{
struct journal_keys *keys = &c->journal_keys;
DARRAY(struct journal_key *) keys_sorted = { 0 };
- struct journal_key **kp;
struct journal *j = &c->journal;
u64 start_seq = c->journal_replay_seq_start;
u64 end_seq = c->journal_replay_seq_start;
struct btree_trans *trans = bch2_trans_get(c);
- int ret;
+ int ret = 0;
if (keys->nr) {
ret = bch2_journal_log_msg(c, "Starting journal replay (%zu keys in entries %llu-%llu)",
goto err;
}
+ BUG_ON(!atomic_read(&keys->ref));
+
/*
* First, attempt to replay keys in sorted order. This is more
- * efficient, but some might fail if that would cause a journal
- * deadlock.
+ * efficient - better locality of btree access - but some might fail if
+ * that would cause a journal deadlock.
*/
for (size_t i = 0; i < keys->nr; i++) {
cond_resched();
struct journal_key *k = keys->d + i;
- ret = commit_do(trans, NULL, NULL,
- BCH_TRANS_COMMIT_no_enospc|
- BCH_TRANS_COMMIT_journal_reclaim|
- (!k->allocated ? BCH_TRANS_COMMIT_no_journal_res : 0),
+ /* Skip fastpath if we're low on space in the journal */
+ ret = c->journal.watermark ? -1 :
+ commit_do(trans, NULL, NULL,
+ BCH_TRANS_COMMIT_no_enospc|
+ BCH_TRANS_COMMIT_journal_reclaim|
+ (!k->allocated ? BCH_TRANS_COMMIT_no_journal_res : 0),
bch2_journal_replay_key(trans, k));
BUG_ON(!ret && !k->overwritten);
if (ret) {
BUG_ON(!k->overwritten);
}
+ /*
+ * We need to put our btree_trans before calling flush_all_pins(), since
+ * that will use a btree_trans internally
+ */
bch2_trans_put(trans);
trans = NULL;
+ if (!c->opts.keep_journal)
+ bch2_journal_keys_put_initial(c);
+
replay_now_at(j, j->replay_journal_seq_end);
j->replay_journal_seq = 0;
bch2_journal_set_replay_done(j);
- bch2_journal_flush_all_pins(j);
- ret = bch2_journal_error(j);
- if (keys->nr && !ret)
+ if (keys->nr)
bch2_journal_log_msg(c, "journal replay finished");
err:
if (trans)
struct bch_dev *ca = bch_dev_bkey_exists(c, le32_to_cpu(u->dev));
unsigned i, nr_types = jset_entry_dev_usage_nr_types(u);
- ca->usage_base->buckets_ec = le64_to_cpu(u->buckets_ec);
-
for (i = 0; i < min_t(unsigned, nr_types, BCH_DATA_NR); i++) {
ca->usage_base->d[i].buckets = le64_to_cpu(u->d[i].buckets);
ca->usage_base->d[i].sectors = le64_to_cpu(u->d[i].sectors);
static int journal_replay_early(struct bch_fs *c,
struct bch_sb_field_clean *clean)
{
- struct jset_entry *entry;
- int ret;
-
if (clean) {
- for (entry = clean->start;
+ for (struct jset_entry *entry = clean->start;
entry != vstruct_end(&clean->field);
entry = vstruct_next(entry)) {
- ret = journal_replay_entry_early(c, entry);
+ int ret = journal_replay_entry_early(c, entry);
if (ret)
return ret;
}
continue;
vstruct_for_each(&i->j, entry) {
- ret = journal_replay_entry_early(c, entry);
+ int ret = journal_replay_entry_early(c, entry);
if (ret)
return ret;
}
ret = bch2_btree_insert(c, BTREE_ID_snapshot_trees, &root_tree.k_i, NULL, 0) ?:
bch2_btree_insert(c, BTREE_ID_snapshots, &root_snapshot.k_i, NULL, 0) ?:
bch2_btree_insert(c, BTREE_ID_subvolumes, &root_volume.k_i, NULL, 0);
- if (ret)
- bch_err_fn(c, ret);
+ bch_err_fn(c, ret);
return ret;
}
{
int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw,
__bch2_fs_upgrade_for_subvolumes(trans));
- if (ret)
- bch_err_fn(c, ret);
+ bch_err_fn(c, ret);
return ret;
}
move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
keys->gap = keys->nr;
- set_bit(BCH_FS_MAY_GO_RW, &c->flags);
- if (keys->nr)
+ set_bit(BCH_FS_may_go_rw, &c->flags);
+
+ if (keys->nr || c->opts.fsck || !c->sb.clean)
