IO-less dirty throttling v10

@@ -40,6 +40,7 @@ typedef int (congested_fn)(void *, int);
 enum bdi_stat_item {
 	BDI_RECLAIMABLE,
 	BDI_WRITEBACK,
+	BDI_DIRTIED,
 	BDI_WRITTEN,
 	NR_BDI_STAT_ITEMS
 };

@@ -1333,6 +1333,7 @@ void account_page_dirtied(struct page *p
 		__inc_zone_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_DIRTIED);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+		__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
 		task_dirty_inc(current);
 		task_io_account_write(PAGE_CACHE_SIZE);
 	}

@@ -97,6 +97,7 @@ static int bdi_debug_stats_show(struct s
 		   "BdiDirtyThresh:     %10lu kB\n"
 		   "DirtyThresh:        %10lu kB\n"
 		   "BackgroundThresh:   %10lu kB\n"
+		   "BdiDirtied:         %10lu kB\n"
 		   "BdiWritten:         %10lu kB\n"
 		   "BdiWriteBandwidth:  %10lu kBps\n"
 		   "b_dirty:            %10lu\n"

@@ -109,6 +110,7 @@ static int bdi_debug_stats_show(struct s
 		   K(bdi_thresh),
 		   K(dirty_thresh),
 		   K(background_thresh),
+		   (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)),
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
 		   (unsigned long) K(bdi->write_bandwidth),
 		   nr_dirty,

@@ -46,6 +46,8 @@
  */
 #define BANDWIDTH_INTERVAL	max(HZ/5, 1)
 
+#define RATELIMIT_CALC_SHIFT	10
+
 /*
  * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
  * will look to see if it needs to force writeback or throttling.

@@ -409,6 +411,12 @@ int bdi_set_max_ratio(struct backing_dev
 }
 EXPORT_SYMBOL(bdi_set_max_ratio);
 
+static unsigned long dirty_freerun_ceiling(unsigned long thresh,
+					   unsigned long bg_thresh)
+{
+	return (thresh + bg_thresh) / 2;
+}
+
 static unsigned long hard_dirty_limit(unsigned long thresh)
 {
 	return max(thresh, global_dirty_limit);

@@ -493,6 +501,197 @@ unsigned long bdi_dirty_limit(struct bac
 	return bdi_dirty;
 }
 
