From 7ad72ca60b6be3c79f90a81ce5883e12a2c6e667 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: Remove unused variable from ext4_show_options Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 02bf2434397..588cfb40864 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -671,7 +671,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) unsigned long def_mount_opts; struct super_block *sb = vfs->mnt_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); - journal_t *journal = sbi->s_journal; struct ext4_super_block *es = sbi->s_es; def_mount_opts = le32_to_cpu(es->s_default_mount_opts); -- cgit v1.2.3 From 772cb7c83ba256a11c7bf99a11bef3858d23767c Mon Sep 17 00:00:00 2001 From: "Jose R. Santos" Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: New inode allocation for FLEX_BG meta-data groups. This patch mostly controls the way inode are allocated in order to make ialloc aware of flex_bg block group grouping. It achieves this by bypassing the Orlov allocator when block group meta-data are packed toghether through mke2fs. Since the impact on the block allocator is minimal, this patch should have little or no effect on other block allocation algorithms. By controlling the inode allocation, it can basically control where the initial search for new block begins and thus indirectly manipulate the block allocator. This allocator favors data and meta-data locality so the disk will gradually be filled from block group zero upward. This helps improve performance by reducing seek time. Since the group of inode tables within one flex_bg are treated as one giant inode table, uninitialized block groups would not need to partially initialize as many inode table as with Orlov which would help fsck time as the filesystem usage goes up. Signed-off-by: Jose R. Santos Signed-off-by: Valerie Clement Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 14 ++++++++ fs/ext4/ext4.h | 25 ++++++++++++++- fs/ext4/ext4_sb.h | 3 ++ fs/ext4/ialloc.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/ext4/mballoc.c | 15 +++++++++ fs/ext4/super.c | 57 +++++++++++++++++++++++++++++++++ 6 files changed, 209 insertions(+), 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index ba411233cc2..0b2b7549ac6 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -809,6 +809,13 @@ do_more: spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_add(&sbi->s_freeblocks_counter, count); + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, block_group); + spin_lock(sb_bgl_lock(sbi, flex_group)); + sbi->s_flex_groups[flex_group].free_blocks += count; + spin_unlock(sb_bgl_lock(sbi, flex_group)); + } + /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_journal_dirty_metadata(handle, bitmap_bh); @@ -1883,6 +1890,13 @@ allocated: spin_unlock(sb_bgl_lock(sbi, group_no)); percpu_counter_sub(&sbi->s_freeblocks_counter, num); + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, group_no); + spin_lock(sb_bgl_lock(sbi, flex_group)); + sbi->s_flex_groups[flex_group].free_blocks -= num; + spin_unlock(sb_bgl_lock(sbi, flex_group)); + } + BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor"); err = ext4_journal_dirty_metadata(handle, gdp_bh); if (!fatal) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 109c7d4c19a..0bfeae18f1a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -170,6 +170,15 @@ struct ext4_group_desc __u32 bg_reserved2[3]; }; +/* + * Structure of a flex block group info + */ + +struct flex_groups { + __u32 free_inodes; + __u32 free_blocks; +}; + #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 */ @@ -647,7 +656,10 @@ struct ext4_super_block { __le16 s_mmp_interval; /* # seconds to wait in MMP checking */ __le64 s_mmp_block; /* Block for multi-mount protection */ __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ - __u32 s_reserved[163]; /* Padding to the end of the 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 */ }; #ifdef __KERNEL__ @@ -1160,6 +1172,17 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb, } +static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi, + ext4_group_t block_group) +{ + return block_group >> sbi->s_log_groups_per_flex; +} + +static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi) +{ + return 1 << sbi->s_log_groups_per_flex; +} + #define ext4_std_error(sb, errno) \ do { \ if ((errno)) \ diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h index 4de9a75ca6a..6300226d553 100644 --- a/fs/ext4/ext4_sb.h +++ b/fs/ext4/ext4_sb.h @@ -143,6 +143,9 @@ struct ext4_sb_info { /* locality groups */ struct ext4_locality_group *s_locality_groups; + + unsigned int s_log_groups_per_flex; + struct flex_groups *s_flex_groups; }; #endif /* _EXT4_SB */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b30cc79b9fc..8b0a10acd70 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -157,6 +157,7 @@ void ext4_free_inode (handle_t *handle, struct inode * inode) struct ext4_super_block * es; struct ext4_sb_info *sbi; int fatal = 0, err; + ext4_group_t flex_group; if (atomic_read(&inode->i_count) > 1) { printk ("ext4_free_inode: inode has count=%d\n", @@ -232,6 +233,12 @@ void ext4_free_inode (handle_t *handle, struct inode * inode) if (is_directory) percpu_counter_dec(&sbi->s_dirs_counter); + if (sbi->s_log_groups_per_flex) { + flex_group = ext4_flex_group(sbi, block_group); + spin_lock(sb_bgl_lock(sbi, flex_group)); + sbi->s_flex_groups[flex_group].free_inodes++; + spin_unlock(sb_bgl_lock(sbi, flex_group)); + } } BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata"); err = ext4_journal_dirty_metadata(handle, bh2); @@ -286,6 +293,80 @@ static int find_group_dir(struct super_block *sb, struct inode *parent, return ret; } +#define free_block_ratio 10 + +static int find_group_flex(struct super_block *sb, struct inode *parent, + ext4_group_t *best_group) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *desc; + struct buffer_head *bh; + struct flex_groups *flex_group = sbi->s_flex_groups; + ext4_group_t parent_group = EXT4_I(parent)->i_block_group; + ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group); + ext4_group_t ngroups = sbi->s_groups_count; + int flex_size = ext4_flex_bg_size(sbi); + ext4_group_t best_flex = parent_fbg_group; + int blocks_per_flex = sbi->s_blocks_per_group * flex_size; + int flexbg_free_blocks; + int flex_freeb_ratio; + ext4_group_t n_fbg_groups; + ext4_group_t i; + + n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >> + sbi->s_log_groups_per_flex; + +find_close_to_parent: + flexbg_free_blocks = flex_group[best_flex].free_blocks; + flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex; + if (flex_group[best_flex].free_inodes && + flex_freeb_ratio > free_block_ratio) + goto found_flexbg; + + if (best_flex && best_flex == parent_fbg_group) { + best_flex--; + goto find_close_to_parent; + } + + for (i = 0; i < n_fbg_groups; i++) { + if (i == parent_fbg_group || i == parent_fbg_group - 1) + continue; + + flexbg_free_blocks = flex_group[i].free_blocks; + flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex; + + if (flex_freeb_ratio > free_block_ratio && + flex_group[i].free_inodes) { + best_flex = i; + goto found_flexbg; + } + + if (best_flex < 0 || + (flex_group[i].free_blocks > + flex_group[best_flex].free_blocks && + flex_group[i].free_inodes)) + best_flex = i; + } + + if (!flex_group[best_flex].free_inodes || + !flex_group[best_flex].free_blocks) + return -1; + +found_flexbg: + for (i = best_flex * flex_size; i < ngroups && + i < (best_flex + 1) * flex_size; i++) { + desc = ext4_get_group_desc(sb, i, &bh); + if (le16_to_cpu(desc->bg_free_inodes_count)) { + *best_group = i; + goto out; + } + } + + return -1; +out: + return 0; +} + /* * Orlov's allocator for directories. * @@ -501,6 +582,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode) struct inode *ret; ext4_group_t i; int free = 0; + ext4_group_t flex_group; /* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) @@ -514,6 +596,12 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode) sbi = EXT4_SB(sb); es = sbi->s_es; + + if (sbi->s_log_groups_per_flex) { + ret2 = find_group_flex(sb, dir, &group); + goto got_group; + } + if (S_ISDIR(mode)) { if (test_opt (sb, OLDALLOC)) ret2 = find_group_dir(sb, dir, &group); @@ -522,6 +610,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode) } else ret2 = find_group_other(sb, dir, &group); +got_group: err = -ENOSPC; if (ret2 == -1) goto out; @@ -676,6 +765,13 @@ got: percpu_counter_inc(&sbi->s_dirs_counter); sb->s_dirt = 1; + if (sbi->s_log_groups_per_flex) { + flex_group = ext4_flex_group(sbi, group); + spin_lock(sb_bgl_lock(sbi, flex_group)); + sbi->s_flex_groups[flex_group].free_inodes--; + spin_unlock(sb_bgl_lock(sbi, flex_group)); + } + inode->i_uid = current->fsuid; if (test_opt (sb, GRPID)) inode->i_gid = dir->i_gid; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index b882868f466..5dcb826401b 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2842,6 +2842,14 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group)); percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len); + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, + ac->ac_b_ex.fe_group); + spin_lock(sb_bgl_lock(sbi, flex_group)); + sbi->s_flex_groups[flex_group].free_blocks -= ac->ac_b_ex.fe_len; + spin_unlock(sb_bgl_lock(sbi, flex_group)); + } + err = ext4_journal_dirty_metadata(handle, bitmap_bh); if (err) goto out_err; @@ -4342,6 +4350,13 @@ do_more: spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_add(&sbi->s_freeblocks_counter, count); + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, block_group); + spin_lock(sb_bgl_lock(sbi, flex_group)); + sbi->s_flex_groups[flex_group].free_blocks += count; + spin_unlock(sb_bgl_lock(sbi, flex_group)); + } + ext4_mb_release_desc(&e4b); *freed += count; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 588cfb40864..b9ad3d85206 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -517,6 +517,7 @@ static void ext4_put_super (struct super_block * sb) for (i = 0; i < sbi->s_gdb_count; i++) brelse(sbi->s_group_desc[i]); kfree(sbi->s_group_desc); + kfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -1442,6 +1443,54 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, return res; } +static int ext4_fill_flex_info(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp = NULL; + struct buffer_head *bh; + ext4_group_t flex_group_count; + ext4_group_t flex_group; + int groups_per_flex = 0; + __u64 block_bitmap = 0; + int i; + + if (!sbi->s_es->s_log_groups_per_flex) { + sbi->s_log_groups_per_flex = 0; + return 1; + } + + sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; + groups_per_flex = 1 << sbi->s_log_groups_per_flex; + + flex_group_count = (sbi->s_groups_count + groups_per_flex - 1) / + groups_per_flex; + sbi->s_flex_groups = kmalloc(flex_group_count * + sizeof(struct flex_groups), GFP_KERNEL); + if (sbi->s_flex_groups == NULL) { + printk(KERN_ERR "EXT4-fs: not enough memory\n"); + goto failed; + } + memset(sbi->s_flex_groups, 0, flex_group_count * + sizeof(struct flex_groups)); + + gdp = ext4_get_group_desc(sb, 1, &bh); + block_bitmap = ext4_block_bitmap(sb, gdp) - 1; + + for (i = 0; i < sbi->s_groups_count; i++) { + gdp = ext4_get_group_desc(sb, i, &bh); + + flex_group = ext4_flex_group(sbi, i); + sbi->s_flex_groups[flex_group].free_inodes += + le16_to_cpu(gdp->bg_free_inodes_count); + sbi->s_flex_groups[flex_group].free_blocks += + le16_to_cpu(gdp->bg_free_blocks_count); + } + + return 1; +failed: + return 0; +} + __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, struct ext4_group_desc *gdp) { @@ -2137,6 +2186,14 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n"); goto failed_mount2; } + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + if (!ext4_fill_flex_info(sb)) { + printk(KERN_ERR + "EXT4-fs: unable to initialize " + "flex_bg meta info!\n"); + goto failed_mount2; + } + sbi->s_gdb_count = db_count; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); -- cgit v1.2.3 From f9a8ac99fd79eb961a8573ccf058439bc17b4d3a Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: remove redundant code in ext4_fill_super() The previous sb_min_blocksize() has already set the block size. Signed-off-by: Li Zefan Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b9ad3d85206..6c80f37433e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1899,11 +1899,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) goto out_fail; } - if (!sb_set_blocksize(sb, blocksize)) { - printk(KERN_ERR "EXT4-fs: bad blocksize %d.\n", blocksize); - goto out_fail; - } - /* * The ext4 superblock will not be buffer aligned for other than 1kB * block sizes. We need to calculate the offset from buffer start. -- cgit v1.2.3 From 7477827f6686ce29b6216d9eb26f6b9027742dcc Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: Fix sparse warning Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 2 +- fs/ext4/super.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 0b2b7549ac6..6dcbec9b256 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -47,7 +47,7 @@ static int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block, ext4_group_t block_group) { ext4_group_t actual_group; - ext4_get_group_no_and_offset(sb, block, &actual_group, 0); + ext4_get_group_no_and_offset(sb, block, &actual_group, NULL); if (actual_group == block_group) return 1; return 0; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6c80f37433e..80f06159ee9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1858,8 +1858,8 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) } static int ext4_fill_super (struct super_block *sb, void *data, int silent) - __releases(kernel_sem) - __acquires(kernel_sem) + __releases(kernel_lock) + __acquires(kernel_lock) { struct buffer_head * bh; -- cgit v1.2.3 From 47b4a50bebfd34b5e1fa2a9c673c8f31fa231cc1 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: Set journal pointer to NULL when journal is released Set sbi->s_journal to NULL after we call journal_destroy(). This will be later needed because after journal_destroy() is called, ext4_clear_inode() can still be called for some inodes (e.g. root inode) and we'll need to detect there that journal doesn't exists anymore. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 80f06159ee9..1b330cd71ca 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -506,6 +506,7 @@ static void ext4_put_super (struct super_block * sb) ext4_ext_release(sb); ext4_xattr_put_super(sb); jbd2_journal_destroy(sbi->s_journal); + sbi->s_journal = NULL; if (!(sb->s_flags & MS_RDONLY)) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); @@ -2423,6 +2424,7 @@ cantfind_ext4: failed_mount4: jbd2_journal_destroy(sbi->s_journal); + sbi->s_journal = NULL; failed_mount3: percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); -- cgit v1.2.3 From 678aaf481496b01473b778685eca231d6784098b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: Use new framework for data=ordered mode in JBD2 This patch makes ext4 use inode-based implementation of data=ordered mode in JBD2. It allows us to unify some data=ordered and data=writeback paths (especially writepage since we don't have to start a transaction anymore) and remove some buffer walking. Updated fix from Aneesh Kumar K.V to fix file system hang due to corrupt jinode values. Signed-off-by: Jan Kara Signed-off-by: Aneesh Kumar K.V Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_i.h | 1 + fs/ext4/ext4_jbd2.h | 7 ++- fs/ext4/inode.c | 158 ++++++++++++++++------------------------------------ fs/ext4/super.c | 5 +- 4 files changed, 59 insertions(+), 112 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/ext4_i.h b/fs/ext4/ext4_i.h index abf2744164e..c2903ef7215 100644 --- a/fs/ext4/ext4_i.h +++ b/fs/ext4/ext4_i.h @@ -150,6 +150,7 @@ struct ext4_inode_info { */ struct rw_semaphore i_data_sem; struct inode vfs_inode; + struct jbd2_inode jinode; unsigned long i_ext_generation; struct ext4_ext_cache i_cached_extent; diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index d0aa9ee20f8..eb8bc3afe6e 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -154,8 +154,6 @@ int __ext4_journal_dirty_metadata(const char *where, #define ext4_journal_forget(handle, bh) \ __ext4_journal_forget(__func__, (handle), (bh)) -int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh); - handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); int __ext4_journal_stop(const char *where, handle_t *handle); @@ -192,6 +190,11 @@ static inline int ext4_journal_force_commit(journal_t *journal) return jbd2_journal_force_commit(journal); } +static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode) +{ + return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode); +} + /* super.c */ int ext4_force_commit(struct super_block *sb); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 320acb6c35b..7b9569179fd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -39,6 +39,13 @@ #include "xattr.h" #include "acl.h" +static inline int ext4_begin_ordered_truncate(struct inode *inode, + loff_t new_size) +{ + return jbd2_journal_begin_ordered_truncate(&EXT4_I(inode)->jinode, + new_size); +} + /* * Test whether an inode is a fast symlink. */ @@ -181,6 +188,8 @@ void ext4_delete_inode (struct inode * inode) { handle_t *handle; + if (ext4_should_order_data(inode)) + ext4_begin_ordered_truncate(inode, 