From aeac589a74b91c4c07458272767e089810fbd23d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 17 Oct 2013 18:56:16 -0400 Subject: [PATCH] ext4: fix performance regression in ext4_writepages Commit 4e7ea81db5(ext4: restructure writeback path) introduces another performance regression on random write: - one more page may be added to ext4 extent in mpage_prepare_extent_to_map, and will be submitted for I/O so nr_to_write will become -1 before 'done' is set - the worse thing is that dirty pages may still be retrieved from page cache after nr_to_write becomes negative, so lots of small chunks can be submitted to block device when page writeback is catching up with write path, and performance is hurted. On one arm A15 board with sata 3.0 SSD(CPU: 1.5GHz dura core, RAM: 2GB, SATA controller: 3.0Gbps), this patch can improve below test's result from 157MB/sec to 174MB/sec(>10%): dd if=/dev/zero of=./z.img bs=8K count=512K The above test is actually prototype of block write in bonnie++ utility. This patch makes sure no more pages than nr_to_write can be added to extent for mapping, so that nr_to_write won't become negative. Cc: linux-ext4@vger.kernel.org Acked-by: Jan Kara Signed-off-by: Ming Lei Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e7e5b3d8f002..94aac67b55c9 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2298,6 +2298,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) struct address_space *mapping = mpd->inode->i_mapping; struct pagevec pvec; unsigned int nr_pages; + long left = mpd->wbc->nr_to_write; pgoff_t index = mpd->first_page; pgoff_t end = mpd->last_page; int tag; @@ -2333,6 +2334,17 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) if (page->index > end) goto out; + /* + * Accumulated enough dirty pages? This doesn't apply + * to WB_SYNC_ALL mode. For integrity sync we have to + * keep going because someone may be concurrently + * dirtying pages, and we might have synced a lot of + * newly appeared dirty pages, but have not synced all + * of the old dirty pages. + */ + if (mpd->wbc->sync_mode == WB_SYNC_NONE && left <= 0) + goto out; + /* If we can't merge this page, we are done. */ if (mpd->map.m_len > 0 && mpd->next_page != page->index) goto out; @@ -2367,19 +2379,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) if (err <= 0) goto out; err = 0; - - /* - * Accumulated enough dirty pages? This doesn't apply - * to WB_SYNC_ALL mode. For integrity sync we have to - * keep going because someone may be concurrently - * dirtying pages, and we might have synced a lot of - * newly appeared dirty pages, but have not synced all - * of the old dirty pages. - */ - if (mpd->wbc->sync_mode == WB_SYNC_NONE && - mpd->next_page - mpd->first_page >= - mpd->wbc->nr_to_write) - goto out; + left--; } pagevec_release(&pvec); cond_resched();