From: "Amit K. Arora" Subject: Re: [Patch 1/2] preallocation patch (using fallocate inode op) Date: Wed, 21 Mar 2007 18:01:29 +0530 Message-ID: <20070321123129.GC27273@amitarora.in.ibm.com> References: <1174319308.11636.8.camel@kleikamp.austin.ibm.com> <1174324522.11657.14.camel@localhost.localdomain> <20070321121951.GB27273@amitarora.in.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Dave Kleikamp , Theodore Tso , ext4 development To: Mingming Cao Return-path: Received: from e6.ny.us.ibm.com ([32.97.182.146]:43088 "EHLO e6.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752669AbXCUMcu (ORCPT ); Wed, 21 Mar 2007 08:32:50 -0400 Received: from d01relay02.pok.ibm.com (d01relay02.pok.ibm.com [9.56.227.234]) by e6.ny.us.ibm.com (8.13.8/8.13.8) with ESMTP id l2LCXa0w031539 for ; Wed, 21 Mar 2007 08:33:36 -0400 Received: from d01av01.pok.ibm.com (d01av01.pok.ibm.com [9.56.224.215]) by d01relay02.pok.ibm.com (8.13.8/8.13.8/NCO v8.3) with ESMTP id l2LCVWKE146060 for ; Wed, 21 Mar 2007 08:31:32 -0400 Received: from d01av01.pok.ibm.com (loopback [127.0.0.1]) by d01av01.pok.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id l2LCVVb4003921 for ; Wed, 21 Mar 2007 08:31:32 -0400 Content-Disposition: inline In-Reply-To: <20070321121951.GB27273@amitarora.in.ibm.com> Sender: linux-ext4-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org This is the new preallocation patch, which implements ext4_fallocate() to do the preallocation. Signed-off-by: Amit K Arora --- fs/ext4/extents.c | 201 +++++++++++++++++++++++++++++++--------- fs/ext4/file.c | 1 include/linux/ext4_fs.h | 7 + include/linux/ext4_fs_extents.h | 13 ++ 4 files changed, 179 insertions(+), 43 deletions(-) Index: linux-2.6.20.1/fs/ext4/extents.c =================================================================== --- linux-2.6.20.1.orig/fs/ext4/extents.c +++ linux-2.6.20.1/fs/ext4/extents.c @@ -283,7 +283,7 @@ static void ext4_ext_show_path(struct in } else if (path->p_ext) { ext_debug(" %d:%d:%llu ", le32_to_cpu(path->p_ext->ee_block), - le16_to_cpu(path->p_ext->ee_len), + ext4_ext_get_actual_len(path->p_ext), ext_pblock(path->p_ext)); } else ext_debug(" []"); @@ -306,7 +306,7 @@ static void ext4_ext_show_leaf(struct in for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block), - le16_to_cpu(ex->ee_len), ext_pblock(ex)); + ext4_ext_get_actual_len(ex), ext_pblock(ex)); } ext_debug("\n"); } @@ -426,7 +426,7 @@ ext4_ext_binsearch(struct inode *inode, ext_debug(" -> %d:%llu:%d ", le32_to_cpu(path->p_ext->ee_block), ext_pblock(path->p_ext), - le16_to_cpu(path->p_ext->ee_len)); + ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH { @@ -687,7 +687,7 @@ static int ext4_ext_split(handle_t *hand ext_debug("move %d:%llu:%d in new leaf %llu\n", le32_to_cpu(path[depth].p_ext->ee_block), ext_pblock(path[depth].p_ext), - le16_to_cpu(path[depth].p_ext->ee_len), + ext4_ext_get_actual_len(path[depth].p_ext), newblock); /*memmove(ex++, path[depth].p_ext++, sizeof(struct ext4_extent)); @@ -1107,7 +1107,19 @@ static int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { - if (le32_to_cpu(ex1->ee_block) + le16_to_cpu(ex1->ee_len) != + unsigned short ext1_ee_len, ext2_ee_len; + + /* + * Make sure that either both extents are uninitialized, or + * both are _not_. + */ + if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2)) + return 0; + + ext1_ee_len = ext4_ext_get_actual_len(ex1); + ext2_ee_len = ext4_ext_get_actual_len(ex2); + + if (le32_to_cpu(ex1->ee_block) + ext1_ee_len != le32_to_cpu(ex2->ee_block)) return 0; @@ -1116,14 +1128,14 @@ ext4_can_extents_be_merged(struct inode * as an RO_COMPAT feature, refuse to merge to extents if * this can result in the top bit