+/*
+ * Dirty position control.
+ *
+ * (o) global/bdi setpoints
+ *
+ * We want the dirty pages be balanced around the global/bdi setpoints.
+ * When the number of dirty pages is higher/lower than the setpoint, the
+ * dirty position control ratio (and hence task dirty ratelimit) will be
+ * decreased/increased to bring the dirty pages back to the setpoint.
+ *
+ *     pos_ratio = 1 << RATELIMIT_CALC_SHIFT
+ *
+ *     if (dirty < setpoint) scale up   pos_ratio
+ *     if (dirty > setpoint) scale down pos_ratio
+ *
+ *     if (bdi_dirty < bdi_setpoint) scale up   pos_ratio
+ *     if (bdi_dirty > bdi_setpoint) scale down pos_ratio
+ *
+ *     task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT
+ *
+ * (o) global control line
+ *
+ *     ^ pos_ratio
+ *     |
+ *     |            |<===== global dirty control scope ======>|
+ * 2.0 .............*
+ *     |            .*
+ *     |            . *
+ *     |            .   *
+ *     |            .     *
+ *     |            .        *
+ *     |            .            *
+ * 1.0 ................................*
+ *     |            .                  .     *
+ *     |            .                  .          *
+ *     |            .                  .              *
+ *     |            .                  .                 *
+ *     |            .                  .                    *
+ *   0 +------------.------------------.----------------------*------------->
+ *           freerun^          setpoint^                 limit^   dirty pages
+ *
+ * (o) bdi control lines
+ *
+ * The control lines for the global/bdi setpoints both stretch up to @limit.
+ * The below figure illustrates the main bdi control line with an auxiliary
+ * line extending it to @limit.
+ *
+ *   o
+ *     o
+ *       o                                      [o] main control line
+ *         o                                    [*] auxiliary control line
+ *           o
+ *             o
+ *               o
+ *                 o
+ *                   o
+ *                     o
+ *                       o--------------------- balance point, rate scale = 1
+ *                       | o
+ *                       |   o
+ *                       |     o
+ *                       |       o
+ *                       |         o
+ *                       |           o
+ *                       |             o------- connect point, rate scale = 1/2
+ *                       |               .*
+ *                       |                 .   *
+ *                       |                   .      *
+ *                       |                     .         *
+ *                       |                       .           *
+ *                       |                         .              *
+ *                       |                           .                 *
+ *  [--------------------+-----------------------------.--------------------*]
+ *  0              bdi_setpoint                    x_intercept           limit
+ *
+ * The auxiliary control line allows smoothly throttling bdi_dirty down to
+ * normal if it starts high in situations like
+ * - start writing to a slow SD card and a fast disk at the same time. The SD
+ *   card's bdi_dirty may rush to many times higher than bdi_setpoint.
+ * - the bdi dirty thresh drops quickly due to change of JBOD workload
+ */
+static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
+					unsigned long thresh,
+					unsigned long bg_thresh,
+					unsigned long dirty,
+					unsigned long bdi_thresh,
+					unsigned long bdi_dirty)
+{
+	unsigned long write_bw = bdi->avg_write_bandwidth;
+	unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
+	unsigned long limit = hard_dirty_limit(thresh);
+	unsigned long x_intercept;
+	unsigned long setpoint;		/* dirty pages' target balance point */
+	unsigned long bdi_setpoint;
+	unsigned long span;
+	long long pos_ratio;		/* for scaling up/down the rate limit */
+	long x;
+
+	if (unlikely(dirty >= limit))
+		return 0;
+
+	/*
+	 * global setpoint
+	 *
+	 *                           setpoint - dirty 3
+	 *        f(dirty) := 1.0 + (----------------)
+	 *                           limit - setpoint
+	 *
+	 * it's a 3rd order polynomial that subjects to
+	 *
+	 * (1) f(freerun)  = 2.0 => rampup dirty_ratelimit reasonably fast
+	 * (2) f(setpoint) = 1.0 => the balance point
+	 * (3) f(limit)    = 0   => the hard limit
+	 * (4) df/dx      <= 0	 => negative feedback control
+	 * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
+	 *     => fast response on large errors; small oscillation near setpoint
+	 */
+	setpoint = (freerun + limit) / 2;
+	x = div_s64((setpoint - dirty) << RATELIMIT_CALC_SHIFT,
+		    limit - setpoint + 1);
+	pos_ratio = x;
+	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
+	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
+	pos_ratio += 1 << RATELIMIT_CALC_SHIFT;
+
+	/*
+	 * We have computed basic pos_ratio above based on global situation. If
+	 * the bdi is over/under its share of dirty pages, we want to scale
+	 * pos_ratio further down/up. That is done by the following mechanism.
+	 */
+
+	/*
+	 * bdi setpoint
+	 *
+	 *        f(bdi_dirty) := 1.0 + k * (bdi_dirty - bdi_setpoint)
+	 *
+	 *                        x_intercept - bdi_dirty
+	 *                     := --------------------------
+	 *                        x_intercept - bdi_setpoint
+	 *
+	 * The main bdi control line is a linear function that subjects to
+	 *
+	 * (1) f(bdi_setpoint) = 1.0
+	 * (2) k = - 1 / (8 * write_bw)  (in single bdi case)
+	 *     or equally: x_intercept = bdi_setpoint + 8 * write_bw
+	 *
+	 * For single bdi case, the dirty pages are observed to fluctuate
+	 * regularly within range
+	 *        [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2]
+	 * for various filesystems, where (2) can yield in a reasonable 12.5%
+	 * fluctuation range for pos_ratio.
+	 *
+	 * For JBOD case, bdi_thresh (not bdi_dirty!) could fluctuate up to its
+	 * own size, so move the slope over accordingly and choose a slope that
+	 * yields 100% pos_ratio fluctuation on suddenly doubled bdi_thresh.
+	 */
+	if (unlikely(bdi_thresh > thresh))
+		bdi_thresh = thresh;
+	/*
+	 * scale global setpoint to bdi's:
+	 *	bdi_setpoint = setpoint * bdi_thresh / thresh
+	 */
+	x = div_u64((u64)bdi_thresh << 16, thresh + 1);
+	bdi_setpoint = setpoint * (u64)x >> 16;
+	/*
+	 * Use span=(8*write_bw) in single bdi case as indicated by
+	 * (thresh - bdi_thresh ~= 0) and transit to bdi_thresh in JBOD case.
+	 *
+	 *        bdi_thresh                    thresh - bdi_thresh
+	 * span = ---------- * (8 * write_bw) + ------------------- * bdi_thresh
+	 *          thresh                            thresh
+	 */
+	span = (thresh - bdi_thresh + 8 * write_bw) * (u64)x >> 16;
+	x_intercept = bdi_setpoint + span;
+
+	span >>= 1;
+	if (unlikely(bdi_dirty > bdi_setpoint + span)) {
+		if (unlikely(bdi_dirty > limit))
+			return 0;
+		if (x_intercept < limit) {
+			x_intercept = limit;	/* auxiliary control line */
+			bdi_setpoint += span;
+			pos_ratio >>= 1;
+		}
+	}
+	pos_ratio *= x_intercept - bdi_dirty;
+	do_div(pos_ratio, x_intercept - bdi_setpoint + 1);
+
+	return pos_ratio;
+}
+
 static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
 				       unsigned long elapsed,
 				       unsigned long written)

