summaryrefslogtreecommitdiff
path: root/fs/btrfs/dir-item.c
diff options
context:
space:
mode:
authorChris Mason <chris.mason@oracle.com>2009-03-13 11:00:37 -0400
committerChris Mason <chris.mason@oracle.com>2009-03-24 16:14:28 -0400
commitb9473439d3e84d9fc1a0a83faca69cc1b7566341 (patch)
treebef8321b80589026b617d61d0fabaf545d459269 /fs/btrfs/dir-item.c
parent89573b9c516b24af8a3b9958dd5afca8fa874e3d (diff)
Btrfs: leave btree locks spinning more often
btrfs_mark_buffer dirty would set dirty bits in the extent_io tree for the buffers it was dirtying. This may require a kmalloc and it was not atomic. So, anyone who called btrfs_mark_buffer_dirty had to set any btree locks they were holding to blocking first. This commit changes dirty tracking for extent buffers to just use a flag in the extent buffer. Now that we have one and only one extent buffer per page, this can be safely done without losing dirty bits along the way. This also introduces a path->leave_spinning flag that callers of btrfs_search_slot can use to indicate they will properly deal with a path returned where all the locks are spinning instead of blocking. Many of the btree search callers now expect spinning paths, resulting in better btree concurrency overall. Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs/dir-item.c')
-rw-r--r--fs/btrfs/dir-item.c3
1 files changed, 3 insertions, 0 deletions
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 926a0b287a7d..1d70236ba00c 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -145,7 +145,10 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
key.objectid = dir;
btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY);
key.offset = btrfs_name_hash(name, name_len);
+
path = btrfs_alloc_path();
+ path->leave_spinning = 1;
+
data_size = sizeof(*dir_item) + name_len;
dir_item = insert_with_overflow(trans, root, path, &key, data_size,
name, name_len);