Skip to contentSkip to conversation

rcu/kvfree: Update KFREE_DRAIN_JIFFIES interval

PATCH In review Uladzislau Rezki (Sony) 2 participants 2 messages Jun 30, 2022 – Jul 1, 2022 RCU

lore
Share & tools
lore

Uladzislau Rezki (Sony)

author maintainer
#0 lore raw

PATCH v4 1/1 rcu/kvfree: Update KFREE_DRAIN_JIFFIES interval

Currently the monitor work is scheduled with a fixed interval of HZ/20, which is roughly 50 milliseconds. The drawback of this approach is low utilization of the 512 page slots in scenarios with infrequence kvfree_rcu() calls. For example on an Android system:

<snip>

  kworker/3:3-507     [003] ....   470.286305: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=6
  kworker/6:1-76      [006] ....   470.416613: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000ea0d6556 nr_records=1
  kworker/6:1-76      [006] ....   470.416625: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000003e025849 nr_records=9
  kworker/3:3-507     [003] ....   471.390000: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000815a8713 nr_records=48
  kworker/1:1-73      [001] ....   471.725785: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000fda9bf20 nr_records=3
  kworker/1:1-73      [001] ....   471.725833: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000a425b67b nr_records=76
  kworker/0:4-1411    [000] ....   472.085673: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007996be9d nr_records=1
  kworker/0:4-1411    [000] ....   472.085728: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=5
  kworker/6:1-76      [006] ....   472.260340: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000065630ee4 nr_records=102

<snip>

in many cases, out of 512 slots, fewer than 10 were actually used. In order to improve batching and make utilization more efficient this commit sets a drain interval to a fixed 5-seconds interval. Floods are detected when a page fills quickly, and in that case, the reclaim work is re-scheduled for the next scheduling-clock tick (jiffy).

After this change:

<snip>

  kworker/7:1-371     [007] ....  5630.725708: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000005ab0ffb3 nr_records=121
  kworker/7:1-371     [007] ....  5630.989702: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000060c84761 nr_records=47
  kworker/7:1-371     [007] ....  5630.989714: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000000babf308 nr_records=510
  kworker/7:1-371     [007] ....  5631.553790: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000bb7bd0ef nr_records=169
  kworker/7:1-371     [007] ....  5631.553808: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000044c78753 nr_records=510
  kworker/5:6-9428    [005] ....  5631.746102: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d98519aa nr_records=123
  kworker/4:7-9434    [004] ....  5632.001758: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000526c9d44 nr_records=322
  kworker/4:7-9434    [004] ....  5632.002073: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000002c6a8afa nr_records=185
  kworker/7:1-371     [007] ....  5632.277515: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007f4a962f nr_records=510

<snip>

---
 kernel/rcu/tree.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)
kernel/rcu/tree.c +23 -4
index fd16c0b46d9e..a1b0a5736916 100644
@@ -3249,7 +3249,7 @@ EXPORT_SYMBOL_GPL(call_rcu);
 
 
 /* Maximum number of jiffies to wait before draining a batch. */
-#define KFREE_DRAIN_JIFFIES (HZ / 50)
+#define KFREE_DRAIN_JIFFIES (5 * HZ)
 #define KFREE_N_BATCHES 2
 #define FREE_N_CHANNELS 2
 
@@ -3510,6 +3510,25 @@ need_offload_krc(struct kfree_rcu_cpu *krcp)
 	return !!krcp->head;
 }
 
+static void
+schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
+{
+	long delay, delay_left;
+
+	delay = READ_ONCE(krcp->count) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES;
+
+	if (delayed_work_pending(&krcp->monitor_work)) {
+		delay_left = krcp->monitor_work.timer.expires - jiffies;
+
+		if (delay < delay_left)
+			mod_delayed_work(system_wq, &krcp->monitor_work, delay);
+
+		return;
+	}
+
+	queue_delayed_work(system_wq, &krcp->monitor_work, delay);
+}
+
 /*
  * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
  */
@@ -3567,7 +3586,7 @@ static void kfree_rcu_monitor(struct work_struct *work)
 	// work to repeat an attempt. Because previous batches are
 	// still in progress.
 	if (need_offload_krc(krcp))
-		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+		schedule_delayed_monitor_work(krcp);
 
