[PATCH 1/2] writeback: Improve busyloop prevention

[Jan Kara <jack@suse.cz>]

Writeback of an inode can be stalled by things like internal fs locks being
held. So in case we didn't write anything during a pass through b_io list,
just wait for a moment and try again. When retrying is fruitless for a long
time, or we have some other work to do, we just stop current work to avoid
blocking flusher thread.

CC: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/fs-writeback.c |   39 +++++++++++++++++++++++++++------------
 1 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 04cf3b9..b619f3a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -699,8 +699,11 @@ static long wb_writeback(struct bdi_writeback *wb,
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
 	unsigned long oldest_jif;
-	struct inode *inode;
 	long progress;
+	long pause = 1;
+	long max_pause = dirty_writeback_interval ?
+			   msecs_to_jiffies(dirty_writeback_interval * 10) :
+			   HZ;
 
 	oldest_jif = jiffies;
 	work->older_than_this = &oldest_jif;
@@ -755,25 +758,37 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * mean the overall work is done. So we keep looping as long
 		 * as made some progress on cleaning pages or inodes.
 		 */
-		if (progress)
+		if (progress) {
+			pause = 1;
 			continue;
+		}
 		/*
 		 * No more inodes for IO, bail
 		 */
 		if (list_empty(&wb->b_more_io))
 			break;
 		/*
-		 * Nothing written. Wait for some inode to
-		 * become available for writeback. Otherwise
-		 * we'll just busyloop.
+		 * Nothing written (some internal fs locks were unavailable or
+		 * inode was under writeback from balance_dirty_pages() or
+		 * similar conditions).
 		 */
-		if (!list_empty(&wb->b_more_io))  {
-			trace_writeback_wait(wb->bdi, work);
-			inode = wb_inode(wb->b_more_io.prev);
-			spin_lock(&inode->i_lock);
-			inode_wait_for_writeback(inode, wb);
-			spin_unlock(&inode->i_lock);
-		}
+		/* If there's some other work to do, proceed with it... */
+		if (!list_empty(&wb->bdi->work_list) ||
+		    (!work->for_background && over_bground_thresh()))
+			break;
+		/*
+		 * Wait for a while to avoid busylooping unless we waited for
+		 * so long it does not make sense to retry anymore.
+		 */
+		if (pause > max_pause)
+			break;
+		trace_writeback_wait(wb->bdi, work);
+		spin_unlock(&wb->list_lock);
+		__set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(pause);
+		if (pause < max_pause)
+			pause <<= 1;
+		spin_lock(&wb->list_lock);
 	}
 	spin_unlock(&wb->list_lock);
 
-- 
1.7.1