@@ -591,6 +790,7 @@ static void global_update_bandwidth(unsi
 
 void __bdi_update_bandwidth(struct backing_dev_info *bdi,
 			    unsigned long thresh,
+			    unsigned long bg_thresh,
 			    unsigned long dirty,
 			    unsigned long bdi_thresh,
 			    unsigned long bdi_dirty,

@@ -627,6 +827,7 @@ snapshot:
 
 static void bdi_update_bandwidth(struct backing_dev_info *bdi,
 				 unsigned long thresh,
+				 unsigned long bg_thresh,
 				 unsigned long dirty,
 				 unsigned long bdi_thresh,
 				 unsigned long bdi_dirty,

@@ -635,8 +836,8 @@ static void bdi_update_bandwidth(struct 
 	if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL))
 		return;
 	spin_lock(&bdi->wb.list_lock);
-	__bdi_update_bandwidth(bdi, thresh, dirty, bdi_thresh, bdi_dirty,
-			       start_time);
+	__bdi_update_bandwidth(bdi, thresh, bg_thresh, dirty,
+			       bdi_thresh, bdi_dirty, start_time);
 	spin_unlock(&bdi->wb.list_lock);
 }
 

@@ -677,7 +878,8 @@ static void balance_dirty_pages(struct a
 		 * catch-up. This avoids (excessively) small writeouts
 		 * when the bdi limits are ramping up.
 		 */
-		if (nr_dirty <= (background_thresh + dirty_thresh) / 2)
+		if (nr_dirty <= dirty_freerun_ceiling(dirty_thresh,
+						      background_thresh))
 			break;
 
 		bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);

@@ -721,8 +923,9 @@ static void balance_dirty_pages(struct a
 		if (!bdi->dirty_exceeded)
 			bdi->dirty_exceeded = 1;
 
-		bdi_update_bandwidth(bdi, dirty_thresh, nr_dirty,
-				     bdi_thresh, bdi_dirty, start_time);
+		bdi_update_bandwidth(bdi, dirty_thresh, background_thresh,
+				     nr_dirty, bdi_thresh, bdi_dirty,
+				     start_time);
 
 		/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
 		 * Unstable writes are a feature of certain networked

@@ -675,7 +675,7 @@ static inline bool over_bground_thresh(v
 static void wb_update_bandwidth(struct bdi_writeback *wb,
 				unsigned long start_time)
 {
-	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, start_time);
+	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time);
 }
 
 /*

@@ -141,6 +141,7 @@ unsigned long bdi_dirty_limit(struct bac
 
 void __bdi_update_bandwidth(struct backing_dev_info *bdi,
 			    unsigned long thresh,
+			    unsigned long bg_thresh,
 			    unsigned long dirty,
 			    unsigned long bdi_thresh,
 			    unsigned long bdi_dirty,

@@ -75,10 +75,17 @@ struct backing_dev_info {
 	struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
 
 	unsigned long bw_time_stamp;	/* last time write bw is updated */
+	unsigned long dirtied_stamp;
 	unsigned long written_stamp;	/* pages written at bw_time_stamp */
 	unsigned long write_bandwidth;	/* the estimated write bandwidth */
 	unsigned long avg_write_bandwidth; /* further smoothed write bw */
 
+	/*
+	 * The base dirty throttle rate, re-calculated on every 200ms.
+	 * All the bdi tasks' dirty rate will be curbed under it.
+	 */
+	unsigned long dirty_ratelimit;
+
 	struct prop_local_percpu completions;
 	int dirty_exceeded;
 

@@ -670,6 +670,7 @@ int bdi_init(struct backing_dev_info *bd
 	bdi->bw_time_stamp = jiffies;
 	bdi->written_stamp = 0;
 
+	bdi->dirty_ratelimit = INIT_BW;
 	bdi->write_bandwidth = INIT_BW;
 	bdi->avg_write_bandwidth = INIT_BW;
 

110 lines not on this page · raw message

@@ -809,6 +809,7 @@ static void bdi_update_dirty_ratelimit(s
 	unsigned long task_ratelimit;
 	unsigned long balanced_dirty_ratelimit;
 	unsigned long pos_ratio;
+	unsigned long step;
 
