ext4: add support for lazy inode table initialization

When the lazy_itable_init extended option is passed to mke2fs, it
considerably speeds up filesystem creation because inode tables are
not zeroed out.  The fact that parts of the inode table are
uninitialized is not a problem so long as the block group descriptors,
which contain information regarding how much of the inode table has
been initialized, has not been corrupted However, if the block group
checksums are not valid, e2fsck must scan the entire inode table, and
the the old, uninitialized data could potentially cause e2fsck to
report false problems.

Hence, it is important for the inode tables to be initialized as soon
as possble.  This commit adds this feature so that mke2fs can safely
use the lazy inode table initialization feature to speed up formatting
file systems.

This is done via a new new kernel thread called ext4lazyinit, which is
created on demand and destroyed, when it is no longer needed.  There
is only one thread for all ext4 filesystems in the system. When the
first filesystem with inititable mount option is mounted, ext4lazyinit
thread is created, then the filesystem can register its request in the
request list.

This thread then walks through the list of requests picking up
scheduled requests and invoking ext4_init_inode_table(). Next schedule
time for the request is computed by multiplying the time it took to
zero out last inode table with wait multiplier, which can be set with
the (init_itable=n) mount option (default is 10).  We are doing
this so we do not take the whole I/O bandwidth. When the thread is no
longer necessary (request list is empty) it frees the appropriate
structures and exits (and can be created later later by another
filesystem).

We do not disturb regular inode allocations in any way, it just do not
care whether the inode table is, or is not zeroed. But when zeroing, we
have to skip used inodes, obviously. Also we should prevent new inode
allocations from the group, while zeroing is on the way. For that we
take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem
in the ext4_claim_inode, so when we are unlucky and allocator hits the
group which is currently being zeroed, it just has to wait.

This can be suppresed using the mount option no_init_itable.
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

Documentation/filesystems/ext4.txt

@@ -353,6 +353,20 @@ noauto_da_alloc		replacing existing files via patterns such as
 			system crashes before the delayed allocation
 			blocks are forced to disk.
 
+noinit_itable		Do not initialize any uninitialized inode table
+			blocks in the background.  This feature may be
+			used by installation CD's so that the install
+			process can complete as quickly as possible; the
+			inode table initialization process would then be
+			deferred until the next time the  file system
+			is unmounted.
+
+init_itable=n		The lazy itable init code will wait n times the
+			number of milliseconds it took to zero out the
+			previous block group's inode table.  This
+			minimizes the impact on the systme performance
+			while file system's inode table is being initialized.
+
 discard		Controls whether ext4 should issue discard/TRIM
 nodiscard(*)		commands to the underlying block device when
 			blocks are freed.  This is useful for SSD devices

fs/ext4/ext4.h

@@ -890,6 +890,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
 #define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
+#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
 
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt
 #define set_opt(o, opt)			o |= EXT4_MOUNT_##opt
@@ -1173,6 +1174,11 @@ struct ext4_sb_info {
 
 	/* timer for periodic error stats printing */
 	struct timer_list s_err_report;
+
+	/* Lazy inode table initialization info */
+	struct ext4_li_request *s_li_request;
+	/* Wait multiplier for lazy initialization thread */
+	unsigned int s_li_wait_mult;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1536,6 +1542,38 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 
 extern struct proc_dir_entry *ext4_proc_root;
 
+/*
+ * Timeout and state flag for lazy initialization inode thread.
+ */
+#define EXT4_DEF_LI_WAIT_MULT			10
+#define EXT4_DEF_LI_MAX_START_DELAY		5
+#define EXT4_LAZYINIT_QUIT			0x0001
+#define EXT4_LAZYINIT_RUNNING			0x0002
+
+/*
+ * Lazy inode table initialization info
+ */
+struct ext4_lazy_init {
+	unsigned long		li_state;
+
+	wait_queue_head_t	li_wait_daemon;
+	wait_queue_head_t	li_wait_task;
+	struct timer_list	li_timer;
+	struct task_struct	*li_task;
+
+	struct list_head	li_request_list;
+	struct mutex		li_list_mtx;
+};
+
+struct ext4_li_request {
+	struct super_block	*lr_super;
+	struct ext4_sb_info	*lr_sbi;
+	ext4_group_t		lr_next_group;
+	struct list_head	lr_request;
+	unsigned long		lr_next_sched;
+	unsigned long		lr_timeout;
+};
+
 /*
  * Function prototypes
  */
@@ -1611,6 +1649,8 @@ extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
 				       ext4_group_t group,
 				       struct ext4_group_desc *desc);
 extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern int ext4_init_inode_table(struct super_block *sb,
+				 ext4_group_t group, int barrier);
 
