From 88aa3cff4e9a38b953de9fbc54c96e619a2bb9f9 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 16 Aug 2008 07:57:35 -0400 Subject: ext4: Use ext4_discard_reservations instead of mballoc-specific call In ext4_ext_truncate(), we should use the more generic ext4_discard_reservations() call so we do the right thing when the filesystem is mounted with the nomballoc option. Signed-off-by: "Theodore Ts'o" Reviewed-by: Mingming Cao --- fs/ext4/extents.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 612c3d2c3824..7212947a8ca3 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2819,7 +2819,7 @@ void ext4_ext_truncate(struct inode *inode) down_write(&EXT4_I(inode)->i_data_sem); ext4_ext_invalidate_cache(inode); - ext4_mb_discard_inode_preallocations(inode); + ext4_discard_reservation(inode); /* * TODO: optimization is possible here. -- cgit v1.2.2 From ee12b630687d510f6f4b6d4acdc4e267fd4adeda Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Tue, 19 Aug 2008 22:16:05 -0400 Subject: ext4: journal credits reservation fixes for extent file writepage This patch modified the writepage/write_begin credit calculation for extent files, to use the credits caculation helper function. The current calculation of how many index/leaf blocks should be accounted is too conservetive, it always considered the worse case, where the tree level is 5, and in the case of multiple chunk allocations, it always assumed no blocks were dirtied in common across the allocations. This path uses the accurate depth of the inode with some extras to calculate the index blocks, and also less conservative in the case of multiple allocation accounting. Signed-off-by: Mingming Cao Reviewed-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 104 +++++++++++++++++++++++------------------------------- 1 file changed, 44 insertions(+), 60 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7212947a8ca3..5c5dd3a1d657 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1747,54 +1747,61 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, } /* - * ext4_ext_calc_credits_for_insert: - * This routine returns max. credits that the extent tree can consume. - * It should be OK for low-performance paths like ->writepage() - * To allow many writing processes to fit into a single transaction, - * the caller should calculate credits under i_data_sem and - * pass the actual path. + * ext4_ext_calc_credits_for_single_extent: + * This routine returns max. credits that needed to insert an extent + * to the extent tree. + * When pass the actual path, the caller should calculate credits + * under i_data_sem. */ -int ext4_ext_calc_credits_for_insert(struct inode *inode, +int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, struct ext4_ext_path *path) { - int depth, needed; - if (path) { + int depth = ext_depth(inode); + int ret; + /* probably there is space in leaf? */ - depth = ext_depth(inode); if (le16_to_cpu(path[depth].p_hdr->eh_entries) - < le16_to_cpu(path[depth].p_hdr->eh_max)) - return 1; - } + < le16_to_cpu(path[depth].p_hdr->eh_max)) { - /* - * given 32-bit logical block (4294967296 blocks), max. tree - * can be 4 levels in depth -- 4 * 340^4 == 53453440000. - * Let's also add one more level for imbalance. - */ - depth = 5; - - /* allocation of new data block(s) */ - needed = 2; + /* + * There are some space in the leaf tree, no + * need to account for leaf block credit + * + * bitmaps and block group descriptor blocks + * and other metadat blocks still need to be + * accounted. + */ + /* 1 one bitmap, 1 block group descriptor */ + ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); + } + } - /* - * tree can be full, so it would need to grow in depth: - * we need one credit to modify old root, credits for - * new root will be added in split accounting - */ - needed += 1; + return ext4_meta_trans_blocks(inode, num, 1); +} - /* - * Index split can happen, we would need: - * allocate intermediate indexes (bitmap + group) - * + change two blocks at each level, but root (already included) - */ - needed += (depth * 2) + (depth * 2); +/* + * How many index/leaf blocks need to change/allocate to modify nrblocks? + * + * if nrblocks are fit in a single extent (chunk flag is 1), then + * in the worse case, each tree level index/leaf need to be changed + * if the tree split due to insert a new extent, then the old tree + * index/leaf need to be updated too + * + * If the nrblocks are discontiguous, they could cause + * the whole tree split more than once, but this is really rare. + */ +int ext4_ext_index_trans_blocks(struct inode *inode, int num, int chunk) +{ + int index; + int depth = ext_depth(inode); - /* any allocation modifies superblock */ - needed += 1; + if (chunk) + index = depth * 2; + else + index = depth * 3; - return needed; + return index; } static int ext4_remove_blocks(handle_t *handle, struct inode *inode, @@ -1921,9 +1928,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, correct_index = 1; credits += (ext_depth(inode)) + 1; } -#ifdef CONFIG_QUOTA credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); -#endif err = ext4_ext_journal_restart(handle, credits); if (err) @@ -2858,27 +2863,6 @@ out_stop: ext4_journal_stop(handle); } -/* - * ext4_ext_writepage_trans_blocks: - * calculate max number of blocks we could modify - * in order to allocate new block for an inode - */ -int ext4_ext_writepage_trans_blocks(struct inode *inode, int num) -{ - int needed; - - needed = ext4_ext_calc_credits_for_insert(inode, NULL); - - /* caller wants to allocate num blocks, but note it includes sb */ - needed = needed * num - (num - 1); - -#ifdef CONFIG_QUOTA - needed += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); -#endif - - return needed; -} - static void ext4_falloc_update_inode(struct inode *inode, int mode, loff_t new_size, int update_ctime) { -- cgit v1.2.2 From f3bd1f3fa8ca7ec70cfd87aa94dc5e1a260901f2 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Tue, 19 Aug 2008 22:16:03 -0400 Subject: 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 Reviewed-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5c5dd3a1d657..5596b70efa20 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) { -- cgit v1.2.2 From 525f4ed8dcb72c71b306a78ecbf06f41d08fe441 Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Tue, 19 Aug 2008 22:15:58 -0400 Subject: ext4: journal credit fix for the delayed allocation's writepages() function Previous delalloc writepages implementation started a new transaction outside of a loop which called get_block() to do the block allocation. Since we didn't know exactly how many blocks would need to be allocated, the estimated journal credits required was very conservative and caused many issues. With the reworked delayed allocation, a new transaction is created for each get_block(), thus we don't need to guess how many credits for the multiple chunk of allocation. We start every transaction with enough credits for inserting a single exent. When estimate the credits for indirect blocks to allocate a chunk of blocks, we need to know the number of data blocks to allocate. We use the total number of reserved delalloc datablocks; if that is too big, for non-extent files, we need to limit the number of blocks to EXT4_MAX_TRANS_BLOCKS. Code cleanup from Aneesh. Signed-off-by: Mingming Cao Reviewed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5596b70efa20..b24d3c53f20c 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1753,7 +1753,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, * When pass the actual path, the caller should calculate credits * under i_data_sem. */ -int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, +int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, struct ext4_ext_path *path) { if (path) { @@ -1772,12 +1772,12 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, * and other metadat blocks still need to be * accounted. */ - /* 1 one bitmap, 1 block group descriptor */ + /* 1 bitmap, 1 block group descriptor */ ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); } } - return ext4_chunk_trans_blocks(inode, num); + return ext4_chunk_trans_blocks(inode, nrblocks); } /* @@ -1791,7 +1791,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, * If the nrblocks are discontiguous, they could cause * the whole tree split more than once, but this is really rare. */ -int ext4_ext_index_trans_blocks(struct inode *inode, int num, int chunk) +int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) { int index; int depth = ext_depth(inode); -- cgit v1.2.2