diff options
author | Chris Mason <chris.mason@oracle.com> | 2011-11-03 15:17:42 -0400 |
---|---|---|
committer | Chris Mason <chris.mason@oracle.com> | 2011-11-06 03:04:15 -0500 |
commit | af31f5e5b84b5bf2bcec464153a5130b170b2770 (patch) | |
tree | f8f5d8f18a115431e8826fa1c46580311dc1e485 /fs/btrfs | |
parent | 6c41761fc6efe1503103a1afe03a6635c0b5d4ec (diff) | |
download | talos-obmc-linux-af31f5e5b84b5bf2bcec464153a5130b170b2770.tar.gz talos-obmc-linux-af31f5e5b84b5bf2bcec464153a5130b170b2770.zip |
Btrfs: add a log of past tree roots
This takes some of the free space in the btrfs super block
to record information about most of the roots in the last four
commits.
It also adds a -o recovery to use the root history log when
we're not able to read the tree of tree roots, the extent
tree root, the device tree root or the csum root.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs')
-rw-r--r-- | fs/btrfs/ctree.h | 95 | ||||
-rw-r--r-- | fs/btrfs/disk-io.c | 291 | ||||
-rw-r--r-- | fs/btrfs/super.c | 7 |
3 files changed, 369 insertions, 24 deletions
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 5181c53c1124..78f43d1102a0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -361,6 +361,47 @@ struct btrfs_header { #define BTRFS_LABEL_SIZE 256 /* + * just in case we somehow lose the roots and are not able to mount, + * we store an array of the roots from previous transactions + * in the super. + */ +#define BTRFS_NUM_BACKUP_ROOTS 4 +struct btrfs_root_backup { + __le64 tree_root; + __le64 tree_root_gen; + + __le64 chunk_root; + __le64 chunk_root_gen; + + __le64 extent_root; + __le64 extent_root_gen; + + __le64 fs_root; + __le64 fs_root_gen; + + __le64 dev_root; + __le64 dev_root_gen; + + __le64 csum_root; + __le64 csum_root_gen; + + __le64 total_bytes; + __le64 bytes_used; + __le64 num_devices; + /* future */ + __le64 unsed_64[4]; + + u8 tree_root_level; + u8 chunk_root_level; + u8 extent_root_level; + u8 fs_root_level; + u8 dev_root_level; + u8 csum_root_level; + /* future and to align */ + u8 unused_8[10]; +} __attribute__ ((__packed__)); + +/* * the super block basically lists the main trees of the FS * it currently lacks any block count etc etc */ @@ -406,6 +447,7 @@ struct btrfs_super_block { /* future expansion */ __le64 reserved[31]; u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; + struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; } __attribute__ ((__packed__)); /* @@ -1113,6 +1155,9 @@ struct btrfs_fs_info { u64 fs_state; struct btrfs_delayed_root *delayed_root; + + /* next backup root to be overwritten */ + int backup_root_index; }; /* @@ -1357,6 +1402,7 @@ struct btrfs_ioctl_defrag_range_args { #define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15) #define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16) #define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17) +#define BTRFS_MOUNT_RECOVERY (1 << 18) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) @@ -1972,6 +2018,55 @@ static inline bool btrfs_root_readonly(struct btrfs_root *root) return root->root_item.flags & BTRFS_ROOT_SUBVOL_RDONLY; } +/* struct btrfs_root_backup */ +BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup, + tree_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_tree_root_gen, struct btrfs_root_backup, + tree_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_tree_root_level, struct btrfs_root_backup, + tree_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root, struct btrfs_root_backup, + chunk_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_gen, struct btrfs_root_backup, + chunk_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_level, struct btrfs_root_backup, + chunk_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_extent_root, struct btrfs_root_backup, + extent_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_extent_root_gen, struct btrfs_root_backup, + extent_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_extent_root_level, struct btrfs_root_backup, + extent_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_fs_root, struct btrfs_root_backup, + fs_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_fs_root_gen, struct btrfs_root_backup, + fs_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_fs_root_level, struct btrfs_root_backup, + fs_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_dev_root, struct btrfs_root_backup, + dev_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_dev_root_gen, struct btrfs_root_backup, + dev_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_dev_root_level, struct btrfs_root_backup, + dev_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_csum_root, struct btrfs_root_backup, + csum_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_csum_root_gen, struct btrfs_root_backup, + csum_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_csum_root_level, struct btrfs_root_backup, + csum_root_level, 8); +BTRFS_SETGET_STACK_FUNCS(backup_total_bytes, struct btrfs_root_backup, + total_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(backup_bytes_used, struct btrfs_root_backup, + bytes_used, 64); +BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup, + num_devices, 64); + /* struct btrfs_super_block */ BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 761717c98278..a61f8a6cf219 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1134,10 +1134,12 @@ static int find_and_setup_root(struct btrfs_root *tree_root, generation = btrfs_root_generation(&root->root_item); blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item)); + root->commit_root = NULL; root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), blocksize, generation); if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) { free_extent_buffer(root->node); + root->node = NULL; return -EIO; } root->commit_root = btrfs_root_node(root); @@ -1576,6 +1578,228 @@ sleep: return 0; } +/* + * this will find the highest generation in the array of + * root backups. The index of the highest array is returned, + * or -1 if we can't find anything. + * + * We check to make sure the array is valid by comparing the + * generation of the latest root in the array with the generation + * in the super block. If they don't match we pitch it. + */ +static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen) +{ + u64 cur; + int newest_index = -1; + struct btrfs_root_backup *root_backup; + int i; + + for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { + root_backup = info->super_copy->super_roots + i; + cur = btrfs_backup_tree_root_gen(root_backup); + if (cur == newest_gen) + newest_index = i; + } + + /* check to see if we actually wrapped around */ + if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) { + root_backup = info->super_copy->super_roots; + cur = btrfs_backup_tree_root_gen(root_backup); + if (cur == newest_gen) + newest_index = 0; + } + return newest_index; +} + + +/* + * find the oldest backup so we know where to store new entries + * in the backup array. This will set the backup_root_index + * field in the fs_info struct + */ +static void find_oldest_super_backup(struct btrfs_fs_info *info, + u64 newest_gen) +{ + int newest_index = -1; + + newest_index = find_newest_super_backup(info, newest_gen); + /* if there was garbage in there, just move along */ + if (newest_index == -1) { + info->backup_root_index = 0; + } else { + info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS; + } +} + +/* + * copy all the root pointers into the super backup array. + * this will bump the backup pointer by one when it is + * done + */ +static void backup_super_roots(struct btrfs_fs_info *info) +{ + int next_backup; + struct btrfs_root_backup *root_backup; + int last_backup; + + next_backup = info->backup_root_index; + last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) % + BTRFS_NUM_BACKUP_ROOTS; + + /* + * just overwrite the last backup if we're at the same generation + * this happens only at umount + */ + root_backup = info->super_for_commit->super_roots + last_backup; + if (btrfs_backup_tree_root_gen(root_backup) == + btrfs_header_generation(info->tree_root->node)) + next_backup = last_backup; + + root_backup = info->super_for_commit->super_roots + next_backup; + + /* + * make sure all of our padding and empty slots get zero filled + * regardless of which ones we use today + */ + memset(root_backup, 0, sizeof(*root_backup)); + + info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS; + + btrfs_set_backup_tree_root(root_backup, info->tree_root->node->start); + btrfs_set_backup_tree_root_gen(root_backup, + btrfs_header_generation(info->tree_root->node)); + + btrfs_set_backup_tree_root_level(root_backup, + btrfs_header_level(info->tree_root->node)); + + btrfs_set_backup_chunk_root(root_backup, info->chunk_root->node->start); + btrfs_set_backup_chunk_root_gen(root_backup, + btrfs_header_generation(info->chunk_root->node)); + btrfs_set_backup_chunk_root_level(root_backup, + btrfs_header_level(info->chunk_root->node)); + + btrfs_set_backup_extent_root(root_backup, info->extent_root->node->start); + btrfs_set_backup_extent_root_gen(root_backup, + btrfs_header_generation(info->extent_root->node)); + btrfs_set_backup_extent_root_level(root_backup, + btrfs_header_