1 files changed, 66 insertions, 41 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 93d8d2f7108c..e5363f34e025 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -34,6 +34,7 @@
 #include <linux/syscalls.h>
 #include <linux/buffer_head.h> /* __set_page_dirty_buffers */
 #include <linux/pagevec.h>
+#include <linux/timer.h>
 #include <trace/events/writeback.h>
 
 /*
@@ -135,7 +136,20 @@ unsigned long global_dirty_limit;
  * measured in page writeback completions.
  *
  */
-static struct prop_descriptor vm_completions;
+static struct fprop_global writeout_completions;
+
+static void writeout_period(unsigned long t);
+/* Timer for aging of writeout_completions */
+static struct timer_list writeout_period_timer =
+                TIMER_DEFERRED_INITIALIZER(writeout_period, 0, 0);
+static unsigned long writeout_period_time = 0;
+
+/*
+ * Length of period for aging writeout fractions of bdis. This is an
+ * arbitrarily chosen number. The longer the period, the slower fractions will
+ * reflect changes in current writeout rate.
+ */
+#define VM_COMPLETIONS_PERIOD_LEN (3*HZ)
 
 /*
  * Work out the current dirty-memory clamping and background writeout
@@ -322,34 +336,6 @@ bool zone_dirty_ok(struct zone *zone)
                zone_page_state(zone, NR_WRITEBACK) <= limit;
 }
 
-/*
- * couple the period to the dirty_ratio:
- *
- *   period/2 ~ roundup_pow_of_two(dirty limit)
- */
-static int calc_period_shift(void)
-{
-        unsigned long dirty_total;
-
-        if (vm_dirty_bytes)
-                dirty_total = vm_dirty_bytes / PAGE_SIZE;
-        else
-                dirty_total = (vm_dirty_ratio * global_dirtyable_memory()) /
-                                100;
-        return 2 + ilog2(dirty_total - 1);
-}
-
-/*
- * update the period when the dirty threshold changes.
- */
-static void update_completion_period(void)
-{
-        int shift = calc_period_shift();
-        prop_change_shift(&vm_completions, shift);
-
-        writeback_set_ratelimit();
-}
-
 int dirty_background_ratio_handler(struct ctl_table *table, int write,
                 void __user *buffer, size_t *lenp,
                 loff_t *ppos)
@@ -383,7 +369,7 @@ int dirty_ratio_handler(struct ctl_table *table, int write,
 
         ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
         if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
-                update_completion_period();
+                writeback_set_ratelimit();
                 vm_dirty_bytes = 0;
         }
         return ret;
@@ -398,12 +384,21 @@ int dirty_bytes_handler(struct ctl_table *table, int write,
 
         ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
         if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
-                update_completion_period();
+                writeback_set_ratelimit();
                 vm_dirty_ratio = 0;
         }
         return ret;
 }
 
+static unsigned long wp_next_time(unsigned long cur_time)
+{
+        cur_time += VM_COMPLETIONS_PERIOD_LEN;
+        /* 0 has a special meaning... */
+        if (!cur_time)
+                return 1;
+        return cur_time;
+}
+
 /*
  * Increment the BDI's writeout completion count and the global writeout
  * completion count. Called from test_clear_page_writeback().
@@ -411,8 +406,19 @@ int dirty_bytes_handler(struct ctl_table *table, int write,
 static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
 {
         __inc_bdi_stat(bdi, BDI_WRITTEN);
-        __prop_inc_percpu_max(&vm_completions, &bdi->completions,
-                              bdi->max_prop_frac);
+        __fprop_inc_percpu_max(&writeout_completions, &bdi->completions,
+                               bdi->max_prop_frac);
+        /* First event after period switching was turned off? */
+        if (!unlikely(writeout_period_time)) {
+                /*
+                 * We can race with other __bdi_writeout_inc calls here but
+                 * it does not cause any harm since the resulting time when
+                 * timer will fire and what is in writeout_period_time will be
+                 * roughly the same.
+                 */
+                writeout_period_time = wp_next_time(jiffies);
+                mod_timer(&writeout_period_timer, writeout_period_time);
+        }
 }
 
 void bdi_writeout_inc(struct backing_dev_info *bdi)
@@ -431,11 +437,33 @@ EXPORT_SYMBOL_GPL(bdi_writeout_inc);
 static void bdi_writeout_fraction(struct backing_dev_info *bdi,
                 long *numerator, long *denominator)
 {
-        prop_fraction_percpu(&vm_completions, &bdi->completions,
+        fprop_fraction_percpu(&writeout_completions, &bdi->completions,
                                 numerator, denominator);
 }
 
 /*
+ * On idle system, we can be called long after we scheduled because we use
+ * deferred timers so count with missed periods.
+ */
+static void writeout_period(unsigned long t)
+{
+        int miss_periods = (jiffies - writeout_period_time) /
+                                                 VM_COMPLETIONS_PERIOD_LEN;
+
+        if (fprop_new_period(&writeout_completions, miss_periods + 1)) {
+                writeout_period_time = wp_next_time(writeout_period_time +
+                                miss_periods * VM_COMPLETIONS_PERIOD_LEN);
+                mod_timer(&writeout_period_timer, writeout_period_time);
+        } else {
+                /*
+                 * Aging has zeroed all fractions. Stop wasting CPU on period
+                 * updates.
+                 */
+                writeout_period_time = 0;
+        }
+}
+
+/*
  * bdi_min_ratio keeps the sum of the minimum dirty shares of all
  * registered backing devices, which, for obvious reasons, can not
  * exceed 100%.
@@ -475,7 +503,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
                 ret = -EINVAL;
         } else {
                 bdi->max_ratio = max_ratio;
-                bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
+                bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100;
         }
         spin_unlock_bh(&bdi_lock);
 
@@ -918,7 +946,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
          *      bdi->dirty_ratelimit = balanced_dirty_ratelimit;
          *
          * However to get a more stable dirty_ratelimit, the below elaborated
-         * code makes use of task_ratelimit to filter out sigular points and
+         * code makes use of task_ratelimit to filter out singular points and
          * limit the step size.
          *
          * The below code essentially only uses the relative value of
@@ -941,7 +969,7 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
          * feel and care are stable dirty rate and small position error.
          *
          * |task_ratelimit - dirty_ratelimit| is used to limit the step size
-         * and filter out the sigular points of balanced_dirty_ratelimit. Which
+         * and filter out the singular points of balanced_dirty_ratelimit. Which
          * keeps jumping around randomly and can even leap far away at times
          * due to the small 200ms estimation period of dirty_rate (we want to
          * keep that period small to reduce time lags).
@@ -1606,13 +1634,10 @@ static struct notifier_block __cpuinitdata ratelimit_nb = {
  */
 void __init page_writeback_init(void)
 {
-        int shift;
-
         writeback_set_ratelimit();
         register_cpu_notifier(&ratelimit_nb);
 
-        shift = calc_period_shift();
-        prop_descriptor_init(&vm_completions, shift);
+        fprop_global_init(&writeout_completions);
 }
 
 /**