 	/*
 	 * The dirty rate will match the writeout rate in long term, except

@@ -857,7 +858,68 @@ static void bdi_update_dirty_ratelimit(s
 	balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw,
 					   dirty_rate | 1);
 
-	bdi->dirty_ratelimit = max(balanced_dirty_ratelimit, 1UL);
+	/*
+	 * We could safely do this and return immediately:
+	 *
+	 *	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
+	 * limit the step size.
+	 *
+	 * The below code essentially only uses the relative value of
+	 *
+	 *	task_ratelimit - dirty_ratelimit
+	 *	= (pos_ratio - 1) * dirty_ratelimit
+	 *
+	 * which reflects the direction and size of dirty position error.
+	 */
+
+	/*
+	 * dirty_ratelimit will follow balanced_dirty_ratelimit iff
+	 * task_ratelimit is on the same side of dirty_ratelimit, too.
+	 * For example, when
+	 * - dirty_ratelimit > balanced_dirty_ratelimit
+	 * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint)
+	 * lowering dirty_ratelimit will help meet both the position and rate
+	 * control targets. Otherwise, don't update dirty_ratelimit if it will
+	 * only help meet the rate target. After all, what the users ultimately
+	 * 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
+	 * 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).
+	 */
+	step = 0;
+	if (dirty_ratelimit < balanced_dirty_ratelimit) {
+		if (dirty_ratelimit < task_ratelimit)
+			step = min(balanced_dirty_ratelimit,
+				   task_ratelimit) - dirty_ratelimit;
+	} else {
+		if (dirty_ratelimit > task_ratelimit)
+			step = dirty_ratelimit - max(balanced_dirty_ratelimit,
+						     task_ratelimit);
+	}
+
+	/*
+	 * Don't pursue 100% rate matching. It's impossible since the balanced
+	 * rate itself is constantly fluctuating. So decrease the track speed
+	 * when it gets close to the target. Helps eliminate pointless tremors.
+	 */
+	step >>= dirty_ratelimit / (8 * step + 1);
+	/*
+	 * Limit the tracking speed to avoid overshooting.
+	 */
+	step = (step + 7) / 8;
+
+	if (dirty_ratelimit < balanced_dirty_ratelimit)
+		dirty_ratelimit += step;
+	else
+		dirty_ratelimit -= step;
+
+	bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL);
 }
 
 void __bdi_update_bandwidth(struct backing_dev_info *bdi,

@@ -1525,6 +1525,13 @@ struct task_struct {
 	int make_it_fail;
 #endif
 	struct prop_local_single dirties;
+	/*
+	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
+	 * balance_dirty_pages() for some dirty throttling pause
+	 */
+	int nr_dirtied;
+	int nr_dirtied_pause;
+
 #ifdef CONFIG_LATENCYTOP
 	int latency_record_count;
 	struct latency_record latency_record[LT_SAVECOUNT];

148 lines not on this page · raw message

@@ -1301,6 +1301,9 @@ static struct task_struct *copy_process(
 	p->pdeath_signal = 0;
 	p->exit_state = 0;
 
+	p->nr_dirtied = 0;
+	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
+
 	/*
 	 * Ok, make it visible to the rest of the system.
 	 * We dont wake it up yet.

@@ -309,50 +309,6 @@ static void bdi_writeout_fraction(struct
 				numerator, denominator);
 }
 
-static inline void task_dirties_fraction(struct task_struct *tsk,
-		long *numerator, long *denominator)
-{
-	prop_fraction_single(&vm_dirties, &tsk->dirties,
-				numerator, denominator);
-}
-
-/*
- * task_dirty_limit - scale down dirty throttling threshold for one task
- *
- * task specific dirty limit:
- *
- *   dirty -= (dirty/8) * p_{t}
- *
- * To protect light/slow dirtying tasks from heavier/fast ones, we start
- * throttling individual tasks before reaching the bdi dirty limit.
- * Relatively low thresholds will be allocated to heavy dirtiers. So when
- * dirty pages grow large, heavy dirtiers will be throttled first, which will
- * effectively curb the growth of dirty pages. Light dirtiers with high enough
- * dirty threshold may never get throttled.
- */
-#define TASK_LIMIT_FRACTION 8
-static unsigned long task_dirty_limit(struct task_struct *tsk,
-				       unsigned long bdi_dirty)
-{
-	long numerator, denominator;
-	unsigned long dirty = bdi_dirty;
-	u64 inv = dirty / TASK_LIMIT_FRACTION;
-
-	task_dirties_fraction(tsk, &numerator, &denominator);
-	inv *= numerator;
-	do_div(inv, denominator);
-
-	dirty -= inv;
-
-	return max(dirty, bdi_dirty/2);
-}
-
-/* Minimum limit for any task */
-static unsigned long task_min_dirty_limit(unsigned long bdi_dirty)
-{
-	return bdi_dirty - bdi_dirty / TASK_LIMIT_FRACTION;
-}
-
 /*
  *
  */

