From 77b7aad195099e7c6da11e94b7fa6ef5e6fb0025 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 9 Jan 2019 15:02:23 +0100 Subject: [PATCH 1/5] Revert "btrfs: balance dirty metadata pages in btrfs_finish_ordered_io" This reverts commit e73e81b6d0114d4a303205a952ab2e87c44bd279. This patch causes a few problems: - adds latency to btrfs_finish_ordered_io - as btrfs_finish_ordered_io is used for free space cache, generating more work from btrfs_btree_balance_dirty_nodelay could end up in the same workque, effectively deadlocking 12260 kworker/u96:16+btrfs-freespace-write D [<0>] balance_dirty_pages+0x6e6/0x7ad [<0>] balance_dirty_pages_ratelimited+0x6bb/0xa90 [<0>] btrfs_finish_ordered_io+0x3da/0x770 [<0>] normal_work_helper+0x1c5/0x5a0 [<0>] process_one_work+0x1ee/0x5a0 [<0>] worker_thread+0x46/0x3d0 [<0>] kthread+0xf5/0x130 [<0>] ret_from_fork+0x24/0x30 [<0>] 0xffffffffffffffff Transaction commit will wait on the freespace cache: 838 btrfs-transacti D [<0>] btrfs_start_ordered_extent+0x154/0x1e0 [<0>] btrfs_wait_ordered_range+0xbd/0x110 [<0>] __btrfs_wait_cache_io+0x49/0x1a0 [<0>] btrfs_write_dirty_block_groups+0x10b/0x3b0 [<0>] commit_cowonly_roots+0x215/0x2b0 [<0>] btrfs_commit_transaction+0x37e/0x910 [<0>] transaction_kthread+0x14d/0x180 [<0>] kthread+0xf5/0x130 [<0>] ret_from_fork+0x24/0x30 [<0>] 0xffffffffffffffff And then writepages ends up waiting on transaction commit: 9520 kworker/u96:13+flush-btrfs-1 D [<0>] wait_current_trans+0xac/0xe0 [<0>] start_transaction+0x21b/0x4b0 [<0>] cow_file_range_inline+0x10b/0x6b0 [<0>] cow_file_range.isra.69+0x329/0x4a0 [<0>] run_delalloc_range+0x105/0x3c0 [<0>] writepage_delalloc+0x119/0x180 [<0>] __extent_writepage+0x10c/0x390 [<0>] extent_write_cache_pages+0x26f/0x3d0 [<0>] extent_writepages+0x4f/0x80 [<0>] do_writepages+0x17/0x60 [<0>] __writeback_single_inode+0x59/0x690 [<0>] writeback_sb_inodes+0x291/0x4e0 [<0>] __writeback_inodes_wb+0x87/0xb0 [<0>] wb_writeback+0x3bb/0x500 [<0>] wb_workfn+0x40d/0x610 [<0>] process_one_work+0x1ee/0x5a0 [<0>] worker_thread+0x1e0/0x3d0 [<0>] kthread+0xf5/0x130 [<0>] ret_from_fork+0x24/0x30 [<0>] 0xffffffffffffffff Eventually, we have every process in the system waiting on balance_dirty_pages(), and nobody is able to make progress on page writeback. The original patch tried to fix an OOM condition, that happened on 4.4 but no success reproducing that on later kernels (4.19 and 4.20). This is more likely a problem in OOM itself. Link: https://lore.kernel.org/linux-btrfs/20180528054821.9092-1-ethanlien@synology.com/ Reported-by: Chris Mason CC: stable@vger.kernel.org # 4.18+ CC: ethanlien Signed-off-by: David Sterba --- fs/btrfs/inode.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 43eb4535319d..b6025b5d0b25 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3129,9 +3129,6 @@ out: /* once for the tree */ btrfs_put_ordered_extent(ordered_extent); - /* Try to release some metadata so we don't get an OOM but don't wait */ - btrfs_btree_balance_dirty_nodelay(fs_info); - return ret; } From 31890da0bfdd24b135a258404b93c58a65510c7a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 21 Nov 2018 14:05:41 -0500 Subject: [PATCH 2/5] 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 ++++ fs/btrfs/disk-io.c | 1 + fs/btrfs/extent-tree.c | 12 +++++------- 3 files changed, 10 insertions(+), 7 deletions(-) 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, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8da2f380d3c0..469a51b4b273 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4265,6 +4265,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, if (pin_bytes) btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); btrfs_put_delayed_ref_head(head); cond_resched(); spin_lock(&delayed_refs->lock); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b15afeae16df..6f6fae410fc1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2456,12 +2456,10 @@ static int run_and_cleanup_extent_op(struct btrfs_trans_handle *trans, return ret ? ret : 1; } -static void cleanup_ref_head_accounting(struct btrfs_trans_handle *trans, - struct btrfs_delayed_ref_head *head) +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) { - struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_delayed_ref_root *delayed_refs = - &trans->transaction->delayed_refs; int nr_items = 1; /* Dropping this ref head update. */ if (head->total_ref_mod < 0) { @@ -2544,7 +2542,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, } } - cleanup_ref_head_accounting(trans, head); + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); trace_run_delayed_ref_head(fs_info, head, 0); btrfs_delayed_ref_unlock(head); @@ -7188,7 +7186,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, if (head->must_insert_reserved) ret = 1; - cleanup_ref_head_accounting(trans, head); + btrfs_cleanup_ref_head_accounting(trans->fs_info, delayed_refs, head); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); return