return bch2_fs_read_write_early(c);
return 0;
}
static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
{
- struct recovery_pass_fn *p = recovery_pass_fns + c->curr_recovery_pass;
+ struct recovery_pass_fn *p = recovery_pass_fns + pass;
if (c->opts.norecovery && pass > BCH_RECOVERY_PASS_snapshots_read)
return false;
static int bch2_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
{
+ struct recovery_pass_fn *p = recovery_pass_fns + pass;
int ret;
- c->curr_recovery_pass = pass;
+ if (!(p->when & PASS_SILENT))
+ bch2_print(c, KERN_INFO bch2_log_msg(c, "%s..."),
+ bch2_recovery_passes[pass]);
+ ret = p->fn(c);
+ if (ret)
+ return ret;
+ if (!(p->when & PASS_SILENT))
+ bch2_print(c, KERN_CONT " done\n");
- if (should_run_recovery_pass(c, pass)) {
- struct recovery_pass_fn *p = recovery_pass_fns + pass;
+ return 0;
+}
- if (!(p->when & PASS_SILENT))
- printk(KERN_INFO bch2_log_msg(c, "%s..."),
- bch2_recovery_passes[pass]);
- ret = p->fn(c);
- if (ret)
- return ret;
- if (!(p->when & PASS_SILENT))
- printk(KERN_CONT " done\n");
+static int bch2_run_recovery_passes(struct bch_fs *c)
+{
+ int ret = 0;
+
+ while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) {
+ if (should_run_recovery_pass(c, c->curr_recovery_pass)) {
+ ret = bch2_run_recovery_pass(c, c->curr_recovery_pass);
+ if (bch2_err_matches(ret, BCH_ERR_restart_recovery))
+ continue;
+ if (ret)
+ break;
- c->recovery_passes_complete |= BIT_ULL(pass);
+ c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass);
+ }
+ c->curr_recovery_pass++;
+ c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass);
}
- return 0;
+ return ret;
}
-static int bch2_run_recovery_passes(struct bch_fs *c)
+int bch2_run_online_recovery_passes(struct bch_fs *c)
{
int ret = 0;
- while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) {
- ret = bch2_run_recovery_pass(c, c->curr_recovery_pass);
- if (bch2_err_matches(ret, BCH_ERR_restart_recovery))
+ for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) {
+ struct recovery_pass_fn *p = recovery_pass_fns + i;
+
+ if (!(p->when & PASS_ONLINE))
continue;
+
+ ret = bch2_run_recovery_pass(c, i);
+ if (bch2_err_matches(ret, BCH_ERR_restart_recovery)) {
+ i = c->curr_recovery_pass;
+ continue;
+ }
if (ret)
break;
- c->curr_recovery_pass++;
}
return ret;
/* If we fixed errors, verify that fs is actually clean now: */
if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) &&
- test_bit(BCH_FS_ERRORS_FIXED, &c->flags) &&
- !test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags) &&
- !test_bit(BCH_FS_ERROR, &c->flags)) {
+ test_bit(BCH_FS_errors_fixed, &c->flags) &&
+ !test_bit(BCH_FS_errors_not_fixed, &c->flags) &&
+ !test_bit(BCH_FS_error, &c->flags)) {
+ bch2_flush_fsck_errs(c);
+
bch_info(c, "Fixed errors, running fsck a second time to verify fs is clean");
- clear_bit(BCH_FS_ERRORS_FIXED, &c->flags);
+ clear_bit(BCH_FS_errors_fixed, &c->flags);
c->curr_recovery_pass = BCH_RECOVERY_PASS_check_alloc_info;
if (ret)
goto err;
- if (test_bit(BCH_FS_ERRORS_FIXED, &c->flags) ||
- test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags)) {
+ if (test_bit(BCH_FS_errors_fixed, &c->flags) ||
+ test_bit(BCH_FS_errors_not_fixed, &c->flags)) {
bch_err(c, "Second fsck run was not clean");
- set_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags);
+ set_bit(BCH_FS_errors_not_fixed, &c->flags);
}
- set_bit(BCH_FS_ERRORS_FIXED, &c->flags);
+ set_bit(BCH_FS_errors_fixed, &c->flags);
