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>

1 files changed, 47 insertions, 0 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e2bdf93693a6..dd4ff9c87358 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -37,12 +37,14 @@
 #include <linux/quotaops.h>
 #include <linux/seq_file.h>
 #include <linux/log2.h>
+#include <linux/crc16.h>
 
 #include <asm/uaccess.h>
 
 #include "xattr.h"
 #include "acl.h"
 #include "namei.h"
+#include "group.h"
 
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
                              unsigned long journal_devnum);
@@ -1308,6 +1310,43 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
         return res;
 }
 
+__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
+                            struct ext4_group_desc *gdp)
+{
+        __u16 crc = 0;
+
+        if (sbi->s_es->s_feature_ro_compat &
+            cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+                int offset = offsetof(struct ext4_group_desc, bg_checksum);
+                __le32 le_group = cpu_to_le32(block_group);
+
+                crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
+                crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
+                crc = crc16(crc, (__u8 *)gdp, offset);
+                offset += sizeof(gdp->bg_checksum); /* skip checksum */
+                /* for checksum of struct ext4_group_desc do the rest...*/
+                if ((sbi->s_es->s_feature_incompat &
+                     cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) &&
+                    offset < le16_to_cpu(sbi->s_es->s_desc_size))
+                        crc = crc16(crc, (__u8 *)gdp + offset,
+                                    le16_to_cpu(sbi->s_es->s_desc_size) -
+                                        offset);
+        }
+
+        return cpu_to_le16(crc);
+}
+
+int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
+                                struct ext4_group_desc *gdp)
+{
+        if ((sbi->s_es->s_feature_ro_compat &
+             cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) &&
+            (gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp)))
+                return 0;
+
+        return 1;
+}
+
 /* Called at mount-time, super-block is locked */
 static int ext4_check_descriptors (struct super_block * sb)
 {
@@ -1362,6 +1401,14 @@ static int ext4_check_descriptors (struct super_block * sb)
                                     i, inode_table);
                         return 0;
                 }
+                if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
+                        ext4_error(sb, __FUNCTION__,
+                                   "Checksum for group %d failed (%u!=%u)\n", i,
+                                   le16_to_cpu(ext4_group_desc_csum(sbi, i,
+                                                                    gdp)),
+                                   le16_to_cpu(gdp->bg_checksum));
+                        return 0;
+                }
                 first_block += EXT4_BLOCKS_PER_GROUP(sb);
                 gdp = (struct ext4_group_desc *)
                         ((__u8 *)gdp + EXT4_DESC_SIZE(sb));