[PATCH 0/6 v3] Lazy itable initialization for Ext4

[PATCH 0/6 v3] Lazy itable initialization for Ext4

[Lukas Czerner]

Hi all,

not much has changed since my last post. Some small cleanup and adjustments
proposed by Andreas. There are two noticeable changes though:

 * you can now mount with inititable=n option, where n is a number which
   be used as wait multiplier for thread scheduling purposes (see patch #3).

 * introduced sysfs interface for advertising features like lazy itable
   initialization, to user space (see patch #6)

Thanks for review!

-Lukas

---
 [PATCH 1/6] Add helper function for blkdev_issue_zeroout
 [PATCH 2/6] Add inititable/noinititable mount options for ext4
 [PATCH 3/6] Add inode table initialization code for Ext4
 [PATCH 4/6] Use sb_issue_zeroout in setup_new_group_blocks
 [PATCH 5/6] Use sb_issue_discard in ext4_ext_zeroout
 [PATCH 6/6] Add interface to advertise ext4 features in sysfs

 fs/ext4/ext4.h         |   44 +++++
 fs/ext4/extents.c      |   68 +------
 fs/ext4/ialloc.c       |  116 ++++++++++++
 fs/ext4/resize.c       |   44 +----
 fs/ext4/super.c        |  490 +++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/blkdev.h |    8 +
 6 files changed, 671 insertions(+), 99 deletions(-)

[PATCH 1/6] Add helper function for blkdev_issue_zeroout

[Lukas Czerner]

This is done the same way as function sb_issue_discard for
blkdev_issue_discard.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 include/linux/blkdev.h |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 09a8402..a22939d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1023,6 +1023,14 @@ static inline int sb_issue_discard(struct super_block *sb,
 	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
 				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 }
+static inline int sb_issue_zeroout(struct super_block *sb,
+				   sector_t block, sector_t nr_blocks)
+{
+	block <<= (sb->s_blocksize_bits - 9);
+	nr_blocks <<= (sb->s_blocksize_bits - 9);
+	return blkdev_issue_zeroout(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
+				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+}
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
 
-- 
1.7.2.2

Re: [PATCH 1/6] Add helper function for blkdev_issue_zeroout

[Mike Snitzer]

On Wed, Sep 15, 2010 at 12:36 PM, Lukas Czerner <lczerner@redhat.com> wrote:
> This is done the same way as function sb_issue_discard for
> blkdev_issue_discard.
>
> Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> ---
>  include/linux/blkdev.h |    8 ++++++++
>  1 files changed, 8 insertions(+), 0 deletions(-)
>
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 09a8402..a22939d 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -1023,6 +1023,14 @@ static inline int sb_issue_discard(struct super_block *sb,
>        return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
>                                   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
>  }
> +static inline int sb_issue_zeroout(struct super_block *sb,
> +                                  sector_t block, sector_t nr_blocks)
> +{
> +       block <<= (sb->s_blocksize_bits - 9);
> +       nr_blocks <<= (sb->s_blocksize_bits - 9);
> +       return blkdev_issue_zeroout(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
> +                                  BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
> +}

You'll need to rebase this patch against Jens' linux-2.6-block.git
'for-next' branch.  The flags have changed such that the
sb_issue_discard caller passes them in (and BLKDEV_IFL_BARRIER no
longer exists).  See the following commits from linux-2.6-block.git:

http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commit;h=2cf6d26a354ab
http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commit;h=61002f7db33c7
http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commit;h=8c5553678237b
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 2/6] Add inititable/noinititable mount options for ext4

[Lukas Czerner]

Add new mount flag EXT4_MOUNT_INIT_INODE_TABLE and add new pair of mount
options (inititable/noinititable). When mounted with inititable file
system should try to initialize uninitialized inode tables, otherwise it
should prevent initializing inode tables. For now, default is noinittable.

One can also specify inititable=n where n is a number that will be used
as the wait multiplier (see "Add inode table initialization code into
Ext4" patch for more info). Bigger number means slower inode table
initialization thus less impact on performance, but longer
inititalization (default is 10).

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/ext4.h  |    1 +
 fs/ext4/super.c |   22 ++++++++++++++++++++++
 2 files changed, 23 insertions(+), 0 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 19a4de5..dbd6760 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -885,6 +885,7 @@ 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
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4e8983a..3dbae36 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -986,6 +986,10 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (test_opt(sb, DIOREAD_NOLOCK))
 		seq_puts(seq, ",dioread_nolock");
 
+	if (test_opt(sb, INIT_INODE_TABLE))
+		seq_printf(seq, ",init_inode_table=%u",
+			   (unsigned) sbi->s_li_wait_mult);
+
 	ext4_show_quota_options(seq, sb);
 
 	return 0;
@@ -1161,6 +1165,7 @@ enum {
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard,
+	Opt_init_inode_table, Opt_noinit_inode_table,
 };
 
 static const match_table_t tokens = {
@@ -1231,6 +1236,9 @@ static const match_table_t tokens = {
 	{Opt_dioread_lock, "dioread_lock"},
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
+	{Opt_init_inode_table, "inititable=%u"},
+	{Opt_init_inode_table, "inititable"},
+	{Opt_noinit_inode_table, "noinititable"},
 	{Opt_err, NULL},
 };
 
@@ -1699,6 +1707,20 @@ set_qf_format:
 		case Opt_dioread_lock:
 			clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
 			break;
+		case Opt_init_inode_table:
+			set_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
+			if (args[0].from) {
+				if (match_int(&args[0], &option))
+					return 0;
+			} else
+				option = EXT4_DEF_LI_WAIT_MULT;
+			if (option < 0)
+				return 0;
+			sbi->s_li_wait_mult = option;
+			break;
+		case Opt_noinit_inode_table:
+			clear_opt(sbi->s_mount_opt, INIT_INODE_TABLE);
+			break;
 		default:
 			ext4_msg(sb, KERN_ERR,
 			       "Unrecognized mount option \"%s\" "
-- 
1.7.2.2

[PATCH 3/6] Add inode table initialization code for Ext4

[Lukas Czerner]

When lazy_itable_init extended option is passed to mke2fs, it
considerably speed up filesystem creation because inode tables are
not zeroed out, thus contains some old data. When this fs is mounted
filesystem code should initialize (zero out) inode tables.
So far this code was missing for ext4 and this patch adds this feature.

For purpose of zeroing inode tables it introduces 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
(inititable=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.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/ext4.h   |   38 +++++
 fs/ext4/ialloc.c |  116 +++++++++++++++
 fs/ext4/super.c  |  418 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 569 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index dbd6760..0df3977 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1144,6 +1144,11 @@ struct ext4_sb_info {
 
 	/* workqueue for dio unwritten */
 	struct workqueue_struct *dio_unwritten_wq;
+
+	/* 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)
@@ -1467,6 +1472,37 @@ 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;
+};
+
+/*
  * Function prototypes
  */
 
@@ -1539,6 +1575,8 @@ 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);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 25c4b31..08d2df3 100644
--- a/fs/ext4/ialloc.c
+++ b/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 +1219,105 @@ 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)
+{
+	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;
+
+	/* 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);
+	ret = sb_issue_zeroout(sb, blk, num);
+	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;
+}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3dbae36..3e285eb 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -41,6 +41,9 @@
 #include <linux/crc16.h>
 #include <asm/uaccess.h>
 
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -52,6 +55,8 @@
 
 struct proc_dir_entry *ext4_proc_root;
 static struct kset *ext4_kset;
+struct ext4_lazy_init *ext4_li_info;
+struct mutex ext4_li_mtx;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
@@ -70,6 +75,8 @@ static void ext4_write_super(struct super_block *sb);
 static int ext4_freeze(struct super_block *sb);
 static int ext4_get_sb(struct file_system_type *fs_type, int flags,
 		       const char *dev_name, void *data, struct vfsmount *mnt);
+static void ext4_destroy_lazyinit_thread(void);
+static void ext4_unregister_li_request(struct super_block *sb);
 
 #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext3_fs_type = {
@@ -664,6 +671,7 @@ static void ext4_put_super(struct super_block *sb)
 				   "Couldn't clean up the journal");
 	}
 
+	ext4_unregister_li_request(sb);
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
@@ -1904,7 +1912,8 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
 }
 
 /* Called at mount-time, super-block is locked */
-static int ext4_check_descriptors(struct super_block *sb)
+static int ext4_check_descriptors(struct super_block *sb,
+				  ext4_group_t *first_not_zeroed)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
@@ -1913,7 +1922,7 @@ static int ext4_check_descriptors(struct super_block *sb)
 	ext4_fsblk_t inode_bitmap;
 	ext4_fsblk_t inode_table;
 	int flexbg_flag = 0;
-	ext4_group_t i;
+	ext4_group_t i, grp = sbi->s_groups_count;
 
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
 		flexbg_flag = 1;
@@ -1929,6 +1938,10 @@ static int ext4_check_descriptors(struct super_block *sb)
 			last_block = first_block +
 				(EXT4_BLOCKS_PER_GROUP(sb) - 1);
 
+		if ((grp == sbi->s_groups_count) &&
+		   !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			grp = i;
+
 		block_bitmap = ext4_block_bitmap(sb, gdp);
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -1966,6 +1979,8 @@ static int ext4_check_descriptors(struct super_block *sb)
 		if (!flexbg_flag)
 			first_block += EXT4_BLOCKS_PER_GROUP(sb);
 	}
+	if (NULL != first_not_zeroed)
+		*first_not_zeroed = grp;
 
 	ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
 	sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
@@ -2453,6 +2468,381 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 	return 1;
 }
 
+static void ext4_lazyinode_timeout(unsigned long data)
+{
+	struct task_struct *p = (struct task_struct *)data;
+	wake_up_process(p);
+}
+
+/* Find next suitable group adn run ext4_init_inode_table */
+static int ext4_run_li_request(struct ext4_li_request *elr)
+{
+	struct ext4_group_desc *gdp = NULL;
+	ext4_group_t group, ngroups;
+	struct super_block *sb;
+	int ret = 0;
+
+	sb = elr->lr_super;
+	ngroups = EXT4_SB(sb)->s_groups_count;
+
+	printk(KERN_CRIT "next is -%d\n", elr->lr_next_group+1);
+	for (group = elr->lr_next_group; group < ngroups; group++) {
+		gdp = ext4_get_group_desc(sb, group, NULL);
+		if (!gdp) {
+			ret = 1;
+			break;
+		}
+
+		if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			break;
+	}
+
+	if (group == ngroups)
+		ret = 1;
+	
+	printk(KERN_CRIT "Going to zeroout group %d next is %d\n",group, elr->lr_next_group+1);
+	if (!ret) {
+		ret = ext4_init_inode_table(sb, group);
+		elr->lr_next_group = group + 1;
+	}
+
+	return ret;
+}
+
+/*
+ * Remove lr_request from the list_request and free the
+ * request tructure. Should be called with li_list_mtx held
+ */
+static void ext4_remove_li_request(struct ext4_li_request *elr)
+{
+	struct ext4_sb_info *sbi;
+
+	if (!elr)
+		return;
+
+	sbi = elr->lr_sbi;
+
+	list_del(&elr->lr_request);
+	sbi->s_li_request = NULL;
+	kfree(elr);
+}
+
+static void ext4_unregister_li_request(struct super_block *sb)
+{
+	struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
+
+	if (!ext4_li_info)
+		return;
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	ext4_remove_li_request(elr);
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+/*
+ * This is the function where ext4lazyinit thread lives. It walks
+ * through the request list searching for next scheduled filesystem.
+ * When such a fs is found, run the lazy initialization request
+ * (ext4_rn_li_request) and keep track of the time spend in this
+ * function. Based on that time we compute next schedule time of
+ * the request. When walking through the list is complete, compute
+ * next waking time and put itself into sleep.
+ */
+static int ext4_lazyinit_thread(void *arg)
+{
+	struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
+	struct list_head *pos, *n;
+	struct ext4_li_request *elr;
+	struct ext4_sb_info *sbi;
+	unsigned long next_wakeup;
+	unsigned long timeout = 0;
+	int ret;
+
+	BUG_ON(NULL == eli);
+
+	eli->li_timer.data = (unsigned long)current;
+	eli->li_timer.function = ext4_lazyinode_timeout;
+
+	eli->li_task = current;
+	wake_up(&eli->li_wait_task);
+
+cont_thread:
+	while (true) {
+		next_wakeup = ULONG_MAX;
+
+		mutex_lock(&eli->li_list_mtx);
+		if (list_empty(&eli->li_request_list)) {
+			mutex_unlock(&eli->li_list_mtx);
+			goto exit_thread;
+		}
+
+		list_for_each_safe(pos, n, &eli->li_request_list) {
+			elr = list_entry(pos, struct ext4_li_request,
+					 lr_request);
+
+			if (time_before_eq(jiffies, elr->lr_next_sched))
+				continue;
+			sbi = elr->lr_sbi;
+
+			timeout = jiffies;
+			ret = ext4_run_li_request(elr);
+			timeout = (jiffies - timeout) * sbi->s_li_wait_mult;
+
+			if (ret) {
+				ext4_remove_li_request(elr);
+				continue;
+			}
+
+			elr->lr_next_sched = jiffies + timeout;
+			if (elr->lr_next_sched < next_wakeup)
+				next_wakeup = elr->lr_next_sched;
+		}
+		mutex_unlock(&eli->li_list_mtx);
+
+		/*
+		 * We need to check this otherwise we may end up sleeping
+		 * for very long time.
+		 */
+		if (jiffies >= next_wakeup) {
+			cond_resched();
+			continue;
+		}
+
+		eli->li_timer.expires = next_wakeup;
+		add_timer(&eli->li_timer);
+
+		if (freezing(current)) {
+			refrigerator();
+		} else {
+			DEFINE_WAIT(wait);
+			prepare_to_wait(&eli->li_wait_daemon, &wait,
+					TASK_INTERRUPTIBLE);
+			schedule();
+			finish_wait(&eli->li_wait_daemon, &wait);
+		}
+	}
+
+exit_thread:
+	/*
+	 * It looks like the request list is empty, but we need
+	 * to check it under the li_list_mtx lock, to prevent any
+	 * additions into it, and of course we should lock ext4_li_mtx
+	 * to atomically free the list and ext4_li_info, because at
+	 * this point another ext4 filesystem could be registering
+	 * new one.
+	 */
+	mutex_lock(&ext4_li_mtx);
+	mutex_lock(&eli->li_list_mtx);
+	if (!list_empty(&eli->li_request_list)) {
+		mutex_unlock(&eli->li_list_mtx);
+		mutex_unlock(&ext4_li_mtx);
+		goto cont_thread;
+	}
+	mutex_unlock(&eli->li_list_mtx);
+	del_timer_sync(&ext4_li_info->li_timer);
+	eli->li_task = NULL;
+	wake_up(&eli->li_wait_task);
+
+	kfree(ext4_li_info);
+	ext4_li_info = NULL;
+	mutex_unlock(&ext4_li_mtx);
+
+	printk(KERN_CRIT "Thread exiting\n");
+	return 0;
+}
+
+static void ext4_clear_request_list(void)
+{
+	struct list_head *pos, *n;
+	struct ext4_li_request *elr;
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	if (list_empty(&ext4_li_info->li_request_list))
+		return;
+
+	list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
+		elr = list_entry(pos, struct ext4_li_request,
+				 lr_request);
+		ext4_remove_li_request(elr);
+	}
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+static int ext4_run_lazyinit_thread(void)
+{
+	struct task_struct *t;
+
+	t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
+	if (IS_ERR(t)) {
+		int err = PTR_ERR(t);
+		ext4_clear_request_list();
+		del_timer_sync(&ext4_li_info->li_timer);
+		kfree(ext4_li_info);
+		ext4_li_info = NULL;
+		printk(KERN_CRIT "EXT4: error %d creating inode table "
+				 "initialization thread\n",
+				 err);
+		return err;
+	}
+	ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
+
+	wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
+	return 0;
+}
+
+/*
+ * Check whether it make sense to run itable init. thread or not.
+ * If there is at least one uninitialized inode table, return
+ * corresponding group number, else the loop goes through all
+ * groups and return total number of groups.
+ */
+static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
+{
+	ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
+	struct ext4_group_desc *gdp = NULL;
+
+	for (group = 0; group < ngroups; group++) {
+		gdp = ext4_get_group_desc(sb, group, NULL);
+		if (!gdp)
+			continue;
+
+		if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			break;
+	}
+
+	return group;
+}
+
+static int ext4_li_info_new(void)
+{
+	struct ext4_lazy_init *eli = NULL;
+
+	eli = kzalloc(sizeof(*eli), GFP_KERNEL);
+	if (!eli)
+		return -ENOMEM;
+
+	eli->li_task = NULL;
+	INIT_LIST_HEAD(&eli->li_request_list);
+	mutex_init(&eli->li_list_mtx);
+
+	init_waitqueue_head(&eli->li_wait_daemon);
+	init_waitqueue_head(&eli->li_wait_task);
+	init_timer(&eli->li_timer);
+	eli->li_state |= EXT4_LAZYINIT_QUIT;
+
+	ext4_li_info = eli;
+
+	return 0;
+}
+
+static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
+					    ext4_group_t start)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_li_request *elr;
+	unsigned long rnd;
+
+	elr = kzalloc(sizeof(*elr), GFP_KERNEL);
+	if (!elr)
+		return NULL;
+
+	elr->lr_super = sb;
+	elr->lr_sbi = sbi;
+	elr->lr_next_group = start;
+
+	/*
+	 * Randomize first schedule time of the request to
+	 * spread the inode table initialization requests
+	 * better.
+	 */
+	get_random_bytes(&rnd, sizeof(rnd));
+	elr->lr_next_sched = jiffies + (unsigned long)rnd %
+			     (EXT4_DEF_LI_MAX_START_DELAY * HZ);
+
+	return elr;
+}
+
+static int ext4_register_li_request(struct super_block *sb,
+				    ext4_group_t first_not_zeroed)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_li_request *elr;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	int ret = 0;
+
+	if (sbi->s_li_request != NULL)
+		goto out;
+
+	if (first_not_zeroed == ngroups ||
+	    (sb->s_flags & MS_RDONLY) ||
+	    !test_opt(sb, INIT_INODE_TABLE)) {
+		sbi->s_li_request = NULL;
+		goto out;
+	}
+
+	if (first_not_zeroed == ngroups) {
+		sbi->s_li_request = NULL;
+		goto out;
+	}
+	
+	elr = ext4_li_request_new(sb, first_not_zeroed);
+	if (!elr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	mutex_lock(&ext4_li_mtx);
+
+	if (NULL == ext4_li_info) {
+		ret = ext4_li_info_new();
+		if (ret)
+			goto out;
+	}
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	list_add(&elr->lr_request, &ext4_li_info->li_request_list);
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+
+	sbi->s_li_request = elr;
+
+	if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
+		ret = ext4_run_lazyinit_thread();
+		if (ret)
+			goto out;
+	}
+
+	mutex_unlock(&ext4_li_mtx);
+
+out:
+	if (ret) {
+		mutex_unlock(&ext4_li_mtx);
+		kfree(elr);
+	}
+	return ret;
+}
+
+/*
+ * We do not need to lock anything since this is called on
+ * module unload.
+ */
+static void ext4_destroy_lazyinit_thread(void)
+{
+	/*
+	 * If thread exited earlier
+	 * there's nothing to be done.
+	 */
+	if (!ext4_li_info)
+		return;
+	
+	ext4_clear_request_list();
+
+	while (ext4_li_info->li_task) {
+		wake_up(&ext4_li_info->li_wait_daemon);
+		wait_event(ext4_li_info->li_wait_task,
+			   ext4_li_info->li_task == NULL);
+	}
+}
+
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				__releases(kernel_lock)
 				__acquires(kernel_lock)
@@ -2478,6 +2868,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	__u64 blocks_count;
 	int err;
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+	ext4_group_t first_not_zeroed;
 