level(info->extent_root->node)); + + btrfs_set_backup_fs_root(root_backup, info->fs_root->node->start); + btrfs_set_backup_fs_root_gen(root_backup, + btrfs_header_generation(info->fs_root->node)); + btrfs_set_backup_fs_root_level(root_backup, + btrfs_header_level(info->fs_root->node)); + + btrfs_set_backup_dev_root(root_backup, info->dev_root->node->start); + btrfs_set_backup_dev_root_gen(root_backup, + btrfs_header_generation(info->dev_root->node)); + btrfs_set_backup_dev_root_level(root_backup, + btrfs_header_level(info->dev_root->node)); + + btrfs_set_backup_csum_root(root_backup, info->csum_root->node->start); + btrfs_set_backup_csum_root_gen(root_backup, + btrfs_header_generation(info->csum_root->node)); + btrfs_set_backup_csum_root_level(root_backup, + btrfs_header_level(info->csum_root->node)); + + btrfs_set_backup_total_bytes(root_backup, + btrfs_super_total_bytes(info->super_copy)); + btrfs_set_backup_bytes_used(root_backup, + btrfs_super_bytes_used(info->super_copy)); + btrfs_set_backup_num_devices(root_backup, + btrfs_super_num_devices(info->super_copy)); + + /* + * if we don't copy this out to the super_copy, it won't get remembered + * for the next commit + */ + memcpy(&info->super_copy->super_roots, + &info->super_for_commit->super_roots, + sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS); +} + +/* + * this copies info out of the root backup array and back into + * the in-memory super block. It is meant to help iterate through + * the array, so you send it the number of backups you've already + * tried and the last backup index you used. + * + * this returns -1 when it has tried all the backups + */ +static noinline int next_root_backup(struct btrfs_fs_info *info, + struct btrfs_super_block *super, + int *num_backups_tried, int *backup_index) +{ + struct btrfs_root_backup *root_backup; + int newest = *backup_index; + + if (*num_backups_tried == 0) { + u64 gen = btrfs_super_generation(super); + + newest = find_newest_super_backup(info, gen); + if (newest == -1) + return -1; + + *backup_index = newest; + *num_backups_tried = 1; + } else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) { + /* we've tried all the backups, all done */ + return -1; + } else { + /* jump to the next oldest backup */ + newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) % + BTRFS_NUM_BACKUP_ROOTS; + *backup_index = newest; + *num_backups_tried += 1; + } + root_backup = super->super_roots + newest; + + btrfs_set_super_generation(super, + btrfs_backup_tree_root_gen(root_backup)); + btrfs_set_super_root(super, btrfs_backup_tree_root(root_backup)); + btrfs_set_super_root_level(super, + btrfs_backup_tree_root_level(root_backup)); + btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup)); + + /* + * fixme: the total bytes and num_devices need to match or we should + * need a fsck + */ + btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup)); + btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup)); + return 0; +} + +/* helper to cleanup tree roots */ +static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) +{ + free_extent_buffer(info->tree_root->node); + free_extent_buffer(info->tree_root->commit_root); + free_extent_buffer(info->dev_root->node); + free_extent_buffer(info->dev_root->commit_root); + free_extent_buffer(info->extent_root->node); + free_extent_buffer(info->extent_root->commit_root); + free_extent_buffer(info->csum_root->node); + free_extent_buffer(info->csum_root->commit_root); + + info->tree_root->node = NULL; + info->tree_root->commit_root = NULL; + info->dev_root->node = NULL; + info->dev_root->commit_root = NULL; + info->extent_root->node = NULL; + info->extent_root->commit_root = NULL; + info->csum_root->node = NULL; + info->csum_root->commit_root = NULL; + + if (chunk_root) { + free_extent_buffer(info->chunk_root->node); + free_extent_buffer(info->chunk_root->commit_root); + info->chunk_root->node = NULL; + info->chunk_root->commit_root = NULL; + } +} + + struct btrfs_root *open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options) @@ -1603,6 +1827,8 @@ struct btrfs_root *open_ctree(struct super_block *sb, int ret; int err = -EINVAL; + int num_backups_tried = 0; + int backup_index = 0; struct btrfs_super_block *disk_super; @@ -1782,6 +2008,13 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); /* + * run through our array of backup supers and setup + * our ring pointer to the oldest one + */ + generation = btrfs_super_generation(disk_super); + find_oldest_super_backup(fs_info, generation); + + /* * In the long term, we'll store the compression type in the super * block, and it'll