summaryrefslogtreecommitdiffstats
path: root/include/linux/ext4_fs.h
diff options
context:
space:
mode:
authorAndreas Dilger <adilger@clusterfs.com>2007-10-16 18:38:25 -0400
committerTheodore Ts'o <tytso@mit.edu>2007-10-17 18:50:00 -0400
commit717d50e4971b81b96c0199c91cdf0039a8cb181a (patch)
treea8d68edbc1f064c76cbfee206e093d2c86c80ba0 /include/linux/ext4_fs.h
parent4074fe3736b1a43431dff870bf9055ac5dcf3f03 (diff)
Ext4: Uninitialized Block Groups
In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Diffstat (limited to 'include/linux/ext4_fs.h')
-rw-r--r--include/linux/ext4_fs.h16
1 files changed, 12 insertions, 4 deletions
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index 151738af6be..b77b59fe7f5 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -105,19 +105,25 @@
*/
struct ext4_group_desc
{
- __le32 bg_block_bitmap; /* Blocks bitmap block */
- __le32 bg_inode_bitmap; /* Inodes bitmap block */
+ __le32 bg_block_bitmap; /* Blocks bitmap block */
+ __le32 bg_inode_bitmap; /* Inodes bitmap block */
__le32 bg_inode_table; /* Inodes table block */
__le16 bg_free_blocks_count; /* Free blocks count */
__le16 bg_free_inodes_count; /* Free inodes count */
__le16 bg_used_dirs_count; /* Directories count */
- __u16 bg_flags;
- __u32 bg_reserved[3];
+ __le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */
+ __u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */
+ __le16 bg_itable_unused; /* Unused inodes count */
+ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */
__le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
__le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */
__le32 bg_inode_table_hi; /* Inodes table block MSB */
};
+#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
+#define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */
+#define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */
+
#ifdef __KERNEL__
#include <linux/ext4_fs_i.h>
#include <linux/ext4_fs_sb.h>
@@ -665,6 +671,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004
+#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
@@ -684,6 +691,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
EXT4_FEATURE_INCOMPAT_64BIT)
#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR)