summaryrefslogtreecommitdiff
path: root/fs/btrfs/extent-tree.c
diff options
context:
space:
mode:
authorJosef Bacik <jbacik@fb.com>2015-02-11 15:08:59 -0500
committerChris Mason <clm@fb.com>2015-02-14 08:22:48 -0800
commitdcab6a3b2ae657a2017637083c28ee303b6b1b8e (patch)
tree4aa9951e7ab997702f90aec9882f305e1885fc40 /fs/btrfs/extent-tree.c
parent3266789f9d08b27275bae5ab1dcd27d1bbf15e79 (diff)
Btrfs: account for large extents with enospc
On our gluster boxes we stream large tar balls of backups onto our fses. With 160gb of ram this means we get really large contiguous ranges of dirty data, but the way our ENOSPC stuff works is that as long as it's contiguous we only hold metadata reservation for one extent. The problem is we limit our extents to 128mb, so we'll end up with at least 800 extents so our enospc accounting is quite a bit lower than what we need. To keep track of this make sure we increase outstanding_extents for every multiple of the max extent size so we can be sure to have enough reserved metadata space. Thanks, Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
Diffstat (limited to 'fs/btrfs/extent-tree.c')
-rw-r--r--fs/btrfs/extent-tree.c16
1 files changed, 11 insertions, 5 deletions
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 50de1fa6fc9e..0f6737063142 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4963,19 +4963,25 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
/**
* drop_outstanding_extent - drop an outstanding extent
* @inode: the inode we're dropping the extent for
+ * @num_bytes: the number of bytes we're relaseing.
*
* This is called when we are freeing up an outstanding extent, either called
* after an error or after an extent is written. This will return the number of
* reserved extents that need to be freed. This must be called with
* BTRFS_I(inode)->lock held.
*/
-static unsigned drop_outstanding_extent(struct inode *inode)
+static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
{
unsigned drop_inode_space = 0;
unsigned dropped_extents = 0;
+ unsigned num_extents = 0;
- BUG_ON(!BTRFS_I(inode)->outstanding_extents);
- BTRFS_I(inode)->outstanding_extents--;
+ num_extents = (unsigned)div64_u64(num_bytes +
+ BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+ ASSERT(num_extents);
+ ASSERT(BTRFS_I(inode)->outstanding_extents >= num_extents);
+ BTRFS_I(inode)->outstanding_extents -= num_extents;
if (BTRFS_I(inode)->outstanding_extents == 0 &&
test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
@@ -5146,7 +5152,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
out_fail:
spin_lock(&BTRFS_I(inode)->lock);
- dropped = drop_outstanding_extent(inode);
+ dropped = drop_outstanding_extent(inode, num_bytes);
/*
* If the inodes csum_bytes is the same as the original
* csum_bytes then we know we haven't raced with any free()ers
@@ -5225,7 +5231,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
num_bytes = ALIGN(num_bytes, root->sectorsize);
spin_lock(&BTRFS_I(inode)->lock);
- dropped = drop_outstanding_extent(inode);
+ dropped = drop_outstanding_extent(inode, num_bytes);
if (num_bytes)
to_free = calc_csum_metadata_size(inode, num_bytes, 0);