@@ -989,29 +945,34 @@ static unsigned long dirty_poll_interval
 /*
  * balance_dirty_pages() must be called by processes which are generating dirty
  * data.  It looks at the number of dirty pages in the machine and will force
- * the caller to perform writeback if the system is over `vm_dirty_ratio'.
+ * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2.
  * If we're over `background_thresh' then the writeback threads are woken to
  * perform some writeout.
  */
 static void balance_dirty_pages(struct address_space *mapping,
-				unsigned long write_chunk)
+				unsigned long pages_dirtied)
 {
-	unsigned long nr_reclaimable, bdi_nr_reclaimable;
+	unsigned long nr_reclaimable;
 	unsigned long nr_dirty;  /* = file_dirty + writeback + unstable_nfs */
 	unsigned long bdi_dirty;
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
-	unsigned long task_bdi_thresh;
-	unsigned long min_task_bdi_thresh;
-	unsigned long pages_written = 0;
-	unsigned long pause = 1;
+	long pause = 0;
 	bool dirty_exceeded = false;
-	bool clear_dirty_exceeded = true;
+	unsigned long task_ratelimit;
+	unsigned long base_rate;
+	unsigned long pos_ratio;
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 	unsigned long start_time = jiffies;
 
 	for (;;) {
+		/*
+		 * Unstable writes are a feature of certain networked
+		 * filesystems (i.e. NFS) in which data may have been
+		 * written to the server's write cache, but has not yet
+		 * been flushed to permanent storage.
+		 */
 		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
 					global_page_state(NR_UNSTABLE_NFS);
 		nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);

@@ -1027,9 +988,23 @@ static void balance_dirty_pages(struct a
 						      background_thresh))
 			break;
 
+		if (unlikely(!writeback_in_progress(bdi)))
+			bdi_start_background_writeback(bdi);
+
+		/*
+		 * bdi_thresh is not treated as some limiting factor as
+		 * dirty_thresh, due to reasons
+		 * - in JBOD setup, bdi_thresh can fluctuate a lot
+		 * - in a system with HDD and USB key, the USB key may somehow
+		 *   go into state (bdi_dirty >> bdi_thresh) either because
+		 *   bdi_dirty starts high, or because bdi_thresh drops low.
+		 *   In this case we don't want to hard throttle the USB key
+		 *   dirtiers for 100 seconds until bdi_dirty drops under
+		 *   bdi_thresh. Instead the auxiliary bdi control line in
+		 *   bdi_position_ratio() will let the dirtier task progress
+		 *   at some rate <= (write_bw / 2) for bringing down bdi_dirty.
+		 */
 		bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
-		min_task_bdi_thresh = task_min_dirty_limit(bdi_thresh);
-		task_bdi_thresh = task_dirty_limit(current, bdi_thresh);
 
 		/*
 		 * In order to avoid the stacked BDI deadlock we need

@@ -1041,57 +1016,38 @@ static void balance_dirty_pages(struct a
 		 * actually dirty; with m+n sitting in the percpu
 		 * deltas.
 		 */
-		if (task_bdi_thresh < 2 * bdi_stat_error(bdi)) {
-			bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
-			bdi_dirty = bdi_nr_reclaimable +
+		if (bdi_thresh < 2 * bdi_stat_error(bdi))
+			bdi_dirty = bdi_stat_sum(bdi, BDI_RECLAIMABLE) +
 				    bdi_stat_sum(bdi, BDI_WRITEBACK);
-		} else {
-			bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
-			bdi_dirty = bdi_nr_reclaimable +
+		else
+			bdi_dirty = bdi_stat(bdi, BDI_RECLAIMABLE) +
 				    bdi_stat(bdi, BDI_WRITEBACK);
-		}
 
