aboutsummaryrefslogtreecommitdiffstats
path: root/fs/btrfs/ctree.h
diff options
context:
space:
mode:
authorJosef Bacik <josef@redhat.com>2009-09-11 16:12:44 -0400
committerChris Mason <chris.mason@oracle.com>2009-09-28 16:29:42 -0400
commit9ed74f2dba6ebf9f30b80554290bfc73cc3ef083 (patch)
tree763d58a4a11ceca26dcdaedefb1fd662c4e2fa8b /fs/btrfs/ctree.h
parentc65ddb52dc412c9b67681b1aa16cd1bac8434e24 (diff)
Btrfs: proper -ENOSPC handling
At the start of a transaction we do a btrfs_reserve_metadata_space() and specify how many items we plan on modifying. Then once we've done our modifications and such, just call btrfs_unreserve_metadata_space() for the same number of items we reserved. For keeping track of metadata needed for data I've had to add an extent_io op for when we merge extents. This lets us track space properly when we are doing sequential writes, so we don't end up reserving way more metadata space than what we need. The only place where the metadata space accounting is not done is in the relocation code. This is because Yan is going to be reworking that code in the near future, so running btrfs-vol -b could still possibly result in a ENOSPC related panic. This patch also turns off the metadata_ratio stuff in order to allow users to more efficiently use their disk space. This patch makes it so we track how much metadata we need for an inode's delayed allocation extents by tracking how many extents are currently waiting for allocation. It introduces two new callbacks for the extent_io tree's, merge_extent_hook and split_extent_hook. These help us keep track of when we merge delalloc extents together and split them up. Reservations are handled prior to any actually dirty'ing occurs, and then we unreserve after we dirty. btrfs_unreserve_metadata_for_delalloc() will make the appropriate unreservations as needed based on the number of reservations we currently have and the number of extents we currently have. Doing the reservation outside of doing any of the actual dirty'ing lets us do things like filemap_flush() the inode to try and force delalloc to happen, or as a last resort actually start allocation on all delalloc inodes in the fs. This has survived dbench, fs_mark and an fsx torture test. Signed-off-by: Josef Bacik <jbacik@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs/ctree.h')
-rw-r--r--fs/btrfs/ctree.h23
1 files changed, 16 insertions, 7 deletions
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 80599b4e42bd..b3959a150c3b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -675,18 +675,19 @@ struct btrfs_space_info {
675 current allocations */ 675 current allocations */
676 u64 bytes_readonly; /* total bytes that are read only */ 676 u64 bytes_readonly; /* total bytes that are read only */
677 u64 bytes_super; /* total bytes reserved for the super blocks */ 677 u64 bytes_super; /* total bytes reserved for the super blocks */
678 678 u64 bytes_root; /* the number of bytes needed to commit a
679 /* delalloc accounting */ 679 transaction */
680 u64 bytes_delalloc; /* number of bytes reserved for allocation,
681 this space is not necessarily reserved yet
682 by the allocator */
683 u64 bytes_may_use; /* number of bytes that may be used for 680 u64 bytes_may_use; /* number of bytes that may be used for
684 delalloc */ 681 delalloc/allocations */
682 u64 bytes_delalloc; /* number of bytes currently reserved for
683 delayed allocation */
685 684
686 int full; /* indicates that we cannot allocate any more 685 int full; /* indicates that we cannot allocate any more
687 chunks for this space */ 686 chunks for this space */
688 int force_alloc; /* set if we need to force a chunk alloc for 687 int force_alloc; /* set if we need to force a chunk alloc for
689 this space */ 688 this space */
689 int force_delalloc; /* make people start doing filemap_flush until
690 we're under a threshold */
690 691
691 struct list_head list; 692 struct list_head list;
692 693
@@ -695,6 +696,9 @@ struct btrfs_space_info {
695 spinlock_t lock; 696 spinlock_t lock;
696 struct rw_semaphore groups_sem; 697 struct rw_semaphore groups_sem;
697 atomic_t caching_threads; 698 atomic_t caching_threads;
699
700 int allocating_chunk;
701 wait_queue_head_t wait;
698}; 702};
699 703
700/* 704/*
@@ -2022,7 +2026,12 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
2022void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde); 2026void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
2023void btrfs_clear_space_info_full(struct btrfs_fs_info *info); 2027void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
2024 2028
2025int btrfs_check_metadata_free_space(struct btrfs_root *root); 2029int btrfs_reserve_metadata_space(struct btrfs_root *root, int num_items);
2030int btrfs_unreserve_metadata_space(struct btrfs_root *root, int num_items);
2031int btrfs_unreserve_metadata_for_delalloc(struct btrfs_root *root,
2032 struct inode *inode, int num_items);
2033int btrfs_reserve_metadata_for_delalloc(struct btrfs_root *root,
2034 struct inode *inode, int num_items);
2026int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode, 2035int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode,
2027 u64 bytes); 2036 u64 bytes);
2028void btrfs_free_reserved_data_space(struct btrfs_root *root, 2037void btrfs_free_reserved_data_space(struct btrfs_root *root,