While removing a file with dedup extents, we could have a great number of
delayed refs pending to process, and these refs refer to droping
a ref of the extent, which is of BTRFS_DROP_DELAYED_REF type.
But in order to prevent an extent's ref count from going down to zero when
there still are pending delayed refs, we first select those "adding a ref"
ones, which is of BTRFS_ADD_DELAYED_REF type.
So in removing case, all of our delayed refs are of BTRFS_DROP_DELAYED_REF type,
but we have to walk all the refs issued to the extent to find any
BTRFS_ADD_DELAYED_REF types and end up there is no such thing, and then start
over again to find BTRFS_DROP_DELAYED_REF.
This is really unnecessary, we can improve this by tracking how many
BTRFS_ADD_DELAYED_REF refs we have and search by the right type.
Signed-off-by: Liu Bo <bo.li....@oracle.com>
---
fs/btrfs/delayed-ref.c | 8 ++++++++
fs/btrfs/delayed-ref.h | 3 +++
fs/btrfs/extent-tree.c | 16 +++++++++++++---
3 files changed, 24 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 3ab37b6..6435d78 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -538,6 +538,9 @@ update_existing_head_ref(struct btrfs_delayed_ref_node
*existing,
* currently, for refs we just added we know we're a-ok.
*/
existing->ref_mod += update->ref_mod;
+ WARN_ON(update->ref_mod > 1);
+ if (update->ref_mod == 1)
+ existing_ref->add_cnt++;
spin_unlock(&existing_ref->lock);
}
@@ -601,6 +604,11 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
head_ref->is_data = is_data;
head_ref->ref_root = RB_ROOT;
head_ref->processing = 0;
+ /* track added ref, more comments in select_delayed_ref() */
+ if (count_mod == 1)
+ head_ref->add_cnt = 1;
+ else
+ head_ref->add_cnt = 0;
spin_lock_init(&head_ref->lock);
mutex_init(&head_ref->mutex);
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 4ba9b93..905f991 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -87,6 +87,9 @@ struct btrfs_delayed_ref_head {
struct rb_node href_node;
struct btrfs_delayed_extent_op *extent_op;
+
+ int add_cnt;
+
/*
* when a new extent is allocated, it is just reserved in memory
* The actual extent isn't inserted into the extent allocation tree
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 088846c..191f0a7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2347,7 +2347,11 @@ static noinline struct btrfs_delayed_ref_node *
select_delayed_ref(struct btrfs_delayed_ref_head *head)
{
struct rb_node *node;
- struct btrfs_delayed_ref_node *ref, *last = NULL;;
+ struct btrfs_delayed_ref_node *ref, *last = NULL;
+ int action = BTRFS_ADD_DELAYED_REF;
+
+ if (head->add_cnt == 0)
+ action = BTRFS_DROP_DELAYED_REF;
/*
* select delayed ref of type BTRFS_ADD_DELAYED_REF first.
@@ -2358,10 +2362,13 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head)
while (node) {
ref = rb_entry(node, struct btrfs_delayed_ref_node,
rb_node);
- if (ref->action == BTRFS_ADD_DELAYED_REF)
+ if (ref->action == action) {
+ if (ref->action == BTRFS_ADD_DELAYED_REF)
+ head->add_cnt--;
return ref;
- else if (last == NULL)
+ } else if (last == NULL) {
last = ref;
+ }
node = rb_next(node);
}
return last;
@@ -2435,6 +2442,9 @@ static noinline int __btrfs_run_delayed_refs(struct
btrfs_trans_handle *trans,
if (ref && ref->seq &&
btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
+ if (ref->action == BTRFS_ADD_DELAYED_REF)
+ locked_ref->add_cnt++;
+
spin_unlock(&locked_ref->lock);
btrfs_delayed_ref_unlock(locked_ref);
spin_lock(&delayed_refs->lock);
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
