1
linux/fs/ext4/ext4_i.h
Theodore Ts'o a4912123b6 ext4: New inode/block allocation algorithms for flex_bg filesystems
The find_group_flex() inode allocator is now only used if the
filesystem is mounted using the "oldalloc" mount option.  It is
replaced with the original Orlov allocator that has been updated for
flex_bg filesystems (it should behave the same way if flex_bg is
disabled).  The inode allocator now functions by taking into account
each flex_bg group, instead of each block group, when deciding whether
or not it's time to allocate a new directory into a fresh flex_bg.

The block allocator has also been changed so that the first block
group in each flex_bg is preferred for use for storing directory
blocks.  This keeps directory blocks close together, which is good for
speeding up e2fsck since large directories are more likely to look
like this:

debugfs:  stat /home/tytso/Maildir/cur
Inode: 1844562   Type: directory    Mode:  0700   Flags: 0x81000
Generation: 1132745781    Version: 0x00000000:0000ad71
User: 15806   Group: 15806   Size: 1060864
File ACL: 0    Directory ACL: 0
Links: 2   Blockcount: 2072
Fragment:  Address: 0    Number: 0    Size: 0
 ctime: 0x499c0ff4:164961f4 -- Wed Feb 18 08:41:08 2009
 atime: 0x499c0ff4:00000000 -- Wed Feb 18 08:41:08 2009
 mtime: 0x49957f51:00000000 -- Fri Feb 13 09:10:25 2009
crtime: 0x499c0f57:00d51440 -- Wed Feb 18 08:38:31 2009
Size of extra inode fields: 28
BLOCKS:
(0):7348651, (1-258):7348654-7348911
TOTAL: 259

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2009-03-12 12:18:34 -04:00

141 lines
4.0 KiB
C

/*
* ext4_i.h
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/include/linux/minix_fs_i.h
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#ifndef _EXT4_I
#define _EXT4_I
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/seqlock.h>
#include <linux/mutex.h>
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
/* data type for filesystem-wide blocks number */
typedef unsigned long long ext4_fsblk_t;
/* data type for file logical block number */
typedef __u32 ext4_lblk_t;
/* data type for block group number */
typedef unsigned int ext4_group_t;
/*
* storage for cached extent
*/
struct ext4_ext_cache {
ext4_fsblk_t ec_start;
ext4_lblk_t ec_block;
__u32 ec_len; /* must be 32bit to return holes */
__u32 ec_type;
};
/*
* fourth extended file system inode data in memory
*/
struct ext4_inode_info {
__le32 i_data[15]; /* unconverted */
__u32 i_flags;
ext4_fsblk_t i_file_acl;
__u32 i_dtime;
/*
* i_block_group is the number of the block group which contains
* this file's inode. Constant across the lifetime of the inode,
* it is ued for making block allocation decisions - we try to
* place a file's data blocks near its inode block, and new inodes
* near to their parent directory's inode.
*/
ext4_group_t i_block_group;
__u32 i_state; /* Dynamic state flags for ext4 */
ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
/*
* Extended attributes can be read independently of the main file
* data. Taking i_mutex even when reading would cause contention
* between readers of EAs and writers of regular file data, so
* instead we synchronize on xattr_sem when reading or changing
* EAs.
*/
struct rw_semaphore xattr_sem;
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
#endif
struct list_head i_orphan; /* unlinked but open inodes */
/*
* i_disksize keeps track of what the inode size is ON DISK, not
* in memory. During truncate, i_size is set to the new size by
* the VFS prior to calling ext4_truncate(), but the filesystem won't
* set i_disksize to 0 until the truncate is actually under way.
*
* The intent is that i_disksize always represents the blocks which
* are used by this file. This allows recovery to restart truncate
* on orphans if we crash during truncate. We actually write i_disksize
* into the on-disk inode when writing inodes out, instead of i_size.
*
* The only time when i_disksize and i_size may be different is when
* a truncate is in progress. The only things which change i_disksize
* are ext4_get_block (growth) and ext4_truncate (shrinkth).
*/
loff_t i_disksize;
/*
* i_data_sem is for serialising ext4_truncate() against
* ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's
* data tree are chopped off during truncate. We can't do that in
* ext4 because whenever we perform intermediate commits during
* truncate, the inode and all the metadata blocks *must* be in a
* consistent state which allows truncation of the orphans to restart
* during recovery. Hence we must fix the get_block-vs-truncate race
* by other means, so we have i_data_sem.
*/
struct rw_semaphore i_data_sem;
struct inode vfs_inode;
struct jbd2_inode jinode;
struct ext4_ext_cache i_cached_extent;
/*
* File creation time. Its function is same as that of
* struct timespec i_{a,c,m}time in the generic inode.
*/
struct timespec i_crtime;
/* mballoc */
struct list_head i_prealloc_list;
spinlock_t i_prealloc_lock;
/* ialloc */
ext4_group_t i_last_alloc_group;
/* allocation reservation info for delalloc */
unsigned int i_reserved_data_blocks;
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
unsigned short i_delalloc_reserved_flag;
/* on-disk additional length */
__u16 i_extra_isize;
spinlock_t i_block_reservation_lock;
};
#endif /* _EXT4_I */