From: Zhang Yi <[email protected]>
v1->v2:
- Fix the format type warning.
- Add more check of journal_cycle_record mount options in remount.
Hello, This patch set introduce a new mount option names
journal_cycle_record, it save journal head for a clean unmounted file
system, let ext4 continue/cycled record new journal transactions after
previous mount or recovered transactions for unclean file system. It
could give us more info when analysing a corrupted file system image
and locate kernel consistency bugs more conveniently.
This is just the kernel part and have already passed throuth xfstests in
auto mode (it depends on one prefix patch[1]). I will continue the
e2fsprogs' part if nobody strong dislike that. Any comments are welcome.
[1] https://lore.kernel.org/linux-ext4/20230130111138.76tp6pij3yhh4brh@quack3/T/#m96a1cffd567bdd844233b3115a6635391ed0b45b
Thanks,
Yi.
Zhang Yi (2):
jbd2: cycled record log on clean journal logging area
ext4: add journal cycled recording support
fs/ext4/ext4.h | 2 ++
fs/ext4/super.c | 18 ++++++++++++++++++
fs/jbd2/journal.c | 18 ++++++++++++++++--
fs/jbd2/recovery.c | 22 +++++++++++++++++-----
include/linux/jbd2.h | 9 +++++++--
5 files changed, 60 insertions(+), 9 deletions(-)
--
2.31.1
Introduce a new mount option names 'journal_cycle_record' to let jbd2
continue record journal log from the recovered head transaction block
or checkpointed/cleaned transactions on the previous mount.
Signed-off-by: Zhang Yi <[email protected]>
---
fs/ext4/ext4.h | 2 ++
fs/ext4/super.c | 18 ++++++++++++++++++
2 files changed, 20 insertions(+)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 140e1eb300d1..b62e7886fc2c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1267,6 +1267,8 @@ struct ext4_inode_info {
#define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group
* scanning in mballoc
*/
+#define EXT4_MOUNT2_JOURNAL_CYCLE_RECORD 0x00000100 /* Journal cycled record
+ * log on empty logging area */
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 260c1b3e3ef2..d9eeda327539 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1591,6 +1591,7 @@ enum {
Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan,
Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type,
+ Opt_journal_cycle_record,
#ifdef CONFIG_EXT4_DEBUG
Opt_fc_debug_max_replay, Opt_fc_debug_force
#endif
@@ -1670,6 +1671,7 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
fsparam_flag ("journal_checksum", Opt_journal_checksum),
fsparam_flag ("nojournal_checksum", Opt_nojournal_checksum),
fsparam_flag ("journal_async_commit",Opt_journal_async_commit),
+ fsparam_flag ("journal_cycle_record",Opt_journal_cycle_record),
fsparam_flag ("abort", Opt_abort),
fsparam_enum ("data", Opt_data, ext4_param_data),
fsparam_enum ("data_err", Opt_data_err,
@@ -1826,6 +1828,8 @@ static const struct mount_opts {
{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
{Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS,
MOPT_SET},
+ {Opt_journal_cycle_record, EXT4_MOUNT2_JOURNAL_CYCLE_RECORD,
+ MOPT_SET | MOPT_2 | MOPT_NO_EXT2},
#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
@@ -2772,6 +2776,13 @@ static int ext4_check_opt_consistency(struct fs_context *fc,
!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) {
goto fail_dax_change_remount;
}
+
+ if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_JOURNAL_CYCLE_RECORD) &&
+ !test_opt2(sb, JOURNAL_CYCLE_RECORD)) {
+ ext4_msg(NULL, KERN_ERR,
+ "can't change journal_cycle_record on remount");
+ return -EINVAL;
+ }
}
return ext4_check_quota_consistency(fc, sb);
@@ -5293,6 +5304,11 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
goto failed_mount3a;
}
+ if (test_opt2(sb, JOURNAL_CYCLE_RECORD)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "journal_cycle_record, fs mounted w/o journal");
+ goto failed_mount3a;
+ }
if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"journal_checksum, fs mounted w/o journal");
@@ -5698,6 +5714,8 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
else
journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
+ if (test_opt2(sb, JOURNAL_CYCLE_RECORD))
+ journal->j_flags |= JBD2_CYCLE_RECORD;
write_unlock(&journal->j_state_lock);
}
--
2.31.1
For a newly mounted file system, the journal committing thread always
record log from the beginning of the journal area, no matter whether the
journal is clean or it has just been recovered. It is disadvantageous to
analysis corrupted file system image and locate the file system
inconsistency bugs. When we get a corrupted file system image and want
to find out what has happened, besides lookup the system log, one
effective may is to backtrack the journal log. But we may not always run
e2fsck before each mount and the default fsck -a mode also cannot always
find all inconsistencies, so it could left over some inconsistencies
into the next mount until we detect it. Finally, the transactions in the
journal may probably discontinuous and some relatively new transactions
has been covered, it becomes hard to analyse. So if we could records
transactions continuously between each mounts, we could acquire more
useful info from the journal.
