We used to issue a checksum to an extent state of 4K range for read endio,
but now we want to use larger range for performance optimization, so instead we
create a radix tree for checksum, where an item stands for checksum of 4K data.
Signed-off-by: Liu Bo <liubo2009@xxxxxxxxxxxxxx>
---
fs/btrfs/extent_io.c | 84 ++++++++++++--------------------------------------
fs/btrfs/extent_io.h | 2 +
fs/btrfs/inode.c | 7 +---
3 files changed, 23 insertions(+), 70 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2c8f7b2..2923ede 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -117,10 +117,12 @@ void extent_io_tree_init(struct extent_io_tree *tree,
{
tree->state = RB_ROOT;
INIT_RADIX_TREE(&tree->buffer, GFP_ATOMIC);
+ INIT_RADIX_TREE(&tree->csum, GFP_ATOMIC);
tree->ops = NULL;
tree->dirty_bytes = 0;
spin_lock_init(&tree->lock);
spin_lock_init(&tree->buffer_lock);
+ spin_lock_init(&tree->csum_lock);
tree->mapping = mapping;
}
@@ -703,15 +705,6 @@ static void cache_state(struct extent_state *state,
}
}
-static void uncache_state(struct extent_state **cached_ptr)
-{
- if (cached_ptr && (*cached_ptr)) {
- struct extent_state *state = *cached_ptr;
- *cached_ptr = NULL;
- free_extent_state(state);
- }
-}
-
/*
* set some bits on a range in the tree. This may require allocations or
* sleeping, so the gfp mask is used to indicate what is allowed.
@@ -1666,56 +1659,32 @@ out:
*/
int set_state_private(struct extent_io_tree *tree, u64 start, u64 private)
{
- struct rb_node *node;
- struct extent_state *state;
int ret = 0;
- spin_lock(&tree->lock);
- /*
- * this search will find all the extents that end after
- * our range starts.
- */
- node = tree_search(tree, start);
- if (!node) {
- ret = -ENOENT;
- goto out;
- }
- state = rb_entry(node, struct extent_state, rb_node);
- if (state->start != start) {
- ret = -ENOENT;
- goto out;
- }
- state->private = private;
-out:
- spin_unlock(&tree->lock);
+ spin_lock(&tree->csum_lock);
+ ret = radix_tree_insert(&tree->csum, (unsigned long)start,
+ (void *)((unsigned long)private << 1));
+ BUG_ON(ret);
+ spin_unlock(&tree->csum_lock);
return ret;
}
int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private)
{
- struct rb_node *node;
- struct extent_state *state;
- int ret = 0;
+ void **slot = NULL;
- spin_lock(&tree->lock);
- /*
- * this search will find all the extents that end after
- * our range starts.
- */
- node = tree_search(tree, start);
- if (!node) {
- ret = -ENOENT;
- goto out;
- }
- state = rb_entry(node, struct extent_state, rb_node);
- if (state->start != start) {
- ret = -ENOENT;
- goto out;
+ spin_lock(&tree->csum_lock);
+ slot = radix_tree_lookup_slot(&tree->csum, (unsigned long)start);
+ if (!slot) {
+ spin_unlock(&tree->csum_lock);
+ return -ENOENT;
}
- *private = state->private;
-out:
- spin_unlock(&tree->lock);
- return ret;
+ *private = (u64)(*slot) >> 1;
+
+ radix_tree_delete(&tree->csum, (unsigned long)start);
+ spin_unlock(&tree->csum_lock);
+
+ return 0;
}
/*
@@ -2294,7 +2263,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
do {
struct page *page = bvec->bv_page;
struct extent_state *cached = NULL;
- struct extent_state *state;
pr_debug("end_bio_extent_readpage: bi_vcnt=%d, idx=%d, err=%d, "
"mirror=%ld\n", bio->bi_vcnt, bio->bi_idx, err,
@@ -2313,21 +2281,10 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
if (++bvec <= bvec_end)
prefetchw(&bvec->bv_page->flags);
- spin_lock(&tree->lock);
- state = find_first_extent_bit_state(tree, start, EXTENT_LOCKED);
- if (state && state->start == start) {
- /*
- * take a reference on the state, unlock will drop
- * the ref
- */
- cache_state(state, &cached);
- }
- spin_unlock(&tree->lock);
-
mirror = (int)(unsigned long)bio->bi_bdev;
if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
ret = tree->ops->readpage_end_io_hook(page, start, end,
- state, mirror);
+ NULL, mirror);
if (ret) {
/* no IO indicated but software detected errors
* in the block, either checksum errors or
@@ -2369,7 +2326,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
test_bit(BIO_UPTODATE, &bio->bi_flags);
if (err)
uptodate = 0;
- uncache_state(&cached);
continue;
}
}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 25900af..c896962 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -96,11 +96,13 @@ struct extent_io_ops {
struct extent_io_tree {
struct rb_root state;
struct radix_tree_root buffer;
+ struct radix_tree_root csum;
struct address_space *mapping;
u64 dirty_bytes;
int track_uptodate;
spinlock_t lock;
spinlock_t buffer_lock;
+ spinlock_t csum_lock;
struct extent_io_ops *ops;
};
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f6ab6f5..da0da44 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2008,12 +2008,7 @@ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
return 0;
}
- if (state && state->start == start) {
- private = state->private;
- ret = 0;
- } else {
- ret = get_state_private(io_tree, start, &private);
- }
+ ret = get_state_private(io_tree, start, &private);
kaddr = kmap_atomic(page);
if (ret)
goto zeroit;
--
1.6.5.2
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
