From 5d4f98a28c7d334091c1b7744f48a1acdd2a4ae0 Mon Sep 17 00:00:00 2001 From: Yan Zheng Date: Wed, 10 Jun 2009 10:45:14 -0400 Subject: Btrfs: Mixed back reference (FORWARD ROLLING FORMAT CHANGE) This commit introduces a new kind of back reference for btrfs metadata. Once a filesystem has been mounted with this commit, IT WILL NO LONGER BE MOUNTABLE BY OLDER KERNELS. When a tree block in subvolume tree is cow'd, the reference counts of all extents it points to are increased by one. At transaction commit time, the old root of the subvolume is recorded in a "dead root" data structure, and the btree it points to is later walked, dropping reference counts and freeing any blocks where the reference count goes to 0. The increments done during cow and decrements done after commit cancel out, and the walk is a very expensive way to go about freeing the blocks that are no longer referenced by the new btree root. This commit reduces the transaction overhead by avoiding the need for dead root records. When a non-shared tree block is cow'd, we free the old block at once, and the new block inherits old block's references. When a tree block with reference count > 1 is cow'd, we increase the reference counts of all extents the new block points to by one, and decrease the old block's reference count by one. This dead tree avoidance code removes the need to modify the reference counts of lower level extents when a non-shared tree block is cow'd. But we still need to update back ref for all pointers in the block. This is because the location of the block is recorded in the back ref item. We can solve this by introducing a new type of back ref. The new back ref provides information about pointer's key, level and in which tree the pointer lives. This information allow us to find the pointer by searching the tree. The shortcoming of the new back ref is that it only works for pointers in tree blocks referenced by their owner trees. This is mostly a problem for snapshots, where resolving one of these fuzzy back references would be O(number_of_snapshots) and quite slow. The solution used here is to use the fuzzy back references in the common case where a given tree block is only referenced by one root, and use the full back references when multiple roots have a reference on a given block. This commit adds per subvolume red-black tree to keep trace of cached inodes. The red-black tree helps the balancing code to find cached inodes whose inode numbers within a given range. This commit improves the balancing code by introducing several data structures to keep the state of balancing. The most important one is the back ref cache. It caches how the upper level tree blocks are referenced. This greatly reduce the overhead of checking back ref. The improved balancing code scales significantly better with a large number of snapshots. This is a very large commit and was written in a number of pieces. But, they depend heavily on the disk format change and were squashed together to make sure git bisect didn't end up in a bad state wrt space balancing or the format change. Signed-off-by: Yan Zheng Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 102 +++++++++++++++++++--------------------------------- 1 file changed, 36 insertions(+), 66 deletions(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index db5e212e8445..2b41fc08c34a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -430,18 +430,16 @@ no_copy: static noinline struct inode *read_one_inode(struct btrfs_root *root, u64 objectid) { + struct btrfs_key key; struct inode *inode; - inode = btrfs_iget_locked(root->fs_info->sb, objectid, root); - if (inode->i_state & I_NEW) { - BTRFS_I(inode)->root = root; - BTRFS_I(inode)->location.objectid = objectid; - BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; - BTRFS_I(inode)->location.offset = 0; - btrfs_read_locked_inode(inode); - unlock_new_inode(inode); - } - if (is_bad_inode(inode)) { + key.objectid = objectid; + key.type = BTRFS_INODE_ITEM_KEY; + key.offset = 0; + inode = btrfs_iget(root->fs_info->sb, &key, root); + if (IS_ERR(inode)) { + inode = NULL; + } else if (is_bad_inode(inode)) { iput(inode); inode = NULL; } @@ -541,6 +539,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { + u64 offset; unsigned long dest_offset; struct btrfs_key ins; @@ -555,6 +554,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ins.objectid = btrfs_file_extent_disk_bytenr(eb, item); ins.offset = btrfs_file_extent_disk_num_bytes(eb, item); ins.type = BTRFS_EXTENT_ITEM_KEY; + offset = key->offset - btrfs_file_extent_offset(eb, item); if (ins.objectid > 0) { u64 csum_start; @@ -569,19 +569,16 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, if (ret == 0) { ret = btrfs_inc_extent_ref(trans, root, ins.objectid, ins.offset, - path->nodes[0]->start, - root->root_key.objectid, - trans->transid, key->objectid); + 