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
@@ -2805,7 +3196,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
-	if (!ext4_check_descriptors(sb)) {
+	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
 		goto failed_mount2;
 	}
@@ -3037,6 +3428,10 @@ no_journal:
 		goto failed_mount4;
 	}
 
+	err = ext4_register_li_request(sb, first_not_zeroed);
+	if (err)
+		goto failed_mount4;
+
 	sbi->s_kobj.kset = ext4_kset;
 	init_completion(&sbi->s_kobj_unregister);
 	err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
@@ -3733,6 +4128,19 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			enable_quota = 1;
 		}
 	}
+
+	/*
+	 * Reinitialize lazy itable initialization thread based on
+	 * current settings
+	 */
+	if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
+		ext4_unregister_li_request(sb);
+	else {
+		ext4_group_t first_not_zeroed;
+		first_not_zeroed = ext4_has_uninit_itable(sb);
+		ext4_register_li_request(sb, first_not_zeroed);
+	}
+
 	ext4_setup_system_zone(sb);
 	if (sbi->s_journal == NULL)
 		ext4_commit_super(sb, 1);
@@ -4200,6 +4608,9 @@ static int __init init_ext4_fs(void)
 	err = register_filesystem(&ext4_fs_type);
 	if (err)
 		goto out;
+
+	ext4_li_info = NULL;
+	mutex_init(&ext4_li_mtx);
 	return 0;
 out:
 	unregister_as_ext2();
@@ -4219,6 +4630,7 @@ out4:
 
 static void __exit exit_ext4_fs(void)
 {
+	ext4_destroy_lazyinit_thread();
 	unregister_as_ext2();
 	unregister_as_ext3();
 	unregister_filesystem(&ext4_fs_type);
-- 
1.7.2.2

Re: [PATCH 3/6] Add inode table initialization code for Ext4

[Lukas Czerner]

When lazy_itable_init extended option is passed to mke2fs, it
considerably speed up filesystem creation because inode tables are
not zeroed out, thus contains some old data. When this fs is mounted
filesystem code should initialize (zero out) inode tables.
So far this code was missing for ext4 and this patch adds this feature.

