ext4: online defrag -- Exchange the extents between two inodes From: Akira Fujita <a-fujita@xxxxxxxxxxxxx> For each page, exchange the extents between the temporary inode and the original inode, and then write them. Signed-off-by: Akira Fujita <a-fujita@xxxxxxxxxxxxx> Signed-off-by: Takashi Sato <t-sato@xxxxxxxxxxxxx> --- fs/ext4/defrag.c | 477 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 files changed, 476 insertions(+), 1 deletions(-) diff --git a/fs/ext4/defrag.c b/fs/ext4/defrag.c index 729f001..0b90d4d 100644 --- a/fs/ext4/defrag.c +++ b/fs/ext4/defrag.c @@ -91,6 +91,361 @@ err: } /** + * ext4_defrag_merge_extents - Merge new extent + * + * @handle: journal handle + * @org_inode: original inode + * @org_path: path indicates first extent to be defraged + * @o_start: first original extent to be defraged + * @o_end: last original extent to be defraged + * @start_ext: first new extent to be merged + * @new_ext: middle of new extent to be merged + * @end_ext: last new extent to be merged + * @replaced: the number of blocks which will be replaced with new_ext + * + * This function returns 0 if succeed, otherwise returns error value. + */ +static int +ext4_defrag_merge_extents(handle_t *handle, struct inode *org_inode, + struct ext4_ext_path *org_path, + struct ext4_extent *o_start, struct ext4_extent *o_end, + struct ext4_extent *start_ext, struct ext4_extent *new_ext, + struct ext4_extent *end_ext, ext4_fsblk_t replaced) +{ + return 0; +} + +/** + * ext4_defrag_leaf_block - Defragmentation for one leaf extent block + * + * @handle: journal handle + * @org_inode: original inode + * @org_path: path indicates first extent to be defraged + * @dext: destination extent + * @from: start offset on the target file + * + * This function returns 0 if succeed, otherwise returns error value. + */ +static int +ext4_defrag_leaf_block(handle_t *handle, struct inode *org_inode, + struct ext4_ext_path *org_path, struct ext4_extent *dext, + ext4_lblk_t *from) +{ + struct ext4_extent *oext, *o_start = NULL, *o_end = NULL, *prev_ext; + struct ext4_extent new_ext, start_ext, end_ext; + ext4_fsblk_t replaced = 0; + ext4_lblk_t new_end, lblock; + unsigned long depth; + unsigned short len; + ext4_fsblk_t new_phys_end; + int ret; + + depth = ext_depth(org_inode); + start_ext.ee_len = end_ext.ee_len = 0; + o_start = o_end = oext = org_path[depth].p_ext; + ext4_ext_store_pblock(&new_ext, ext_pblock(dext)); + new_ext.ee_len = dext->ee_len; + len = le16_to_cpu(new_ext.ee_len); + new_ext.ee_block = cpu_to_le32(*from); + lblock = le32_to_cpu(oext->ee_block); + new_end = le32_to_cpu(new_ext.ee_block) + + le16_to_cpu(new_ext.ee_len) - 1; + new_phys_end = ext_pblock(&new_ext) + + le16_to_cpu(new_ext.ee_len) - 1; + + /* + * First original extent + * dest |---------------| + * org |---------------| + */ + if (le32_to_cpu(new_ext.ee_block) > + le32_to_cpu(oext->ee_block) && + le32_to_cpu(new_ext.ee_block) < + le32_to_cpu(oext->ee_block) + + le16_to_cpu(oext->ee_len)) { + start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) + - le32_to_cpu(oext->ee_block)); + replaced += le16_to_cpu(oext->ee_len) + - le16_to_cpu(start_ext.ee_len); + } else if (oext > EXT_FIRST_EXTENT(org_path[depth].p_hdr)) { + /* We can merge previous extent. */ + prev_ext = oext - 1; + if (((ext_pblock(prev_ext) + le16_to_cpu(prev_ext->ee_len)) + == ext_pblock(&new_ext)) + && (le32_to_cpu(prev_ext->ee_block) + + le16_to_cpu(prev_ext->ee_len) + == le32_to_cpu(new_ext.ee_block))) { + o_start = prev_ext; + start_ext.ee_len = cpu_to_le16( + le16_to_cpu(prev_ext->ee_len) + + le16_to_cpu(new_ext.ee_len)); + new_ext.ee_len = 0; + } + } + + for (;;) { + /* The extent for destination must be found. */ + BUG_ON(!oext || lblock != le32_to_cpu(oext->ee_block)); + lblock += le16_to_cpu(oext->ee_len); + + /* + * Middle of original extent + * dest |-------------------| + * org |-----------------| + */ + if (le32_to_cpu(new_ext.ee_block) <= + le32_to_cpu(oext->ee_block) && + new_end >= le32_to_cpu(oext->ee_block) + + le16_to_cpu(oext->ee_len) - 1) + replaced += le16_to_cpu(oext->ee_len); + + /* + * Last original extent + * dest |----------------| + * org |---------------| + */ + if (new_end >= le32_to_cpu(oext->ee_block) && + new_end < le32_to_cpu(oext->ee_block) + + le16_to_cpu(oext->ee_len) - 1) { + end_ext.ee_len + = cpu_to_le16(le32_to_cpu(oext->ee_block) + + le16_to_cpu(oext->ee_len) - 1 - new_end); + ext4_ext_store_pblock(&end_ext, (ext_pblock(o_end) + + le16_to_cpu(oext->ee_len) + - le16_to_cpu(end_ext.ee_len))); + end_ext.ee_block + = cpu_to_le32(le32_to_cpu(o_end->ee_block) + + le16_to_cpu(oext->ee_len) + - le16_to_cpu(end_ext.ee_len)); + replaced += le16_to_cpu(oext->ee_len) + - le16_to_cpu(end_ext.ee_len); + } + + /* + * Detected the block end, reached the number of replaced + * blocks to dext->ee_len. Then merge the extent. + */ + if (oext == EXT_LAST_EXTENT(org_path[depth].p_hdr) || + new_end <= le32_to_cpu(oext->ee_block) + + le16_to_cpu(oext->ee_len) - 1) { + ret = ext4_defrag_merge_extents(handle, org_inode, + org_path, o_start, o_end, &start_ext, + &new_ext, &end_ext, replaced); + if (ret < 0) + return ret; + + /* All expected blocks are replaced */ + if (le16_to_cpu(new_ext.ee_len) <= 0) + return 0; + + /* Re-calculate new_ext */ + le16_add_cpu(&new_ext.ee_len, -replaced); + le32_add_cpu(&new_ext.ee_block, replaced); + ext4_ext_store_pblock(&new_ext, ext_pblock(&new_ext) + + replaced); + replaced = 0; + start_ext.ee_len = end_ext.ee_len = 0; + o_start = NULL; + + /* All expected blocks are replaced. */ + if (le16_to_cpu(new_ext.ee_len) <= 0) + return 0; + } + + /* Get the next extent for original. */ + if (org_path) + ext4_ext_drop_refs(org_path); + org_path = ext4_ext_find_extent(org_inode, lblock, org_path); + if (IS_ERR(org_path)) { + ret = PTR_ERR(org_path); + org_path = NULL; + return ret; + } + depth = ext_depth(org_inode); + oext = org_path[depth].p_ext; + if (le32_to_cpu(oext->ee_block) + le16_to_cpu(oext->ee_len) + <= lblock) + return -ENOENT; + + o_end = oext; + if (!o_start) + o_start = oext; + } +} + +/** + * ext4_defrag_replace_branches - Replace original extents with new extents + * + * @handle: journal handle + * @org_inode: original inode + * @dest_inode: temporary inode + * @from: block offset of org_inode + * @dest_off: block offset of dest_inode + * @count: block count to be replaced + * + * This function returns 0 if succeed, otherwise returns error value. + * Replace extents for blocks from "from" to "from + count - 1". + */ +static int +ext4_defrag_replace_branches(handle_t *handle, struct inode *org_inode, + struct inode *dest_inode, ext4_lblk_t from, + ext4_lblk_t dest_off, ext4_lblk_t count) +{ + struct ext4_ext_path *org_path = NULL; + struct ext4_ext_path *dest_path = NULL; + struct ext4_extent *oext, *dext, *swap_ext; + struct ext4_extent tmp_ext, tmp_ext2; + ext4_lblk_t diff, org_diff; + int err = 0; + int depth; + int replaced_count = 0; + + /* Get the original extent for the block "from" */ + org_path = ext4_ext_find_extent(org_inode, from, NULL); + if (IS_ERR(org_path)) { + err = PTR_ERR(org_path); + org_path = NULL; + goto out; + } + + /* Get the destination extent for the head */ + dest_path = ext4_ext_find_extent(dest_inode, dest_off, NULL); + if (IS_ERR(dest_path)) { + err = PTR_ERR(dest_path); + dest_path = NULL; + goto out; + } + depth = ext_depth(dest_inode); + dext = dest_path[depth].p_ext; + /* When dext is too large, pick up the target range. */ + diff = dest_off - le32_to_cpu(dext->ee_block); + ext4_ext_store_pblock(&tmp_ext, ext_pblock(dext) + diff); + tmp_ext.ee_block = cpu_to_le32(le32_to_cpu(dext->ee_block) + diff); + tmp_ext.ee_len = cpu_to_le16(le16_to_cpu(dext->ee_len) - diff); + if (count < le16_to_cpu(tmp_ext.ee_len)) + tmp_ext.ee_len = cpu_to_le16(count); + dext = &tmp_ext; + + depth = ext_depth(org_inode); + oext = org_path[depth].p_ext; + org_diff = from - le32_to_cpu(oext->ee_block); + ext4_ext_store_pblock(&tmp_ext2, ext_pblock(oext) + org_diff); + tmp_ext2.ee_block = tmp_ext.ee_block; + + /* Adjust extent length when blocksize != pagesize */ + if (le16_to_cpu(tmp_ext.ee_len) <= + le16_to_cpu(oext->ee_len) - org_diff) { + tmp_ext2.ee_len = tmp_ext.ee_len; + } else { + tmp_ext2.ee_len = cpu_to_le16(le16_to_cpu(oext->ee_len) + - org_diff); + tmp_ext.ee_len = tmp_ext2.ee_len; + } + swap_ext = &tmp_ext2; + + /* Loop for the destination extents */ + while (1) { + /* The extent for destination must be found. */ + BUG_ON(!dext || dest_off != le32_to_cpu(dext->ee_block)); + + /* Loop for the original extent blocks */ + err = ext4_defrag_leaf_block(handle, org_inode, + org_path, dext, &from); + if (err < 0) + goto out; + + /* + * We need the function which fixes extent information for + * inserting. + * e.g. ext4_defrag_merge_extents() + */ + err = ext4_defrag_leaf_block(handle, dest_inode, + dest_path, swap_ext, &dest_off); + if (err < 0) + goto out; + + replaced_count += le16_to_cpu(dext->ee_len); + dest_off += le16_to_cpu(dext->ee_len); + from += le16_to_cpu(dext->ee_len); + + /* Already moved the expected blocks */ + if (replaced_count >= count) + break; + + if (org_path) + ext4_ext_drop_refs(org_path); + org_path = ext4_ext_find_extent(org_inode, from, NULL); + if (IS_ERR(org_path)) { + err = PTR_ERR(org_path); + org_path = NULL; + goto out; + } + depth = ext_depth(org_inode); + oext = org_path[depth].p_ext; + if (le32_to_cpu(oext->ee_block) + le16_to_cpu(oext->ee_len) + <= from) { + err = 0; + goto out; + } + + if (dest_path) + ext4_ext_drop_refs(dest_path); + dest_path = ext4_ext_find_extent(dest_inode, dest_off, NULL); + if (IS_ERR(dest_path)) { + err = PTR_ERR(dest_path); + dest_path = NULL; + goto out; + } + depth = ext_depth(dest_inode); + dext = dest_path[depth].p_ext; + if (le32_to_cpu(dext->ee_block) + le16_to_cpu(dext->ee_len) + <= dest_off) { + err = 0; + goto out; + } + + /* When dext is too large, pick up the target range. */ + diff = dest_off - le32_to_cpu(dext->ee_block); + ext4_ext_store_pblock(&tmp_ext, ext_pblock(dext) + diff); + tmp_ext.ee_block = + cpu_to_le32(le32_to_cpu(dext->ee_block) + diff); + tmp_ext.ee_len = cpu_to_le16(le16_to_cpu(dext->ee_len) - diff); + + if (count - replaced_count < le16_to_cpu(tmp_ext.ee_len)) + tmp_ext.ee_len = cpu_to_le16(count - replaced_count); + + dext = &tmp_ext; + + org_diff = from - le32_to_cpu(oext->ee_block); + ext4_ext_store_pblock(&tmp_ext2, ext_pblock(oext) + org_diff); + tmp_ext2.ee_block = tmp_ext.ee_block; + + /* Adjust extent length when blocksize != pagesize */ + if (le16_to_cpu(tmp_ext.ee_len) <= + le16_to_cpu(oext->ee_len) - org_diff) { + tmp_ext2.ee_len = tmp_ext.ee_len; + } else { + tmp_ext2.ee_len = cpu_to_le16(le16_to_cpu(oext->ee_len) + - org_diff); + tmp_ext.ee_len = tmp_ext2.ee_len; + } + swap_ext = &tmp_ext2; + } + +out: + if (org_path) { + ext4_ext_drop_refs(org_path); + kfree(org_path); + } + if (dest_path) { + ext4_ext_drop_refs(dest_path); + kfree(dest_path); + } + + return err; +} + +/** * ext4_defrag_fill_ar - Prepare to multiple block allocate for tmp inode * * @org_inode: original inode @@ -185,7 +540,127 @@ ext4_defrag_partial(struct inode *tmp_inode, struct file *filp, pgoff_t org_page_offset, ext4_lblk_t dest_blk_offset, int data_offset_in_page, int block_len_in_page) { - return 0; + struct inode *org_inode = filp->f_dentry->d_inode; + struct address_space *mapping = org_inode->i_mapping; + struct buffer_head *bh; + struct page *page = NULL; + const struct address_space_operations *a_ops = mapping->a_ops; + handle_t *handle; + ext4_lblk_t org_blk_offset; + long long offs = org_page_offset << PAGE_CACHE_SHIFT; + unsigned long blocksize = org_inode->i_sb->s_blocksize; + unsigned int w_flags = 0; + unsigned int tmp_data_len; + unsigned data_len; + void *fsdata; + int ret, i, jblocks; + int blocks_per_page = PAGE_CACHE_SIZE >> org_inode->i_blkbits; + + /* + * It needs twice the amount of ordinary journal buffers because + * inode and tmp_inode may change each different metadata blocks. + */ + jblocks = ext4_writepage_trans_blocks(org_inode) * 2; + handle = ext4_journal_start(org_inode, jblocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + return ret; + } + + if (segment_eq(get_fs(), KERNEL_DS)) + w_flags |= AOP_FLAG_UNINTERRUPTIBLE; + + org_blk_offset = org_page_offset * blocks_per_page + + data_offset_in_page; + offs = (long long)org_blk_offset << org_inode->i_blkbits; + + /* Calculate data_len */ + if ((org_blk_offset + block_len_in_page - 1) == + ((org_inode->i_size - 1) >> org_inode->i_blkbits)) { + /* the case which we replace the last block */ + tmp_data_len = org_inode->i_size & (blocksize - 1); + /* + * If data_len equal zero, it shows data_len is multiples of + * blocksize. So we set appropriate value. + */ + if (tmp_data_len == 0) + tmp_data_len = blocksize; + + data_len = tmp_data_len + + ((block_len_in_page - 1) << org_inode->i_blkbits); + } else { + data_len = block_len_in_page << org_inode->i_blkbits; + } + + up_write(&EXT4_I(org_inode)->i_data_sem); + ret = a_ops->write_begin(filp, mapping, offs, data_len, w_flags, &page, + &fsdata); + down_write(&EXT4_I(org_inode)->i_data_sem); + + if (unlikely(ret < 0)) + goto out; + + if (!PageUptodate(page)) { + up_write(&EXT4_I(org_inode)->i_data_sem); + mapping->a_ops->readpage(filp, page); + down_write(&EXT4_I(org_inode)->i_data_sem); + lock_page(page); + } + + /* + * try_to_release_page() doesn't call releasepage in writeback mode. + * We should care about the order of writing to the same file + * by multiple defrag processes. + * It needs to call wait_on_page_writeback() to wait for the + * writeback of the page. + */ + if (PageWriteback(page)) + wait_on_page_writeback(page); + + /* Release old bh and drop refs */ + try_to_release_page(page, 0); + ret = ext4_defrag_replace_branches(handle, org_inode, tmp_inode, + org_blk_offset, dest_blk_offset, + block_len_in_page); + if (ret < 0) + goto out; + + /* Clear the inode cache not to refer to the old data */ + ext4_ext_invalidate_cache(org_inode); + + if (!page_has_buffers(page)) + create_empty_buffers(page, 1 << org_inode->i_blkbits, 0); + + bh = page_buffers(page); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + + for (i = 0; i < block_len_in_page; i++) { + up_write(&EXT4_I(org_inode)->i_data_sem); + ret = ext4_get_block(org_inode, (sector_t)(org_blk_offset + i), + bh, 0); + down_write(&EXT4_I(org_inode)->i_data_sem); + + if (ret < 0) + goto out; + + if (bh->b_this_page != NULL) + bh = bh->b_this_page; + } + + ret = a_ops->write_end(filp, mapping, offs, data_len, data_len, page, + fsdata); + page = NULL; + +out: + if (unlikely(page)) { + if (PageLocked(page)) + unlock_page(page); + page_cache_release(page); + } + ext4_journal_stop(handle); + + return ret < 0 ? ret : 0; } /** -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html