0, root->root_key.objectid, + key->objectid, offset); } else { /* * insert the extent pointer in the extent * allocation tree */ - ret = btrfs_alloc_logged_extent(trans, root, - path->nodes[0]->start, - root->root_key.objectid, - trans->transid, key->objectid, - &ins); + ret = btrfs_alloc_logged_file_extent(trans, + root, root->root_key.objectid, + key->objectid, offset, &ins); BUG_ON(ret); } btrfs_release_path(root, path); @@ -1706,9 +1703,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); - ret = btrfs_drop_leaf_ref(trans, root, next); - BUG_ON(ret); - WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID); ret = btrfs_free_reserved_extent(root, @@ -1753,10 +1747,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); - if (*level == 0) { - ret = btrfs_drop_leaf_ref(trans, root, next); - BUG_ON(ret); - } WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID); ret = btrfs_free_reserved_extent(root, bytenr, blocksize); BUG_ON(ret); @@ -1811,12 +1801,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); - if (*level == 0) { - ret = btrfs_drop_leaf_ref(trans, root, - next); - BUG_ON(ret); - } - WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID); ret = btrfs_free_reserved_extent(root, path->nodes[*level]->start, @@ -1884,11 +1868,6 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); - if (orig_level == 0) { - ret = btrfs_drop_leaf_ref(trans, log, - next); - BUG_ON(ret); - } WARN_ON(log->root_key.objectid != BTRFS_TREE_LOG_OBJECTID); ret = btrfs_free_reserved_extent(log, next->start, @@ -2027,9 +2006,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = btrfs_write_and_wait_marked_extents(log, &log->dirty_log_pages); BUG_ON(ret); - btrfs_set_root_bytenr(&log->root_item, log->node->start); - btrfs_set_root_generation(&log->root_item, trans->transid); - btrfs_set_root_level(&log->root_item, btrfs_header_level(log->node)); + btrfs_set_root_node(&log->root_item, log->node); root->log_batch = 0; root->log_transid++; @@ -2581,7 +2558,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, ins_keys, ins_sizes, nr); BUG_ON(ret); - for (i = 0; i < nr; i++) { + for (i = 0; i < nr; i++, dst_path->slots[0]++) { dst_offset = btrfs_item_ptr_offset(dst_path->nodes[0], dst_path->slots[0]); @@ -2617,36 +2594,31 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, found_type = btrfs_file_extent_type(src, extent); if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { - u64 ds = btrfs_file_extent_disk_bytenr(src, - extent); - u64 dl = btrfs_file_extent_disk_num_bytes(src, - extent); - u64 cs = btrfs_file_extent_offset(src, extent); - u64 cl = btrfs_file_extent_num_bytes(src, - extent);; + u64 ds, dl, cs, cl; + ds = btrfs_file_extent_disk_bytenr(src, + extent); + /* ds == 0 is a hole */ + if (ds == 0) + continue; + + dl = btrfs_file_extent_disk_num_bytes(src, + extent); + cs = btrfs_file_extent_offset(src, extent); + cl = btrfs_file_extent_num_bytes(src, + extent);; if (btrfs_file_extent_compression(src, extent)) { cs = 0; cl = dl; } - /* ds == 0 is a hole */ - if (ds != 0) { - ret = btrfs_inc_extent_ref(trans, log, - ds, dl, - dst_path->nodes[0]->start, - BTRFS_TREE_LOG_OBJECTID, - trans->transid, - ins_keys[i].objectid); - BUG_ON(ret); - ret = btrfs_lookup_csums_range( - log->fs_info->csum_root, - ds + cs, ds + cs + cl - 1, - &ordered_sums); - BUG_ON(ret); - } + + ret = btrfs_lookup_csums_range( + log->fs_info->csum_root, + ds + cs, ds + cs + cl - 1, + &ordered_sums); + BUG_ON(ret); } } - dst_path->slots[0]++; } btrfs_mark_buffer_dirty(dst_path->nodes[0]); @@ -3029,9 +3001,7 @@ again: BUG_ON(!wc.replay_dest); wc.replay_dest->log_root = log; - mutex_lock(&fs_info->trans_mutex); - btrfs_record_root_in_trans(wc.replay_dest); - mutex_unlock(&fs_info->trans_mutex); + btrfs_record_root_in_trans(trans, wc.replay_dest); ret = walk_log_tree(trans, log, &wc); BUG_ON(ret); -- cgit v1.2.2 From b263c2c8bf13c273485bd99dbbeba79c844409dd Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 11 Jun 2009 11:24:47 -0400 Subject: Btrfs: fix extent_buffer leak during tree log replay During tree log replay, we read in the tree log roots, process them and then free them. A recent change takes an extra reference on the root node of the tree when the root is read in, and stores that reference in root->commit_root. This reference was not being freed, leaving us with one buffer pinned in ram for each subvol with a tree log root after a crash. Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2b41fc08c34a..c13922206d1b 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3019,6 +3019,7 @@ again: key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); + free_extent_buffer(log->commit_root); kfree(log); if (found_key.offset == 0) -- cgit v1.2.2 From 817d52f8dba26d0295c26035531c30ce5f1e3c3e Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 13 Jul 2009 21:29:25 -0400 Subject: Btrfs: async block group caching This patch moves the caching of the block group off to a kthread in order to allow people to allocate sooner. Instead of blocking up behind the caching mutex, we instead kick of the caching kthread, and then attempt to make an allocation. If we cannot, we wait on the block groups caching waitqueue, which the caching kthread will wake the waiting threads up everytime it finds 2 meg worth of space, and then again when its finished caching. This is how I tested the speedup from this mkfs the disk mount the disk fill the disk up with fs_mark unmount the disk mount the disk time touch /mnt/foo Without my changes this took 11 seconds on my box, with these changes it now takes 1 second. Another change thats been put in place is we lock the super mirror's in the pinned extent map in order to keep us from adding that stuff as free space when caching the block group. This doesn't really change anything else as far as the pinned extent map is concerned, since for actual pinned extents we use EXTENT_DIRTY, but it does mean that when we unmount we have to go in and unlock those extents to keep from leaking memory. I've also added a check where when we are reading block groups from disk, if the amount of space used == the size of the block group, we go ahead and mark the block group as cached. This drastically reduces the amount of time it takes to cache the block groups. Using the same test as above, except doing a dd to a file and then unmounting, it used to take 33 seconds to umount, now it takes 3 seconds. This version uses the commit_root in the caching kthread, and then keeps track of how many async caching threads are running at any given time so if one of the async threads is still running as we cross transactions we can wait until its finished before handling the pinned extents. Thank you, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c13922206d1b..195606862618 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -264,7 +264,7 @@ static int process_one_buffer(struct btrfs_root *log, { if (wc->pin) btrfs_update_pinned_extents(log->fs_info->extent_root, - eb->start, eb->len, 1); + eb->start, eb->len, 1, 0); if (btrfs_buffer_uptodate(eb, gen)) { if (wc->write) -- cgit v1.2.2 From 631c07c8d12bcc6ce4a0fbfbd64ea843d78e2b10 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Mon, 27 Jul 2009 13:57:00 -0400 Subject: Btrfs: Correct redundant test in add_inode_ref dir has already been tested. It seems that this test should be on the recently returned value inode. A simplified version of the semantic match that finds this problem is as follows: (http://www.emn.fr/x-info/coccinelle/) Signed-off-by: Julia Lawall Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 195606862618..11d0787c6188 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -797,7 +797,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, return -ENOENT; inode = read_one_inode(root, key->objectid); - BUG_ON(!dir); + BUG_ON(!inode); ref_ptr = btrfs_item_ptr_offset(eb, slot); ref_end = ref_ptr + btrfs_item_size_nr(eb, slot); -- cgit v1.2.2 From 68b38550ddbea13d296184bf69edff387618b1d3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 27 Jul 2009 13:57:01 -0400 Subject: Btrfs: change how we unpin extents We are racy with async block caching and unpinning extents. This patch makes things much less complicated by only unpinning the extent if the block group is cached. We check the block_group->cached var under the block_group->lock spin lock. If it is set to BTRFS_CACHE_FINISHED then we update the pinned counters, and unpin the extent and add the free space back. If it is not set to this, we start the caching of the block group so the next time we unpin extents we can unpin the extent. This keeps us from racing with the async caching threads, lets us kill the fs wide async thread counter, and keeps us from having to set DELALLOC bits for every extent we hit if there are caching kthreads going. One thing that needed to be changed was btrfs_free_super_mirror_extents. Now instead of just looking for LOCKED extents, we also look for DIRTY extents, since we could have left some extents pinned in the previous transaction that will never get freed now that we are unmounting, which would cause us to leak memory. So btrfs_free_super_mirror_extents has been changed to btrfs_free_pinned_extents, and it will clear the extents locked for the super mirror, and any remaining pinned extents that may be present. Thank you, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/tree-log.c') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 11d0787c6188..d91b0de7c502 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -264,7 +264,7 @@ static int process_one_buffer(struct btrfs_root *log, { if (wc->pin) btrfs_update_pinned_extents(log->fs_info->extent_root, - eb->start, eb->len, 1, 0); + eb->start, eb->len, 1); if (btrfs_buffer_uptodate(eb, gen)) { if (wc->write) -- cgit v1.2.2