 	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
@@ -3755,7 +3774,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
-		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+		schedule_delayed_monitor_work(krcp);
 
 unlock_return:
 	krc_this_cpu_unlock(krcp, flags);
@@ -3831,7 +3850,7 @@ void __init kfree_rcu_scheduler_running(void)
 
 		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (need_offload_krc(krcp))
-			schedule_delayed_work_on(cpu, &krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+			schedule_delayed_monitor_work(krcp);
 		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 	}
 }
Signature · 1 line
2.30.2
maintainer
#1 lore raw
Quoted 35 lines · Uladzislau Rezki (Sony)

Currently the monitor work is scheduled with a fixed interval of HZ/20, which is roughly 50 milliseconds. The drawback of this approach is low utilization of the 512 page slots in scenarios with infrequence kvfree_rcu() calls. For example on an Android system:

<snip>

  kworker/3:3-507     [003] ....   470.286305: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=6
  kworker/6:1-76      [006] ....   470.416613: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000ea0d6556 nr_records=1
  kworker/6:1-76      [006] ....   470.416625: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000003e025849 nr_records=9
  kworker/3:3-507     [003] ....   471.390000: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000815a8713 nr_records=48
  kworker/1:1-73      [001] ....   471.725785: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000fda9bf20 nr_records=3
  kworker/1:1-73      [001] ....   471.725833: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000a425b67b nr_records=76
  kworker/0:4-1411    [000] ....   472.085673: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007996be9d nr_records=1
  kworker/0:4-1411    [000] ....   472.085728: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=5
  kworker/6:1-76      [006] ....   472.260340: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000065630ee4 nr_records=102

<snip>

in many cases, out of 512 slots, fewer than 10 were actually used. In order to improve batching and make utilization more efficient this commit sets a drain interval to a fixed 5-seconds interval. Floods are detected when a page fills quickly, and in that case, the reclaim work is re-scheduled for the next scheduling-clock tick (jiffy).

After this change:

<snip>

  kworker/7:1-371     [007] ....  5630.725708: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000005ab0ffb3 nr_records=121
  kworker/7:1-371     [007] ....  5630.989702: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000060c84761 nr_records=47
  kworker/7:1-371     [007] ....  5630.989714: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000000babf308 nr_records=510
  kworker/7:1-371     [007] ....  5631.553790: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000bb7bd0ef nr_records=169
  kworker/7:1-371     [007] ....  5631.553808: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000044c78753 nr_records=510
  kworker/5:6-9428    [005] ....  5631.746102: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d98519aa nr_records=123
  kworker/4:7-9434    [004] ....  5632.001758: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000526c9d44 nr_records=322
  kworker/4:7-9434    [004] ....  5632.002073: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000002c6a8afa nr_records=185
  kworker/7:1-371     [007] ....  5632.277515: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007f4a962f nr_records=510
Quoted 3 lines

<snip>

Very good! As usual, I did a bit of wordsmithing, so please let me know if I messed anything up.

Thanx, Paul

------------------------------------------------------------------------

commit 57720248bb6152ea37348bc04a7f73940e4b5efe

Author: Uladzislau Rezki (Sony) <[email protected]>
Date:   Thu Jun 30 18:33:35 2022 +0200
    rcu/kvfree: Update KFREE_DRAIN_JIFFIES interval
    
    Currently the monitor work is scheduled with a fixed interval of HZ/20,
    which is roughly 50 milliseconds. The drawback of this approach is
    low utilization of the 512 page slots in scenarios with infrequence
    kvfree_rcu() calls.  For example on an Android system:
    
