Re: Interesting interaction between lguest and CFS

[Ingo Molnar]

* Ingo Molnar <mingo@xxxxxxx> wrote:

> thanks. It shows the anomaly in action:

> So all the time references we have show that (no surprise here) 1 
> second passed between the two samples. But sched_clock() shows a 
> _large_ jump:
> 
>   .clock                 : 125652924079659272
>   .clock                 : 125653018059166371
> 
> also reflected in .clock_max_delta:
> 
>   .clock_max_delta       : 92976502936
> 
> that's a 93 seconds jump (!) in a single 1-second sample. [...]

we also had a similar jump in exec_clock, which suggests that the 
sched_clock() "jump" occured while there was a task running. (i.e. not 
during ACPI-C2/C3) Could you try the patch below? It should catch such 
large jumps. The 'clock_overflows' counter in /proc/sched_debug will 
show whether this new protection triggered on your box.

	Ingo

Index: linux/kernel/sched.c
===================================================================
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
@@ -149,12 +149,12 @@ struct rq {
 
 	u64 clock, prev_clock_raw;
 	s64 clock_max_delta;
-	u64 fair_clock, prev_fair_clock;
-	u64 exec_clock, prev_exec_clock;
+	u64 fair_clock, prev_fair_clock;
+	u64 exec_clock, prev_exec_clock;
 	s64 wait_runtime;
 	unsigned long wait_runtime_overruns, wait_runtime_underruns;
 
-	unsigned int clock_warps;
+	unsigned int clock_warps, clock_overflows;
 	unsigned int clock_unstable_events;
 
 	struct sched_class *load_balance_class;
@@ -245,9 +245,17 @@ static inline unsigned long long __rq_cl
 		clock++;
 		rq->clock_warps++;
 	} else {
-		if (unlikely(delta > rq->clock_max_delta))
-			rq->clock_max_delta = delta;
-		clock += delta;
+		/*
+		 * Catch too large forward jumps too:
+		 */
+		if (delta > 2*TICK_NSEC) {
+			clock++;
+			rq->clock_overflows++;
+		} else {
+			if (unlikely(delta > rq->clock_max_delta))
+				rq->clock_max_delta = delta;
+			clock += delta;
+		}
 	}
 
 	rq->prev_clock_raw = now;
Index: linux/kernel/sched_debug.c
===================================================================
--- linux.orig/kernel/sched_debug.c
+++ linux/kernel/sched_debug.c
@@ -117,13 +119,13 @@ static void print_cpu(struct seq_file *m
 	P(clock);
 	P(prev_clock_raw);
 	P(clock_warps);
+	P(clock_overflows);
 	P(clock_unstable_events);
 	P(clock_max_delta);
-	rq->clock_max_delta = 0;
 	P(fair_clock);
-	P(prev_fair_clock);
+	P(prev_fair_clock);
 	P(exec_clock);
-	P(prev_exec_clock);
+	P(prev_exec_clock);
 	P(wait_runtime);
 	P(wait_runtime_overruns);
 	P(wait_runtime_underruns);
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/