From 074ca44283bf031678e67af7d82668bb03c55a55 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 6 Feb 2009 16:23:37 -0500 Subject: ext4: Remove stale block allocator references from ext4.h Remove some leftovers from when the old block allocator was removed (c2ea3fde). ext4_sb_info is now a bit lighter. Also remove a dangling read_block_bitmap() prototype. Signed-off-by: Mike Snitzer Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6083bb38057b..0db01421da3e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -32,14 +32,6 @@ */ #undef EXT4FS_DEBUG -/* - * Define EXT4_RESERVATION to reserve data blocks for expanding files - */ -#define EXT4_DEFAULT_RESERVE_BLOCKS 8 -/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ -#define EXT4_MAX_RESERVE_BLOCKS 1027 -#define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0 - /* * Debug code */ @@ -54,8 +46,6 @@ #define ext4_debug(f, a...) do {} while (0) #endif -#define EXT4_MULTIBLOCK_ALLOCATOR 1 - /* prefer goal again. length */ #define EXT4_MB_HINT_MERGE 1 /* blocks already reserved */ -- cgit v1.2.1 From 3d0518f4758eca4339e75e5b9dbb7e06a5ce08b4 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sat, 14 Feb 2009 23:01:36 -0500 Subject: ext4: New rec_len encoding for very large blocksizes The rec_len field in the directory entry is 16 bits, so to encode blocksizes larger than 64k becomes problematic. This patch allows us to supprot block sizes up to 256k, by using the low 2 bits to extend the range of rec_len to 2**18-1 (since valid rec_len sizes must be a multiple of 4). We use the convention that a rec_len of 0 or 65535 means the filesystem block size, for compatibility with older kernels. It's unlikely we'll see VM pages of up to 256k, but at some point we might find that the Linux VM has been enhanced to support filesystem block sizes > than the VM page size, at which point it might be useful for some applications to allow very large filesystem block sizes. Signed-off-by: Wei Yongjun Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 21 +++------------------ 1 file changed, 3 insertions(+), 18 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0db01421da3e..d5193b55ca94 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -855,24 +855,6 @@ struct ext4_dir_entry_2 { ~EXT4_DIR_ROUND) #define EXT4_MAX_REC_LEN ((1<<16)-1) -static inline unsigned ext4_rec_len_from_disk(__le16 dlen) -{ - unsigned len = le16_to_cpu(dlen); - - if (len == EXT4_MAX_REC_LEN || len == 0) - return 1 << 16; - return len; -} - -static inline __le16 ext4_rec_len_to_disk(unsigned len) -{ - if (len == (1 << 16)) - return cpu_to_le16(EXT4_MAX_REC_LEN); - else if (len > (1 << 16)) - BUG(); - return cpu_to_le16(len); -} - /* * Hash Tree Directory indexing * (c) Daniel Phillips, 2001 @@ -1097,7 +1079,10 @@ extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); + /* namei.c */ +extern unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize); +extern __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize); extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, -- cgit v1.2.1 From 8fa43a81b97853fc69417bb6054182e78f95cbeb Mon Sep 17 00:00:00 2001 From: Duane Griffin Date: Sun, 15 Feb 2009 18:57:26 -0500 Subject: ext4: don't inherit inappropriate inode flags from parent At present INDEX and EXTENTS are the only flags that new ext4 inodes do NOT inherit from their parent. In addition prevent the flags DIRTY, ECOMPR, IMAGIC, TOPDIR, HUGE_FILE and EXT_MIGRATE from being inherited. List inheritable flags explicitly to prevent future flags from accidentally being inherited. This fixes the TOPDIR flag inheritance bug reported at http://bugzilla.kernel.org/show_bug.cgi?id=9866. Signed-off-by: Duane Griffin Acked-by: Andreas Dilger Cc: Signed-off-by: Andrew Morton Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d5193b55ca94..d4700d101ea7 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -239,6 +239,13 @@ struct flex_groups { #define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ #define EXT4_FL_USER_MODIFIABLE 0x000B80FF /* User modifiable flags */ +/* Flags that should be inherited by new inodes from their parent. */ +#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ + EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\ + EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ + EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ + EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL) + /* * Inode dynamic state flags */ -- cgit v1.2.1 From 