    <snip>
      kworker/3:3-507     [003] ....   470.286305: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=6
      kworker/6:1-76      [006] ....   470.416613: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000ea0d6556 nr_records=1
      kworker/6:1-76      [006] ....   470.416625: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000003e025849 nr_records=9
      kworker/3:3-507     [003] ....   471.390000: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000815a8713 nr_records=48
      kworker/1:1-73      [001] ....   471.725785: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000fda9bf20 nr_records=3
      kworker/1:1-73      [001] ....   471.725833: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000a425b67b nr_records=76
      kworker/0:4-1411    [000] ....   472.085673: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007996be9d nr_records=1
      kworker/0:4-1411    [000] ....   472.085728: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d0f0dde5 nr_records=5
      kworker/6:1-76      [006] ....   472.260340: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000065630ee4 nr_records=102
    <snip>
    
    In many cases, out of 512 slots, fewer than 10 were actually used.
    In order to improve batching and make utilization more efficient this
    commit sets a drain interval to a fixed 5-seconds interval. Floods are
    detected when a page fills quickly, and in that case, the reclaim work
    is re-scheduled for the next scheduling-clock tick (jiffy).
    
    After this change:
    
    <snip>
      kworker/7:1-371     [007] ....  5630.725708: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000005ab0ffb3 nr_records=121
      kworker/7:1-371     [007] ....  5630.989702: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000060c84761 nr_records=47
      kworker/7:1-371     [007] ....  5630.989714: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000000babf308 nr_records=510
      kworker/7:1-371     [007] ....  5631.553790: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000bb7bd0ef nr_records=169
      kworker/7:1-371     [007] ....  5631.553808: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x0000000044c78753 nr_records=510
      kworker/5:6-9428    [005] ....  5631.746102: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000d98519aa nr_records=123
      kworker/4:7-9434    [004] ....  5632.001758: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x00000000526c9d44 nr_records=322
      kworker/4:7-9434    [004] ....  5632.002073: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000002c6a8afa nr_records=185
      kworker/7:1-371     [007] ....  5632.277515: rcu_invoke_kfree_bulk_callback: rcu_preempt bulk=0x000000007f4a962f nr_records=510
    <snip>
    
    Here, all but one of the cases, more than one hundreds slots were used,
    representing an order-of-magnitude improvement.
    
    Signed-off-by: Uladzislau Rezki (Sony) <[email protected]>
    Signed-off-by: Paul E. McKenney <[email protected]>
kernel/rcu/tree.c +19 -4
index b2c499f89e9ff..84d2817766888 100644
@@ -2832,7 +2832,7 @@ EXPORT_SYMBOL_GPL(call_rcu);
 
 
 /* Maximum number of jiffies to wait before draining a batch. */
-#define KFREE_DRAIN_JIFFIES (HZ / 50)
+#define KFREE_DRAIN_JIFFIES (5 * HZ)
 #define KFREE_N_BATCHES 2
 #define FREE_N_CHANNELS 2
 
@@ -3093,6 +3093,21 @@ need_offload_krc(struct kfree_rcu_cpu *krcp)
 	return !!krcp->head;
 }
 
+static void
+schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
+{
+	long delay, delay_left;
+
+	delay = READ_ONCE(krcp->count) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES;
+	if (delayed_work_pending(&krcp->monitor_work)) {
+		delay_left = krcp->monitor_work.timer.expires - jiffies;
+		if (delay < delay_left)
+			mod_delayed_work(system_wq, &krcp->monitor_work, delay);
+		return;
+	}
+	queue_delayed_work(system_wq, &krcp->monitor_work, delay);
+}
+
 /*
  * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
  */
@@ -3150,7 +3165,7 @@ static void kfree_rcu_monitor(struct work_struct *work)
 	// work to repeat an attempt. Because previous batches are
 	// still in progress.
 	if (need_offload_krc(krcp))
-		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+		schedule_delayed_monitor_work(krcp);
 
 	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
@@ -3339,7 +3354,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
-		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+		schedule_delayed_monitor_work(krcp);
 
 unlock_return:
 	krc_this_cpu_unlock(krcp, flags);
@@ -3415,7 +3430,7 @@ void __init kfree_rcu_scheduler_running(void)
 
 		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (need_offload_krc(krcp))
-			schedule_delayed_work_on(cpu, &krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+			schedule_delayed_monitor_work(krcp);
 		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 	}
 }