[PATCH-v9 3/3] ext4: add optimization for the lazytime mount option

[Theodore Ts'o <tytso@mit.edu>]

Add an optimization for the MS_LAZYTIME mount option so that we will
opportunistically write out any inodes with the I_DIRTY_TIME flag set
in a particular inode table block when we need to update some inode in
that inode table block anyway.

Also add some temporary code so that we can set the lazytime mount
option without needing a modified /sbin/mount program which can set
MS_LAZYTIME.  We can eventually make this go away once util-linux has
added support.

Google-Bug-Id: 18297052

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c             | 64 +++++++++++++++++++++++++++++++++++++++++++--
 fs/ext4/super.c             | 10 +++++++
 include/trace/events/ext4.h | 30 +++++++++++++++++++++
 3 files changed, 102 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 628df5b..9193ea1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4139,6 +4139,65 @@ static int ext4_inode_blocks_set(handle_t *handle,
 	return 0;
 }
 
+struct other_inode {
+	unsigned long		orig_ino;
+	struct ext4_inode	*raw_inode;
+};
+
+static int other_inode_match(struct inode * inode, unsigned long ino,
+			     void *data)
+{
+	struct other_inode *oi = (struct other_inode *) data;
+
+	if ((inode->i_ino != ino) ||
+	    (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
+			       I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
+	    ((inode->i_state & I_DIRTY_TIME) == 0))
+		return 0;
+	spin_lock(&inode->i_lock);
+	if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
+				I_DIRTY_SYNC | I_DIRTY_DATASYNC)) == 0) &&
+	    (inode->i_state & I_DIRTY_TIME)) {
+		struct ext4_inode_info	*ei = EXT4_I(inode);
+
+		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		spin_unlock(&inode->i_lock);
+
+		spin_lock(&ei->i_raw_lock);
+		EXT4_INODE_SET_XTIME(i_ctime, inode, oi->raw_inode);
+		EXT4_INODE_SET_XTIME(i_mtime, inode, oi->raw_inode);
+		EXT4_INODE_SET_XTIME(i_atime, inode, oi->raw_inode);
+		ext4_inode_csum_set(inode, oi->raw_inode, ei);
+		spin_unlock(&ei->i_raw_lock);
+		trace_ext4_other_inode_update_time(inode, oi->orig_ino);
+		return -1;
+	}
+	spin_unlock(&inode->i_lock);
+	return -1;
+}
+
+/*
+ * Opportunistically update the other time fields for other inodes in
+ * the same inode table block.
+ */
+static void ext4_update_other_inodes_time(struct super_block *sb,
+					  unsigned long orig_ino, char *buf)
+{
+	struct other_inode oi;
+	unsigned long ino;
+	int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+	int inode_size = EXT4_INODE_SIZE(sb);
+
+	oi.orig_ino = orig_ino;
+	ino = orig_ino & ~(inodes_per_block - 1);
+	for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
+		if (ino == orig_ino)
+			continue;
+		oi.raw_inode = (struct ext4_inode *) buf;
+		(void) find_inode_nowait(sb, ino, other_inode_match, &oi);
+	}
+}
+
 /*
  * Post the struct inode info into an on-disk inode location in the
  * buffer-cache.  This gobbles the caller's reference to the
@@ -4248,10 +4307,11 @@ static int ext4_do_update_inode(handle_t *handle,
 				cpu_to_le16(ei->i_extra_isize);
 		}
 	}
-
 	ext4_inode_csum_set(inode, raw_inode, ei);
-
 	spin_unlock(&ei->i_raw_lock);
+	if (inode->i_sb->s_flags & MS_LAZYTIME)
+		ext4_update_other_inodes_time(inode->i_sb, inode->i_ino,
+					      bh->b_data);
 
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 74c5f53..362b23c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1139,6 +1139,7 @@ enum {
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_i_version,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+	Opt_lazytime, Opt_nolazytime,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
@@ -1202,6 +1203,8 @@ static const match_table_t tokens = {
 	{Opt_i_version, "i_version"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
+	{Opt_lazytime, "lazytime"},
+	{Opt_nolazytime, "nolazytime"},
 	{Opt_nodelalloc, "nodelalloc"},
 	{Opt_removed, "mblk_io_submit"},
 	{Opt_removed, "nomblk_io_submit"},
@@ -1459,6 +1462,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 	case Opt_i_version:
 		sb->s_flags |= MS_I_VERSION;
 		return 1;
+	case Opt_lazytime:
+		sb->s_flags |= MS_LAZYTIME;
+		return 1;
+	case Opt_nolazytime:
+		sb->s_flags &= ~MS_LAZYTIME;
+		return 1;
 	}
 
 	for (m = ext4_mount_opts; m->token != Opt_err; m++)
@@ -5020,6 +5029,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	}
 #endif
 
+	*flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME);
 	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
 	kfree(orig_data);
 	return 0;
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 6cfb841..6e5abd6 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -73,6 +73,36 @@ struct extent_status;
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
 
+TRACE_EVENT(ext4_other_inode_update_time,
+	TP_PROTO(struct inode *inode, ino_t orig_ino),
+
+	TP_ARGS(inode, orig_ino),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	ino_t,	orig_ino		)
+		__field(	uid_t,	uid			)
+		__field(	gid_t,	gid			)
+		__field(	__u16, mode			)
+	),
+
+	TP_fast_assign(
+		__entry->orig_ino = orig_ino;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->uid	= i_uid_read(inode);
+		__entry->gid	= i_gid_read(inode);
+		__entry->mode	= inode->i_mode;
+	),
+
+	TP_printk("dev %d,%d orig_ino %lu ino %lu mode 0%o uid %u gid %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->orig_ino,
+		  (unsigned long) __entry->ino, __entry->mode,
+		  __entry->uid, __entry->gid)
+);
+
 TRACE_EVENT(ext4_free_inode,
 	TP_PROTO(struct inode *inode),
 
-- 
2.1.0