From 4a8c9a62d7f7f058eed4b8a6f2c890a887778093 Mon Sep 17 00:00:00 2001 From: Yan Zheng Date: Wed, 22 Jul 2009 10:07:05 -0400 Subject: Btrfs: make sure all dirty blocks are written at commit time Write dirty block groups may allocate new block, and so may add new delayed back ref. btrfs_run_delayed_refs may make some block groups dirty. commit_cowonly_roots does not handle the recursion properly, and some dirty blocks can be left unwritten at commit time. This patch moves btrfs_run_delayed_refs into the loop that writes dirty block groups, and makes the code not break out of the loop until there are no dirty block groups or delayed back refs. Signed-off-by: Yan Zheng Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'fs/btrfs/transaction.c') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 2dbf1c1f56e..81f7124c305 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -444,9 +444,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans, btrfs_write_dirty_block_groups(trans, root); - ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); - BUG_ON(ret); - while (1) { old_root_bytenr = btrfs_root_bytenr(&root->root_item); if (old_root_bytenr == root->node->start) @@ -457,9 +454,8 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans, &root->root_key, &root->root_item); BUG_ON(ret); - btrfs_write_dirty_block_groups(trans, root); - ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); + ret = btrfs_write_dirty_block_groups(trans, root); BUG_ON(ret); } free_extent_buffer(root->commit_root); @@ -495,9 +491,6 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, root = list_entry(next, struct btrfs_root, dirty_list); update_cowonly_root(trans, root); - - ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); - BUG_ON(ret); } return 0; } -- cgit v1.2.3 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/transaction.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'fs/btrfs/transaction.c') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 81f7124c305..32454d1c566 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -40,6 +40,14 @@ static noinline void put_transaction(struct btrfs_transaction *transaction) } } +static noinline void switch_commit_root(struct btrfs_root *root) +{ + down_write(&root->commit_root_sem); + free_extent_buffer(root->commit_root); + root->commit_root = btrfs_root_node(root); + up_write(&root->commit_root_sem); +} + /* * either allocate a new transaction or hop into the existing one */ @@ -458,8 +466,7 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans, ret = btrfs_write_dirty_block_groups(trans, root); BUG_ON(ret); } - free_extent_buffer(root->commit_root); - root->commit_root = btrfs_root_node(root); + switch_commit_root(root); return 0; } @@ -537,8 +544,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans, btrfs_update_reloc_root(trans, root); if (root->commit_root != root->node) { - free_extent_buffer(root->commit_root); - root->commit_root = btrfs_root_node(root); + switch_commit_root(root); btrfs_set_root_node(&root->root_item, root->node); } @@ -1002,15 +1008,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, btrfs_set_root_node(&root->fs_info->tree_root->root_item, root->fs_info->tree_root->node); - free_extent_buffer(root->fs_info->tree_root->commit_root); - root->fs_info->tree_root->commit_root = - btrfs_root_node(root->fs_info->tree_root); + switch_commit_root(root->fs_info->tree_root); btrfs_set_root_node(&root->fs_info->chunk_root->root_item, root->fs_info->chunk_root->node); - free_extent_buffer(root->fs_info->chunk_root->commit_root); - root->fs_info->chunk_root->commit_root = - btrfs_root_node(root->fs_info->chunk_root); + switch_commit_root(root->fs_info->chunk_root); update_super_roots(root); @@ -1050,6 +1052,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, cur_trans->commit_done = 1; root->fs_info->last_trans_committed = cur_trans->transid; + wake_up(&cur_trans->commit_wait); put_transaction(cur_trans); -- cgit v1.2.3 From ebecd3d9d2adba144c15f1d35c78e0c26ead1bfd Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Fri, 24 Jul 2009 13:17:44 -0400 Subject: Btrfs: make flushoncommit mount option correctly wait on ordered_extents The commit_transaction call to wait_ordered_extents when snap_pending passes nocow_only=1 to process only NOCOW or PREALLOC extents. This isn't correct for the 'flushoncommit' mode, as it skips extents we just started IO on in start_delalloc_inodes. So, in the flushoncommit case, wait on all ordered extents. Otherwise, only pass the nocow_only flag to wait_ordered_extents if snap_pending. Signed-off-by: Sage Weil Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/transaction.c') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 32454d1c566..e51d2bc532f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -942,9 +942,11 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, mutex_unlock(&root->fs_info->trans_mutex); - if (flush_on_commit || snap_pending) { - if (flush_on_commit) - btrfs_start_delalloc_inodes(root); + if (flush_on_commit) { + btrfs_start_delalloc_inodes(root); + ret = btrfs_wait_ordered_extents(root, 0); + BUG_ON(ret); + } else if (snap_pending) { ret = btrfs_wait_ordered_extents(root, 1); BUG_ON(ret); } -- cgit v1.2.3 From 276e680d192a67d222fcea51af37b056feffb665 Mon Sep 17 00:00:00 2001 From: Yan Zheng Date: Thu, 30 Jul 2009 09:40:40 -0400 Subject: Btrfs: preserve commit_root for async caching The async block group caching code uses the commit_root pointer to get a stable version of the extent allocation tree for scanning. This copy of the tree root isn't going to change and it significantly reduces the complexity of the scanning code. During a commit, we have a loop where we update the extent allocation tree root. We need to loop because updating the root pointer in the tree of tree roots may allocate blocks which may change the extent allocation tree. Right now the commit_root pointer is changed inside this loop. It is more correct to change the commit_root pointer only after all the looping is done. Signed-off-by: Yan Zheng Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/transaction.c') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index e51d2bc532f..de48e4ec808 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -42,10 +42,8 @@ static noinline void put_transaction(struct btrfs_transaction *transaction) static noinline void switch_commit_root(struct btrfs_root *root) { - down_write(&root->commit_root_sem); free_extent_buffer(root->commit_root); root->commit_root = btrfs_root_node(root); - up_write(&root->commit_root_sem); } /* @@ -466,7 +464,10 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans, ret = btrfs_write_dirty_block_groups(trans, root); BUG_ON(ret); } - switch_commit_root(root); + + if (root != root->fs_info->extent_root) + switch_commit_root(root); + return 0; } @@ -499,6 +500,11 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, update_cowonly_root(trans, root); } + + down_write(&fs_info->extent_commit_sem); + switch_commit_root(fs_info->extent_root); + up_write(&fs_info->extent_commit_sem); + return 0; } -- cgit v1.2.3 From f36f3042eae238bdaefe7c79310afe573bfc3622 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 30 Jul 2009 10:04:48 -0400 Subject: Btrfs: be more polite in the async caching threads The semaphore used by the async caching threads can prevent a transaction commit, which can make the FS appear to stall. This releases the semaphore more often when a transaction commit is in progress. Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs/btrfs/transaction.c') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index de48e4ec808..cdbb5022da5 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -857,6 +857,16 @@ static void update_super_roots(struct btrfs_root *root) super->root_level = root_item->level; } +int btrfs_transaction_in_commit(struct btrfs_fs_info *info) +{ + int ret = 0; + spin_lock(&info->new_trans_lock); + if (info->running_transaction) + ret = info->running_transaction->in_commit; + spin_unlock(&info->new_trans_lock); + return ret; +} + int btrfs_commit_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root) { -- cgit v1.2.3