ext4: avoid unnecessary transaction stalls during writeback

Currently ext4_writepages() submits all pages with transaction started.
When no page needs block allocation or extent conversion we can submit
all dirty pages in the inode while holding a single transaction handle
and when device is congested this can take significant amount of time.
Thus ext4_writepages() can block transaction commits for extended
periods of time.

Take for example a simple benchmark simulating PostgreSQL database
(pgioperf in mmtest). The benchmark runs 16 processes doing random reads
from a huge file, one process doing random writes to the huge file, and
one process doing sequential writes to a small files and frequently
running fsync. With unpatched kernel transaction commits take on average
~18s with standard deviation of ~41s, top 5 commit times are:

274.466639s, 126.467347s, 86.992429s, 34.351563s, 31.517653s.

After this patch transaction commits take on average 0.1s with standard
deviation of 0.15s, top 5 commit times are:

0.563792s, 0.519980s, 0.509841s, 0.471700s, 0.469899s

[ Modified so we use an explicit do_map flag instead of relying on
  io_end not being allocated, the since io_end->inode is needed for I/O
  error handling. -- tytso ]

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 35 insertions, 0 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 88203ae5b154..2a4507deb925 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1643,6 +1643,7 @@ struct mpage_da_data {
 	 */
 	struct ext4_map_blocks map;
 	struct ext4_io_submit io_submit;	/* IO submission data */
+	unsigned int do_map:1;
 };
 
 static void mpage_release_unused_pages(struct mpage_da_data *mpd,
@@ -2179,6 +2180,9 @@ static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
 
 	/* First block in the extent? */
 	if (map->m_len == 0) {
+		/* We cannot map unless handle is started... */
+		if (!mpd->do_map)
+			return false;
 		map->m_lblk = lblk;
 		map->m_len = 1;
 		map->m_flags = bh->b_state & BH_FLAGS;
@@ -2231,6 +2235,9 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 			/* Found extent to map? */
 			if (mpd->map.m_len)
 				return 0;
+			/* Buffer needs mapping and handle is not started? */
+			if (!mpd->do_map)
+				return 0;
 			/* Everything mapped so far and we hit EOF */
 			break;
 		}
@@ -2747,6 +2754,29 @@ retry:
 		tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
 	done = false;
 	blk_start_plug(&plug);
+
+	/*
+	 * First writeback pages that don't need mapping - we can avoid
+	 * starting a transaction unnecessarily and also avoid being blocked
+	 * in the block layer on device congestion while having transaction
+	 * started.
+	 */
+	mpd.do_map = 0;
+	mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
+	if (!mpd.io_submit.io_end) {
+		ret = -ENOMEM;
+		goto unplug;
+	}
+	ret = mpage_prepare_extent_to_map(&mpd);
+	/* Submit prepared bio */
+	ext4_io_submit(&mpd.io_submit);
+	ext4_put_io_end_defer(mpd.io_submit.io_end);
+	mpd.io_submit.io_end = NULL;
+	/* Unlock pages we didn't use */
+	mpage_release_unused_pages(&mpd, false);
+	if (ret < 0)
+		goto unplug;
+
 	while (!done && mpd.first_page <= mpd.last_page) {
 		/* For each extent of pages we use new io_end */
 		mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
@@ -2775,8 +2805,10 @@ retry:
 				wbc->nr_to_write, inode->i_ino, ret);
 			/* Release allocated io_end */
 			ext4_put_io_end(mpd.io_submit.io_end);
+			mpd.io_submit.io_end = NULL;
 			break;
 		}
+		mpd.do_map = 1;
 
 		trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
 		ret = mpage_prepare_extent_to_map(&mpd);
@@ -2807,6 +2839,7 @@ retry:
 		if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
 			ext4_journal_stop(handle);
 			handle = NULL;
+			mpd.do_map = 0;
 		}
 		/* Submit prepared bio */
 		ext4_io_submit(&mpd.io_submit);
@@ -2824,6 +2857,7 @@ retry:
 			ext4_journal_stop(handle);
 		} else
 			ext4_put_io_end(mpd.io_submit.io_end);
+		mpd.io_submit.io_end = NULL;
 
 		if (ret == -ENOSPC && sbi->s_journal) {
 			/*
@@ -2839,6 +2873,7 @@ retry:
 		if (ret)
 			break;
 	}
+unplug:
 	blk_finish_plug(&plug);
 	if (!ret && !cycled && wbc->nr_to_write > 0) {
 		cycled = 1;