writeback: balance_dirty_pages() shall write more than dirtied pages

Some filesystem may choose to write much more than ratelimit_pages
before calling balance_dirty_pages_ratelimited_nr(). So it is safer to
determine number to write based on real number of dirtied pages.

Otherwise it is possible that
  loop {
    btrfs_file_write():     dirty 1024 pages
    balance_dirty_pages():  write up to 48 pages (= ratelimit_pages * 1.5)
  }
in which the writeback rate cannot keep up with dirty rate, and the
dirty pages go all the way beyond dirty_thresh.

The increased write_chunk may make the dirtier more bumpy.
So filesystems shall be take care not to dirty too much at
a time (eg. > 4MB) without checking the ratelimit.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5f378dd588027c227dc95551e27e4b6431e5df60..cbd4cba468bdf2b5b13bd95a82b9eda1074681cf 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -44,12 +44,15 @@ static long ratelimit_pages = 32;
 /*
  * When balance_dirty_pages decides that the caller needs to perform some
  * non-background writeback, this is how many pages it will attempt to write.
- * It should be somewhat larger than RATELIMIT_PAGES to ensure that reasonably
+ * It should be somewhat larger than dirtied pages to ensure that reasonably
  * large amounts of I/O are submitted.
  */
-static inline long sync_writeback_pages(void)
+static inline long sync_writeback_pages(unsigned long dirtied)
 {
-       return ratelimit_pages + ratelimit_pages / 2;
+       if (dirtied < ratelimit_pages)
+               dirtied = ratelimit_pages;
+
+       return dirtied + dirtied / 2;
 }
 
 /* The following parameters are exported via /proc/sys/vm */
@@ -477,7 +480,8 @@ get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
  * If we're over `background_thresh' then pdflush is woken to perform some
  * writeout.
  */
-static void balance_dirty_pages(struct address_space *mapping)
+static void balance_dirty_pages(struct address_space *mapping,
+                               unsigned long write_chunk)
 {
        long nr_reclaimable, bdi_nr_reclaimable;
        long nr_writeback, bdi_nr_writeback;
@@ -485,7 +489,6 @@ static void balance_dirty_pages(struct address_space *mapping)
        unsigned long dirty_thresh;
        unsigned long bdi_thresh;
        unsigned long pages_written = 0;
-       unsigned long write_chunk = sync_writeback_pages();
        unsigned long pause = 1;
 
        struct backing_dev_info *bdi = mapping->backing_dev_info;
@@ -640,9 +643,10 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
        p =  &__get_cpu_var(bdp_ratelimits);
        *p += nr_pages_dirtied;
        if (unlikely(*p >= ratelimit)) {
+               ratelimit = sync_writeback_pages(*p);
                *p = 0;
                preempt_enable();
-               balance_dirty_pages(mapping);
+               balance_dirty_pages(mapping, ratelimit);
                return;
        }
        preempt_enable();