Btrfs: rework qgroup accounting
Currently qgroups account for space by intercepting delayed ref updates to fs
trees. It does this by adding sequence numbers to delayed ref updates so that
it can figure out how the tree looked before the update so we can adjust the
counters properly. The problem with this is that it does not allow delayed refs
to be merged, so if you say are defragging an extent with 5k snapshots pointing
to it we will thrash the delayed ref lock because we need to go back and
manually merge these things together. Instead we want to process quota changes
when we know they are going to happen, like when we first allocate an extent, we
free a reference for an extent, we add new references etc. This patch
accomplishes this by only adding qgroup operations for real ref changes. We
only modify the sequence number when we need to lookup roots for bytenrs, this
reduces the amount of churn on the sequence number and allows us to merge
delayed refs as we add them most of the time. This patch encompasses a bunch of
architectural changes
1) qgroup ref operations: instead of tracking qgroup operations through the
delayed refs we simply add new ref operations whenever we notice that we need to
when we've modified the refs themselves.
2) tree mod seq: we no longer have this separation of major/minor counters.
this makes the sequence number stuff much more sane and we can remove some
locking that was needed to protect the counter.
3) delayed ref seq: we now read the tree mod seq number and use that as our
sequence. This means each new delayed ref doesn't have it's own unique sequence
number, rather whenever we go to lookup backrefs we inc the sequence number so
we can make sure to keep any new operations from screwing up our world view at
that given point. This allows us to merge delayed refs during runtime.
With all of these changes the delayed ref stuff is a little saner and the qgroup
accounting stuff no longer goes negative in some cases like it was before.
Thanks,
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 242a37c..a21a4ac 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -58,6 +58,7 @@
#include "dev-replace.h"
#include "props.h"
#include "sysfs.h"
+#include "qgroup.h"
#ifdef CONFIG_64BIT
/* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
@@ -2941,6 +2942,41 @@
return ret;
}
+/* Helper to check and see if this root currently has a ref on the given disk
+ * bytenr. If it does then we need to update the quota for this root. This
+ * doesn't do anything if quotas aren't enabled.
+ */
+static int check_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+ u64 disko)
+{
+ struct seq_list tree_mod_seq_elem = {};
+ struct ulist *roots;
+ struct ulist_iterator uiter;
+ struct ulist_node *root_node = NULL;
+ int ret;
+
+ if (!root->fs_info->quota_enabled)
+ return 1;
+
+ btrfs_get_tree_mod_seq(root->fs_info, &tree_mod_seq_elem);
+ ret = btrfs_find_all_roots(trans, root->fs_info, disko,
+ tree_mod_seq_elem.seq, &roots);
+ if (ret < 0)
+ goto out;
+ ret = 0;
+ ULIST_ITER_INIT(&uiter);
+ while ((root_node = ulist_next(roots, &uiter))) {
+ if (root_node->val == root->objectid) {
+ ret = 1;
+ break;
+ }
+ }
+ ulist_free(roots);
+out:
+ btrfs_put_tree_mod_seq(root->fs_info, &tree_mod_seq_elem);
+ return ret;
+}
+
/**
* btrfs_clone() - clone a range from inode file to another
*
@@ -2964,7 +3000,9 @@
u32 nritems;
int slot;
int ret;
+ int no_quota;
u64 len = olen_aligned;
+ u64 last_disko = 0;
ret = -ENOMEM;
buf = vmalloc(btrfs_level_size(root, 0));
@@ -2996,6 +3034,7 @@
nritems = btrfs_header_nritems(path->nodes[0]);
process_slot:
+ no_quota = 1;
if (path->slots[0] >= nritems) {
ret = btrfs_next_leaf(BTRFS_I(src)->root, path);
if (ret < 0)
@@ -3128,6 +3167,28 @@
datao);
btrfs_set_file_extent_num_bytes(leaf, extent,
datal);
+
+ /*
+ * We need to look up the roots that point at
+ * this bytenr and see if the new root does. If
+ * it does not we need to make sure we update
+ * quotas appropriately.
+ */
+ if (disko && root != BTRFS_I(src)->root &&
+ disko != last_disko) {
+ no_quota = check_ref(trans, root,
+ disko);
+ if (no_quota < 0) {
+ btrfs_abort_transaction(trans,
+ root,
+ ret);
+ btrfs_end_transaction(trans,
+ root);
+ ret = no_quota;
+ goto out;
+ }
+ }
+
if (disko) {
inode_add_bytes(inode, datal);
ret = btrfs_inc_extent_ref(trans, root,
@@ -3135,7 +3196,7 @@
root->root_key.objectid,
btrfs_ino(inode),
new_key.offset - datao,
- 0);
+ no_quota);
if (ret) {
btrfs_abort_transaction(trans,
root,