0); truncate_inode_pages(&inode->i_data, 0); if (is_bad_inode(inode)) @@ -1273,15 +1282,6 @@ out: return ret; } -int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh) -{ - int err = jbd2_journal_dirty_data(handle, bh); - if (err) - ext4_journal_abort_handle(__func__, __func__, - bh, handle, err); - return err; -} - /* For write_end() in data=journal mode */ static int write_end_fn(handle_t *handle, struct buffer_head *bh) { @@ -1311,8 +1311,7 @@ static int ext4_ordered_write_end(struct file *file, from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; - ret = walk_page_buffers(handle, page_buffers(page), - from, to, NULL, ext4_journal_dirty_data); + ret = ext4_jbd2_file_inode(handle, inode); if (ret == 0) { /* @@ -1472,25 +1471,22 @@ static int bput_one(handle_t *handle, struct buffer_head *bh) return 0; } -static int jbd2_journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh) -{ - if (buffer_mapped(bh)) - return ext4_journal_dirty_data(handle, bh); - return 0; -} - static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) { return !buffer_mapped(bh) || buffer_delay(bh); } /* - * Note that we don't need to start a transaction unless we're journaling - * data because we should have holes filled from ext4_page_mkwrite(). If - * we are journaling data, we cannot start transaction directly because - * transaction start ranks above page lock so we have to do some magic... + * Note that we don't need to start a transaction unless we're journaling data + * because we should have holes filled from ext4_page_mkwrite(). We even don't + * need to file the inode to the transaction's list in ordered mode because if + * we are writing back data added by write(), the inode is already there and if + * we are writing back data modified via mmap(), noone guarantees in which + * transaction the data will hit the disk. In case we are journaling data, we + * cannot start transaction directly because transaction start ranks above page + * lock so we have to do some magic. * - * In all journalling modes block_write_full_page() will start the I/O. + * In all journaling modes block_write_full_page() will start the I/O. * * Problem: * @@ -1533,86 +1529,7 @@ static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) * us. * */ -static int __ext4_ordered_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - struct buffer_head *page_bufs; - handle_t *handle = NULL; - int ret = 0; - int err; - - if (!page_has_buffers(page)) { - create_empty_buffers(page, inode->i_sb->s_blocksize, - (1 << BH_Dirty)|(1 << BH_Uptodate)); - } - page_bufs = page_buffers(page); - walk_page_buffers(handle, page_bufs, 0, - PAGE_CACHE_SIZE, NULL, bget_one); - - ret = block_write_full_page(page, ext4_get_block, wbc); - - /* - * The page can become unlocked at any point now, and - * truncate can then come in and change things. So we - * can't touch *page from now on. But *page_bufs is - * safe due to elevated refcount. - */ - - /* - * And attach them to the current transaction. But only if - * block_write_full_page() succeeded. Otherwise they are unmapped, - * and generally junk. - */ - if (ret == 0) { - handle = ext4_journal_start(inode, - ext4_writepage_trans_blocks(inode)); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out_put; - } - - ret = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, - NULL, jbd2_journal_dirty_data_fn); - err = ext4_journal_stop(handle); - if (!ret) - ret = err; - } -out_put: - walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL, - bput_one); - return ret; -} - -static int ext4_ordered_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - loff_t size = i_size_read(inode); - loff_t len; - - J_ASSERT(PageLocked(page)); - J_ASSERT(page_has_buffers(page)); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped_or_delay)); - - /* - * We give up here if we're reentered, because it might be for a - * different filesystem. - */ - if (!ext4_journal_current_handle()) - return __ext4_ordered_writepage(page, wbc); - - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} - -static int __ext4_writeback_writepage(struct page *page, +static int __ext4_normal_writepage(struct page *page, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; @@ -1624,7 +1541,7 @@ static int __ext4_writeback_writepage(struct page *page, } -static int ext4_writeback_writepage(struct page *page, +static int ext4_normal_writepage(struct page *page, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; @@ -1641,7 +1558,7 @@ static int ext4_writeback_writepage(struct page *page, ext4_bh_unmapped_or_delay)); if (!ext4_journal_current_handle()) - return __ext4_writeback_writepage(page, wbc); + return __ext4_normal_writepage(page, wbc); redirty_page_for_writepage(wbc, page); unlock_page(page); @@ -1877,7 +1794,7 @@ static int ext4_journalled_set_page_dirty(struct page *page) static const struct address_space_operations ext4_ordered_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_ordered_writepage, + .writepage = ext4_normal_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_ordered_write_end, @@ -1891,7 +1808,7 @@ static const struct address_space_operations ext4_ordered_aops = { static const struct address_space_operations ext4_writeback_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_writeback_writepage, + .writepage = ext4_normal_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_writeback_write_end, @@ -2019,7 +1936,7 @@ int ext4_block_truncate_page(handle_t *handle, err = ext4_journal_dirty_metadata(handle, bh); } else { if (ext4_should_order_data(inode)) - err = ext4_journal_dirty_data(handle, bh); + err = ext4_jbd2_file_inode(handle, inode); mark_buffer_dirty(bh); } @@ -3171,7 +3088,14 @@ int ext4_write_inode(struct inode *inode, int wait) * be freed, so we have a strong guarantee that no future commit will * leave these blocks visible to the user.) * - * Called with inode->sem down. + * Another thing we have to assure is that if we are in ordered mode + * and inode is still attached to the committing transaction, we must + * we start writeout of all the dirty pages which are being truncated. + * This way we are sure that all the data written in the previous + * transaction are already on disk (truncate waits for pages under + * writeback). + * + * Called with inode->i_mutex down. */ int ext4_setattr(struct dentry *dentry, struct iattr *attr) { @@ -3237,6 +3161,22 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (!error) error = rc; ext4_journal_stop(handle); + + if (ext4_should_order_data(inode)) { + error = ext4_begin_ordered_truncate(inode, + attr->ia_size); + if (error) { + /* Do as much error cleanup as possible */ + handle = ext4_journal_start(inode, 3); + if (IS_ERR(handle)) { + ext4_orphan_del(NULL, inode); + goto err_out; + } + ext4_orphan_del(handle, inode); + ext4_journal_stop(handle); + goto err_out; + } + } } rc = inode_setattr(inode, attr); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1b330cd71ca..629d0fa27e3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -573,6 +573,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache)); INIT_LIST_HEAD(&ei->i_prealloc_list); spin_lock_init(&ei->i_prealloc_lock); + jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode); return &ei->vfs_inode; } @@ -637,6 +638,8 @@ static void ext4_clear_inode(struct inode *inode) EXT4_I(inode)->i_block_alloc_info = NULL; if (unlikely(rsv)) kfree(rsv); + jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal, + &EXT4_I(inode)->jinode); } static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) @@ -3378,7 +3381,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, err = ext4_journal_dirty_metadata(handle, bh); else { /* Always do at least ordered writes for quotas */ - err = ext4_journal_dirty_data(handle, bh); + err = ext4_jbd2_file_inode(handle, inode); mark_buffer_dirty(bh); } brelse(bh); -- cgit v1.2.3 From 64769240bd07f446f83660bb143bb609d8ab4910 Mon Sep 17 00:00:00 2001 From: Alex Tomas Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: Add delayed allocation support in data=writeback mode Updated with fixes from Mingming Cao to unlock and release the page from page cache if the delalloc write_begin failed, and properly handle preallocated blocks. Also added a fix to clear buffer_delay in block_write_full_page() after allocating a delayed buffer. Updated with fixes from Aneesh Kumar K.V to update i_disksize properly and to add bmap support for delayed allocation. Updated with a fix from Valerie Clement to avoid filesystem corruption when the filesystem is mounted with the delalloc option and blocksize < pagesize. Signed-off-by: Alex Tomas Signed-off-by: Mingming Cao Signed-off-by: Dave Kleikamp Signed-off-by: "Theodore Ts'o" Signed-off-by: Aneesh Kumar K.V --- fs/ext4/ext4.h | 1 + fs/ext4/inode.c | 699 +++++++++++++++++++++++++++++++++++++++++++++++++++++++- fs/ext4/super.c | 6 +- 3 files changed, 700 insertions(+), 6 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f65829bbe7a..ee9576dc0ba 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -536,6 +536,7 @@ do { \ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ #define EXT4_MOUNT_MBALLOC 0x4000000 /* Buddy allocation support */ +#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7b9569179fd..2bef4f879e4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -46,6 +47,8 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, new_size); } +static void ext4_invalidatepage(struct page *page, unsigned long offset); + /* * Test whether an inode is a fast symlink. */ @@ -1407,6 +1410,669 @@ static int ext4_journalled_write_end(struct file *file, return ret ? ret : copied; } +/* + * Delayed allocation stuff + */ + +struct mpage_da_data { + struct inode *inode; + struct buffer_head lbh; /* extent of blocks */ + unsigned long first_page, next_page; /* extent of pages */ + get_block_t *get_block; + struct writeback_control *wbc; +}; + +/* + * mpage_da_submit_io - walks through extent of pages and try to write + * them with __mpage_writepage() + * + * @mpd->inode: inode + * @mpd->first_page: first page of the extent + * @mpd->next_page: page after the last page of the extent + * @mpd->get_block: the filesystem's block mapper function + * + * By the time mpage_da_submit_io() is called we expect all blocks + * to be allocated. this may be wrong if allocation failed. + * + * As pages are already locked by write_cache_pages(), we can't use it + */ +static int mpage_da_submit_io(struct mpage_da_data *mpd) +{ + struct address_space *mapping = mpd->inode->i_mapping; + struct mpage_data mpd_pp = { + .bio = NULL, + .last_block_in_bio = 0, + .get_block = mpd->get_block, + .use_writepage = 1, + }; + int ret = 0, err, nr_pages, i; + unsigned long index, end; + struct pagevec pvec; + + BUG_ON(mpd->next_page <= mpd->first_page); + + pagevec_init(&pvec, 0); + index = mpd->first_page; + end = mpd->next_page - 1; + + while (index <= end) { + /* XXX: optimize tail */ + nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + index = page->index; + if (index > end) + break; + index++; + + err = __mpage_writepage(page, mpd->wbc, &mpd_pp); + + /* + * In error case, we have to continue because + * remaining pages are still locked + * XXX: unlock and re-dirty them? + */ + if (ret == 0) + ret = err; + } + pagevec_release(&pvec); + } + if (mpd_pp.bio) + mpage_bio_submit(WRITE, mpd_pp.bio); + + return ret; +} + +/* + * mpage_put_bnr_to_bhs - walk blocks and assign them actual numbers + * + * @mpd->inode - inode to walk through + * @exbh->b_blocknr - first block on a disk + * @exbh->b_size - amount of space in bytes + * @logical - first logical block to start assignment with + * + * the function goes through all passed space and put actual disk + * block numbers into buffer heads, dropping BH_Delay + */ +static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, + struct buffer_head *exbh) +{ + struct inode *inode = mpd->inode; + struct address_space *mapping = inode->i_mapping; + int blocks = exbh->b_size >> inode->i_blkbits; + sector_t pblock = exbh->b_blocknr, cur_logical; + struct buffer_head *head, *bh; + unsigned long index, end; + struct pagevec pvec; + int nr_pages, i; + + index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + end = (logical + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + + pagevec_init(&pvec, 0); + + while (index <= end) { + /* XXX: optimize tail */ + nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + index = page->index; + if (index > end) + break; + index++; + + BUG_ON(!PageLocked(page)); + BUG_ON(PageWriteback(page)); + BUG_ON(!page_has_buffers(page)); + + bh = page_buffers(page); + head = bh; + + /* skip blocks out of the range */ + do { + if (cur_logical >= logical) + break; + cur_logical++; + } while ((bh = bh->b_this_page) != head); + + do { + if (cur_logical >= logical + blocks) + break; + + if (buffer_delay(bh)) { + bh->b_blocknr = pblock; + clear_buffer_delay(bh); + } else if (buffer_mapped(bh)) { + BUG_ON(bh->b_blocknr != pblock); + } + + cur_logical++; + pblock++; + } while ((bh = bh->b_this_page) != head); + } + pagevec_release(&pvec); + } +} + + +/* + * __unmap_underlying_blocks - just a helper function to unmap + * set of blocks described by @bh + */ +static inline void __unmap_underlying_blocks(struct inode *inode, + struct buffer_head *bh) +{ + struct block_device *bdev = inode->i_sb->s_bdev; + int blocks, i; + + blocks = bh->b_size >> inode->i_blkbits; + for (i = 0; i < blocks; i++) + unmap_underlying_metadata(bdev, bh->b_blocknr + i); +} + +/* + * mpage_da_map_blocks - go through given space + * + * @mpd->lbh - bh describing space + * @mpd->get_block - the filesystem's block mapper function + * + * The function skips space we know is already mapped to disk blocks. + * + * The function ignores errors ->get_block() returns, thus real + * error handling is postponed to __mpage_writepage() + */ +static void mpage_da_map_blocks(struct mpage_da_data *mpd) +{ + struct buffer_head *lbh = &mpd->lbh; + int err = 0, remain = lbh->b_size; + sector_t next = lbh->b_blocknr; + struct buffer_head new; + + /* + * We consider only non-mapped and non-allocated blocks + */ + if (buffer_mapped(lbh) && !buffer_delay(lbh)) + return; + + while (remain) { + new.b_state = lbh->b_state; + new.b_blocknr = 0; + new.b_size = remain; + err = mpd->get_block(mpd->inode, next, &new, 1); + if (err) { + /* + * Rather than implement own error handling + * here, we just leave remaining blocks + * unallocated and try again with ->writepage() + */ + break; + } + BUG_ON(new.b_size == 0); + + if (buffer_new(&new)) + __unmap_underlying_blocks(mpd->inode, &new); + + /* + * If blocks are delayed marked, we need to + * put actual blocknr and drop delayed bit + */ + if (buffer_delay(lbh)) + mpage_put_bnr_to_bhs(mpd, next, &new); + + /* go for the remaining blocks */ + next += new.b_size >> mpd->inode->i_blkbits; + remain -= new.b_size; + } +} + +#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | (1 << BH_Delay)) + +/* + * mpage_add_bh_to_extent - try to add one more block to extent of blocks + * + * @mpd->lbh - extent of blocks + * @logical - logical number of the block in the file + * @bh - bh of the block (used to access block's state) + * + * the function is used to collect contig. blocks in same state + */ +static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, + sector_t logical, struct buffer_head *bh) +{ + struct buffer_head *lbh = &mpd->lbh; + sector_t next; + + next = lbh->b_blocknr + (lbh->b_size >> mpd->inode->i_blkbits); + + /* + * First block in the extent + */ + if (lbh->b_size == 0) { + lbh->b_blocknr = logical; + lbh->b_size = bh->b_size; + lbh->b_state = bh->b_state & BH_FLAGS; + return; + } + + /* + * Can we merge the block to our big extent? + */ + if (logical == next && (bh->b_state & BH_FLAGS) == lbh->b_state) { + lbh->b_size += bh->b_size; + return; + } + + /* + * We couldn't merge the block to our extent, so we + * need to flush current extent and start new one + */ + mpage_da_map_blocks(mpd); + + /* + * Now start a new extent + */ + lbh->b_size = bh->b_size; + lbh->b_state = bh->b_state & BH_FLAGS; + lbh->b_blocknr = logical; +} + +/* + * __mpage_da_writepage - finds extent of pages and blocks + * + * @page: page to consider + * @wbc: not used, we just follow rules + * @data: context + * + * The function finds extents of pages and scan them for all blocks. + */ +static int __mpage_da_writepage(struct page *page, + struct writeback_control *wbc, void *data) +{ + struct mpage_da_data *mpd = data; + struct inode *inode = mpd->inode; + struct buffer_head *bh, *head, fake; + sector_t logical; + + /* + * Can we merge this page to current extent? + */ + if (mpd->next_page != page->index) { + /* + * Nope, we can't. So, we map non-allocated blocks + * and start IO on them using __mpage_writepage() + */ + if (mpd->next_page != mpd->first_page) { + mpage_da_map_blocks(mpd); + mpage_da_submit_io(mpd); + } + + /* + * Start next extent of pages ... + */ + mpd->first_page = page->index; + + /* + * ... and blocks + */ + mpd->lbh.b_size = 0; + mpd->lbh.b_state = 0; + mpd->lbh.b_blocknr = 0; + } + + mpd->next_page = page->index + 1; + logical = (sector_t) page->index << + (PAGE_CACHE_SHIFT - inode->i_blkbits); + + if (!page_has_buffers(page)) { + /* + * There is no attached buffer heads yet (mmap?) + * we treat the page asfull of dirty blocks + */ + bh = &fake; + bh->b_size = PAGE_CACHE_SIZE; + bh->b_state = 0; + set_buffer_dirty(bh); + set_buffer_uptodate(bh); + mpage_add_bh_to_extent(mpd, logical, bh); + } else { + /* + * Page with regular buffer heads, just add all dirty ones + */ + head = page_buffers(page); + bh = head; + do { + BUG_ON(buffer_locked(bh)); + if (buffer_dirty(bh)) + mpage_add_bh_to_extent(mpd, logical, bh); + logical++; + } while ((bh = bh->b_this_page) != head); + } + + return 0; +} + +/* + * mpage_da_writepages - walk the list of dirty pages of the given + * address space, allocates non-allocated blocks, maps newly-allocated + * blocks to existing bhs and issue IO them + * + * @mapping: address space structure to write + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * @get_block: the filesystem's block mapper function. + * + * This is a library function, which implements the writepages() + * address_space_operation. + * + * In order to avoid duplication of logic that deals with partial pages, + * multiple bio per page, etc, we find non-allocated blocks, allocate + * them with minimal calls to ->get_block() and re-use __mpage_writepage() + * + * It's important that we call __mpage_writepage() only once for each + * involved page, otherwise we'd have to implement more complicated logic + * to deal with pages w/o PG_lock or w/ PG_writeback and so on. + * + * See comments to mpage_writepages() + */ +static int mpage_da_writepages(struct address_space *mapping, + struct writeback_control *wbc, + get_block_t get_block) +{ + struct mpage_da_data mpd; + int ret; + + if (!get_block) + return generic_writepages(mapping, wbc); + + mpd.wbc = wbc; + mpd.inode = mapping->host; + mpd.lbh.b_size = 0; + mpd.lbh.b_state = 0; + mpd.lbh.b_blocknr = 0; + mpd.first_page = 0; + mpd.next_page = 0; + mpd.get_block = get_block; + + ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, &mpd); + + /* + * Handle last extent of pages + */ + if (mpd.next_page != mpd.first_page) { + mpage_da_map_blocks(&mpd); + mpage_da_submit_io(&mpd); + } + + return ret; +} + +/* + * this is a special callback for ->write_begin() only + * it's intention is to return mapped block or reserve space + */ +static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + int ret = 0; + + BUG_ON(create == 0); + BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize); + + /* + * first, we need to know whether the block is allocated already + * preallocated blocks are unmapped but should treated + * the same as allocated blocks. + */ + ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0); + if (ret == 0) { + /* the block isn't allocated yet, let's reserve space */ + /* XXX: call reservation here */ + /* + * XXX: __block_prepare_write() unmaps passed block, + * is it OK? + */ + map_bh(bh_result, inode->i_sb, 0); + set_buffer_new(bh_result); + set_buffer_delay(bh_result); + } else if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; + } + + return ret; +} + +static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + int ret, needed_blocks = ext4_writepage_trans_blocks(inode); + unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + loff_t disksize = EXT4_I(inode)->i_disksize; + handle_t *handle = NULL; + + if (create) { + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + } + + ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, + bh_result, create, 0); + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + + /* + * Update on-disk size along with block allocation + * we don't use 'extend_disksize' as size may change + * within already allocated block -bzzz + */ + disksize = ((loff_t) iblock + ret) << inode->i_blkbits; + if (disksize > i_size_read(inode)) + disksize = i_size_read(inode); + if (disksize > EXT4_I(inode)->i_disksize) { + /* + * XXX: replace with spinlock if seen contended -bzzz + */ + down_write(&EXT4_I(inode)->i_data_sem); + if (disksize > EXT4_I(inode)->i_disksize) + EXT4_I(inode)->i_disksize = disksize; + up_write(&EXT4_I(inode)->i_data_sem); + + if (EXT4_I(inode)->i_disksize == disksize) { + if (handle == NULL) + handle = ext4_journal_start(inode, 1); + if (!IS_ERR(handle)) + ext4_mark_inode_dirty(handle, inode); + } + } + + ret = 0; + } + +out: + if (handle && !IS_ERR(handle)) + ext4_journal_stop(handle); + + return ret; +} +/* FIXME!! only support data=writeback mode */ +static int ext4_da_writepage(struct page *page, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + handle_t *handle = NULL; + int ret = 0; + int err; + + if (ext4_journal_current_handle()) + goto out_fail; + + handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_fail; + } + + if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) + ret = nobh_writepage(page, ext4_get_block, wbc); + else + ret = block_write_full_page(page, ext4_get_block, wbc); + + if (!ret && inode->i_size > EXT4_I(inode)->i_disksize) { + EXT4_I(inode)->i_disksize = inode->i_size; + ext4_mark_inode_dirty(handle, inode); + } + + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; + +out_fail: + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return ret; +} + +static int ext4_da_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + return mpage_da_writepages(mapping, wbc, ext4_da_get_block_write); +} + +static int ext4_da_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + int ret; + struct page *page; + pgoff_t index; + unsigned from, to; + struct inode *inode = mapping->host; + handle_t *handle; + + index = pos >> PAGE_CACHE_SHIFT; + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + len; + + /* + * With delayed allocation, we don't log the i_disksize update + * if there is delayed block allocation. But we still need + * to journalling the i_disksize update if writes to the end + * of file which has an already mapped buffer. + */ + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + page = __grab_cache_page(mapping, index); + if (!page) + return -ENOMEM; + *pagep = page; + + ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ext4_da_get_block_prep); + if (ret < 0) { + unlock_page(page); + ext4_journal_stop(handle); + page_cache_release(page); + } + +out: + return ret; +} + +static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +{ + return !buffer_mapped(bh) || buffer_delay(bh); +} + +static int ext4_da_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + struct inode *inode = mapping->host; + int ret = 0, ret2; + handle_t *handle = ext4_journal_current_handle(); + loff_t new_i_size; + + /* + * generic_write_end() will run mark_inode_dirty() if i_size + * changes. So let's piggyback the i_disksize mark_inode_dirty + * into that. + */ + + new_i_size = pos + copied; + if (new_i_size > EXT4_I(inode)->i_disksize) + if (!walk_page_buffers(NULL, page_buffers(page), + 0, len, NULL, ext4_bh_unmapped_or_delay)){ + /* + * Updating i_disksize when extending file without + * needing block allocation + */ + if (ext4_should_order_data(inode)) + ret = ext4_jbd2_file_inode(handle, inode); + + EXT4_I(inode)->i_disksize = new_i_size; + } + ret2 = generic_write_end(file, mapping, pos, len, copied, + page, fsdata); + copied = ret2; + if (ret2 < 0) + ret = ret2; + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + + return ret ? ret : copied; +} + +static void ext4_da_invalidatepage(struct page *page, unsigned long offset) +{ + struct buffer_head *head, *bh; + unsigned int curr_off = 0; + + /* + * Drop reserved blocks + */ + BUG_ON(!PageLocked(page)); + if (!page_has_buffers(page)) + goto out; + + head = page_buffers(page); + bh = head; + do { + unsigned int next_off = curr_off + bh->b_size; + + /* + * is this block fully invalidated? + */ + if (offset <= curr_off && buffer_delay(bh)) { + clear_buffer_delay(bh); + /* XXX: add real stuff here */ + } + curr_off = next_off; + bh = bh->b_this_page; + } while (bh != head); + +out: + ext4_invalidatepage(page, offset); + + return; +} + + /* * bmap() is special. It gets used by applications such as lilo and by * the swapper to find the on-disk block of a specific piece of data. @@ -1427,6 +2093,16 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) journal_t *journal; int err; + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && + test_opt(inode->i_sb, DELALLOC)) { + /* + * With delalloc we want to sync the file + * so that we can make sure we allocate + * blocks for file + */ + filemap_write_and_wait(mapping); + } + if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) { /* * This is a REALLY heavyweight approach, but the use of @@ -1471,11 +2147,6 @@ static int bput_one(handle_t *handle, struct