-		/*
-		 * The bdi thresh is somehow "soft" limit derived from the
-		 * global "hard" limit. The former helps to prevent heavy IO
-		 * bdi or process from holding back light ones; The latter is
-		 * the last resort safeguard.
-		 */
-		dirty_exceeded = (bdi_dirty > task_bdi_thresh) ||
+		dirty_exceeded = (bdi_dirty > bdi_thresh) ||
 				  (nr_dirty > dirty_thresh);
-		clear_dirty_exceeded = (bdi_dirty <= min_task_bdi_thresh) &&
-					(nr_dirty <= dirty_thresh);
-
-		if (!dirty_exceeded)
-			break;
-
-		if (!bdi->dirty_exceeded)
+		if (dirty_exceeded && !bdi->dirty_exceeded)
 			bdi->dirty_exceeded = 1;
 
 		bdi_update_bandwidth(bdi, dirty_thresh, background_thresh,
 				     nr_dirty, bdi_thresh, bdi_dirty,
 				     start_time);
 
-		/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
-		 * Unstable writes are a feature of certain networked
-		 * filesystems (i.e. NFS) in which data may have been
-		 * written to the server's write cache, but has not yet
-		 * been flushed to permanent storage.
-		 * Only move pages to writeback if this bdi is over its
-		 * threshold otherwise wait until the disk writes catch
-		 * up.
-		 */
-		trace_balance_dirty_start(bdi);
-		if (bdi_nr_reclaimable > task_bdi_thresh) {
-			pages_written += writeback_inodes_wb(&bdi->wb,
-							     write_chunk);
-			trace_balance_dirty_written(bdi, pages_written);
-			if (pages_written >= write_chunk)
-				break;		/* We've done our duty */
+		base_rate = bdi->dirty_ratelimit;
+		pos_ratio = bdi_position_ratio(bdi, dirty_thresh,
+					       background_thresh, nr_dirty,
+					       bdi_thresh, bdi_dirty);
+		if (unlikely(pos_ratio == 0)) {
+			pause = MAX_PAUSE;
+			goto pause;
 		}
+		task_ratelimit = (u64)base_rate *
+					pos_ratio >> RATELIMIT_CALC_SHIFT;
+		pause = (HZ * pages_dirtied) / (task_ratelimit | 1);
+		pause = min(pause, (long)MAX_PAUSE);
+
+pause:
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		io_schedule_timeout(pause);
-		trace_balance_dirty_wait(bdi);
 
 		dirty_thresh = hard_dirty_limit(dirty_thresh);
 		/*

@@ -1100,22 +1056,11 @@ static void balance_dirty_pages(struct a
 		 * 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 &&
-		    bdi_dirty < (task_bdi_thresh + bdi_thresh) / 2 &&
-		    time_after(jiffies, start_time + MAX_PAUSE))
+		if (nr_dirty < dirty_thresh)
 			break;
-
-		/*
-		 * Increase the delay for each loop, up to our previous
-		 * default of taking a 100ms nap.
-		 */
-		pause <<= 1;
-		if (pause > HZ / 10)
-			pause = HZ / 10;
 	}
 
-	/* Clear dirty_exceeded flag only when no task can exceed the limit */
-	if (clear_dirty_exceeded && bdi->dirty_exceeded)
+	if (!dirty_exceeded && bdi->dirty_exceeded)
 		bdi->dirty_exceeded = 0;
 
 	current->nr_dirtied = 0;

@@ -1132,8 +1077,10 @@ static void balance_dirty_pages(struct a
 	 * In normal mode, we start background writeout at the lower
 	 * background_thresh, to keep the amount of dirty memory low.
 	 */
-	if ((laptop_mode && pages_written) ||
-	    (!laptop_mode && (nr_reclaimable > background_thresh)))
+	if (laptop_mode)
+		return;
+
+	if (nr_reclaimable > background_thresh)
 		bdi_start_background_writeback(bdi);
 }
 

@@ -104,30 +104,6 @@ DEFINE_WRITEBACK_EVENT(writeback_bdi_reg
 DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
 DEFINE_WRITEBACK_EVENT(writeback_thread_start);
 DEFINE_WRITEBACK_EVENT(writeback_thread_stop);
-DEFINE_WRITEBACK_EVENT(balance_dirty_start);
-DEFINE_WRITEBACK_EVENT(balance_dirty_wait);
-
-TRACE_EVENT(balance_dirty_written,
-
-	TP_PROTO(struct backing_dev_info *bdi, int written),
-
-	TP_ARGS(bdi, written),
-
-	TP_STRUCT__entry(
-		__array(char,	name, 32)
-		__field(int,	written)
-	),
-
-	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
-		__entry->written = written;
-	),
-
-	TP_printk("bdi %s written %d",
-		  __entry->name,
-		  __entry->written
-	)
-);
 
 DECLARE_EVENT_CLASS(wbc_class,
 	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi),

@@ -1531,6 +1531,7 @@ struct task_struct {
 	 */
 	int nr_dirtied;
 	int nr_dirtied_pause;
+	unsigned long dirty_paused_when; /* start of a write-and-pause period */
 