For purpose of zeroing inode tables it introduces 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
(inititable=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.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/ext4.h   |   38 +++++
 fs/ext4/ialloc.c |  116 +++++++++++++++
 fs/ext4/super.c  |  415 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 566 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index dbd6760..0df3977 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1144,6 +1144,11 @@ struct ext4_sb_info {
 
 	/* workqueue for dio unwritten */
 	struct workqueue_struct *dio_unwritten_wq;
+
+	/* 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)
@@ -1467,6 +1472,37 @@ 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;
+};
+
+/*
  * Function prototypes
  */
 
@@ -1539,6 +1575,8 @@ 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);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 25c4b31..08d2df3 100644
--- a/fs/ext4/ialloc.c
+++ b/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 +1219,105 @@ 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)
+{
+	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;
+
+	/* 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);
+	ret = sb_issue_zeroout(sb, blk, num);
+	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;
+}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3dbae36..0fe6f97 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -41,6 +41,9 @@
 #include <linux/crc16.h>
 #include <asm/uaccess.h>
 
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -52,6 +55,8 @@
 
 struct proc_dir_entry *ext4_proc_root;
 static struct kset *ext4_kset;
+struct ext4_lazy_init *ext4_li_info;
+struct mutex ext4_li_mtx;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
@@ -70,6 +75,8 @@ static void ext4_write_super(struct super_block *sb);
 static int ext4_freeze(struct super_block *sb);
 static int ext4_get_sb(struct file_system_type *fs_type, int flags,
 		       const char *dev_name, void *data, struct vfsmount *mnt);
+static void ext4_destroy_lazyinit_thread(void);
+static void ext4_unregister_li_request(struct super_block *sb);
 
 #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
 static struct file_system_type ext3_fs_type = {
@@ -664,6 +671,7 @@ static void ext4_put_super(struct super_block *sb)
 				   "Couldn't clean up the journal");
 	}
 
+	ext4_unregister_li_request(sb);
 	ext4_release_system_zone(sb);
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
@@ -1904,7 +1912,8 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
 }
 
 /* Called at mount-time, super-block is locked */
-static int ext4_check_descriptors(struct super_block *sb)
+static int ext4_check_descriptors(struct super_block *sb,
+				  ext4_group_t *first_not_zeroed)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
@@ -1913,7 +1922,7 @@ static int ext4_check_descriptors(struct super_block *sb)
 	ext4_fsblk_t inode_bitmap;
 	ext4_fsblk_t inode_table;
 	int flexbg_flag = 0;
-	ext4_group_t i;
+	ext4_group_t i, grp = sbi->s_groups_count;
 
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
 		flexbg_flag = 1;
@@ -1929,6 +1938,10 @@ static int ext4_check_descriptors(struct super_block *sb)
 			last_block = first_block +
 				(EXT4_BLOCKS_PER_GROUP(sb) - 1);
 
+		if ((grp == sbi->s_groups_count) &&
+		   !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			grp = i;
+
 		block_bitmap = ext4_block_bitmap(sb, gdp);
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -1966,6 +1979,8 @@ static int ext4_check_descriptors(struct super_block *sb)
 		if (!flexbg_flag)
 			first_block += EXT4_BLOCKS_PER_GROUP(sb);
 	}
+	if (NULL != first_not_zeroed)
+		*first_not_zeroed = grp;
 
 	ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
 	sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
@@ -2453,6 +2468,378 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 	return 1;
 }
 
