writeback: speed up writeback of big dirty files

After making dirty a 100M file, the normal behavior is to start the
writeback for all data after 30s delays.  But sometimes the following
happens instead:

	- after 30s:    ~4M
	- after 5s:     ~4M
	- after 5s:     all remaining 92M

Some analyze shows that the internal io dispatch queues goes like this:

		s_io            s_more_io
		-------------------------
	1)	100M,1K         0
	2)	1K              96M
	3)	0               96M
1) initial state with a 100M file and a 1K file

2) 4M written, nr_to_write <= 0, so write more

3) 1K written, nr_to_write > 0, no more writes(BUG)

nr_to_write > 0 in (3) fools the upper layer to think that data have all
been written out.  The big dirty file is actually still sitting in
s_more_io.  We cannot simply splice s_more_io back to s_io as soon as s_io
becomes empty, and let the loop in generic_sync_sb_inodes() continue: this
may starve newly expired inodes in s_dirty.  It is also not an option to
draw inodes from both s_more_io and s_dirty, an let the loop go on: this
might lead to live locks, and might also starve other superblocks in sync
time(well kupdate may still starve some superblocks, that's another bug).

We have to return when a full scan of s_io completes.  So nr_to_write > 0
does not necessarily mean that "all data are written".  This patch
introduces a flag writeback_control.more_io to indicate that more io should
be done.  With it the big dirty file no longer has to wait for the next
kupdate invokation 5s later.

In sync_sb_inodes() we only set more_io on super_blocks we actually
visited.  This avoids the interaction between two pdflush deamons.

Also in __sync_single_inode() we don't blindly keep requeuing the io if the
filesystem cannot progress.  Failing to do so may lead to 100% iowait.

Tested-by: Mike Snitzer <snitzer@gmail.com>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Cc: Michael Rubin <mrubin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 23 insertions, 5 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3fe782d70a7..0b3064079fa 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -284,7 +284,17 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
 				 * soon as the queue becomes uncongested.
 				 */
 				inode->i_state |= I_DIRTY_PAGES;
-				requeue_io(inode);
+				if (wbc->nr_to_write <= 0) {
+					/*
+					 * slice used up: queue for next turn
+					 */
+					requeue_io(inode);
+				} else {
+					/*
+					 * somehow blocked: retry later
+					 */
+					redirty_tail(inode);
+				}
 			} else {
 				/*
 				 * Otherwise fully redirty the inode so that
@@ -468,8 +478,12 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
 		iput(inode);
 		cond_resched();
 		spin_lock(&inode_lock);
-		if (wbc->nr_to_write <= 0)
+		if (wbc->nr_to_write <= 0) {
+			wbc->more_io = 1;
 			break;
+		}
+		if (!list_empty(&sb->s_more_io))
+			wbc->more_io = 1;
 	}
 	return;		/* Leave any unwritten inodes on s_io */
 }
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index b2cd826a8c9..b7b3362f771 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -62,6 +62,7 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
+	unsigned more_io:1;		/* more io to be dispatched */
 };
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a4ca162666c..5e00f1772c2 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -567,6 +567,7 @@ static void background_writeout(unsigned long _min_pages)
 			global_page_state(NR_UNSTABLE_NFS) < background_thresh
 				&& min_pages <= 0)
 			break;
+		wbc.more_io = 0;
 		wbc.encountered_congestion = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		wbc.pages_skipped = 0;
@@ -574,8 +575,9 @@ static void background_writeout(unsigned long _min_pages)
 		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
-			congestion_wait(WRITE, HZ/10);
-			if (!wbc.encountered_congestion)
+			if (wbc.encountered_congestion || wbc.more_io)
+				congestion_wait(WRITE, HZ/10);
+			else
 				break;
 		}
 	}
@@ -640,11 +642,12 @@ static void wb_kupdate(unsigned long arg)
 			global_page_state(NR_UNSTABLE_NFS) +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
 	while (nr_to_write > 0) {
+		wbc.more_io = 0;
 		wbc.encountered_congestion = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
-			if (wbc.encountered_congestion)
+			if (wbc.encountered_congestion || wbc.more_io)
 				congestion_wait(WRITE, HZ/10);
 			else
 				break;	/* All the old data is written */