}
if (enabled_qtypes(c)) {
write_sb = true;
}
- if (!test_bit(BCH_FS_ERROR, &c->flags)) {
+ if (!test_bit(BCH_FS_error, &c->flags)) {
c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_alloc_info);
write_sb = true;
}
if (c->opts.fsck &&
- !test_bit(BCH_FS_ERROR, &c->flags) &&
- !test_bit(BCH_FS_ERRORS_NOT_FIXED, &c->flags)) {
+ !test_bit(BCH_FS_error, &c->flags) &&
+ !test_bit(BCH_FS_errors_not_fixed, &c->flags)) {
SET_BCH_SB_HAS_ERRORS(c->disk_sb.sb, 0);
SET_BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb, 0);
write_sb = true;
bch2_move_stats_init(&stats, "recovery");
- bch_info(c, "scanning for old btree nodes");
- ret = bch2_fs_read_write(c) ?:
+ struct printbuf buf = PRINTBUF;
+ bch2_version_to_text(&buf, c->sb.version_min);
+ bch_info(c, "scanning for old btree nodes: min_version %s", buf.buf);
+ printbuf_exit(&buf);
+
+ ret = bch2_fs_read_write_early(c) ?:
bch2_scan_old_btree_nodes(c, &stats);
if (ret)
goto err;
ret = 0;
out:
- set_bit(BCH_FS_FSCK_DONE, &c->flags);
+ set_bit(BCH_FS_fsck_done, &c->flags);
bch2_flush_fsck_errs(c);
if (!c->opts.keep_journal &&
- test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) {
- bch2_journal_keys_free(&c->journal_keys);
- bch2_journal_entries_free(c);
- }
+ test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags))
+ bch2_journal_keys_put_initial(c);
kfree(clean);
- if (!ret && test_bit(BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS, &c->flags)) {
+ if (!ret && test_bit(BCH_FS_need_delete_dead_snapshots, &c->flags)) {
bch2_fs_read_write_early(c);
bch2_delete_dead_snapshots_async(c);
}
- if (ret)
- bch_err_fn(c, ret);
+ bch_err_fn(c, ret);
return ret;
err:
fsck_err:
struct bch_inode_unpacked root_inode, lostfound_inode;
struct bkey_inode_buf packed_inode;
struct qstr lostfound = QSTR("lost+found");
- struct bch_dev *ca;
- unsigned i;
int ret;
bch_notice(c, "initializing new filesystem");
mutex_unlock(&c->sb_lock);
c->curr_recovery_pass = ARRAY_SIZE(recovery_pass_fns);
- set_bit(BCH_FS_MAY_GO_RW, &c->flags);
- set_bit(BCH_FS_FSCK_DONE, &c->flags);
+ set_bit(BCH_FS_may_go_rw, &c->flags);
+ set_bit(BCH_FS_fsck_done, &c->flags);
- for (i = 0; i < BTREE_ID_NR; i++)
+ for (unsigned i = 0; i < BTREE_ID_NR; i++)
bch2_btree_root_alloc(c, i);
- for_each_member_device(ca, c, i)
+ for_each_member_device(c, ca)
bch2_dev_usage_init(ca);
ret = bch2_fs_journal_alloc(c);
if (ret)
goto err;
- for_each_online_member(ca, c, i)
+ for_each_online_member(c, ca)
ca->new_fs_bucket_idx = 0;
ret = bch2_fs_freespace_init(c);
packed_inode.inode.k.p.snapshot = U32_MAX;
ret = bch2_btree_insert(c, BTREE_ID_inodes, &packed_inode.inode.k_i, NULL, 0);
- if (ret) {
- bch_err_msg(c, ret, "creating root directory");
+ bch_err_msg(c, ret, "creating root directory");
+ if (ret)
goto err;
- }
bch2_inode_init_early(c, &lostfound_inode);
&lostfound,
0, 0, S_IFDIR|0700, 0,
NULL, NULL, (subvol_inum) { 0 }, 0));
- if (ret) {
- bch_err_msg(c, ret, "creating lost+found");
+ bch_err_msg(c, ret, "creating lost+found");
+ if (ret)
goto err;
- }
if (enabled_qtypes(c)) {
ret = bch2_fs_quota_read(c);
}
ret = bch2_journal_flush(&c->journal);
- if (ret) {
- bch_err_msg(c, ret, "writing first journal entry");
+ bch_err_msg(c, ret, "writing first journal entry");
+ if (ret)
goto err;
- }
mutex_lock(&c->sb_lock);
SET_BCH_SB_INITIALIZED(c->disk_sb.sb, true);
return 0;
err:
- bch_err_fn(ca, ret);
+ bch_err_fn(c, ret);
return ret;
}
projects / bcachefs-tools-debian / blobdiff