2dc6b0d48ca0599837df21b14bb8393d0804af57 Mon Sep 17 00:00:00 2001 From: Duane Griffin Date: Sun, 15 Feb 2009 18:09:20 -0500 Subject: ext4: tighten restrictions on inode flags At the moment there are few restrictions on which flags may be set on which inodes. Specifically DIRSYNC may only be set on directories and IMMUTABLE and APPEND may not be set on links. Tighten that to disallow TOPDIR being set on non-directories and only NODUMP and NOATIME to be set on non-regular file, non-directories. Introduces a flags masking function which masks flags based on mode and use it during inode creation and when flags are set via the ioctl to facilitate future consistency. Signed-off-by: Duane Griffin Acked-by: Andreas Dilger Cc: Signed-off-by: Andrew Morton Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d4700d101ea7..2cbfc0b04d37 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -246,6 +246,23 @@ struct flex_groups { EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL) +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) + +/* Mask out flags that are inappropriate for the given type of inode. */ +static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & EXT4_REG_FLMASK; + else + return flags & EXT4_OTHER_FLMASK; +} + /* * Inode dynamic state flags */ -- cgit v1.2.1 From a4912123b688e057084e6557cef8924f7ae5bbde Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 12 Mar 2009 12:18:34 -0400 Subject: 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" --- fs/ext4/ext4.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2cbfc0b04d37..096456c8559b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -827,6 +827,12 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_DEF_MIN_BATCH_TIME 0 #define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */ +/* + * Minimum number of groups in a flexgroup before we separate out + * directories into the first block group of a flexgroup + */ +#define EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME 4 + /* * Structure of a directory entry */ -- cgit v1.2.1 From ccd2506bd43113659aa904d5bea5d1300605e2a6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 26 Feb 2009 01:04:07 -0500 Subject: ext4: add EXT4_IOC_ALLOC_DA_BLKS ioctl Add an ioctl which forces all of the delay allocated blocks to be allocated. This also provides a function ext4_alloc_da_blocks() which will be used by the following commits to force files to be fully allocated to preserve application-expected ext3 behaviour. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 096456c8559b..b0ea70cc94db 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -317,7 +317,9 @@ struct ext4_new_group_data { #define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) #define EXT4_IOC_GROUP_ADD _IOW('f', 8, struct ext4_new_group_input) #define EXT4_IOC_MIGRATE _IO('f', 9) + /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */ /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */ +#define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12) /* * ioctl commands in 32 bit emulation @@ -1094,6 +1096,7 @@ extern int ext4_can_truncate(struct inode *inode); extern void ext4_truncate(struct inode *); extern void ext4_set_inode_flags(struct inode *); extern void ext4_get_inode_flags(struct ext4_inode_info *); +extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks); -- cgit v1.2.1 From 7d8f9f7d150dded7b68e61ca6403a1f166fb4edf Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 24 Feb 2009 08:21:14 -0500 Subject: ext4: Automatically allocate delay allocated blocks on close When closing a file that had been previously truncated, force any delay allocated blocks that to be allocated so that if the filesystem is mounted with data=ordered, the data blocks will be pushed out to disk along with the journal commit. Many application programs expect this, so we do this to avoid zero length files if the system crashes unexpectedly. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b0ea70cc94db..1b0c17364631 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -270,6 +270,7 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) #define EXT4_STATE_NEW 0x00000002 /* inode is newly created */ #define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */ #define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */ +#define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */ /* Used to pass group descriptor data when online resize is done */ struct ext4_new_group_input { -- cgit v1.2.1 From afc32f7ee9febc020c73da61402351d4c90437f3 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 28 Feb 2009 19:39:58 -0500 Subject: ext4: Track lifetime disk writes Add a new superblock value which tracks the lifetime amount of writes to the filesystem. This is useful in estimating the amount of wear on solid state drives (SSD's) caused by writes to the filesystem. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1b0c17364631..0bd39188531c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -683,7 +683,8 @@ struct ext4_super_block { __u8 s_log_groups_per_flex; /* FLEX_BG group size */ __u8 s_reserved_char_pad2; __le16 s_reserved_pad; - __u32 s_reserved[162]; /* Padding to the end of the block */ + __le64 s_kbytes_written; /* nr of lifetime kilobytes written */ + __u32 s_reserved[160]; /* Padding to the end of the block */ }; #ifdef __KERNEL__ -- cgit v1.2.1 From b713a5ec55bf73c833f9883cdd761b20ee61a1ab Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 31 Mar 2009 09:11:14 -0400 Subject: ext4: remove /proc tuning knobs Remove tuning knobs in /proc/fs/ext4//*. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0bd39188531c..e5c273ff928b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -976,22 +976,6 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, extern struct proc_dir_entry *ext4_proc_root; -#ifdef CONFIG_PROC_FS -extern const struct file_operations ext4_ui_proc_fops; - -#define EXT4_PROC_HANDLER(name, var) \ -do { \ - proc = proc_create_data(name, mode, sbi->s_proc, \ - &ext4_ui_proc_fops, &sbi->s_##var); \ - if (proc == NULL) { \ - printk(KERN_ERR "EXT4-fs: can't create %s\n", name); \ - goto err_out; \ - } \ -} while (0) -#else -#define EXT4_PROC_HANDLER(name, var) -#endif - /* * Function prototypes */ -- cgit v1.2.1 From 9f24e4208f7ee2748f157368b63287dc903fcf60 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 4 Mar 2009 19:09:10 -0500 Subject: ext4: Use atomic_t's in struct flex_groups Reduce pressure on the sb_bgl_lock family of locks by using atomic_t's to track the number of free blocks and inodes in each flex_group. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e5c273ff928b..e52b48f86ed4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -170,8 +170,8 @@ struct ext4_group_desc */ struct flex_groups { - __u32 free_inodes; - __u32 free_blocks; + atomic_t free_inodes; + atomic_t free_blocks; }; #define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */ -- cgit v1.2.1 From 7d39db14a42cbd719c7515b9da8f85a2eb6a0633 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 4 Mar 2009 19:31:53 -0500 Subject: ext4: Use struct flex_groups to calculate get_orlov_stats() Instead of looping over all of the block groups in a flex group summing their summary statistics, start tracking used_dirs in struct flex_groups, and use struct flex_groups instead. This should save a bit of CPU for mkdir-heavy workloads. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e52b48f86ed4..46aaaa2ed4c5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -172,6 +172,7 @@ struct ext4_group_desc struct flex_groups { atomic_t free_inodes; atomic_t free_blocks; + atomic_t used_dirs; }; #define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */ -- cgit v1.2.1 From afd4672dc7610b7feef5190168aa917cc2e417e4 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 16 Mar 2009 23:12:23 -0400 Subject: ext4: Add auto_da_alloc mount option Add a mount option which allows the user to disable automatic allocation of blocks whose allocation by delayed allocation when the file was originally truncated or when the file is renamed over an existing file. This feature is intended to save users from the effects of naive application writers, but it reduces the effectiveness of the delayed allocation code. This mount option disables this safety feature, which may be desirable for prodcutions systems where the risk of unclean shutdowns or unexpected system crashes is low. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 46aaaa2ed4c5..a004699e7296 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -549,7 +549,7 @@ do { \ #define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ #define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ #define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ -#define EXT4_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */ #define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ #define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */ #define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ -- cgit v1.2.1