ret; From 74d5d229b1bf60f93bff244b2dfc0eb21ec32a07 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 21 Nov 2018 14:05:45 -0500 Subject: [PATCH 3/5] btrfs: wait on ordered extents on abort cleanup If we flip read-only before we initiate writeback on all dirty pages for ordered extents we've created then we'll have ordered extents left over on umount, which results in all sorts of bad things happening. Fix this by making sure we wait on ordered extents if we have to do the aborted transaction cleanup stuff. generic/475 can produce this warning: [ 8531.177332] WARNING: CPU: 2 PID: 11997 at fs/btrfs/disk-io.c:3856 btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.183282] CPU: 2 PID: 11997 Comm: umount Tainted: G W 5.0.0-rc1-default+ #394 [ 8531.185164] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014 [ 8531.187851] RIP: 0010:btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.193082] RSP: 0018:ffffb1ab86163d98 EFLAGS: 00010286 [ 8531.194198] RAX: ffff9f3449494d18 RBX: ffff9f34a2695000 RCX:0000000000000000 [ 8531.195629] RDX: 0000000000000002 RSI: 0000000000000001 RDI:0000000000000000 [ 8531.197315] RBP: ffff9f344e930000 R08: 0000000000000001 R09:0000000000000000 [ 8531.199095] R10: 0000000000000000 R11: ffff9f34494d4ff8 R12:ffffb1ab86163dc0 [ 8531.200870] R13: ffff9f344e9300b0 R14: ffffb1ab86163db8 R15:0000000000000000 [ 8531.202707] FS: 00007fc68e949fc0(0000) GS:ffff9f34bd800000(0000)knlGS:0000000000000000 [ 8531.204851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8531.205942] CR2: 00007ffde8114dd8 CR3: 000000002dfbd000 CR4:00000000000006e0 [ 8531.207516] Call Trace: [ 8531.208175] btrfs_free_fs_roots+0xdb/0x170 [btrfs] [ 8531.210209] ? wait_for_completion+0x5b/0x190 [ 8531.211303] close_ctree+0x157/0x350 [btrfs] [ 8531.212412] generic_shutdown_super+0x64/0x100 [ 8531.213485] kill_anon_super+0x14/0x30 [ 8531.214430] btrfs_kill_super+0x12/0xa0 [btrfs] [ 8531.215539] deactivate_locked_super+0x29/0x60 [ 8531.216633] cleanup_mnt+0x3b/0x70 [ 8531.217497] task_work_run+0x98/0xc0 [ 8531.218397] exit_to_usermode_loop+0x83/0x90 [ 8531.219324] do_syscall_64+0x15b/0x180 [ 8531.220192] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 8531.221286] RIP: 0033:0x7fc68e5e4d07 [ 8531.225621] RSP: 002b:00007ffde8116608 EFLAGS: 00000246 ORIG_RAX:00000000000000a6 [ 8531.227512] RAX: 0000000000000000 RBX: 00005580c2175970 RCX:00007fc68e5e4d07 [ 8531.229098] RDX: 0000000000000001 RSI: 0000000000000000 RDI:00005580c2175b80 [ 8531.230730] RBP: 0000000000000000 R08: 00005580c2175ba0 R09:00007ffde8114e80 [ 8531.232269] R10: 0000000000000000 R11: 0000000000000246 R12:00005580c2175b80 [ 8531.233839] R13: 00007fc68eac61c4 R14: 00005580c2175a68 R15:0000000000000000 Leaving a tree in the rb-tree: 3853 void btrfs_free_fs_root(struct btrfs_root *root) 3854 { 3855 iput(root->ino_cache_inode); 3856 WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); CC: stable@vger.kernel.org Reviewed-by: Nikolay Borisov Signed-off-by: Josef Bacik [ add stacktrace ] Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 469a51b4b273..18eefc5b2532 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4201,6 +4201,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); + + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, From 3ec9a4c81c8cc2a8d9673588dd84d9cc7c31019b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 11 Jan 2019 10:21:01 -0500 Subject: [PATCH 4/5] btrfs: run delayed iputs before committing Delayed iputs means we can have final iputs of deleted inodes in the queue, which could potentially generate a lot of pinned space that could be free'd. So before we decide to commit the transaction for ENOPSC reasons, run the delayed iputs so that any potential space is free'd up. If there is and we freed enough we can then commit the transaction and potentially be able to make our reservation. Reviewed-by: Omar Sandoval Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6f6fae410fc1..d81035b7ea7d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4952,6 +4952,15 @@ static void flush_space(struct btrfs_fs_info *fs_info, ret = 0; break; case COMMIT_TRANS: + /* + * If we have pending delayed iputs then we could free up a + * bunch of pinned space, so make sure we run the iputs before + * we do our pinned bytes check below. + */ + mutex_lock(&fs_info->cleaner_delayed_iput_mutex); + btrfs_run_delayed_iputs(fs_info); + mutex_unlock(&fs_info->cleaner_delayed_iput_mutex); + ret = may_commit_transaction(fs_info, space_info); break; default: From fd340d0f68cc87badfc9efcb226f23a5428826a0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 11 Jan 2019 10:21:02 -0500 Subject: [PATCH 5/5] 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(+) 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)