+static void ext4_lazyinode_timeout(unsigned long data)
+{
+	struct task_struct *p = (struct task_struct *)data;
+	wake_up_process(p);
+}
+
+/* Find next suitable group adn run ext4_init_inode_table */
+static int ext4_run_li_request(struct ext4_li_request *elr)
+{
+	struct ext4_group_desc *gdp = NULL;
+	ext4_group_t group, ngroups;
+	struct super_block *sb;
+	int ret = 0;
+
+	sb = elr->lr_super;
+	ngroups = EXT4_SB(sb)->s_groups_count;
+
+	for (group = elr->lr_next_group; group < ngroups; group++) {
+		gdp = ext4_get_group_desc(sb, group, NULL);
+		if (!gdp) {
+			ret = 1;
+			break;
+		}
+
+		if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			break;
+	}
+
+	if (group == ngroups)
+		ret = 1;
+
+	if (!ret) {
+		ret = ext4_init_inode_table(sb, group);
+		elr->lr_next_group = group + 1;
+	}
+
+	return ret;
+}
+
+/*
+ * Remove lr_request from the list_request and free the
+ * request tructure. Should be called with li_list_mtx held
+ */
+static void ext4_remove_li_request(struct ext4_li_request *elr)
+{
+	struct ext4_sb_info *sbi;
+
+	if (!elr)
+		return;
+
+	sbi = elr->lr_sbi;
+
+	list_del(&elr->lr_request);
+	sbi->s_li_request = NULL;
+	kfree(elr);
+}
+
+static void ext4_unregister_li_request(struct super_block *sb)
+{
+	struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
+
+	if (!ext4_li_info)
+		return;
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	ext4_remove_li_request(elr);
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+/*
+ * This is the function where ext4lazyinit thread lives. It walks
+ * through the request list searching for next scheduled filesystem.
+ * When such a fs is found, run the lazy initialization request
+ * (ext4_rn_li_request) and keep track of the time spend in this
+ * function. Based on that time we compute next schedule time of
+ * the request. When walking through the list is complete, compute
+ * next waking time and put itself into sleep.
+ */
+static int ext4_lazyinit_thread(void *arg)
+{
+	struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
+	struct list_head *pos, *n;
+	struct ext4_li_request *elr;
+	struct ext4_sb_info *sbi;
+	unsigned long next_wakeup;
+	unsigned long timeout = 0;
+	int ret;
+
+	BUG_ON(NULL == eli);
+
+	eli->li_timer.data = (unsigned long)current;
+	eli->li_timer.function = ext4_lazyinode_timeout;
+
+	eli->li_task = current;
+	wake_up(&eli->li_wait_task);
+
+cont_thread:
+	while (true) {
+		next_wakeup = ULONG_MAX;
+
+		mutex_lock(&eli->li_list_mtx);
+		if (list_empty(&eli->li_request_list)) {
+			mutex_unlock(&eli->li_list_mtx);
+			goto exit_thread;
+		}
+
+		list_for_each_safe(pos, n, &eli->li_request_list) {
+			elr = list_entry(pos, struct ext4_li_request,
+					 lr_request);
+
+			if (time_before_eq(jiffies, elr->lr_next_sched))
+				continue;
+			sbi = elr->lr_sbi;
+
+			timeout = jiffies;
+			ret = ext4_run_li_request(elr);
+			timeout = (jiffies - timeout) * sbi->s_li_wait_mult;
+
+			if (ret) {
+				ext4_remove_li_request(elr);
+				continue;
+			}
+
+			elr->lr_next_sched = jiffies + timeout;
+			if (elr->lr_next_sched < next_wakeup)
+				next_wakeup = elr->lr_next_sched;
+		}
+		mutex_unlock(&eli->li_list_mtx);
+
+		/*
+		 * We need to check this otherwise we may end up sleeping
+		 * for very long time.
+		 */
+		if (jiffies >= next_wakeup) {
+			cond_resched();
+			continue;
+		}
+
+		eli->li_timer.expires = next_wakeup;
+		add_timer(&eli->li_timer);
+
+		if (freezing(current)) {
+			refrigerator();
+		} else {
+			DEFINE_WAIT(wait);
+			prepare_to_wait(&eli->li_wait_daemon, &wait,
+					TASK_INTERRUPTIBLE);
+			schedule();
+			finish_wait(&eli->li_wait_daemon, &wait);
+		}
+	}
+
+exit_thread:
+	/*
+	 * It looks like the request list is empty, but we need
+	 * to check it under the li_list_mtx lock, to prevent any
+	 * additions into it, and of course we should lock ext4_li_mtx
+	 * to atomically free the list and ext4_li_info, because at
+	 * this point another ext4 filesystem could be registering
+	 * new one.
+	 */
+	mutex_lock(&ext4_li_mtx);
+	mutex_lock(&eli->li_list_mtx);
+	if (!list_empty(&eli->li_request_list)) {
+		mutex_unlock(&eli->li_list_mtx);
+		mutex_unlock(&ext4_li_mtx);
+		goto cont_thread;
+	}
+	mutex_unlock(&eli->li_list_mtx);
+	del_timer_sync(&ext4_li_info->li_timer);
+	eli->li_task = NULL;
+	wake_up(&eli->li_wait_task);
+
+	kfree(ext4_li_info);
+	ext4_li_info = NULL;
+	mutex_unlock(&ext4_li_mtx);
+
+	return 0;
+}
+
+static void ext4_clear_request_list(void)
+{
+	struct list_head *pos, *n;
+	struct ext4_li_request *elr;
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	if (list_empty(&ext4_li_info->li_request_list))
+		return;
+
+	list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
+		elr = list_entry(pos, struct ext4_li_request,
+				 lr_request);
+		ext4_remove_li_request(elr);
+	}
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+static int ext4_run_lazyinit_thread(void)
+{
+	struct task_struct *t;
+
+	t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
+	if (IS_ERR(t)) {
+		int err = PTR_ERR(t);
+		ext4_clear_request_list();
+		del_timer_sync(&ext4_li_info->li_timer);
+		kfree(ext4_li_info);
+		ext4_li_info = NULL;
+		printk(KERN_CRIT "EXT4: error %d creating inode table "
+				 "initialization thread\n",
+				 err);
+		return err;
+	}
+	ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
+
+	wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
+	return 0;
+}
+
+/*
+ * Check whether it make sense to run itable init. thread or not.
+ * If there is at least one uninitialized inode table, return
+ * corresponding group number, else the loop goes through all
+ * groups and return total number of groups.
+ */
+static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
+{
+	ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
+	struct ext4_group_desc *gdp = NULL;
+
+	for (group = 0; group < ngroups; group++) {
+		gdp = ext4_get_group_desc(sb, group, NULL);
+		if (!gdp)
+			continue;
+
+		if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+			break;
+	}
+
+	return group;
+}
+
+static int ext4_li_info_new(void)
+{
+	struct ext4_lazy_init *eli = NULL;
+
+	eli = kzalloc(sizeof(*eli), GFP_KERNEL);
+	if (!eli)
+		return -ENOMEM;
+
+	eli->li_task = NULL;
+	INIT_LIST_HEAD(&eli->li_request_list);
+	mutex_init(&eli->li_list_mtx);
+
+	init_waitqueue_head(&eli->li_wait_daemon);
+	init_waitqueue_head(&eli->li_wait_task);
+	init_timer(&eli->li_timer);
+	eli->li_state |= EXT4_LAZYINIT_QUIT;
+
+	ext4_li_info = eli;
+
+	return 0;
+}
+
+static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
+					    ext4_group_t start)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_li_request *elr;
+	unsigned long rnd;
+
+	elr = kzalloc(sizeof(*elr), GFP_KERNEL);
+	if (!elr)
+		return NULL;
+
+	elr->lr_super = sb;
+	elr->lr_sbi = sbi;
+	elr->lr_next_group = start;
+
+	/*
+	 * Randomize first schedule time of the request to
+	 * spread the inode table initialization requests
+	 * better.
+	 */
+	get_random_bytes(&rnd, sizeof(rnd));
+	elr->lr_next_sched = jiffies + (unsigned long)rnd %
+			     (EXT4_DEF_LI_MAX_START_DELAY * HZ);
+
+	return elr;
+}
+
+static int ext4_register_li_request(struct super_block *sb,
+				    ext4_group_t first_not_zeroed)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_li_request *elr;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	int ret = 0;
+
+	if (sbi->s_li_request != NULL)
+		goto out;
+
+	if (first_not_zeroed == ngroups ||
+	    (sb->s_flags & MS_RDONLY) ||
+	    !test_opt(sb, INIT_INODE_TABLE)) {
+		sbi->s_li_request = NULL;
+		goto out;
+	}
+
+	if (first_not_zeroed == ngroups) {
+		sbi->s_li_request = NULL;
+		goto out;
+	}
+
+	elr = ext4_li_request_new(sb, first_not_zeroed);
+	if (!elr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	mutex_lock(&ext4_li_mtx);
+
+	if (NULL == ext4_li_info) {
+		ret = ext4_li_info_new();
+		if (ret)
+			goto out;
+	}
+
+	mutex_lock(&ext4_li_info->li_list_mtx);
+	list_add(&elr->lr_request, &ext4_li_info->li_request_list);
+	mutex_unlock(&ext4_li_info->li_list_mtx);
+
+	sbi->s_li_request = elr;
+
+	if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
+		ret = ext4_run_lazyinit_thread();
+		if (ret)
+			goto out;
+	}
+
+	mutex_unlock(&ext4_li_mtx);
+
+out:
+	if (ret) {
+		mutex_unlock(&ext4_li_mtx);
+		kfree(elr);
+	}
+	return ret;
+}
+
+/*
+ * We do not need to lock anything since this is called on
+ * module unload.
+ */
+static void ext4_destroy_lazyinit_thread(void)
+{
+	/*
+	 * If thread exited earlier
+	 * there's nothing to be done.
+	 */
+	if (!ext4_li_info)
+		return;
+
+	ext4_clear_request_list();
+
+	while (ext4_li_info->li_task) {
+		wake_up(&ext4_li_info->li_wait_daemon);
+		wait_event(ext4_li_info->li_wait_task,
+			   ext4_li_info->li_task == NULL);
+	}
+}
+
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				__releases(kernel_lock)
 				__acquires(kernel_lock)
@@ -2478,6 +2865,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	__u64 blocks_count;
 	int err;
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+	ext4_group_t first_not_zeroed;
 
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
@@ -2805,7 +3193,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
-	if (!ext4_check_descriptors(sb)) {
+	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
 		goto failed_mount2;
 	}
@@ -3037,6 +3425,10 @@ no_journal:
 		goto failed_mount4;
 	}
 
+	err = ext4_register_li_request(sb, first_not_zeroed);
+	if (err)
+		goto failed_mount4;
+
 	sbi->s_kobj.kset = ext4_kset;
 	init_completion(&sbi->s_kobj_unregister);
 	err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
@@ -3733,6 +4125,19 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			enable_quota = 1;
 		}
 	}
+
+	/*
+	 * Reinitialize lazy itable initialization thread based on
+	 * current settings
+	 */
+	if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
+		ext4_unregister_li_request(sb);
+	else {
+		ext4_group_t first_not_zeroed;
+		first_not_zeroed = ext4_has_uninit_itable(sb);
+		ext4_register_li_request(sb, first_not_zeroed);
+	}
+
 	ext4_setup_system_zone(sb);
 	if (sbi->s_journal == NULL)
 		ext4_commit_super(sb, 1);
@@ -4200,6 +4605,9 @@ static int __init init_ext4_fs(void)
 	err = register_filesystem(&ext4_fs_type);
 	if (err)
 		goto out;
+
+	ext4_li_info = NULL;
+	mutex_init(&ext4_li_mtx);
 	return 0;
 out:
 	unregister_as_ext2();
@@ -4219,6 +4627,7 @@ out4:
 
 static void __exit exit_ext4_fs(void)
 {
+	ext4_destroy_lazyinit_thread();
 	unregister_as_ext2();
 	unregister_as_ext3();
 	unregister_filesystem(&ext4_fs_type);
-- 
1.7.2.2

[PATCH 4/6] Use sb_issue_zeroout in setup_new_group_blocks

[Lukas Czerner]

Use sn_issue_discard to zero out inode table and descriptor table
blocks instead of old approach which involves journaling.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/resize.c |   44 +++++++++++---------------------------------
 1 files changed, 11 insertions(+), 33 deletions(-)

diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 6df797e..60161bc 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -226,23 +226,12 @@ static int setup_new_group_blocks(struct super_block *sb,
 	}
 
