Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755618Ab0GASMr (ORCPT ); Thu, 1 Jul 2010 14:12:47 -0400 Received: from kroah.org ([198.145.64.141]:60085 "EHLO coco.kroah.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755267Ab0GASKy (ORCPT ); Thu, 1 Jul 2010 14:10:54 -0400 X-Mailbox-Line: From gregkh@clark.site Thu Jul 1 10:28:57 2010 Message-Id: <20100701172857.706696176@clark.site> User-Agent: quilt/0.48-10.1 Date: Thu, 01 Jul 2010 10:27:04 -0700 From: Greg KH To: linux-kernel@vger.kernel.org, stable@kernel.org Cc: stable-review@kernel.org, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, "Jayson R. King" , Theodore Tso , "Aneesh Kumar K.V" , Dave Chinner , Ext4 Developers List , Kay Diederichs Subject: [15/23] ext4: Fix file fragmentation during large file write. In-Reply-To: <20100701175134.GA2098@kroah.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5741 Lines: 193 2.6.27-stable review patch. If anyone has any objections, please let us know. ------------------ From: Aneesh Kumar K.V commit 22208dedbd7626e5fc4339c417f8d24cc21f79d7 upstream. The range_cyclic writeback mode uses the address_space writeback_index as the start index for writeback. With delayed allocation we were updating writeback_index wrongly resulting in highly fragmented file. This patch reduces the number of extents reduced from 4000 to 27 for a 3GB file. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Theodore Ts'o [dev@jaysonking.com: Some changed lines from the original version of this patch were dropped, since they were rolled up with another cherry-picked patch applied to 2.6.27.y earlier.] [dev@jaysonking.com: Use of wbc->no_nrwrite_index_update was dropped, since write_cache_pages_da() implies it.] Signed-off-by: Jayson R. King Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 79 ++++++++++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 33 deletions(-) --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1721,7 +1721,11 @@ static int mpage_da_submit_io(struct mpa pages_skipped = mpd->wbc->pages_skipped; err = mapping->a_ops->writepage(page, mpd->wbc); - if (!err) + if (!err && (pages_skipped == mpd->wbc->pages_skipped)) + /* + * have successfully written the page + * without skipping the same + */ mpd->pages_written++; /* * In error case, we have to continue because @@ -2295,7 +2299,6 @@ static int mpage_da_writepages(struct ad struct writeback_control *wbc, struct mpage_da_data *mpd) { - long to_write; int ret; if (!mpd->get_block) @@ -2310,19 +2313,18 @@ static int mpage_da_writepages(struct ad mpd->pages_written = 0; mpd->retval = 0; - to_write = wbc->nr_to_write; - ret = write_cache_pages_da(mapping, wbc, mpd); - /* * Handle last extent of pages */ if (!mpd->io_done && mpd->next_page != mpd->first_page) { if (mpage_da_map_blocks(mpd) == 0) mpage_da_submit_io(mpd); - } - wbc->nr_to_write = to_write - mpd->pages_written; + mpd->io_done = 1; + ret = MPAGE_DA_EXTENT_TAIL; + } + wbc->nr_to_write -= mpd->pages_written; return ret; } @@ -2567,11 +2569,13 @@ static int ext4_da_writepages_trans_bloc static int ext4_da_writepages(struct address_space *mapping, struct writeback_control *wbc) { + pgoff_t index; + int range_whole = 0; handle_t *handle = NULL; struct mpage_da_data mpd; struct inode *inode = mapping->host; + long pages_written = 0, pages_skipped; int needed_blocks, ret = 0, nr_to_writebump = 0; - long to_write, pages_skipped = 0; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); /* @@ -2605,16 +2609,20 @@ static int ext4_da_writepages(struct add nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write; wbc->nr_to_write = sbi->s_mb_stream_request; } + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) + range_whole = 1; - - pages_skipped = wbc->pages_skipped; + if (wbc->range_cyclic) + index = mapping->writeback_index; + else + index = wbc->range_start >> PAGE_CACHE_SHIFT; mpd.wbc = wbc; mpd.inode = mapping->host; -restart_loop: - to_write = wbc->nr_to_write; - while (!ret && to_write > 0) { + pages_skipped = wbc->pages_skipped; + + while (!ret && wbc->nr_to_write > 0) { /* * we insert one extent at a time. So we need @@ -2647,46 +2655,51 @@ restart_loop: goto out_writepages; } } - to_write -= wbc->nr_to_write; - mpd.get_block = ext4_da_get_block_write; ret = mpage_da_writepages(mapping, wbc, &mpd); ext4_journal_stop(handle); - if (mpd.retval == -ENOSPC) + if (mpd.retval == -ENOSPC) { + /* commit the transaction which would + * free blocks released in the transaction + * and try again + */ jbd2_journal_force_commit_nested(sbi->s_journal); - - /* reset the retry count */ - if (ret == MPAGE_DA_EXTENT_TAIL) { + wbc->pages_skipped = pages_skipped; + ret = 0; + } else if (ret == MPAGE_DA_EXTENT_TAIL) { /* * got one extent now try with * rest of the pages */ - to_write += wbc->nr_to_write; + pages_written += mpd.pages_written; + wbc->pages_skipped = pages_skipped; ret = 0; - } else if (wbc->nr_to_write) { + } else if (wbc->nr_to_write) /* * There is no more writeout needed * or we requested for a noblocking writeout * and we found the device congested */ - to_write += wbc->nr_to_write; break; - } - wbc->nr_to_write = to_write; - } - - if (!wbc->range_cyclic && (pages_skipped != wbc->pages_skipped)) { - /* We skipped pages in this loop */ - wbc->nr_to_write = to_write + - wbc->pages_skipped - pages_skipped; - wbc->pages_skipped = pages_skipped; - goto restart_loop; } + if (pages_skipped != wbc->pages_skipped) + printk(KERN_EMERG "This should not happen leaving %s " + "with nr_to_write = %ld ret = %d\n", + __func__, wbc->nr_to_write, ret); + + /* Update index */ + index += pages_written; + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + /* + * set the writeback_index so that range_cyclic + * mode will write it back later + */ + mapping->writeback_index = index; out_writepages: - wbc->nr_to_write = to_write - nr_to_writebump; + wbc->nr_to_write -= nr_to_writebump; return ret; } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/