 #ifdef CONFIG_LATENCYTOP
 	int latency_record_count;

@@ -913,6 +913,7 @@ static void balance_dirty_pages(struct a
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
+	long period;
 	long pause = 0;
 	bool dirty_exceeded = false;
 	unsigned long task_ratelimit;

@@ -922,6 +923,8 @@ static void balance_dirty_pages(struct a
 	unsigned long start_time = jiffies;
 
 	for (;;) {
+		unsigned long now = jiffies;
+
 		/*
 		 * Unstable writes are a feature of certain networked
 		 * filesystems (i.e. NFS) in which data may have been

@@ -940,8 +943,11 @@ static void balance_dirty_pages(struct a
 		 * when the bdi limits are ramping up.
 		 */
 		if (nr_dirty <= dirty_freerun_ceiling(dirty_thresh,
-						      background_thresh))
+						      background_thresh)) {
+			current->dirty_paused_when = now;
+			current->nr_dirtied = 0;
 			break;
+		}
 
 		bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 

@@ -979,18 +985,41 @@ static void balance_dirty_pages(struct a
 					       background_thresh, nr_dirty,
 					       bdi_thresh, bdi_dirty);
 		if (unlikely(pos_ratio == 0)) {
+			period = MAX_PAUSE;
 			pause = MAX_PAUSE;
 			goto pause;
 		}
 		task_ratelimit = (u64)base_rate *
 					pos_ratio >> RATELIMIT_CALC_SHIFT;
-		pause = (HZ * pages_dirtied) / (task_ratelimit | 1);
+		period = (HZ * pages_dirtied) / (task_ratelimit | 1);
+		pause = current->dirty_paused_when + period - now;
+		/*
+		 * For less than 1s think time (ext3/4 may block the dirtier
+		 * for up to 800ms from time to time on 1-HDD; so does xfs,
+		 * however at much less frequency), try to compensate it in
+		 * future periods by updating the virtual time; otherwise just
+		 * do a reset, as it may be a light dirtier.
+		 */
+		if (unlikely(pause <= 0)) {
+			if (pause < -HZ) {
+				current->dirty_paused_when = now;
+				current->nr_dirtied = 0;
+			} else if (period) {
+				current->dirty_paused_when += period;
+				current->nr_dirtied = 0;
+			}
+			pause = 1; /* avoid resetting nr_dirtied_pause below */
+			break;
+		}
 		pause = min(pause, (long)MAX_PAUSE);
 
 pause:
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		io_schedule_timeout(pause);
 
+		current->dirty_paused_when = now + pause;
+		current->nr_dirtied = 0;
+
 		dirty_thresh = hard_dirty_limit(dirty_thresh);
 		/*
 		 * max-pause area. If dirty exceeded but still within this

@@ -1017,7 +1046,6 @@ pause:
 	if (!dirty_exceeded && bdi->dirty_exceeded)
 		bdi->dirty_exceeded = 0;
 
-	current->nr_dirtied = 0;
 	current->nr_dirtied_pause = dirty_poll_interval(nr_dirty, dirty_thresh);
 
 	if (writeback_in_progress(bdi))

@@ -1303,6 +1303,7 @@ static struct task_struct *copy_process(
 
 	p->nr_dirtied = 0;
 	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
+	p->dirty_paused_when = 0;
 
 	/*
 	 * Ok, make it visible to the rest of the system.

@@ -270,6 +270,85 @@ TRACE_EVENT(dirty_ratelimit,
 	)
 );
 