 	/* Zero out all of the reserved backup group descriptor table blocks */
-	for (i = 0, bit = gdblocks + 1, block = start + bit;
-	     i < reserved_gdb; i++, block++, bit++) {
-		struct buffer_head *gdb;
-
-		ext4_debug("clear reserved block %#04llx (+%d)\n", block, bit);
-
-		if ((err = extend_or_restart_transaction(handle, 1, bh)))
-			goto exit_bh;
+	ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+			block, sbi->s_itb_per_group);
+	err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb);
+	if (err)
+		goto exit_journal;
 
-		if (IS_ERR(gdb = bclean(handle, sb, block))) {
-			err = PTR_ERR(gdb);
-			goto exit_bh;
-		}
-		ext4_handle_dirty_metadata(handle, NULL, gdb);
-		ext4_set_bit(bit, bh->b_data);
-		brelse(gdb);
-	}
 	ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
 		   input->block_bitmap - start);
 	ext4_set_bit(input->block_bitmap - start, bh->b_data);
@@ -251,23 +240,12 @@ static int setup_new_group_blocks(struct super_block *sb,
 	ext4_set_bit(input->inode_bitmap - start, bh->b_data);
 
 	/* Zero out all of the inode table blocks */
-	for (i = 0, block = input->inode_table, bit = block - start;
-	     i < sbi->s_itb_per_group; i++, bit++, block++) {
-		struct buffer_head *it;
-
-		ext4_debug("clear inode block %#04llx (+%d)\n", block, bit);
-
-		if ((err = extend_or_restart_transaction(handle, 1, bh)))
-			goto exit_bh;

[PATCH 5/6] Use sb_issue_discard in ext4_ext_zeroout

[Lukas Czerner]

Change ext4_ext4_zeroout to use sb_issue_discard instead of its
own approach to zero out extents.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/extents.c |   68 ++++------------------------------------------------
 1 files changed, 6 insertions(+), 62 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 377309c..c426d9e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2536,77 +2536,21 @@ void ext4_ext_release(struct super_block *sb)
 #endif
 }
 
-static void bi_complete(struct bio *bio, int error)
-{
-	complete((struct completion *)bio->bi_private);
-}
-
 /* FIXME!! we need to try to merge to left or right after zero-out  */
 static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 {
+	ext4_fsblk_t ee_pblock;
+	unsigned int ee_len;
 	int ret;
-	struct bio *bio;
-	int blkbits, blocksize;
-	sector_t ee_pblock;
-	struct completion event;
-	unsigned int ee_len, len, done, offset;
 
-
-	blkbits   = inode->i_blkbits;
-	blocksize = inode->i_sb->s_blocksize;
 	ee_len    = ext4_ext_get_actual_len(ex);
 	ee_pblock = ext_pblock(ex);
 
-	/* convert ee_pblock to 512 byte sectors */
-	ee_pblock = ee_pblock << (blkbits - 9);
-
-	while (ee_len > 0) {
-
-		if (ee_len > BIO_MAX_PAGES)
-			len = BIO_MAX_PAGES;
-		else
-			len = ee_len;
-
-		bio = bio_alloc(GFP_NOIO, len);
-		if (!bio)
-			return -ENOMEM;
-
-		bio->bi_sector = ee_pblock;
-		bio->bi_bdev   = inode->i_sb->s_bdev;
-
-		done = 0;
-		offset = 0;
-		while (done < len) {
-			ret = bio_add_page(bio, ZERO_PAGE(0),
-							blocksize, offset);
-			if (ret != blocksize) {
-				/*
-				 * We can't add any more pages because of
-				 * hardware limitations.  Start a new bio.
-				 */
-				break;
-			}
-			done++;
-			offset += blocksize;
-			if (offset >= PAGE_CACHE_SIZE)
-				offset = 0;
-		}
-
-		init_completion(&event);
-		bio->bi_private = &event;
-		bio->bi_end_io = bi_complete;
-		submit_bio(WRITE, bio);
-		wait_for_completion(&event);
+	ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len);
+	if (ret > 0)
+		ret = 0;
 
-		if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
-			bio_put(bio);
-			return -EIO;
-		}
-		bio_put(bio);
-		ee_len    -= done;
-		ee_pblock += done  << (blkbits - 9);
-	}
-	return 0;
+	return ret;
 }
 
 #define EXT4_EXT_ZERO_LEN 7
-- 
1.7.2.2

Re: [PATCH 5/6] Use sb_issue_discard in ext4_ext_zeroout

[Mike Snitzer]

On Wed, Sep 15, 2010 at 12:36 PM, Lukas Czerner <lczerner@redhat.com> wrote:
> Change ext4_ext4_zeroout to use sb_issue_discard instead of its
> own approach to zero out extents.

s/sb_issue_discard/sb_issue_zeroout/ in both the Subject and patch
header (above).

Patch 4/6 header also has a typo: s/sn_issue_discard/sb_issue_zeroout/

[PATCH 6/6] Add interface to advertise ext4 features in sysfs

[Lukas Czerner]

User-space should have the opportunity to check what features doest ext4
support in each particular copy. This adds easy interface by creating new
"features" directory in sys/fs/ext4/. In that directory files
advertising feature names can be created.

Add lazy_itable_init to the feature list.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/ext4.h  |    5 +++++
 fs/ext4/super.c |   50 +++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 54 insertions(+), 1 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0df3977..9ecac2e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1502,6 +1502,11 @@ struct ext4_li_request {
 	unsigned long		lr_next_sched;
 };
 
+struct ext4_features {
+	struct kobject f_kobj;
+	struct completion f_kobj_unregister;
+};
+
 /*
  * Function prototypes
  */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3e285eb..b817eba 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -57,6 +57,7 @@ struct proc_dir_entry *ext4_proc_root;
 static struct kset *ext4_kset;
 struct ext4_lazy_init *ext4_li_info;
 struct mutex ext4_li_mtx;
+struct ext4_features *ext4_feat;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
@@ -2349,6 +2350,7 @@ static struct ext4_attr ext4_attr_##_name = {			\
 #define EXT4_ATTR(name, mode, show, store) \
 static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
 
+#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
 #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
 #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
 #define EXT4_RW_ATTR_SBI_UI(name, elname)	\
@@ -2385,6 +2387,14 @@ static struct attribute *ext4_attrs[] = {
 	NULL,
 };
 
+/* Features this copy of ext4 supports */
+EXT4_INFO_ATTR(lazy_itable_init);
+
+static struct attribute *ext4_feat_attrs[] = {
+	ATTR_LIST(lazy_itable_init),
+	NULL,
+};
+
 static ssize_t ext4_attr_show(struct kobject *kobj,
 			      struct attribute *attr, char *buf)
 {
@@ -2413,7 +2423,6 @@ static void ext4_sb_release(struct kobject *kobj)
 	complete(&sbi->s_kobj_unregister);
 }
 
-
 static const struct sysfs_ops ext4_attr_ops = {
 	.show	= ext4_attr_show,
 	.store	= ext4_attr_store,
@@ -2425,6 +2434,17 @@ static struct kobj_type ext4_ktype = {
 	.release	= ext4_sb_release,
 };
 