|Previous mount checkpointed/recovered logs|Current mount logs |
|{------}{---}{--------} ... {------}| ... |{======}{========}...000000|
This patch save the head blocknr in the superblock after flushing the
journal or unmounting the file system, let the next mount could continue
to record new transaction behind it. This change is backward compatible
because the old kernel does not care about the head blocknr of the
journal. It is also fine if we mount a clean old image without valid
head blocknr, we fail back to set it to s_first just like before.
Finally, for the case of mount an unclean file system, we could also get
the journal head easily after scanning the journal, it will continue to
record new transaction after the recovered transactions.
Signed-off-by: Zhang Yi <[email protected]>
---
fs/jbd2/journal.c | 18 ++++++++++++++++--
fs/jbd2/recovery.c | 22 +++++++++++++++++-----
include/linux/jbd2.h | 9 +++++++--
3 files changed, 40 insertions(+), 9 deletions(-)
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 2696f43e7239..41f0f5625e7c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1557,8 +1557,21 @@ static int journal_reset(journal_t *journal)
journal->j_first = first;
journal->j_last = last;
- journal->j_head = journal->j_first;
- journal->j_tail = journal->j_first;
+ if (journal->j_flags & JBD2_CYCLE_RECORD) {
+ /*
+ * Disable the cycled recording mode if the journal head block
+ * number is not correct.
+ */
+ if (journal->j_head < first || journal->j_head >= last) {
+ printk(KERN_WARNING "JBD2: Incorrect Journal head block %lu, "
+ "disable journal_cycle_record\n",
+ journal->j_head);
+ journal->j_head = journal->j_first;
+ }
+ } else {
+ journal->j_head = journal->j_first;
+ }
+ journal->j_tail = journal->j_head;
journal->j_free = journal->j_last - journal->j_first;
journal->j_tail_sequence = journal->j_transaction_sequence;
@@ -1730,6 +1743,7 @@ static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags)
sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
sb->s_start = cpu_to_be32(0);
+ sb->s_head = cpu_to_be32(journal->j_head);
if (jbd2_has_feature_fast_commit(journal)) {
/*
* When journal is clean, no need to commit fast commit flag and
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 8286a9ec122f..0184931d47f7 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -29,6 +29,7 @@ struct recovery_info
{
tid_t start_transaction;
tid_t end_transaction;
+ unsigned long head_block;
int nr_replays;
int nr_revokes;
@@ -301,11 +302,11 @@ int jbd2_journal_recover(journal_t *journal)
* is always zero if, and only if, the journal was cleanly
* unmounted.