buffer_head *bh) return 0; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) -{ - return !buffer_mapped(bh) || buffer_delay(bh); -} - /* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't @@ -1832,10 +2503,28 @@ static const struct address_space_operations ext4_journalled_aops = { .releasepage = ext4_releasepage, }; +static const struct address_space_operations ext4_da_aops = { + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_da_writepage, + .writepages = ext4_da_writepages, + .sync_page = block_sync_page, + .write_begin = ext4_da_write_begin, + .write_end = ext4_da_write_end, + .bmap = ext4_bmap, + .invalidatepage = ext4_da_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, +}; + void ext4_set_aops(struct inode *inode) { if (ext4_should_order_data(inode)) inode->i_mapping->a_ops = &ext4_ordered_aops; + else if (ext4_should_writeback_data(inode) && + test_opt(inode->i_sb, DELALLOC)) + inode->i_mapping->a_ops = &ext4_da_aops; else if (ext4_should_writeback_data(inode)) inode->i_mapping->a_ops = &ext4_writeback_aops; else diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 629d0fa27e3..de9d3d0eb20 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -898,7 +898,7 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version, - Opt_mballoc, Opt_nomballoc, Opt_stripe, + Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, }; static match_table_t tokens = { @@ -957,6 +957,7 @@ static match_table_t tokens = { {Opt_nomballoc, "nomballoc"}, {Opt_stripe, "stripe=%u"}, {Opt_resize, "resize"}, + {Opt_delalloc, "delalloc"}, {Opt_err, NULL}, }; @@ -1335,6 +1336,9 @@ set_qf_format: return 0; sbi->s_stripe = option; break; + case Opt_delalloc: + set_opt(sbi->s_mount_opt, DELALLOC); + break; default: printk (KERN_ERR "EXT4-fs: Unrecognized mount option \"%s\" " -- cgit v1.2.3 From d2a1763791a634e315ec926b62829c1e88842c86 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Mon, 14 Jul 2008 17:52:37 -0400 Subject: ext4: delayed allocation ENOSPC handling This patch does block reservation for delayed allocation, to avoid ENOSPC later at page flush time. Blocks(data and metadata) are reserved at da_write_begin() time, the freeblocks counter is updated by then, and the number of reserved blocks is store in per inode counter. At the writepage time, the unused reserved meta blocks are returned back. At unlink/truncate time, reserved blocks are properly released. Updated fix from Aneesh Kumar K.V to fix the oldallocator block reservation accounting with delalloc, added lock to guard the counters and also fix the reservation for meta blocks. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Mingming Cao Signed-off-by: Theodore Ts'o --- fs/ext4/balloc.c | 49 ++++++++----- fs/ext4/dir.c | 3 +- fs/ext4/ext4.h | 6 +- fs/ext4/ext4_extents.h | 1 + fs/ext4/ext4_i.h | 7 ++ fs/ext4/extents.c | 32 ++++++++- fs/ext4/inode.c | 184 +++++++++++++++++++++++++++++++++++++++++-------- fs/ext4/mballoc.c | 20 +++++- fs/ext4/super.c | 5 ++ 9 files changed, 257 insertions(+), 50 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 6369bacf0dc..495ab21b983 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -1701,7 +1701,12 @@ ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode, } sbi = EXT4_SB(sb); - *count = ext4_has_free_blocks(sbi, *count); + if (!EXT4_I(inode)->i_delalloc_reserved_flag) { + /* + * With delalloc we already reserved the blocks + */ + *count = ext4_has_free_blocks(sbi, *count); + } if (*count == 0) { *errp = -ENOSPC; return 0; /*return with ENOSPC error */ @@ -1902,7 +1907,8 @@ allocated: le16_add_cpu(&gdp->bg_free_blocks_count, -num); gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp); spin_unlock(sb_bgl_lock(sbi, group_no)); - percpu_counter_sub(&sbi->s_freeblocks_counter, num); + if (!EXT4_I(inode)->i_delalloc_reserved_flag) + percpu_counter_sub(&sbi->s_freeblocks_counter, num); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, group_no); @@ -1976,40 +1982,49 @@ static ext4_fsblk_t do_blk_alloc(handle_t *handle, struct inode *inode, } /* - * ext4_new_meta_block() -- allocate block for meta data (indexing) blocks + * ext4_new_meta_blocks() -- allocate block for meta data (indexing) blocks * * @handle: handle to this transaction * @inode: file inode * @goal: given target block(filesystem wide) + * @count: total number of blocks need * @errp: error code * - * Return allocated block number on success + * Return 1st allocated block numberon success, *count stores total account + * error stores in errp pointer */ -ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode, - ext4_fsblk_t goal, int *errp) +ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, unsigned long *count, int *errp) { - unsigned long count = 1; - return do_blk_alloc(handle, inode, 0, goal, - &count, errp, EXT4_META_BLOCK); + ext4_fsblk_t ret; + ret = do_blk_alloc(handle, inode, 0, goal, + count, errp, EXT4_META_BLOCK); + /* + * Account for the allocated meta blocks + */ + if (!(*errp)) { + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + EXT4_I(inode)->i_allocated_meta_blocks += *count; + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + } + return ret; } /* - * ext4_new_meta_blocks() -- allocate block for meta data (indexing) blocks + * ext4_new_meta_block() -- allocate block for meta data (indexing) blocks * * @handle: handle to this transaction * @inode: file inode * @goal: given target block(filesystem wide) - * @count: total number of blocks need * @errp: error code * - * Return 1st allocated block numberon success, *count stores total account - * error stores in errp pointer + * Return allocated block number on success */ -ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, - ext4_fsblk_t goal, unsigned long *count, int *errp) +ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, int *errp) { - return do_blk_alloc(handle, inode, 0, goal, - count, errp, EXT4_META_BLOCK); + unsigned long count = 1; + return ext4_new_meta_blocks(handle, inode, goal, &count, errp); } /* diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 5ed5108766c..d3d23d73c08 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -129,7 +129,8 @@ static int ext4_readdir(struct file * filp, struct buffer_head *bh = NULL; map_bh.b_state = 0; - err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, 0, 0); + err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, + 0, 0, 0); if (err > 0) { pgoff_t index = map_bh.b_blocknr >> (PAGE_CACHE_SHIFT - inode->i_blkbits); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ee9576dc0ba..0962f4e2657 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -74,6 +74,9 @@ #define EXT4_MB_HINT_GOAL_ONLY 256 /* goal is meaningful */ #define EXT4_MB_HINT_TRY_GOAL 512 +/* blocks already pre-reserved by delayed allocation */ +#define EXT4_MB_DELALLOC_RESERVED 1024 + struct ext4_allocation_request { /* target inode for block we're allocating */ @@ -1041,6 +1044,7 @@ extern void ext4_mb_update_group_info(struct ext4_group_info *grp, /* inode.c */ +void ext4_da_release_space(struct inode *inode, int used, int to_free); int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); struct buffer_head *ext4_getblk(handle_t *, struct inode *, @@ -1234,7 +1238,7 @@ extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, int create, - int extend_disksize); + int extend_disksize, int flag); #endif /* __KERNEL__ */ #endif /* _EXT4_H */ diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 75333b595fa..6c166c0a54b 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -212,6 +212,7 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN)); } +extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks); extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *); extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t); extern int ext4_extent_tree_init(handle_t *, struct inode *); diff --git a/fs/ext4/ext4_i.h b/fs/ext4/ext4_i.h index c2903ef7215..ef7409f0e7e 100644 --- a/fs/ext4/ext4_i.h +++ b/fs/ext4/ext4_i.h @@ -163,6 +163,13 @@ struct ext4_inode_info { /* mballoc */ struct list_head i_prealloc_list; spinlock_t i_prealloc_lock; + + /* allocation reservation info for delalloc */ + unsigned long i_reserved_data_blocks; + unsigned long i_reserved_meta_blocks; + unsigned long i_allocated_meta_blocks; + unsigned short i_delalloc_reserved_flag; + spinlock_t i_block_reservation_lock; }; #endif /* _EXT4_I */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7844bbb2bac..dabc3b68d24 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -248,6 +248,36 @@ static int ext4_ext_space_root_idx(struct inode *inode) return size; } +/* + * Calculate the number of metadata blocks needed + * to allocate @blocks + * Worse case is one block per extent + */ +int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks) +{ + int lcap, icap, rcap, leafs, idxs, num; + int newextents = blocks; + + rcap = ext4_ext_space_root_idx(inode); + lcap = ext4_ext_space_block(inode); + icap = ext4_ext_space_block_idx(inode); + + /* number of new leaf blocks needed */ + num = leafs = (newextents + lcap - 1) / lcap; + + /* + * Worse case, we need separate index block(s) + * to link all new leaf blocks + */ + idxs = (leafs + icap - 1) / icap; + do { + num += idxs; + idxs = (idxs + icap - 1) / icap; + } while (idxs > rcap); + + return num; +} + static int ext4_ext_max_entries(struct inode *inode, int depth) { @@ -2910,7 +2940,7 @@ retry: } ret = ext4_get_blocks_wrap(handle, inode, block, max_blocks, &map_bh, - EXT4_CREATE_UNINITIALIZED_EXT, 0); + EXT4_CREATE_UNINITIALIZED_EXT, 0, 0); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2bef4f879e4..a6b800c5847 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -39,6 +39,7 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" +#include "ext4_extents.h" static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) @@ -982,7 +983,7 @@ out: */ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, - int create, int extend_disksize) + int create, int extend_disksize, int flag) { int retval; @@ -1023,6 +1024,15 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, * with create == 1 flag. */ down_write((&EXT4_I(inode)->i_data_sem)); + + /* + * if the caller is from delayed allocation writeout path + * we have already reserved fs blocks for allocation + * let the underlying get_block() function know to + * avoid double accounting + */ + if (flag) + EXT4_I(inode)->i_delalloc_reserved_flag = 1; /* * We need to check for EXT4 here because migrate * could have changed the inode type in between @@ -1044,6 +1054,18 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, ~EXT4_EXT_MIGRATE; } } + + if (flag) { + EXT4_I(inode)->i_delalloc_reserved_flag = 0; + /* + * Update reserved blocks/metadata blocks + * after successful block allocation + * which were deferred till now + */ + if ((retval > 0) && buffer_delay(bh)) + ext4_da_release_space(inode, retval, 0); + } + up_write((&EXT4_I(inode)->i_data_sem)); return retval; } @@ -1069,7 +1091,7 @@ static int ext4_get_block(struct inode *inode, sector_t iblock, } ret = ext4_get_blocks_wrap(handle, inode, iblock, - max_blocks, bh_result, create, 0); + max_blocks, bh_result, create, 0, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -1095,7 +1117,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); err = ext4_get_blocks_wrap(handle, inode, block, 1, - &dummy, create, 1); + &dummy, create, 1, 0); /* * ext4_get_blocks_handle() returns number of blocks * mapped. 0 in case of a HOLE. @@ -1409,6 +1431,122 @@ static int ext4_journalled_write_end(struct file *file, return ret ? ret : copied; } +/* + * Calculate the number of metadata blocks need to reserve + * to allocate @blocks for non extent file based file + */ +static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks) +{ + int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb); + int ind_blks, dind_blks, tind_blks; + + /* number of new indirect blocks needed */ + ind_blks = (blocks + icap - 1) / icap; + + dind_blks = (ind_blks + icap - 1) / icap; + + tind_blks = 1; + + return ind_blks + dind_blks + tind_blks; +} + +/* + * Calculate the number of metadata blocks need to reserve + * to allocate given number of blocks + */ +static int ext4_calc_metadata_amount(struct inode *inode, int blocks) +{ + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_calc_metadata_amount(inode, blocks); + + return ext4_indirect_calc_metadata_amount(inode, blocks); +} + +static int ext4_da_reserve_space(struct inode *inode, int nrblocks) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + unsigned long md_needed, mdblocks, total = 0; + + /* + * recalculate the amount of metadata blocks to reserve + * in order to allocate nrblocks + * worse case is one extent per block + */ + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks; + mdblocks = ext4_calc_metadata_amount(inode, total); + BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks); + + md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks; + total = md_needed + nrblocks; + + if (ext4_has_free_blocks(sbi, total) < total) { + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + return -ENOSPC; + } + + /* reduce fs free blocks counter */ + percpu_counter_sub(&sbi->s_freeblocks_counter, total); + + EXT4_I(inode)->i_reserved_data_blocks += nrblocks; + EXT4_I(inode)->i_reserved_meta_blocks = mdblocks; + + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + return 0; /* success */ +} + +void ext4_da_release_space(struct inode *inode, int used, int to_free) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int total, mdb, mdb_free, release; + + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + /* recalculate the number of metablocks still need to be reserved */ + total = EXT4_I(inode)->i_reserved_data_blocks - used - to_free; + mdb = ext4_calc_metadata_amount(inode, total); + + /* figure out how many metablocks to release */ + BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks); + mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb; + + /* Account for allocated meta_blocks */ + mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks; + + release = to_free + mdb_free; + + /* update fs free blocks counter for truncate case */ + percpu_counter_add(&sbi->s_freeblocks_counter, release); + + /* update per-inode reservations */ + BUG_ON(used + to_free > EXT4_I(inode)->i_reserved_data_blocks); + EXT4_I(inode)->i_reserved_data_blocks -= (used + to_free); + + BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks); + EXT4_I(inode)->i_reserved_meta_blocks = mdb; + EXT4_I(inode)->i_allocated_meta_blocks = 0; + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); +} + +static void ext4_da_page_release_reservation(struct page *page, + unsigned long offset) +{ + int to_release = 0; + struct buffer_head *head, *bh; + unsigned int curr_off = 0; + + head = page_buffers(page); + bh = head; + do { + unsigned int next_off = curr_off + bh->b_size; + + if ((offset <= curr_off) && (buffer_delay(bh))) { + to_release++; + clear_buffer_delay(bh); + } + curr_off = next_off; + } while ((bh = bh->b_this_page) != head); + ext4_da_release_space(page->mapping->host, 0, to_release); +} /* * Delayed allocation stuff @@ -1829,14 +1967,18 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0); - if (ret == 0) { - /* the block isn't allocated yet, let's reserve space */ - /* XXX: call reservation here */ + ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0); + if ((ret == 0) && !buffer_delay(bh_result)) { + /* the block isn't (pre)allocated yet, let's reserve space */ /* * XXX: __block_prepare_write() unmaps passed block, * is it OK? */ + ret = ext4_da_reserve_space(inode, 1); + if (ret) + /* not enough space to reserve */ + return ret; + map_bh(bh_result, inode->i_sb, 0); set_buffer_new(bh_result); set_buffer_delay(bh_result); @@ -1847,7 +1989,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; } - +#define EXT4_DELALLOC_RSVED 1 static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -1865,7 +2007,7 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, } ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, - bh_result, create, 0); + bh_result, create, 0, EXT4_DELALLOC_RSVED); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); @@ -1952,7 +2094,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - int ret; + int ret, retries = 0; struct page *page; pgoff_t index; unsigned from, to; @@ -1963,6 +2105,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; +retry: /* * With delayed allocation, we don't log the i_disksize update * if there is delayed block allocation. But we still need @@ -1988,6 +2131,8 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, page_cache_release(page); } + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; out: return ret; } @@ -2040,9 +2185,6 @@ static int ext4_da_write_end(struct file *file, static void ext4_da_invalidatepage(struct page *page, unsigned long offset) { - struct buffer_head *head, *bh; - unsigned int curr_off = 0; - /* * Drop reserved blocks */ @@ -2050,21 +2192,7 @@ static void ext4_da_invalidatepage(struct page *page, unsigned long offset) if (!page_has_buffers(page)) goto out; - head = page_buffers(page); - bh = head; - do { - unsigned int next_off = curr_off + bh->b_size; - - /* - * is this block fully invalidated? - */ - if (offset <= curr_off && buffer_delay(bh)) { - clear_buffer_delay(bh); - /* XXX: add real stuff here */ - } - curr_off = next_off; - bh = bh->b_this_page; - } while (bh != head); + ext4_da_page_release_reservation(page, offset); out: ext4_invalidatepage(page, offset); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 8d254ca83d9..8d141a25bbe 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2964,7 +2964,15 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, le16_add_cpu(&gdp->bg_free_blocks_count, -ac->ac_b_ex.fe_len); gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp); spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group)); - percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len); + + /* + * free blocks account has already be reduced/reserved + * at write_begin() time for delayed allocation + * do not double accounting + */ + if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) + percpu_counter_sub(&sbi->s_freeblocks_counter, + ac->ac_b_ex.fe_len); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, @@ -4169,7 +4177,12 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, &(ar->len), errp); return block; } - ar->len = ext4_has_free_blocks(sbi, ar->len); + if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag) { + /* + * With delalloc we already reserved the blocks + */ + ar->len = ext4_has_free_blocks(sbi, ar->len); + } if (ar->len == 0) { *errp = -ENOSPC; @@ -4186,6 +4199,9 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, } inquota = ar->len; + if (EXT4_I(ar->inode)->i_delalloc_reserved_flag) + ar->flags |= EXT4_MB_DELALLOC_RESERVED; + ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index de9d3d0eb20..25e2f2488cd 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -574,6 +574,11 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ei->i_prealloc_list); spin_lock_init(&ei->i_prealloc_lock); jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode); + ei->i_reserved_data_blocks = 0; + ei->i_reserved_meta_blocks = 0; + ei->i_allocated_meta_blocks = 0; + ei->i_delalloc_reserved_flag = 0; + spin_lock_init(&(ei->i_block_reservation_lock)); return &ei->vfs_inode; } -- cgit v1.2.3 From dd919b9822c5fd9fd72f95a602440130297c3857 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: Enable delalloc by default. Enable delalloc by default to ensure it gets sufficient testing and because it makes the filesystem much more efficient. Add a nodealalloc option to disable delayed allocation, and update ext4_show_options to show delayed allocation off if it is disabled. If the data=journal mount option is used, disable delayed allocation since the delalloc code doesn't support data=journal yet. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" Signed-off-by: Mingming Cao --- fs/ext4/super.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 25e2f2488cd..4e104dd0ec2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -756,6 +756,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",nomballoc"); if (test_opt(sb, I_VERSION)) seq_puts(seq, ",i_version"); + if (!test_opt(sb, DELALLOC)) + seq_puts(seq, ",nodelalloc"); + if (sbi->s_stripe) seq_printf(seq, ",stripe=%lu", sbi->s_stripe); @@ -903,7 +906,7 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version, - Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, + Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, Opt_nodelalloc, }; static match_table_t tokens = { @@ -963,6 +966,7 @@ static match_table_t tokens = { {Opt_stripe, "stripe=%u"}, {Opt_resize, "resize"}, {Opt_delalloc, "delalloc"}, + {Opt_nodelalloc, "nodelalloc"}, {Opt_err, NULL}, }; @@ -1328,6 +1332,9 @@ set_qf_format: set_opt(sbi->s_mount_opt, I_VERSION); sb->s_flags |= MS_I_VERSION; break; + case Opt_nodelalloc: + clear_opt(sbi->s_mount_opt, DELALLOC); + break; case Opt_mballoc: set_opt(sbi->s_mount_opt, MBALLOC); break; @@ -1984,6 +1991,13 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) */ set_opt(sbi->s_mount_opt, MBALLOC); + /* + * enable delayed allocation by default + * Use -o nodelalloc to turn it off + */ + set_opt(sbi->s_mount_opt, DELALLOC); + + if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum, NULL, 0)) goto failed_mount; @@ -2422,6 +2436,13 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered": "writeback"); + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { + printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - " + "requested data journaling mode\n"); + clear_opt(sbi->s_mount_opt, DELALLOC); + } else if (test_opt(sb, DELALLOC)) + printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n"); + ext4_ext_init(sb); ext4_mb_init(sb, needs_recovery); -- cgit v1.2.3 From c07651b556323e0e763c452587fe29d2b034b314 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: Don't allow nonextenst mount option for large filesystem The block mapped inode format can address only blocks within 2**32. This causes a number of issues, the biggest of which is that the block allocator needs to be taught that certain inodes can not utilize block numbers > 2**32. So until this is fixed, it is simplest to fail mounting of file systems with more than 2**32 blocks if the -o noextents option is given. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4e104dd0ec2..2bf9cdd7a03 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1004,6 +1004,7 @@ static int parse_options (char *options, struct super_block *sb, int qtype, qfmt; char *qname; #endif + ext4_fsblk_t last_block; if (!options) return 1; @@ -1326,6 +1327,20 @@ set_qf_format: set_opt (sbi->s_mount_opt, EXTENTS); break; case Opt_noextents: + /* + * When e2fsprogs support resizing an already existing + * ext3 file system to greater than 2**32 we need to + * add support to block allocator to handle growing + * already existing block mapped inode so that blocks + * allocated for them fall within 2**32 + */ + last_block = ext4_blocks_count(sbi->s_es) - 1; + if (last_block > 0xffffffffULL) { + printk(KERN_ERR "EXT4-fs: Filesystem too " + "large to mount with " + "-o noextents options\n"); + return 0; + } clear_opt (sbi->s_mount_opt, EXTENTS); break; case Opt_i_version: -- cgit v1.2.3 From e4079a11f5ed966b7d972cc69e8d337a0f095e32 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: ext4: do not set extents feature from the kernel We've talked for a while about getting rid of any feature- setting from the kernel; this gets rid of the code which would set the INCOMPAT_EXTENTS flag on the first file write when mounted as ext4[dev]. With this patch, if the extents feature is not already set on disk, then mounting as ext4 will fall back to noextents with a warning, and if -o extents is explicitly requested, the mount will fail, also with warning. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ialloc.c | 6 +----- fs/ext4/super.c | 21 +++++++++++++++++---- 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 8b0a10acd70..a92eb305344 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -836,14 +836,10 @@ got: goto fail_free_drop; if (test_opt(sb, EXTENTS)) { - /* set extent flag only for diretory, file and normal symlink*/ + /* set extent flag only for directory, file and normal symlink*/ if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) { EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL; ext4_ext_tree_init(handle, inode); - err = ext4_update_incompat_feature(handle, sb, - EXT4_FEATURE_INCOMPAT_EXTENTS); - if (err) - goto fail_free_drop; } } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2bf9cdd7a03..1cb371dcd60 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1324,6 +1324,13 @@ set_qf_format: clear_opt(sbi->s_mount_opt, NOBH); break; case Opt_extents: + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_EXTENTS)) { + ext4_warning(sb, __func__, + "extents feature not enabled " + "on this filesystem, use tune2fs\n"); + return 0; + } set_opt (sbi->s_mount_opt, EXTENTS); break; case Opt_noextents: @@ -1997,12 +2004,18 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) /* * turn on extents feature by default in ext4 filesystem - * User -o noextents to turn it off + * only if feature flag already set by mkfs or tune2fs. + * Use -o noextents to turn it off */ - set_opt(sbi->s_mount_opt, EXTENTS); + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) + set_opt(sbi->s_mount_opt, EXTENTS); + else + ext4_warning(sb, __func__, + "extents feature not enabled on this filesystem, " + "use tune2fs.\n"); /* - * turn on mballoc feature by default in ext4 filesystem - * User -o nomballoc to turn it off + * turn on mballoc code by default in ext4 filesystem + * Use -o nomballoc to turn it off */ set_opt(sbi->s_mount_opt, MBALLOC); -- cgit v1.2.3