+static void ext4_feat_release(struct kobject *kobj)
+{
+	complete(&ext4_feat->f_kobj_unregister);
+}
+
+static struct kobj_type ext4_feat_ktype = {
+	.default_attrs	= ext4_feat_attrs,
+	.sysfs_ops	= &ext4_attr_ops,
+	.release	= ext4_feat_release,
+};
+
 /*
  * Check whether this filesystem can be mounted based on
  * the features present and the RDONLY/RDWR mount requested.
@@ -4581,6 +4601,30 @@ static struct file_system_type ext4_fs_type = {
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 
+int __init ext4_init_feat_adverts(void)
+{
+	struct ext4_features *ef;
+	int ret = -ENOMEM;
+
+	ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
+	if (!ef)
+		goto out;
+
+	ef->f_kobj.kset = ext4_kset;
+	init_completion(&ef->f_kobj_unregister);
+	ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
+				   "features");
+	if (ret) {
+		kfree(ef);
+		goto out;
+	}
+
+	ext4_feat = ef;
+	ret = 0;
+out:
+	return ret;
+}
+
 static int __init init_ext4_fs(void)
 {
 	int err;
@@ -4593,6 +4637,9 @@ static int __init init_ext4_fs(void)
 	if (!ext4_kset)
 		goto out4;
 	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+
+	err = ext4_init_feat_adverts();
+
 	err = init_ext4_mballoc();
 	if (err)
 		goto out3;
@@ -4621,6 +4668,7 @@ out1:
 out2:
 	exit_ext4_mballoc();
 out3:
+	kfree(ext4_feat);
 	remove_proc_entry("fs/ext4", NULL);
 	kset_unregister(ext4_kset);
 out4:
-- 
1.7.2.2

Re: [PATCH 6/6] Add interface to advertise ext4 features in sysfs

[Eric Sandeen]

On 09/15/2010 11:36 AM, Lukas Czerner wrote:
> User-space should have the opportunity to check what features doest ext4
> support in each particular copy. This adds easy interface by creating new
> "features" directory in sys/fs/ext4/. In that directory files
> advertising feature names can be created.
> 
> Add lazy_itable_init to the feature list.

This seems to break unloading/reloading in .37; near as I can
tell /sys/fs/ext4 never gets unregistered on module unload.

-Eric

> Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> ---
>  fs/ext4/ext4.h  |    5 +++++
>  fs/ext4/super.c |   50 +++++++++++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 54 insertions(+), 1 deletions(-)
> 
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index 0df3977..9ecac2e 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -1502,6 +1502,11 @@ struct ext4_li_request {
>  	unsigned long		lr_next_sched;
>  };
>  
> +struct ext4_features {
> +	struct kobject f_kobj;
> +	struct completion f_kobj_unregister;
> +};
> +
>  /*
>   * Function prototypes
>   */
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 3e285eb..b817eba 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -57,6 +57,7 @@ struct proc_dir_entry *ext4_proc_root;
>  static struct kset *ext4_kset;
>  struct ext4_lazy_init *ext4_li_info;
>  struct mutex ext4_li_mtx;
> +struct ext4_features *ext4_feat;
>  
>  static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
>  			     unsigned long journal_devnum);
> @@ -2349,6 +2350,7 @@ static struct ext4_attr ext4_attr_##_name = {			\
>  #define EXT4_ATTR(name, mode, show, store) \
>  static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
>  
> +#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
>  #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
>  #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
>  #define EXT4_RW_ATTR_SBI_UI(name, elname)	\
> @@ -2385,6 +2387,14 @@ static struct attribute *ext4_attrs[] = {
>  	NULL,
>  };
>  
> +/* Features this copy of ext4 supports */
> +EXT4_INFO_ATTR(lazy_itable_init);
> +
> +static struct attribute *ext4_feat_attrs[] = {
> +	ATTR_LIST(lazy_itable_init),
> +	NULL,
> +};
> +
>  static ssize_t ext4_attr_show(struct kobject *kobj,
>  			      struct attribute *attr, char *buf)
>  {
> @@ -2413,7 +2423,6 @@ static void ext4_sb_release(struct kobject *kobj)
>  	complete(&sbi->s_kobj_unregister);
>  }
>  
> -
>  static const struct sysfs_ops ext4_attr_ops = {
>  	.show	= ext4_attr_show,
>  	.store	= ext4_attr_store,
> @@ -2425,6 +2434,17 @@ static struct kobj_type ext4_ktype = {
>  	.release	= ext4_sb_release,
>  };
>  
> +static void ext4_feat_release(struct kobject *kobj)
> +{
> +	complete(&ext4_feat->f_kobj_unregister);
> +}
> +
> +static struct kobj_type ext4_feat_ktype = {
> +	.default_attrs	= ext4_feat_attrs,
> +	.sysfs_ops	= &ext4_attr_ops,
> +	.release	= ext4_feat_release,
> +};
> +
>  /*
>   * Check whether this filesystem can be mounted based on
>   * the features present and the RDONLY/RDWR mount requested.
> @@ -4581,6 +4601,30 @@ static struct file_system_type ext4_fs_type = {
>  	.fs_flags	= FS_REQUIRES_DEV,
>  };
>  
> +int __init ext4_init_feat_adverts(void)
> +{
> +	struct ext4_features *ef;
> +	int ret = -ENOMEM;
> +
> +	ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
> +	if (!ef)
> +		goto out;
> +
> +	ef->f_kobj.kset = ext4_kset;
> +	init_completion(&ef->f_kobj_unregister);
> +	ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
> +				   "features");
> +	if (ret) {
> +		kfree(ef);
> +		goto out;
> +	}
> +
> +	ext4_feat = ef;
> +	ret = 0;
> +out:
> +	return ret;
> +}
> +
>  static int __init init_ext4_fs(void)
>  {
>  	int err;
> @@ -4593,6 +4637,9 @@ static int __init init_ext4_fs(void)
>  	if (!ext4_kset)
>  		goto out4;
>  	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
> +
> +	err = ext4_init_feat_adverts();
> +
>  	err = init_ext4_mballoc();
>  	if (err)
>  		goto out3;
> @@ -4621,6 +4668,7 @@ out1:
>  out2:
>  	exit_ext4_mballoc();
>  out3:
> +	kfree(ext4_feat);
>  	remove_proc_entry("fs/ext4", NULL);
>  	kset_unregister(ext4_kset);
>  out4:

Re: [PATCH 6/6] Add interface to advertise ext4 features in sysfs

[Lukas Czerner]

On Mon, 10 Jan 2011, Eric Sandeen wrote:

> On 09/15/2010 11:36 AM, Lukas Czerner wrote:
> > User-space should have the opportunity to check what features doest ext4
> > support in each particular copy. This adds easy interface by creating new
> > "features" directory in sys/fs/ext4/. In that directory files
> > advertising feature names can be created.
> > 
> > Add lazy_itable_init to the feature list.
> 
> This seems to break unloading/reloading in .37; near as I can
> tell /sys/fs/ext4 never gets unregistered on module unload.

That's not good, I'll look at it.

