From: Theodore Ts'o Subject: [PATCH 2.6.33.y 26/40] ext4: don't scan/accumulate more pages than mballoc will allocate Date: Tue, 1 Jun 2010 08:03:13 -0400 Message-ID: <1275393807-14369-26-git-send-email-tytso@mit.edu> References: <1275393807-14369-1-git-send-email-tytso@mit.edu> Cc: Ext4 Developers List , Eric Sandeen , "Theodore Ts'o" To: stable@vger.kernel.org Return-path: Received: from THUNK.ORG ([69.25.196.29]:47346 "EHLO thunker.thunk.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756105Ab0FAMDl (ORCPT ); Tue, 1 Jun 2010 08:03:41 -0400 In-Reply-To: <1275393807-14369-1-git-send-email-tytso@mit.edu> Sender: linux-ext4-owner@vger.kernel.org List-ID: From: Eric Sandeen commit c445e3e0a5c2804524dec6e55f66d63f6bc5bc3e upstream (as of v2.6.34-git13) There was a bug reported on RHEL5 that a 10G dd on a 12G box had a very, very slow sync after that. At issue was the loop in write_cache_pages scanning all the way to the end of the 10G file, even though the subsequent call to mpage_da_submit_io would only actually write a smallish amt; then we went back to the write_cache_pages loop ... wasting tons of time in calling __mpage_da_writepage for thousands of pages we would just revisit (many times) later. Upstream it's not such a big issue for sys_sync because we get to the loop with a much smaller nr_to_write, which limits the loop. However, talking with Aneesh he realized that fsync upstream still gets here with a very large nr_to_write and we face the same problem. This patch makes mpage_add_bh_to_extent stop the loop after we've accumulated 2048 pages, by setting mpd->io_done = 1; which ultimately causes the write_cache_pages loop to break. Repeating the test with a dirty_ratio of 80 (to leave something for fsync to do), I don't see huge IO performance gains, but the reduction in cpu usage is striking: 80% usage with stock, and 2% with the below patch. Instrumenting the loop in write_cache_pages clearly shows that we are wasting time here. Eventually we need to change mpage_da_map_pages() also submit its I/O to the block layer, subsuming mpage_da_submit_io(), and then change it call ext4_get_blocks() multiple times. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 9 +++++++++ 1 files changed, 9 insertions(+), 0 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f01fe28..3c16ab8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2319,6 +2319,15 @@ static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, sector_t next; int nrblocks = mpd->b_size >> mpd->inode->i_blkbits; + /* + * XXX Don't go larger than mballoc is willing to allocate + * This is a stopgap solution. We eventually need to fold + * mpage_da_submit_io() into this function and then call + * ext4_get_blocks() multiple times in a loop + */ + if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize) + goto flush_it; + /* check if thereserved journal credits might overflow */ if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) { if (nrblocks >= EXT4_MAX_TRANS_DATA) { -- 1.6.6.1.1.g974db.dirty