@@ -1152,6 +1152,7 @@ struct ext4_inode_info {
#define EXT4_ERROR_FS 0x0002 /* Errors detected */
#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */
#define EXT4_FC_REPLAY 0x0008 /* Fast commit replay ongoing */
+#define EXT4_FC_INELIGIBLE 0x0010 /* Fast commit ineligible */
/*
* Misc. filesystem flags
@@ -1651,6 +1652,7 @@ enum {
EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */
EXT4_STATE_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */
+ EXT4_STATE_FC_ELIGIBLE, /* File is Fast commit eligible */
};
#define EXT4_INODE_BIT_FNS(name, field, offset) \
@@ -342,6 +342,7 @@ void ext4_reset_inode_fc_info(struct inode *inode)
ei->i_fc_lblk_start = 0;
ei->i_fc_lblk_end = 0;
ei->i_fc_mdata_update = NULL;
+ ext4_clear_inode_state(inode, EXT4_STATE_FC_ELIGIBLE);
}
void ext4_init_inode_fc_info(struct inode *inode)
@@ -373,6 +374,36 @@ static inline tid_t get_running_txn_tid(struct super_block *sb)
return 0;
}
+static bool ext4_is_inode_fc_ineligible(struct inode *inode)
+{
+ if (get_running_txn_tid(inode->i_sb) == EXT4_I(inode)->i_fc_tid)
+ return !ext4_test_inode_state(inode, EXT4_STATE_FC_ELIGIBLE);
+ return false;
+}
+
+void ext4_fc_mark_ineligible(struct inode *inode, int reason)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+ if (!ext4_should_fast_commit(inode->i_sb) ||
+ (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (sbi->s_journal)
+ ei->i_fc_tid = get_running_txn_tid(inode->i_sb);
+ ext4_clear_inode_state(inode, EXT4_STATE_FC_ELIGIBLE);
+
+ ext4_fc_enqueue_inode(inode);
+}
+
+void ext4_fc_disable(struct super_block *sb, int reason)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ sbi->s_mount_state |= EXT4_FC_INELIGIBLE;
+}
+
/*
* Generic fast commit tracking function. If this is the first
* time this we are called after a full commit, we initialize
@@ -398,10 +429,15 @@ static int __ext4_fc_track_template(
write_lock(&ei->i_fc_lock);
if (running_txn_tid == ei->i_fc_tid) {
+ if (!ext4_test_inode_state(inode, EXT4_STATE_FC_ELIGIBLE)) {
+ write_unlock(&ei->i_fc_lock);
+ return -EINVAL;
+ }
update = true;
} else {
ext4_reset_inode_fc_info(inode);
ei->i_fc_tid = running_txn_tid;
+ ext4_set_inode_state(inode, EXT4_STATE_FC_ELIGIBLE);
}
ret = __fc_track_fn(inode, args, update);
write_unlock(&ei->i_fc_lock);
@@ -498,6 +534,27 @@ void ext4_fc_track_create(struct inode *inode, struct dentry *dentry)
trace_ext4_fc_track_create(inode, dentry, ret);
}
+static int __ext4_fc_add_inode(struct inode *inode, void *arg, bool update)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+ if (update)
+ return -EEXIST;
+
+ ei->i_fc_lblk_start = (i_size_read(inode) - 1) >> inode->i_blkbits;
+ ei->i_fc_lblk_end = (i_size_read(inode) - 1) >> inode->i_blkbits;
+
+ return 0;
+}
+
+void ext4_fc_track_inode(struct inode *inode)
+{
+ int ret;
+
+ ret = __ext4_fc_track_template(inode, __ext4_fc_add_inode, NULL);
+ trace_ext4_fc_track_inode(inode, ret);
+}
+
struct __ext4_fc_track_range_args {
ext4_lblk_t start, end;
};
@@ -479,4 +479,8 @@ void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
int __init ext4_init_fc_dentry_cache(void);
+void ext4_fc_track_inode(struct inode *inode);
+void ext4_fc_mark_ineligible(struct inode *inode, int reason);
+void ext4_fc_disable(struct super_block *sb, int reason);
+
#endif /* _EXT4_JBD2_H */
@@ -4335,6 +4335,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
INIT_LIST_HEAD(&sbi->s_fc_q);
INIT_LIST_HEAD(&sbi->s_fc_dentry_q);
+ sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
spin_lock_init(&sbi->s_fc_lock);
sb->s_root = NULL;
@@ -2731,6 +2731,28 @@ DEFINE_TRACE_DENTRY_EVENT(create);
DEFINE_TRACE_DENTRY_EVENT(link);
DEFINE_TRACE_DENTRY_EVENT(unlink);
+TRACE_EVENT(ext4_fc_track_inode,
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(int, ino)
+ __field(int, error)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->error = ret;
+ ),
+
+ TP_printk("dev %d:%d, inode %d, error %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino, __entry->error)
+ );
+
TRACE_EVENT(ext4_fc_track_range,
TP_PROTO(struct inode *inode, long start, long end, int ret),
Under certain situations, such as zeroing a range, there are only data updates and no metadata updates. We need to track such inodes for fast commits. Also, under some situations, we need to fall back to full commits because remembering the delta is either not yet supported or fast commits won't be "fast" enough. In such cases, we need to mark inodes as ineligible for fast commits. Add routines that allow tracking just the inodes and marking inodes as well as entire file system as fast commit ineligible. Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> --- fs/ext4/ext4.h | 2 ++ fs/ext4/ext4_jbd2.c | 57 +++++++++++++++++++++++++++++++++++++ fs/ext4/ext4_jbd2.h | 4 +++ fs/ext4/super.c | 1 + include/trace/events/ext4.h | 22 ++++++++++++++ 5 files changed, 86 insertions(+)