Thanks!
-Lukas

> 
> -Eric
> 
> > Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> > ---
> >  fs/ext4/ext4.h  |    5 +++++
> >  fs/ext4/super.c |   50 +++++++++++++++++++++++++++++++++++++++++++++++++-
> >  2 files changed, 54 insertions(+), 1 deletions(-)
> > 
> > diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> > index 0df3977..9ecac2e 100644
> > --- a/fs/ext4/ext4.h
> > +++ b/fs/ext4/ext4.h
> > @@ -1502,6 +1502,11 @@ struct ext4_li_request {
> >  	unsigned long		lr_next_sched;
> >  };
> >  
> > +struct ext4_features {
> > +	struct kobject f_kobj;
> > +	struct completion f_kobj_unregister;
> > +};
> > +
> >  /*
> >   * Function prototypes
> >   */
> > diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> > index 3e285eb..b817eba 100644
> > --- a/fs/ext4/super.c
> > +++ b/fs/ext4/super.c
> > @@ -57,6 +57,7 @@ struct proc_dir_entry *ext4_proc_root;
> >  static struct kset *ext4_kset;
> >  struct ext4_lazy_init *ext4_li_info;
> >  struct mutex ext4_li_mtx;
> > +struct ext4_features *ext4_feat;
> >  
> >  static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
> >  			     unsigned long journal_devnum);
> > @@ -2349,6 +2350,7 @@ static struct ext4_attr ext4_attr_##_name = {			\
> >  #define EXT4_ATTR(name, mode, show, store) \
> >  static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
> >  
> > +#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
> >  #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
> >  #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
> >  #define EXT4_RW_ATTR_SBI_UI(name, elname)	\
> > @@ -2385,6 +2387,14 @@ static struct attribute *ext4_attrs[] = {
> >  	NULL,
> >  };
> >  
> > +/* Features this copy of ext4 supports */
> > +EXT4_INFO_ATTR(lazy_itable_init);
> > +
> > +static struct attribute *ext4_feat_attrs[] = {
> > +	ATTR_LIST(lazy_itable_init),
> > +	NULL,
> > +};
> > +
> >  static ssize_t ext4_attr_show(struct kobject *kobj,
> >  			      struct attribute *attr, char *buf)
> >  {
> > @@ -2413,7 +2423,6 @@ static void ext4_sb_release(struct kobject *kobj)
> >  	complete(&sbi->s_kobj_unregister);
> >  }
> >  
> > -
> >  static const struct sysfs_ops ext4_attr_ops = {
> >  	.show	= ext4_attr_show,
> >  	.store	= ext4_attr_store,
> > @@ -2425,6 +2434,17 @@ static struct kobj_type ext4_ktype = {
> >  	.release	= ext4_sb_release,
> >  };
> >  
> > +static void ext4_feat_release(struct kobject *kobj)
> > +{
> > +	complete(&ext4_feat->f_kobj_unregister);
> > +}
> > +
> > +static struct kobj_type ext4_feat_ktype = {
> > +	.default_attrs	= ext4_feat_attrs,
> > +	.sysfs_ops	= &ext4_attr_ops,
> > +	.release	= ext4_feat_release,
> > +};
> > +
> >  /*
> >   * Check whether this filesystem can be mounted based on
> >   * the features present and the RDONLY/RDWR mount requested.
> > @@ -4581,6 +4601,30 @@ static struct file_system_type ext4_fs_type = {
> >  	.fs_flags	= FS_REQUIRES_DEV,
> >  };
> >  
> > +int __init ext4_init_feat_adverts(void)
> > +{
> > +	struct ext4_features *ef;
> > +	int ret = -ENOMEM;
> > +
> > +	ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
> > +	if (!ef)
> > +		goto out;
> > +
> > +	ef->f_kobj.kset = ext4_kset;
> > +	init_completion(&ef->f_kobj_unregister);
> > +	ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
> > +				   "features");
> > +	if (ret) {
> > +		kfree(ef);
> > +		goto out;
> > +	}
> > +
> > +	ext4_feat = ef;
> > +	ret = 0;
> > +out:
> > +	return ret;
> > +}
> > +
> >  static int __init init_ext4_fs(void)
> >  {
> >  	int err;
> > @@ -4593,6 +4637,9 @@ static int __init init_ext4_fs(void)
> >  	if (!ext4_kset)
> >  		goto out4;
> >  	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
> > +
> > +	err = ext4_init_feat_adverts();
> > +
> >  	err = init_ext4_mballoc();
> >  	if (err)
> >  		goto out3;
> > @@ -4621,6 +4668,7 @@ out1:
> >  out2:
> >  	exit_ext4_mballoc();
> >  out3:
> > +	kfree(ext4_feat);
> >  	remove_proc_entry("fs/ext4", NULL);
> >  	kset_unregister(ext4_kset);
> >  out4:
> 
> 

-- 

[PATCH 0/6 v4] Lazy itable initialization for Ext4

[Lukas Czerner]

Hi,

as Mike suggested I have rebased the patch #1 against Jens'
linux-2.6-block.git 'for-next' branch and changed sb_issue_zeroout()
to cope with the new blkdev_issue_zeroout(), and changed
sb_issue_zeroout() to the new syntax everywhere I am using it.
Also some typos gets fixed.

-Lukas

[PATCH 6/6] Add interface to advertise ext4 features in sysfs

[Lukas Czerner]

User-space should have the opportunity to check what features doest ext4
support in each particular copy. This adds easy interface by creating new
"features" directory in sys/fs/ext4/. In that directory files
advertising feature names can be created.

Add lazy_itable_init to the feature list.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/ext4.h  |    5 +++++
 fs/ext4/super.c |   50 +++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 54 insertions(+), 1 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 96884c5..74ec1fc 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1572,6 +1572,11 @@ struct ext4_li_request {
 	unsigned long		lr_next_sched;
 };
 
+struct ext4_features {
+	struct kobject f_kobj;
+	struct completion f_kobj_unregister;
+};
+
 /*
  * Function prototypes
  */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2b53a48..bb84c27 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -57,6 +57,7 @@ struct proc_dir_entry *ext4_proc_root;
 static struct kset *ext4_kset;
 struct ext4_lazy_init *ext4_li_info;
 struct mutex ext4_li_mtx;
+struct ext4_features *ext4_feat;
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
@@ -2413,6 +2414,7 @@ static struct ext4_attr ext4_attr_##_name = {			\
 #define EXT4_ATTR(name, mode, show, store) \
 static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
 
+#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
 #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
 #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
 #define EXT4_RW_ATTR_SBI_UI(name, elname)	\
@@ -2449,6 +2451,14 @@ static struct attribute *ext4_attrs[] = {
 	NULL,
 };
 
+/* Features this copy of ext4 supports */
+EXT4_INFO_ATTR(lazy_itable_init);
+
+static struct attribute *ext4_feat_attrs[] = {
+	ATTR_LIST(lazy_itable_init),
+	NULL,
+};
+
 static ssize_t ext4_attr_show(struct kobject *kobj,
 			      struct attribute *attr, char *buf)
 {
@@ -2477,7 +2487,6 @@ static void ext4_sb_release(struct kobject *kobj)
 	complete(&sbi->s_kobj_unregister);
 }
 
-
 static const struct sysfs_ops ext4_attr_ops = {
 	.show	= ext4_attr_show,
 	.store	= ext4_attr_store,
@@ -2489,6 +2498,17 @@ static struct kobj_type ext4_ktype = {
 	.release	= ext4_sb_release,
 };
 
+static void ext4_feat_release(struct kobject *kobj)
+{
+	complete(&ext4_feat->f_kobj_unregister);
+}
+
+static struct kobj_type ext4_feat_ktype = {
+	.default_attrs	= ext4_feat_attrs,
+	.sysfs_ops	= &ext4_attr_ops,
+	.release	= ext4_feat_release,
+};
+
 /*
  * Check whether this filesystem can be mounted based on
  * the features present and the RDONLY/RDWR mount requested.
@@ -4716,6 +4736,30 @@ static struct file_system_type ext4_fs_type = {
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 
+int __init ext4_init_feat_adverts(void)
+{
+	struct ext4_features *ef;
+	int ret = -ENOMEM;
+
+	ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
+	if (!ef)
+		goto out;
+
+	ef->f_kobj.kset = ext4_kset;
+	init_completion(&ef->f_kobj_unregister);
+	ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
+				   "features");
+	if (ret) {
+		kfree(ef);
+		goto out;
+	}
+
+	ext4_feat = ef;
+	ret = 0;
+out:
+	return ret;
+}
+
 static int __init init_ext4_fs(void)
 {
 	int err;
@@ -4728,6 +4772,9 @@ static int __init init_ext4_fs(void)
 	if (!ext4_kset)
 		goto out4;
 	ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+
+	err = ext4_init_feat_adverts();
+
 	err = init_ext4_mballoc();
 	if (err)
 		goto out3;
@@ -4756,6 +4803,7 @@ out1:
 out2:
 	exit_ext4_mballoc();
 out3:
+	kfree(ext4_feat);
 	remove_proc_entry("fs/ext4", NULL);
 	kset_unregister(ext4_kset);
 out4:
-- 
1.7.2.2