:1;
};
/*
@@ -981,7 +982,7 @@ uint8_t bch_inc_gen(struct cache *ca, struct bucket *b);
void bch_rescale_priorities(struct cache_set *c, int sectors);
bool bch_can_invalidate_bucket(struct cache *ca, struct bucket *b);
-void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b);
+bool __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b);
void __bch_bucket_free(struct cache *ca, struct bucket *b);
void bch_bucket_free(struct cache_set *c, struct bkey *k);
--
2.34.1
