From 2f3165ecf103599f82bf0ea254039db335fb5005 Mon Sep 17 00:00:00 2001 From: Zygo Blaxell Date: Thu, 5 May 2016 00:23:49 -0400 Subject: [PATCH] btrfs: don't force mounts to wait for cleaner_kthread to delete one or more subvolumes During a mount, we start the cleaner kthread first because the transaction kthread wants to wake up the cleaner kthread. We start the transaction kthread next because everything in btrfs wants transactions. We do reloc recovery in the thread that was doing the original mount call once the transaction kthread is running. This means that the cleaner kthread could already be running when reloc recovery happens (e.g. if a snapshot delete was started before a crash). Relocation does not play well with the cleaner kthread, so a mutex was added in commit 5f3164813b90f7dbcb5c3ab9006906222ce471b7 "Btrfs: fix race between balance recovery and root deletion" to prevent both from being active at the same time. If the cleaner kthread is already holding the mutex by the time we get to btrfs_recover_relocation, the mount will be blocked until at least one deleted subvolume is cleaned (possibly more if the mount process doesn't get the lock right away). During this time (which could be an arbitrarily long time on a large/slow filesystem), the mount process is stuck and the filesystem is unnecessarily inaccessible. Fix this by locking cleaner_mutex before we start cleaner_kthread, and unlocking the mutex after mount no longer requires it. This ensures that the mounting process will not be blocked by the cleaner kthread. The cleaner kthread is already prepared for mutex contention and will just go to sleep until the mutex is available. Signed-off-by: Zygo Blaxell Reviewed-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4e47849d7427..070c1dad42bd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2517,6 +2517,7 @@ int open_ctree(struct super_block *sb, int num_backups_tried = 0; int backup_index = 0; int max_active; + bool cleaner_mutex_locked = false; tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL); @@ -2997,6 +2998,13 @@ int open_ctree(struct super_block *sb, goto fail_sysfs; } + /* + * Hold the cleaner_mutex thread here so that we don't block + * for a long time on btrfs_recover_relocation. cleaner_kthread + * will wait for us to finish mounting the filesystem. + */ + mutex_lock(&fs_info->cleaner_mutex); + cleaner_mutex_locked = true; fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root, "btrfs-cleaner"); if (IS_ERR(fs_info->cleaner_kthread)) @@ -3056,10 +3064,8 @@ int open_ctree(struct super_block *sb, ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto fail_qgroup; - - mutex_lock(&fs_info->cleaner_mutex); + /* We locked cleaner_mutex before creating cleaner_kthread. */ ret = btrfs_recover_relocation(tree_root); - mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) { printk(KERN_WARNING "BTRFS: failed to recover relocation\n"); @@ -3067,6 +3073,8 @@ int open_ctree(struct super_block *sb, goto fail_qgroup; } } + mutex_unlock(&fs_info->cleaner_mutex); + cleaner_mutex_locked = false; location.objectid = BTRFS_FS_TREE_OBJECTID; location.type = BTRFS_ROOT_ITEM_KEY; @@ -3180,6 +3188,10 @@ int open_ctree(struct super_block *sb, filemap_write_and_wait(fs_info->btree_inode->i_mapping); fail_sysfs: + if (cleaner_mutex_locked) { + mutex_unlock(&fs_info->cleaner_mutex); + cleaner_mutex_locked = false; + } btrfs_sysfs_remove_mounted(fs_info); fail_fsdev_sysfs: -- GitLab