of ee_len being set. */ - if (le16_to_cpu(ex1->ee_len) + le16_to_cpu(ex2->ee_len) > EXT_MAX_LEN) + if (ext1_ee_len + ext2_ee_len > EXT_MAX_LEN) return 0; #ifdef AGRESSIVE_TEST if (le16_to_cpu(ex1->ee_len) >= 4) return 0; #endif - if (ext_pblock(ex1) + le16_to_cpu(ex1->ee_len) == ext_pblock(ex2)) + if (ext_pblock(ex1) + ext1_ee_len == ext_pblock(ex2)) return 1; return 0; } @@ -1145,7 +1157,7 @@ unsigned int ext4_ext_check_overlap(stru unsigned int depth, len1; b1 = le32_to_cpu(newext->ee_block); - len1 = le16_to_cpu(newext->ee_len); + len1 = ext4_ext_get_actual_len(newext); depth = ext_depth(inode); if (!path[depth].p_ext) goto out; @@ -1181,9 +1193,9 @@ int ext4_ext_insert_extent(handle_t *han struct ext4_extent *ex, *fex; struct ext4_extent *nearex; /* nearest extent */ struct ext4_ext_path *npath = NULL; - int depth, len, err, next; + int depth, len, err, next, uninitialized = 0; - BUG_ON(newext->ee_len == 0); + BUG_ON(ext4_ext_get_actual_len(newext) == 0); depth = ext_depth(inode); ex = path[depth].p_ext; BUG_ON(path[depth].p_hdr == NULL); @@ -1191,14 +1203,23 @@ int ext4_ext_insert_extent(handle_t *han /* try to insert block into found extent and return */ if (ex && ext4_can_extents_be_merged(inode, ex, newext)) { ext_debug("append %d block to %d:%d (from %llu)\n", - le16_to_cpu(newext->ee_len), + ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), - le16_to_cpu(ex->ee_len), ext_pblock(ex)); + ext4_ext_get_actual_len(ex), ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; - ex->ee_len = cpu_to_le16(le16_to_cpu(ex->ee_len) - + le16_to_cpu(newext->ee_len)); + + /* ext4_can_extents_be_merged should have checked that either + * both extents are uninitialized, or both aren't. Thus we + * need to check only one of them here. + */ + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + + ext4_ext_get_actual_len(newext)); + if (uninitialized) + ext4_ext_mark_uninitialized(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; @@ -1254,7 +1275,7 @@ has_space: ext_debug("first extent in the leaf: %d:%llu:%d\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), - le16_to_cpu(newext->ee_len)); + ext4_ext_get_actual_len(newext)); path[depth].p_ext = EXT_FIRST_EXTENT(eh); } else if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { @@ -1267,7 +1288,7 @@ has_space: "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), - le16_to_cpu(newext->ee_len), + ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 2, nearex + 1, len); } @@ -1280,7 +1301,7 @@ has_space: "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext_pblock(newext), - le16_to_cpu(newext->ee_len), + ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 1, nearex, len); path[depth].p_ext = nearex; @@ -1299,8 +1320,13 @@ merge: if (!ext4_can_extents_be_merged(inode, nearex, nearex + 1)) break; /* merge with next extent! */ - nearex->ee_len = cpu_to_le16(le16_to_cpu(nearex->ee_len) - + le16_to_cpu(nearex[1].ee_len)); + if (ext4_ext_is_uninitialized(nearex)) + uninitialized = 1; + nearex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(nearex) + + ext4_ext_get_actual_len(nearex + 1)); + if (uninitialized) + ext4_ext_mark_uninitialized(nearex); + if (nearex + 1 < EXT_LAST_EXTENT(eh)) { len = (EXT_LAST_EXTENT(eh) - nearex - 1) * sizeof(struct ext4_extent); @@ -1370,8 +1396,8 @@ int ext4_ext_walk_space(struct inode *in end = le32_to_cpu(ex->ee_block); if (block + num < end) end = block + num; - } else if (block >= - le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len)) { + } else if (block >= le32_to_cpu(ex->ee_block) + + ext4_ext_get_actual_len(ex)) { /* need to allocate space after found extent */ start = block; end = block + num; @@ -1383,7 +1409,8 @@ int ext4_ext_walk_space(struct inode *in * by found extent */ start = block; - end = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len); + end = le32_to_cpu(ex->ee_block) + + ext4_ext_get_actual_len(ex); if (block + num < end) end = block + num; exists = 1; @@ -1399,7 +1426,7 @@ int ext4_ext_walk_space(struct inode *in cbex.ec_type = EXT4_EXT_CACHE_GAP; } else { cbex.ec_block = le32_to_cpu(ex->ee_block); - cbex.ec_len = le16_to_cpu(ex->ee_len); + cbex.ec_len = ext4_ext_get_actual_len(ex); cbex.ec_start = ext_pblock(ex); cbex.ec_type = EXT4_EXT_CACHE_EXTENT; } @@ -1472,15 +1499,15 @@ ext4_ext_put_gap_in_cache(struct inode * ext_debug("cache gap(before): %lu [%lu:%lu]", (unsigned long) block, (unsigned long) le32_to_cpu(ex->ee_block), - (unsigned long) le16_to_cpu(ex->ee_len)); + (unsigned long) ext4_ext_get_actual_len(ex)); } else if (block >= le32_to_cpu(ex->ee_block) - + le16_to_cpu(ex->ee_len)) { + + ext4_ext_get_actual_len(ex)) { lblock = le32_to_cpu(ex->ee_block) - + le16_to_cpu(ex->ee_len); + + ext4_ext_get_actual_len(ex); len = ext4_ext_next_allocated_block(path); ext_debug("cache gap(after): [%lu:%lu] %lu", (unsigned long) le32_to_cpu(ex->ee_block), - (unsigned long) le16_to_cpu(ex->ee_len), + (unsigned long) ext4_ext_get_actual_len(ex), (unsigned long) block); BUG_ON(len == lblock); len = len - lblock; @@ -1610,12 +1637,12 @@ static int ext4_remove_blocks(handle_t * unsigned long from, unsigned long to) { struct buffer_head *bh; + unsigned short ee_len = ext4_ext_get_actual_len(ex); int i; #ifdef EXTENTS_STATS { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - unsigned short ee_len = le16_to_cpu(ex->ee_len); spin_lock(&sbi->s_ext_stats_lock); sbi->s_ext_blocks += ee_len; sbi->s_ext_extents++; @@ -1629,12 +1656,12 @@ static int ext4_remove_blocks(handle_t * } #endif if (from >= le32_to_cpu(ex->ee_block) - && to == le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) { + && to == le32_to_cpu(ex->ee_block) + ee_len - 1) { /* tail removal */ unsigned long num; ext4_fsblk_t start; - num = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - from; - start = ext_pblock(ex) + le16_to_cpu(ex->ee_len) - num; + num = le32_to_cpu(ex->ee_block) + ee_len - from; + start = ext_pblock(ex) + ee_len - num; ext_debug("free last %lu blocks starting %llu\n", num, start); for (i = 0; i < num; i++) { bh = sb_find_get_block(inode->i_sb, start + i); @@ -1642,12 +1669,12 @@ static int ext4_remove_blocks(handle_t * } ext4_free_blocks(handle, inode, start, num); } else if (from == le32_to_cpu(ex->ee_block) - && to <= le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) { + && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) { printk("strange request: removal %lu-%lu from %u:%u\n", - from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len)); + from, to, le32_to_cpu(ex->ee_block), ee_len); } else { printk("strange request: removal(2) %lu-%lu from %u:%u\n", - from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len)); + from, to, le32_to_cpu(ex->ee_block), ee_len); } return 0; } @@ -1661,7 +1688,7 @@ ext4_ext_rm_leaf(handle_t *handle, struc struct ext4_extent_header *eh; unsigned a, b, block, num; unsigned long ex_ee_block; - unsigned short ex_ee_len; + unsigned short ex_ee_len, uninitialized = 0; struct ext4_extent *ex; ext_debug("truncate since %lu in leaf\n", start); @@ -1676,7 +1703,9 @@ ext4_ext_rm_leaf(handle_t *handle, struc ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); - ex_ee_len = le16_to_cpu(ex->ee_len); + if (ext4_ext_is_uninitialized(ex)) + uninitialized = 1; + ex_ee_len = ext4_ext_get_actual_len(ex); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { @@ -1744,6 +1773,8 @@ ext4_ext_rm_leaf(handle_t *handle, struc ex->ee_block = cpu_to_le32(block); ex->ee_len = cpu_to_le16(num); + if (uninitialized) + ext4_ext_mark_uninitialized(ex); err = ext4_ext_dirty(handle, inode, path + depth); if (err) @@ -1753,7 +1784,7 @@ ext4_ext_rm_leaf(handle_t *handle, struc ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); - ex_ee_len = le16_to_cpu(ex->ee_len); + ex_ee_len = ext4_ext_get_actual_len(ex); } if (correct_index && eh->eh_entries) @@ -2029,7 +2060,7 @@ int ext4_ext_get_blocks(handle_t *handle if (ex) { unsigned long ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext_pblock(ex); - unsigned short ee_len = le16_to_cpu(ex->ee_len); + unsigned short ee_len; /* * Allow future support for preallocated extents to be added @@ -2037,8 +2068,9 @@ int ext4_ext_get_blocks(handle_t *handle * Uninitialized extents are treated as holes, except that * we avoid (fail) allocating new blocks during a write. */ - if (ee_len > EXT_MAX_LEN) + if (le16_to_cpu(ex->ee_len) > EXT_MAX_LEN) goto out2; + ee_len = ext4_ext_get_actual_len(ex); /* if found extent covers block, simply return it */ if (iblock >= ee_block && iblock < ee_block + ee_len) { newblock = iblock - ee_block + ee_start; @@ -2046,8 +2078,11 @@ int ext4_ext_get_blocks(handle_t *handle allocated = ee_len - (iblock - ee_block); ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock, ee_block, ee_len, newblock); - ext4_ext_put_in_cache(inode, ee_block, ee_len, - ee_start, EXT4_EXT_CACHE_EXTENT); + /* Do not put uninitialized extent in the cache */ + if (!ext4_ext_is_uninitialized(ex)) + ext4_ext_put_in_cache(inode, ee_block, + ee_len, ee_start, + EXT4_EXT_CACHE_EXTENT); goto out; } } @@ -2089,6 +2124,8 @@ int ext4_ext_get_blocks(handle_t *handle /* try to insert new extent into found leaf and return */ ext4_ext_store_pblock(&newex, newblock); newex.ee_len = cpu_to_le16(allocated); + if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */ + ext4_ext_mark_uninitialized(&newex); err = ext4_ext_insert_extent(handle, inode, path, &newex); if (err) goto out2; @@ -2100,8 +2137,10 @@ int ext4_ext_get_blocks(handle_t *handle newblock = ext_pblock(&newex); __set_bit(BH_New, &bh_result->b_state); - ext4_ext_put_in_cache(inode, iblock, allocated, newblock, - EXT4_EXT_CACHE_EXTENT); + /* Cache only when it is _not_ an uninitialized extent */ + if (create!=EXT4_CREATE_UNINITIALIZED_EXT) + ext4_ext_put_in_cache(inode, iblock, allocated, newblock, + EXT4_EXT_CACHE_EXTENT); out: if (allocated > max_blocks) allocated = max_blocks; @@ -2205,10 +2244,86 @@ int ext4_ext_writepage_trans_blocks(stru return needed; } +/* + * ext4_fallocate: + * preallocate space for a file + * mode is for future use, e.g. for unallocating preallocated blocks etc. + */ +int ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) +{ + handle_t *handle; + ext4_fsblk_t block, max_blocks; + int ret, ret2, nblocks = 0, retries = 0; + struct buffer_head map_bh; + unsigned int credits, blkbits = inode->i_blkbits; + + /* Currently supporting (pre)allocate mode _only_ */ + if (mode != FA_ALLOCATE) + return -EOPNOTSUPP; + + if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + return -ENOTTY; + + block = offset >> blkbits; + max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) + - block; + mutex_lock(&EXT4_I(inode)->truncate_mutex); + credits = ext4_ext_calc_credits_for_insert(inode, NULL); + mutex_unlock(&EXT4_I(inode)->truncate_mutex); + handle=ext4_journal_start(inode, credits + + EXT4_DATA_TRANS_BLOCKS(inode->i_sb)+1); + if (IS_ERR(handle)) + return PTR_ERR(handle); +retry: + ret = 0; + while (ret >= 0 && ret < max_blocks) { + block = block + ret; + max_blocks = max_blocks - ret; + ret = ext4_ext_get_blocks(handle, inode, block, + max_blocks, &map_bh, + EXT4_CREATE_UNINITIALIZED_EXT, 0); + BUG_ON(!ret); + if (ret > 0 && test_bit(BH_New, &map_bh.b_state) + && ((block + ret) > (i_size_read(inode) << blkbits))) + nblocks = nblocks + ret; + } + + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + + /* Time to update the file size. + * Update only when preallocation was requested beyond the file size. + */ + if ((offset + len) > i_size_read(inode)) { + if (ret > 0) { + /* if no error, we assume preallocation succeeded completely */ + mutex_lock(&inode->i_mutex); + i_size_write(inode, offset + len); + EXT4_I(inode)->i_disksize = i_size_read(inode); + mutex_unlock(&inode->i_mutex); + } else if (ret < 0 && nblocks) { + /* Handle partial allocation scenario */ + loff_t newsize; + mutex_lock(&inode->i_mutex); + newsize = (nblocks << blkbits) + i_size_read(inode); + i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits)); + EXT4_I(inode)->i_disksize = i_size_read(inode); + mutex_unlock(&inode->i_mutex); + } + } + ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_journal_stop(handle); + if (ret > 0) + ret = ret2; + + return ret > 0 ? 0 : ret; +} + EXPORT_SYMBOL(ext4_mark_inode_dirty); EXPORT_SYMBOL(ext4_ext_invalidate_cache); EXPORT_SYMBOL(ext4_ext_insert_extent); EXPORT_SYMBOL(ext4_ext_walk_space); EXPORT_SYMBOL(ext4_ext_find_goal); EXPORT_SYMBOL(ext4_ext_calc_credits_for_insert); +EXPORT_SYMBOL(ext4_fallocate); Index: linux-2.6.20.1/include/linux/ext4_fs.h =================================================================== --- linux-2.6.20.1.orig/include/linux/ext4_fs.h +++ linux-2.6.20.1/include/linux/ext4_fs.h @@ -102,6 +102,8 @@ EXT4_GOOD_OLD_FIRST_INO : \ (s)->s_first_ino) #endif +#define EXT4_BLOCK_ALIGN(size, blkbits) (((size)+(1 << blkbits)-1) & \ + (~((1 << blkbits)-1))) /* * Macro-instructions used to manage fragments @@ -225,6 +227,10 @@ struct ext4_new_group_data { __u32 free_blocks_count; }; +/* Following is used by preallocation logic to tell get_blocks() that we + * want uninitialzed extents. + */ +#define EXT4_CREATE_UNINITIALIZED_EXT 2 /* * ioctl commands @@ -976,6 +982,7 @@ extern int ext4_ext_get_blocks(handle_t extern void ext4_ext_truncate(struct inode *, struct page *); extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); +extern int ext4_fallocate(struct inode *, int, loff_t, loff_t); static inline int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, Index: linux-2.6.20.1/include/linux/ext4_fs_extents.h =================================================================== --- linux-2.6.20.1.orig/include/linux/ext4_fs_extents.h +++ linux-2.6.20.1/include/linux/ext4_fs_extents.h @@ -125,6 +125,19 @@ struct ext4_ext_path { #define EXT4_EXT_CACHE_EXTENT 2 /* + * Macro-instructions to handle (mark/unmark/check/create) unitialized + * extents. Applications can issue an IOCTL for preallocation, which results + * in assigning unitialized extents to the file. + */ +#define ext4_ext_mark_uninitialized(ext) ((ext)->ee_len |= \ + cpu_to_le16(0x8000)) +#define ext4_ext_is_uninitialized(ext) ((le16_to_cpu((ext)->ee_len))& \ + 0x8000) +#define ext4_ext_get_actual_len(ext) ((le16_to_cpu((ext)->ee_len))& \ + 0x7FFF) + + +/* * to be called by ext4_ext_walk_space() * negative retcode - error * positive retcode - signal for ext4_ext_walk_space(), see below Index: linux-2.6.20.1/fs/ext4/file.c =================================================================== --- linux-2.6.20.1.orig/fs/ext4/file.c +++ linux-2.6.20.1/fs/ext4/file.c @@ -135,5 +135,6 @@ struct inode_operations ext4_file_inode_ .removexattr = generic_removexattr, #endif .permission = ext4_permission, + .fallocate = ext4_fallocate, };