+TRACE_EVENT(balance_dirty_pages,
+
+	TP_PROTO(struct backing_dev_info *bdi,
+		 unsigned long thresh,
+		 unsigned long bg_thresh,
+		 unsigned long dirty,
+		 unsigned long bdi_thresh,
+		 unsigned long bdi_dirty,
+		 unsigned long base_rate,
+		 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,
+		base_rate, task_ratelimit, dirtied, period, pause, start_time),
+
+	TP_STRUCT__entry(
+		__array(	 char,	bdi, 32)
+		__field(unsigned long,	limit)
+		__field(unsigned long,	goal)
+		__field(unsigned long,	dirty)
+		__field(unsigned long,	bdi_goal)
+		__field(unsigned long,	bdi_dirty)
+		__field(unsigned long,	base_rate)
+		__field(unsigned long,	task_ratelimit)
+		__field(unsigned int,	dirtied)
+		__field(unsigned int,	dirtied_pause)
+		__field(unsigned long,	period)
+		__field(	 long,	think)
+		__field(	 long,	pause)
+		__field(unsigned long,	paused)
+	),
+
+	TP_fast_assign(
+		unsigned long freerun = (thresh + bg_thresh) / 2;
+		strlcpy(__entry->bdi, dev_name(bdi->dev), 32);
+
+		__entry->limit		= global_dirty_limit;
+		__entry->goal		= (global_dirty_limit + freerun) / 2;
+		__entry->dirty		= dirty;
+		__entry->bdi_goal	= __entry->goal * bdi_thresh / (thresh|1);
+		__entry->bdi_dirty	= bdi_dirty;
+		__entry->base_rate	= KBps(base_rate);
+		__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;
+	),
+
+
+	TP_printk("bdi %s: "
+		  "limit=%lu goal=%lu dirty=%lu "
+		  "bdi_goal=%lu bdi_dirty=%lu "
+		  "base_rate=%lu task_ratelimit=%lu "
+		  "dirtied=%u dirtied_pause=%u "
+		  "period=%lu think=%ld pause=%ld paused=%lu",
+		  __entry->bdi,
+		  __entry->limit,
+		  __entry->goal,
+		  __entry->dirty,
+		  __entry->bdi_goal,
+		  __entry->bdi_dirty,
+		  __entry->base_rate,	/* bdi base throttle bandwidth */
+		  __entry->task_ratelimit,	/* task throttle bandwidth */
+		  __entry->dirtied,
+		  __entry->dirtied_pause,
+		  __entry->period,	/* ms */
+		  __entry->think,	/* ms */
+		  __entry->pause,	/* ms */
+		  __entry->paused	/* ms */
+	  )
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),

@@ -946,6 +946,18 @@ static void balance_dirty_pages(struct a
 		 * do a reset, as it may be a light dirtier.
 		 */
 		if (unlikely(pause <= 0)) {
+			trace_balance_dirty_pages(bdi,
+						  dirty_thresh,
+						  background_thresh,
+						  nr_dirty,
+						  bdi_thresh,
+						  bdi_dirty,
+						  base_rate,
+						  task_ratelimit,
+						  pages_dirtied,
+						  period,
+						  pause,
+						  start_time);
 			if (pause < -HZ) {
 				current->dirty_paused_when = now;
 				current->nr_dirtied = 0;

@@ -959,6 +971,18 @@ static void balance_dirty_pages(struct a
 		pause = min(pause, MAX_PAUSE);
 
 pause:
+		trace_balance_dirty_pages(bdi,
+					  dirty_thresh,
+					  background_thresh,
+					  nr_dirty,
+					  bdi_thresh,
+					  bdi_dirty,
+					  base_rate,
+					  task_ratelimit,
+					  pages_dirtied,
+					  period,
+					  pause,
+					  start_time);
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		io_schedule_timeout(pause);
 

@@ -864,6 +864,9 @@ static void bdi_update_dirty_ratelimit(s
 		dirty_ratelimit -= step;
 
 	bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL);
+
+	trace_dirty_ratelimit(bdi, dirty_rate, task_ratelimit,
+			      balanced_dirty_ratelimit);
 }
 
 void __bdi_update_bandwidth(struct backing_dev_info *bdi,

52 lines not on this page · raw message

@@ -180,6 +180,38 @@ TRACE_EVENT(writeback_queue_io,
 		__entry->moved)
 );
 
+TRACE_EVENT(task_io,
+	TP_PROTO(struct task_struct *task),
+	TP_ARGS(task),
+
+	TP_STRUCT__entry(
+		__field(unsigned long long,	read_bytes)
+		__field(unsigned long long,	write_bytes)
+		__field(unsigned long long,	cancelled_write_bytes)
+	),
+
+	TP_fast_assign(
+		struct task_io_accounting *ioac = &task->ioac;
+
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+		__entry->read_bytes		= ioac->read_bytes;
+		__entry->write_bytes		= ioac->write_bytes;
+		__entry->cancelled_write_bytes	= ioac->cancelled_write_bytes;
+#else
+		__entry->read_bytes		= 0;
+		__entry->write_bytes		= 0;
+		__entry->cancelled_write_bytes	= 0;
+#endif
+	),
+
+	TP_printk("read=%llu write=%llu cancelled_write=%llu",
+		  __entry->read_bytes,
+		  __entry->write_bytes,
+		  __entry->cancelled_write_bytes
+	)
+);
+
+
 TRACE_EVENT(global_dirty_state,
 
 	TP_PROTO(unsigned long background_thresh,

@@ -407,6 +407,7 @@ void global_dirty_limits(unsigned long *
 	*pbackground = background;
 	*pdirty = dirty;
 	trace_global_dirty_state(background, dirty);
+	trace_task_io(current);
 }
 
 /**