writeback: dirty ratelimit - think time compensation

Compensate the task's think time when computing the final pause time,
so that ->dirty_ratelimit can be executed accurately.

        think time := time spend outside of balance_dirty_pages()

In the rare case that the task slept longer than the 200ms period time
(result in negative pause time), the sleep time will be compensated in
the following periods, too, if it's less than 1 second.

Accumulated errors are carefully avoided as long as the max pause area
is not hitted.

Pseudo code:

        period = pages_dirtied / task_ratelimit;
        think = jiffies - dirty_paused_when;
        pause = period - think;

1) normal case: period > think

        pause = period - think
        dirty_paused_when = jiffies + pause
        nr_dirtied = 0

                             period time
              |===============================>|
                  think time      pause time
              |===============>|==============>|
        ------|----------------|---------------|------------------------
        dirty_paused_when   jiffies

2) no pause case: period <= think

        don't pause; reduce future pause time by:
        dirty_paused_when += period
        nr_dirtied = 0

                           period time
              |===============================>|
                                  think time
              |===================================================>|
        ------|--------------------------------+-------------------|----
        dirty_paused_when                                       jiffies

Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>

1 files changed, 11 insertions, 3 deletions

diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 99d1d0decf88..8588a8918023 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -300,12 +300,13 @@ TRACE_EVENT(balance_dirty_pages,
                  unsigned long dirty_ratelimit,
                  unsigned long task_ratelimit,
                  unsigned long dirtied,
+                 unsigned long period,
                  long pause,
                  unsigned long start_time),
 
         TP_ARGS(bdi, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty,
                 dirty_ratelimit, task_ratelimit,
-                dirtied, pause, start_time),
+                dirtied, period, pause, start_time),
 
         TP_STRUCT__entry(
                 __array(         char,  bdi, 32)
@@ -320,6 +321,8 @@ TRACE_EVENT(balance_dirty_pages,
                 __field(unsigned int,   dirtied_pause)
                 __field(unsigned long,  paused)
                 __field(         long,  pause)
+                __field(unsigned long,  period)
+                __field(         long,  think)
         ),
 
         TP_fast_assign(
@@ -336,6 +339,9 @@ TRACE_EVENT(balance_dirty_pages,
                 __entry->task_ratelimit = KBps(task_ratelimit);
                 __entry->dirtied        = dirtied;
                 __entry->dirtied_pause  = current->nr_dirtied_pause;
+                __entry->think          = current->dirty_paused_when == 0 ? 0 :
+                         (long)(jiffies - current->dirty_paused_when) * 1000/HZ;
+                __entry->period         = period * 1000 / HZ;
                 __entry->pause          = pause * 1000 / HZ;
                 __entry->paused         = (jiffies - start_time) * 1000 / HZ;
         ),
@@ -346,7 +352,7 @@ TRACE_EVENT(balance_dirty_pages,
                   "bdi_setpoint=%lu bdi_dirty=%lu "
                   "dirty_ratelimit=%lu task_ratelimit=%lu "
                   "dirtied=%u dirtied_pause=%u "
-                  "paused=%lu pause=%ld",
+                  "paused=%lu pause=%ld period=%lu think=%ld",
                   __entry->bdi,
                   __entry->limit,
                   __entry->setpoint,
@@ -358,7 +364,9 @@ TRACE_EVENT(balance_dirty_pages,
                   __entry->dirtied,
                   __entry->dirtied_pause,
                   __entry->paused,      /* ms */
-                  __entry->pause        /* ms */
+                  __entry->pause,       /* ms */
+                  __entry->period,      /* ms */
+                  __entry->think        /* ms */
           )
 );