*/
-
if (!sb->s_start) {
- jbd2_debug(1, "No recovery required, last transaction %d\n",
- be32_to_cpu(sb->s_sequence));
+ jbd2_debug(1, "No recovery required, last transaction %d, head block %u\n",
+ be32_to_cpu(sb->s_sequence), be32_to_cpu(sb->s_head));
journal->j_transaction_sequence = be32_to_cpu(sb->s_sequence) + 1;
+ journal->j_head = be32_to_cpu(sb->s_head);
return 0;
}
@@ -324,6 +325,9 @@ int jbd2_journal_recover(journal_t *journal)
/* Restart the log at the next transaction ID, thus invalidating
* any existing commit records in the log. */
journal->j_transaction_sequence = ++info.end_transaction;
+ journal->j_head = info.head_block;
+ jbd2_debug(1, "JBD2: last transaction %d, head block %lu\n",
+ journal->j_transaction_sequence, journal->j_head);
jbd2_journal_clear_revoke(journal);
err2 = sync_blockdev(journal->j_fs_dev);
@@ -364,6 +368,7 @@ int jbd2_journal_skip_recovery(journal_t *journal)
if (err) {
printk(KERN_ERR "JBD2: error %d scanning journal\n", err);
++journal->j_transaction_sequence;
+ journal->j_head = journal->j_first;
} else {
#ifdef CONFIG_JBD2_DEBUG
int dropped = info.end_transaction -
@@ -373,6 +378,7 @@ int jbd2_journal_skip_recovery(journal_t *journal)
dropped, (dropped == 1) ? "" : "s");
#endif
journal->j_transaction_sequence = ++info.end_transaction;
+ journal->j_head = info.head_block;
}
journal->j_tail = 0;
@@ -462,7 +468,7 @@ static int do_one_pass(journal_t *journal,
struct recovery_info *info, enum passtype pass)
{
unsigned int first_commit_ID, next_commit_ID;
- unsigned long next_log_block;
+ unsigned long next_log_block, head_block;
int err, success = 0;
journal_superblock_t * sb;
journal_header_t * tmp;
@@ -485,6 +491,7 @@ static int do_one_pass(journal_t *journal,
sb = journal->j_superblock;
next_commit_ID = be32_to_cpu(sb->s_sequence);
next_log_block = be32_to_cpu(sb->s_start);
+ head_block = next_log_block;
first_commit_ID = next_commit_ID;
if (pass == PASS_SCAN)
@@ -809,6 +816,7 @@ static int do_one_pass(journal_t *journal,
if (commit_time < last_trans_commit_time)
goto ignore_crc_mismatch;
info->end_transaction = next_commit_ID;
+ info->head_block = head_block;
if (!jbd2_has_feature_async_commit(journal)) {
journal->j_failed_commit =
@@ -817,8 +825,10 @@ static int do_one_pass(journal_t *journal,
break;
}
}
- if (pass == PASS_SCAN)
+ if (pass == PASS_SCAN) {
last_trans_commit_time = commit_time;
+ head_block = next_log_block;
+ }
brelse(bh);
next_commit_ID++;
continue;
@@ -868,6 +878,8 @@ static int do_one_pass(journal_t *journal,
if (pass == PASS_SCAN) {
if (!info->end_transaction)
info->end_transaction = next_commit_ID;
+ if (!info->head_block)
+ info->head_block = head_block;
} else {
/* It's really bad news if different passes end up at
* different places (but possible due to IO errors). */
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 2170e0cc279d..d5843ebfa6ed 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -265,8 +265,10 @@ typedef struct journal_superblock_s
__u8 s_padding2[3];
/* 0x0054 */
__be32 s_num_fc_blks; /* Number of fast commit blocks */
-/* 0x0058 */
- __u32 s_padding[41];
+ __be32 s_head; /* blocknr of head of log, only uptodate
+ * while the filesystem is clean */
+/* 0x005C */
+ __u32 s_padding[40];
__be32 s_checksum; /* crc32c(superblock) */
/* 0x0100 */
@@ -1392,6 +1394,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT)
#define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file
* data write error in ordered
* mode */
+#define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on
+ * clean and empty filesystem
+ * logging area */
#define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */
#define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */
#define JBD2_JOURNAL_FLUSH_DISCARD 0x0001
--
2.31.1