be used for per file compression control. */ @@ -1938,7 +2171,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, if (!test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) { printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n", sb->s_id); - goto fail_chunk_root; + goto fail_tree_roots; } btrfs_set_root_node(&chunk_root->root_item, chunk_root->node); chunk_root->commit_root = btrfs_root_node(chunk_root); @@ -1953,11 +2186,12 @@ struct btrfs_root *open_ctree(struct super_block *sb, if (ret) { printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n", sb->s_id); - goto fail_chunk_root; + goto fail_tree_roots; } btrfs_close_extra_devices(fs_devices); +retry_root_backup: blocksize = btrfs_level_size(tree_root, btrfs_super_root_level(disk_super)); generation = btrfs_super_generation(disk_super); @@ -1965,32 +2199,33 @@ struct btrfs_root *open_ctree(struct super_block *sb, tree_root->node = read_tree_block(tree_root, btrfs_super_root(disk_super), blocksize, generation); - if (!tree_root->node) - goto fail_chunk_root; - if (!test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) { + if (!tree_root->node || + !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) { printk(KERN_WARNING "btrfs: failed to read tree root on %s\n", sb->s_id); - goto fail_tree_root; + + goto recovery_tree_root; } + btrfs_set_root_node(&tree_root->root_item, tree_root->node); tree_root->commit_root = btrfs_root_node(tree_root); ret = find_and_setup_root(tree_root, fs_info, BTRFS_EXTENT_TREE_OBJECTID, extent_root); if (ret) - goto fail_tree_root; + goto recovery_tree_root; extent_root->track_dirty = 1; ret = find_and_setup_root(tree_root, fs_info, BTRFS_DEV_TREE_OBJECTID, dev_root); if (ret) - goto fail_extent_root; + goto recovery_tree_root; dev_root->track_dirty = 1; ret = find_and_setup_root(tree_root, fs_info, BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) - goto fail_dev_root; + goto recovery_tree_root; csum_root->track_dirty = 1; @@ -2123,20 +2358,10 @@ fail_cleaner: fail_block_groups: btrfs_free_block_groups(fs_info); - free_extent_buffer(csum_root->node); - free_extent_buffer(csum_root->commit_root); -fail_dev_root: - free_extent_buffer(dev_root->node); - free_extent_buffer(dev_root->commit_root); -fail_extent_root: - free_extent_buffer(extent_root->node); - free_extent_buffer(extent_root->commit_root); -fail_tree_root: - free_extent_buffer(tree_root->node); - free_extent_buffer(tree_root->commit_root); -fail_chunk_root: - free_extent_buffer(chunk_root->node); - free_extent_buffer(chunk_root->commit_root); + +fail_tree_roots: + free_root_pointers(fs_info, 1); + fail_sb_buffer: btrfs_stop_workers(&fs_info->generic_worker); btrfs_stop_workers(&fs_info->fixup_workers); @@ -2164,6 +2389,25 @@ fail_srcu: fail: free_fs_info(fs_info); return ERR_PTR(err); + +recovery_tree_root: + + if (!btrfs_test_opt(tree_root, RECOVERY)) + goto fail_tree_roots; + + free_root_pointers(fs_info, 0); + + /* don't use the log in recovery mode, it won't be valid */ + btrfs_set_super_log_root(disk_super, 0); + + /* we can't trust the free space cache either */ + btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE); + + ret = next_root_backup(fs_info, fs_info->super_copy, + &num_backups_tried, &backup_index); + if (ret == -1) + goto fail_block_groups; + goto retry_root_backup; } static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) @@ -2333,6 +2577,7 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors) max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1; do_barriers = !btrfs_test_opt(root, NOBARRIER); + backup_super_roots(root->fs_info); sb = root->fs_info->super_for_commit; dev_item = &sb->dev_item; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index f7e9de724ef2..57080dffdfc6 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -164,7 +164,7 @@ enum { Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, - Opt_inode_cache, Opt_no_space_cache, Opt_err, + Opt_inode_cache, Opt_no_space_cache, Opt_recovery, Opt_err, }; static match_table_t tokens = { @@ -198,6 +198,7 @@ static match_table_t tokens = { {Opt_defrag, "autodefrag"}, {Opt_inode_cache, "inode_cache"}, {Opt_no_space_cache, "no_space_cache"}, + {Opt_recovery, "recovery"}, {Opt_err, NULL}, }; @@ -392,6 +393,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) printk(KERN_INFO "btrfs: enabling auto defrag"); btrfs_set_opt(info->mount_opt, AUTO_DEFRAG); break; + case Opt_recovery: + printk(KERN_INFO "btrfs: enabling auto recovery"); + btrfs_set_opt(info->mount_opt, RECOVERY); + break; case Opt_err: printk(KERN_INFO "btrfs: unrecognized mount option " "'%s'\n", p); |