summaryrefslogtreecommitdiff
path: root/fs/btrfs/transaction.c
diff options
context:
space:
mode:
authorFilipe Manana <fdmanana@suse.com>2015-05-20 16:01:54 +0300
committerChris Mason <clm@fb.com>2015-06-03 14:03:04 +0300
commit4fbcdf6694544fd9d2aedbc1e73e52b90a4fcc20 (patch)
tree2d5979c0e29cc6f21a04fa521b261bfb75b04168 /fs/btrfs/transaction.c
parent0d2b2372e097cd3b4150d3ec91e79ac3c5cc750e (diff)
downloadlinux-4fbcdf6694544fd9d2aedbc1e73e52b90a4fcc20.tar.xz
Btrfs: fix -ENOSPC when finishing block group creation
While creating a block group, we often end up getting ENOSPC while updating the chunk tree, which leads to a transaction abortion that produces a trace like the following: [30670.116368] WARNING: CPU: 4 PID: 20735 at fs/btrfs/super.c:260 __btrfs_abort_transaction+0x52/0x106 [btrfs]() [30670.117777] BTRFS: Transaction aborted (error -28) (...) [30670.163567] Call Trace: [30670.163906] [<ffffffff8142fa46>] dump_stack+0x4f/0x7b [30670.164522] [<ffffffff8108b6a2>] ? console_unlock+0x361/0x3ad [30670.165171] [<ffffffff81045ea5>] warn_slowpath_common+0xa1/0xbb [30670.166323] [<ffffffffa035daa7>] ? __btrfs_abort_transaction+0x52/0x106 [btrfs] [30670.167213] [<ffffffff81045f05>] warn_slowpath_fmt+0x46/0x48 [30670.167862] [<ffffffffa035daa7>] __btrfs_abort_transaction+0x52/0x106 [btrfs] [30670.169116] [<ffffffffa03743d7>] btrfs_create_pending_block_groups+0x101/0x130 [btrfs] [30670.170593] [<ffffffffa038426a>] __btrfs_end_transaction+0x84/0x366 [btrfs] [30670.171960] [<ffffffffa038455c>] btrfs_end_transaction+0x10/0x12 [btrfs] [30670.174649] [<ffffffffa036eb6b>] btrfs_check_data_free_space+0x11f/0x27c [btrfs] [30670.176092] [<ffffffffa039450d>] btrfs_fallocate+0x7c8/0xb96 [btrfs] [30670.177218] [<ffffffff812459f2>] ? __this_cpu_preempt_check+0x13/0x15 [30670.178622] [<ffffffff81152447>] vfs_fallocate+0x14c/0x1de [30670.179642] [<ffffffff8116b915>] ? __fget_light+0x2d/0x4f [30670.180692] [<ffffffff81152863>] SyS_fallocate+0x47/0x62 [30670.186737] [<ffffffff81435b32>] system_call_fastpath+0x12/0x17 [30670.187792] ---[ end trace 0373e6b491c4a8cc ]--- This is because we don't do proper space reservation for the chunk block reserve when we have multiple tasks allocating chunks in parallel. So block group creation has 2 phases, and the first phase essentially checks if there is enough space in the system space_info, allocating a new system chunk if there isn't, while the second phase updates the device, extent and chunk trees. However, because the updates to the chunk tree happen in the second phase, if we have N tasks, each with its own transaction handle, allocating new chunks in parallel and if there is only enough space in the system space_info to allocate M chunks, where M < N, none of the tasks ends up allocating a new system chunk in the first phase and N - M tasks will get -ENOSPC when attempting to update the chunk tree in phase 2 if they need to COW any nodes/leafs from the chunk tree. Fix this by doing proper reservation in the chunk block reserve. The issue could be reproduced by running fstests generic/038 in a loop, which eventually triggered the problem. Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
Diffstat (limited to 'fs/btrfs/transaction.c')
-rw-r--r--fs/btrfs/transaction.c6
1 files changed, 6 insertions, 0 deletions
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5628e25250c0..03a3ec7e31ea 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -509,6 +509,7 @@ again:
h->transaction = cur_trans;
h->blocks_used = 0;
h->bytes_reserved = 0;
+ h->chunk_bytes_reserved = 0;
h->root = root;
h->delayed_ref_updates = 0;
h->use_count = 1;
@@ -792,6 +793,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
if (!list_empty(&trans->new_bgs))
btrfs_create_pending_block_groups(trans, root);
+ btrfs_trans_release_chunk_metadata(trans);
+
if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) &&
should_end_transaction(trans, root) &&
ACCESS_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) {
@@ -2054,6 +2057,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
clear_bit(BTRFS_INODE_BTREE_LOG1_ERR, &btree_ino->runtime_flags);
clear_bit(BTRFS_INODE_BTREE_LOG2_ERR, &btree_ino->runtime_flags);
+ btrfs_trans_release_chunk_metadata(trans);
+
spin_lock(&root->fs_info->trans_lock);
cur_trans->state = TRANS_STATE_UNBLOCKED;
root->fs_info->running_transaction = NULL;
@@ -2123,6 +2128,7 @@ scrub_continue:
btrfs_scrub_continue(root);
cleanup_transaction:
btrfs_trans_release_metadata(trans, root);
+ btrfs_trans_release_chunk_metadata(trans);
trans->block_rsv = NULL;
if (trans->qgroup_reserved) {
btrfs_qgroup_free(root, trans->qgroup_reserved);