 /* mballoc.c */
 extern long ext4_mb_stats;

fs/ext4/ialloc.c

@@ -107,6 +107,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	desc = ext4_get_group_desc(sb, block_group, NULL);
 	if (!desc)
 		return NULL;
+
 	bitmap_blk = ext4_inode_bitmap(sb, desc);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
@@ -123,6 +124,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		unlock_buffer(bh);
 		return bh;
 	}
+
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
@@ -133,6 +135,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
+
 	if (buffer_uptodate(bh)) {
 		/*
 		 * if not uninit if bh is uptodate,
@@ -712,8 +715,17 @@ static int ext4_claim_inode(struct super_block *sb,
 {
 	int free = 0, retval = 0, count;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
 
+	/*
+	 * We have to be sure that new inode allocation does not race with
+	 * inode table initialization, because otherwise we may end up
+	 * allocating and writing new inode right before sb_issue_zeroout
+	 * takes place and overwriting our new inode with zeroes. So we
+	 * take alloc_sem to prevent it.
+	 */
+	down_read(&grp->alloc_sem);
 	ext4_lock_group(sb, group);
 	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
 		/* not a free inode */
@@ -724,6 +736,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
 			ino > EXT4_INODES_PER_GROUP(sb)) {
 		ext4_unlock_group(sb, group);
+		up_read(&grp->alloc_sem);
 		ext4_error(sb, "reserved inode or inode > inodes count - "
 			   "block_group = %u, inode=%lu", group,
 			   ino + group * EXT4_INODES_PER_GROUP(sb));
@@ -772,6 +785,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
 err_ret:
 	ext4_unlock_group(sb, group);
+	up_read(&grp->alloc_sem);
 	return retval;
 }
 
@@ -1205,3 +1219,109 @@ unsigned long ext4_count_dirs(struct super_block * sb)
 	}
 	return count;
 }
+
+/*
+ * Zeroes not yet zeroed inode table - just write zeroes through the whole
+ * inode table. Must be called without any spinlock held. The only place
+ * where it is called from on active part of filesystem is ext4lazyinit
+ * thread, so we do not need any special locks, however we have to prevent
+ * inode allocation from the current group, so we take alloc_sem lock, to
+ * block ext4_claim_inode until we are finished.
+ */
+extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+				 int barrier)
+{
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = NULL;
+	struct buffer_head *group_desc_bh;
+	handle_t *handle;
+	ext4_fsblk_t blk;
+	int num, ret = 0, used_blks = 0;
+	unsigned long flags = BLKDEV_IFL_WAIT;
+
+	/* This should not happen, but just to be sure check this */
+	if (sb->s_flags & MS_RDONLY) {
+		ret = 1;
+		goto out;
+	}
+
+	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+	if (!gdp)
+		goto out;
+
+	/*
+	 * We do not need to lock this, because we are the only one
+	 * handling this flag.
+	 */
+	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
+		goto out;
+
+	handle = ext4_journal_start_sb(sb, 1);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	down_write(&grp->alloc_sem);
+	/*
+	 * If inode bitmap was already initialized there may be some
+	 * used inodes so we need to skip blocks with used inodes in
+	 * inode table.
+	 */
+	if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
+		used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
+			    ext4_itable_unused_count(sb, gdp)),
+			    sbi->s_inodes_per_block);
+
+	blk = ext4_inode_table(sb, gdp) + used_blks;
+	num = sbi->s_itb_per_group - used_blks;
+
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	ret = ext4_journal_get_write_access(handle,
+					    group_desc_bh);
+	if (ret)
+		goto err_out;
+
+	if (unlikely(num > EXT4_INODES_PER_GROUP(sb))) {
+		ext4_error(sb, "Something is wrong with group %u\n"
+			   "Used itable blocks: %d"
+			   "Itable blocks per group: %lu\n",
+			   group, used_blks, sbi->s_itb_per_group);
+		ret = 1;
+		goto err_out;
+	}
+
+	/*
+	 * Skip zeroout if the inode table is full. But we set the ZEROED
+	 * flag anyway, because obviously, when it is full it does not need
+	 * further zeroing.
+	 */
+	if (unlikely(num == 0))
+		goto skip_zeroout;
+
+	ext4_debug("going to zero out inode table in group %d\n",
+		   group);
+	if (barrier)
+		flags |= BLKDEV_IFL_BARRIER;
+	ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS, flags);
+	if (ret < 0)
+		goto err_out;
+
+skip_zeroout:
+	ext4_lock_group(sb, group);
+	gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+	ext4_unlock_group(sb, group);
+
+	BUFFER_TRACE(group_desc_bh,
+		     "call ext4_handle_dirty_metadata");
+	ret = ext4_handle_dirty_metadata(handle, NULL,
+					 group_desc_bh);
+
+err_out:
+	up_write(&grp->alloc_sem);
+	ext4_journal_stop(handle);
+out:
+	return ret;
+}