From 31890da0bfdd24b135a258404b93c58a65510c7a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 21 Nov 2018 14:05:41 -0500 Subject: btrfs: handle delayed ref head accounting cleanup in abort We weren't doing any of the accounting cleanup when we aborted transactions. Fix this by making cleanup_ref_head_accounting global and calling it from the abort code, this fixes the issue where our accounting was all wrong after the fs aborts. The test generic/475 on a 2G VM can trigger the problems eg.: [ 8502.136957] WARNING: CPU: 0 PID: 11064 at fs/btrfs/extent-tree.c:5986 btrfs_free_block_grou +ps+0x3dc/0x410 [btrfs] [ 8502.148372] CPU: 0 PID: 11064 Comm: umount Not tainted 5.0.0-rc1-default+ #394 [ 8502.150807] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626 +cc-prebuilt.qemu-project.org 04/01/2014 [ 8502.154317] RIP: 0010:btrfs_free_block_groups+0x3dc/0x410 [btrfs] [ 8502.160623] RSP: 0018:ffffb1ab84b93de8 EFLAGS: 00010206 [ 8502.161906] RAX: 0000000001000000 RBX: ffff9f34b1756400 RCX: 0000000000000000 [ 8502.163448] RDX: 0000000000000002 RSI: 0000000000000001 RDI: ffff9f34b1755400 [ 8502.164906] RBP: ffff9f34b7e8c000 R08: 0000000000000001 R09: 0000000000000000 [ 8502.166716] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9f34b7e8c108 [ 8502.168498] R13: ffff9f34b7e8c158 R14: 0000000000000000 R15: dead000000000100 [ 8502.170296] FS: 00007fb1cf15ffc0(0000) GS:ffff9f34bd400000(0000) knlGS:0000000000000000 [ 8502.172439] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8502.173669] CR2: 00007fb1ced507b0 CR3: 000000002f7a6000 CR4: 00000000000006f0 [ 8502.175094] Call Trace: [ 8502.175759] close_ctree+0x17f/0x350 [btrfs] [ 8502.176721] generic_shutdown_super+0x64/0x100 [ 8502.177702] kill_anon_super+0x14/0x30 [ 8502.178607] btrfs_kill_super+0x12/0xa0 [btrfs] [ 8502.179602] deactivate_locked_super+0x29/0x60 [ 8502.180595] cleanup_mnt+0x3b/0x70 [ 8502.181406] task_work_run+0x98/0xc0 [ 8502.182255] exit_to_usermode_loop+0x83/0x90 [ 8502.183113] do_syscall_64+0x15b/0x180 [ 8502.183919] entry_SYSCALL_64_after_hwframe+0x49/0xbe Corresponding to release_global_block_rsv() { ... WARN_ON(fs_info->delayed_refs_rsv.reserved > 0); CC: stable@vger.kernel.org Signed-off-by: Josef Bacik [ add log dump ] Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs/btrfs/ctree.h') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f031a447a047..34019c8b6158 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -35,6 +35,7 @@ struct btrfs_trans_handle; struct btrfs_transaction; struct btrfs_pending_snapshot; +struct btrfs_delayed_ref_root; extern struct kmem_cache *btrfs_trans_handle_cachep; extern struct kmem_cache *btrfs_bit_radix_cachep; extern struct kmem_cache *btrfs_path_cachep; @@ -2664,6 +2665,9 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, unsigned long count); int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info, unsigned long count, u64 transid, int wait); +void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head); int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len); int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, -- cgit v1.2.3-55-g7522 From fd340d0f68cc87badfc9efcb226f23a5428826a0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 11 Jan 2019 10:21:02 -0500 Subject: btrfs: wakeup cleaner thread when adding delayed iput The cleaner thread usually takes care of delayed iputs, with the exception of the btrfs_end_transaction_throttle path. Delaying iputs means we are potentially delaying the eviction of an inode and it's respective space. The cleaner thread only gets woken up every 30 seconds, or when we require space. If there are a lot of inodes that need to be deleted we could induce a serious amount of latency while we wait for these inodes to be evicted. So instead wakeup the cleaner if it's not already awake to process any new delayed iputs we add to the list. If we suddenly need space we will less likely be backed up behind a bunch of inodes that are waiting to be deleted, and we could possibly free space before we need to get into the flushing logic which will save us some latency. Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 3 +++ fs/btrfs/disk-io.c | 3 +++ fs/btrfs/inode.c | 2 ++ 3 files changed, 8 insertions(+) (limited to 'fs/btrfs/ctree.h') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 34019c8b6158..8b1d06fa222d 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -787,6 +787,9 @@ enum { * main phase. The fs_info::balance_ctl is initialized. */ BTRFS_FS_BALANCE_RUNNING, + + /* Indicate that the cleaner thread is awake and doing something. */ + BTRFS_FS_CLEANER_RUNNING, }; struct btrfs_fs_info { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 18eefc5b2532..6a2a2a951705 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1682,6 +1682,8 @@ static int cleaner_kthread(void *arg) while (1) { again = 0; + set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + /* Make the cleaner go to sleep early. */ if (btrfs_need_cleaner_sleep(fs_info)) goto sleep; @@ -1728,6 +1730,7 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park()) kthread_parkme(); if (kthread_should_stop()) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b6025b5d0b25..5c349667c761 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3251,6 +3251,8 @@ void btrfs_add_delayed_iput(struct inode *inode) ASSERT(list_empty(&binode->delayed_iput)); list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs); spin_unlock(&fs_info->delayed_iput_lock); + if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags)) + wake_up_process(fs_info->cleaner_kthread); } void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) -- cgit v1.2.3-55-g7522