writeback: introduce max-pause and pass-good dirty limits

The max-pause limit helps to keep the sleep time inside
balance_dirty_pages() within MAX_PAUSE=200ms. The 200ms max sleep means
per task rate limit of 8pages/200ms=160KB/s when dirty exceeded, which
normally is enough to stop dirtiers from continue pushing the dirty
pages high, unless there are a sufficient large number of slow dirtiers
(eg. 500 tasks doing 160KB/s will still sum up to 80MB/s, exceeding the
write bandwidth of a slow disk and hence accumulating more and more dirty
pages).

The pass-good limit helps to let go of the good bdi's in the presence of
a blocked bdi (ie. NFS server not responding) or slow USB disk which for
some reason build up a large number of initial dirty pages that refuse
to go away anytime soon.

For example, given two bdi's A and B and the initial state

	bdi_thresh_A = dirty_thresh / 2
	bdi_thresh_B = dirty_thresh / 2
	bdi_dirty_A  = dirty_thresh / 2
	bdi_dirty_B  = dirty_thresh / 2

Then A get blocked, after a dozen seconds

	bdi_thresh_A = 0
	bdi_thresh_B = dirty_thresh
	bdi_dirty_A  = dirty_thresh / 2
	bdi_dirty_B  = dirty_thresh / 2

The (bdi_dirty_B < bdi_thresh_B) test is now useless and the dirty pages
will be effectively throttled by condition (nr_dirty < dirty_thresh).
This has two problems:
(1) we lose the protections for light dirtiers
(2) balance_dirty_pages() effectively becomes IO-less because the
    (bdi_nr_reclaimable > bdi_thresh) test won't be true. This is good
    for IO, but balance_dirty_pages() loses an important way to break
    out of the loop which leads to more spread out throttle delays.

DIRTY_PASSGOOD_AREA can eliminate the above issues. The only problem is,
DIRTY_PASSGOOD_AREA needs to be defined as 2 to fully cover the above
example while this patch uses the more conservative value 8 so as not to
surprise people with too many dirty pages than expected.

The max-pause limit won't noticeably impact the speed dirty pages are
knocked down when there is a sudden drop of global/bdi dirty thresholds.
Because the heavy dirties will be throttled below 160KB/s which is slow
enough. It does help to avoid long dirty throttle delays and especially
will make light dirtiers more responsive.

Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index e9d371b6053b9061a2b3c4bfe4b74e5e5df90e74..b625073b80c87f3bacb3152ca2d682c2a475b269 100644 (file)
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -7,6 +7,27 @@
 #include <linux/sched.h>
 #include <linux/fs.h>
 
+/*
+ * The 1/16 region above the global dirty limit will be put to maximum pauses:
+ *
+ *     (limit, limit + limit/DIRTY_MAXPAUSE_AREA)
+ *
+ * The 1/16 region above the max-pause region, dirty exceeded bdi's will be put
+ * to loops:
+ *
+ *     (limit + limit/DIRTY_MAXPAUSE_AREA, limit + limit/DIRTY_PASSGOOD_AREA)
+ *
+ * Further beyond, all dirtier tasks will enter a loop waiting (possibly long
+ * time) for the dirty pages to drop, unless written enough pages.
+ *
+ * The global dirty threshold is normally equal to the global dirty limit,
+ * except when the system suddenly allocates a lot of anonymous memory and
+ * knocks down the global dirty threshold quickly, in which case the global
+ * dirty limit will follow down slowly to prevent livelocking all dirtier tasks.
+ */
+#define DIRTY_MAXPAUSE_AREA            16
+#define DIRTY_PASSGOOD_AREA            8
+
 struct backing_dev_info;
 
 /*

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index da959952b9f52dedee9dd7af28ed31d9b08ddda8..798842a22474fb6bfb538cbca1285a1d6f39f64e 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,6 +36,11 @@
 #include <linux/pagevec.h>
 #include <trace/events/writeback.h>
 
+/*
+ * Sleep at most 200ms at a time in balance_dirty_pages().
+ */
+#define MAX_PAUSE              max(HZ/5, 1)
+
 /*
  * Estimate write bandwidth at 200ms intervals.
  */
@@ -399,6 +404,11 @@ unsigned long determine_dirtyable_memory(void)
        return x + 1;   /* Ensure that we never return 0 */
 }
 
+static unsigned long hard_dirty_limit(unsigned long thresh)
+{
+       return max(thresh, global_dirty_limit);
+}
+
 /*
  * global_dirty_limits - background-writeback and dirty-throttling thresholds
  *
@@ -723,6 +733,29 @@ static void balance_dirty_pages(struct address_space *mapping,
                io_schedule_timeout(pause);
                trace_balance_dirty_wait(bdi);
 
+               dirty_thresh = hard_dirty_limit(dirty_thresh);
+               /*
+                * max-pause area. If dirty exceeded but still within this
+                * area, no need to sleep for more than 200ms: (a) 8 pages per
+                * 200ms is typically more than enough to curb heavy dirtiers;
+                * (b) the pause time limit makes the dirtiers more responsive.
+                */
+               if (nr_dirty < dirty_thresh +
+                              dirty_thresh / DIRTY_MAXPAUSE_AREA &&
+                   time_after(jiffies, start_time + MAX_PAUSE))
+                       break;
+               /*
+                * pass-good area. When some bdi gets blocked (eg. NFS server
+                * not responding), or write bandwidth dropped dramatically due
+                * to concurrent reads, or dirty threshold suddenly dropped and
+                * the dirty pages cannot be brought down anytime soon (eg. on
+                * slow USB stick), at least let go of the good bdi's.
+                */
+               if (nr_dirty < dirty_thresh +
+                              dirty_thresh / DIRTY_PASSGOOD_AREA &&
+                   bdi_dirty < bdi_thresh)
+                       break;
+
                /*
                 * Increase the delay for each loop, up to our previous
                 * default of taking a 100ms nap.