[PATCH 1/7] fs/writeback: avoid to writeback non-expired inode in kupdate writeback

[Kemeng Shi]

In kupdate writeback, only expired inode (have been dirty for longer than
dirty_expire_interval) is supposed to be written back. However, kupdate
writeback will writeback non-expired inode left in b_io or b_more_io from
last wb_writeback. As a result, writeback will keep being triggered
unexpected when we keep dirtying pages even dirty memory is under
threshold and inode is not expired. To be more specific:
Assume dirty background threshold is > 1G and dirty_expire_centisecs is
> 60s. When we running fio -size=1G -invalidate=0 -ioengine=libaio
--time_based -runtime=60... (keep dirtying), the writeback will keep
being triggered as following:
wb_workfn
  wb_do_writeback
    wb_check_background_flush
      /*
       * Wb dirty background threshold starts at 0 if device was idle and
       * grows up when bandwidth of wb is updated. So a background
       * writeback is triggered.
       */
      wb_over_bg_thresh
      /*
       * Dirtied inode will be written back and added to b_more_io list
       * after slice used up (because we keep dirtying the inode).
       */
      wb_writeback

Writeback is triggered per dirty_writeback_centisecs as following:
wb_workfn
  wb_do_writeback
    wb_check_old_data_flush
      /*
       * Write back inode left in b_io and b_more_io from last wb_writeback
       * even the inode is non-expired and it will be added to b_more_io
       * again as slice will be used up (because we keep dirtying the
       * inode)
       */
      wb_writeback

Fix this by moving non-expired inode in io list from last wb_writeback to
dirty list in kudpate writeback.

Test as following:
/* make it more easier to observe the issue */
echo 300000 > /proc/sys/vm/dirty_expire_centisecs
echo 100 > /proc/sys/vm/dirty_writeback_centisecs
/* create a idle device */
mkfs.ext4 -F /dev/vdb
mount /dev/vdb /bdi1/
/* run buffer write with fio */
fio -name test -filename=/bdi1/file -size=800M -ioengine=libaio -bs=4K \
-iodepth=1 -rw=write -direct=0 --time_based -runtime=60 -invalidate=0

Result before fix (run three tests):
1360MB/s
1329MB/s
1455MB/s

Result after fix (run three tests);
790MB/s
1820MB/s
1804MB/s

Signed-off-by: Kemeng Shi <shikemeng@xxxxxxxxxxxxxxx>
---
 fs/fs-writeback.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 5ab1aaf805f7..a9a918972719 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2046,6 +2046,23 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 	return nr_pages - work.nr_pages;
 }
 
+static void filter_expired_io(struct bdi_writeback *wb)
+{
+	struct inode *inode, *tmp;
+	unsigned long expired_jiffies = jiffies -
+		msecs_to_jiffies(dirty_expire_interval * 10);
+
+	spin_lock(&wb->list_lock);
+	list_for_each_entry_safe(inode, tmp, &wb->b_io, i_io_list)
+		if (inode_dirtied_after(inode, expired_jiffies))
+			redirty_tail(inode, wb);
+
+	list_for_each_entry_safe(inode, tmp, &wb->b_more_io, i_io_list)
+		if (inode_dirtied_after(inode, expired_jiffies))
+			redirty_tail(inode, wb);
+	spin_unlock(&wb->list_lock);
+}
+
 /*
  * Explicit flushing or periodic writeback of "old" data.
  *
@@ -2070,6 +2087,9 @@ static long wb_writeback(struct bdi_writeback *wb,
 	long progress;
 	struct blk_plug plug;
 
+	if (work->for_kupdate)
+		filter_expired_io(wb);
+
 	blk_start_plug(&plug);
 	for (;;) {
 		/*
-- 
2.30.0