diff options
author | Mingming Cao <cmm@us.ibm.com> | 2008-08-19 22:16:03 -0400 |
---|---|---|
committer | Theodore Ts'o <tytso@mit.edu> | 2008-08-19 22:16:03 -0400 |
commit | f3bd1f3fa8ca7ec70cfd87aa94dc5e1a260901f2 (patch) | |
tree | a0f0ce2e044f8a75009e94d5f788b45a3948bbe3 /fs | |
parent | ee12b630687d510f6f4b6d4acdc4e267fd4adeda (diff) | |
download | op-kernel-dev-f3bd1f3fa8ca7ec70cfd87aa94dc5e1a260901f2.zip op-kernel-dev-f3bd1f3fa8ca7ec70cfd87aa94dc5e1a260901f2.tar.gz |
ext4: journal credits reservation fixes for DIO, fallocate
DIO and fallocate credit calculation is different than writepage, as
they do start a new journal right for each call to ext4_get_blocks_wrap().
This patch uses the helper function in DIO and fallocate case, passing
a flag indicating that the modified data are contigous thus could account
less indirect/index blocks.
This patch also fixed the journal credit reservation for direct I/O
(DIO). Previously the estimated credits for DIO only was calculated for
non-extent files, which was not enough if the file is extent-based.
Also fixed was fallocate double-counting credits for modifying the the
superblock.
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs')
-rw-r--r-- | fs/ext4/ext4.h | 1 | ||||
-rw-r--r-- | fs/ext4/extents.c | 11 | ||||
-rw-r--r-- | fs/ext4/inode.c | 45 |
3 files changed, 30 insertions, 27 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 38e661b..2950032 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1073,6 +1073,7 @@ extern void ext4_get_inode_flags(struct ext4_inode_info *); 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); +extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5c5dd3a..5596b70 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1758,7 +1758,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, { if (path) { int depth = ext_depth(inode); - int ret; + int ret = 0; /* probably there is space in leaf? */ if (le16_to_cpu(path[depth].p_hdr->eh_entries) @@ -1777,7 +1777,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, } } - return ext4_meta_trans_blocks(inode, num, 1); + return ext4_chunk_trans_blocks(inode, num); } /* @@ -2810,7 +2810,7 @@ void ext4_ext_truncate(struct inode *inode) /* * probably first extent we're gonna free will be last in block */ - err = ext4_writepage_trans_blocks(inode) + 3; + err = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, err); if (IS_ERR(handle)) return; @@ -2923,10 +2923,9 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) - block; /* - * credits to insert 1 extent into extent tree + buffers to be able to - * modify 1 super block, 1 block bitmap and 1 group descriptor. + * credits to insert 1 extent into extent tree */ - credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3; + credits = ext4_chunk_trans_blocks(inode, max_blocks); mutex_lock(&inode->i_mutex); retry: while (ret >= 0 && ret < max_blocks) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a271290..ffc95ba 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1044,18 +1044,6 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); } -/* Maximum number of blocks we map for direct IO at once. */ -#define DIO_MAX_BLOCKS 4096 -/* - * Number of credits we need for writing DIO_MAX_BLOCKS: - * We need sb + group descriptor + bitmap + inode -> 4 - * For B blocks with A block pointers per block we need: - * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect). - * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25. - */ -#define DIO_CREDITS 25 - - /* * The ext4_get_blocks_wrap() function try to look up the requested blocks, * and returns if the blocks are already mapped. @@ -1167,19 +1155,23 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, return retval; } +/* Maximum number of blocks we map for direct IO at once. */ +#define DIO_MAX_BLOCKS 4096 + static int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { handle_t *handle = ext4_journal_current_handle(); int ret = 0, started = 0; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + int dio_credits; if (create && !handle) { /* Direct IO write... */ if (max_blocks > DIO_MAX_BLOCKS) max_blocks = DIO_MAX_BLOCKS; - handle = ext4_journal_start(inode, DIO_CREDITS + - 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb)); + dio_credits = ext4_chunk_trans_blocks(inode, max_blocks); + handle = ext4_journal_start(inode, dio_credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; @@ -2243,7 +2235,7 @@ static int ext4_da_writepage(struct page *page, * for DIO, writepages, and truncate */ #define EXT4_MAX_WRITEBACK_PAGES DIO_MAX_BLOCKS -#define EXT4_MAX_WRITEBACK_CREDITS DIO_CREDITS +#define EXT4_MAX_WRITEBACK_CREDITS 25 static int ext4_da_writepages(struct address_space *mapping, struct writeback_control *wbc) @@ -4441,7 +4433,8 @@ int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) /* * Calulate the total number of credits to reserve to fit - * the modification of a single pages into a single transaction + * the modification of a single pages into a single transaction, + * which may include multiple chunks of block allocations. * * This could be called via ext4_write_begin() or later * ext4_da_writepages() in delalyed allocation case. @@ -4449,11 +4442,6 @@ int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) * In both case it's possible that we could allocating multiple * chunks of blocks. We need to consider the worse case, when * one new block per extent. - * - * For Direct IO and fallocate, the journal credits reservation - * is based on one single extent allocation, so they could use - * EXT4_DATA_TRANS_BLOCKS to get the needed credit to log a single - * chunk of allocation needs. */ int ext4_writepage_trans_blocks(struct inode *inode) { @@ -4467,6 +4455,21 @@ int ext4_writepage_trans_blocks(struct inode *inode) ret += bpp; return ret; } + +/* + * Calculate the journal credits for a chunk of data modification. + * + * This is called from DIO, fallocate or whoever calling + * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks. + * + * journal buffers for data blocks are not included here, as DIO + * and fallocate do no need to journal data buffers. + */ +int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) +{ + return ext4_meta_trans_blocks(inode, nrblocks, 1); +} + /* * The caller must have previously called ext4_reserve_inode_write(). * Give this, we know that the caller already has write access to iloc->bh. |