Add a core event, SCX_EV_BYPASS_DISPATCH, which represents how many
tasks have been dispatched in the bypass mode.

__scx_add_event() is used since the caller holds an rq lock,
so the preemption has already been disabled.

Signed-off-by: Changwoo Min <changwoo@igalia.com>
---
 kernel/sched/ext.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 07d54b52e971..236cdb0071eb 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1468,6 +1468,11 @@ struct scx_event_stats {
 	 */
 	u64		SCX_EV_ENQ_SKIP_EXITING;
 
+	/*
+	 * The number of tasks dispatched in the bypassing mode.
+	 */
+	u64		SCX_EV_BYPASS_DISPATCH;
+
 	/*
 	 * The number of times the bypassing mode has been activated.
 	 */
@@ -2869,11 +2874,17 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	}
 
 	/* if there already are tasks to run, nothing to do */
-	if (rq->scx.local_dsq.nr)
+	if (rq->scx.local_dsq.nr) {
+		if (scx_rq_bypassing(rq))
+			__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
 		goto has_tasks;
+	}
 
-	if (consume_global_dsq(rq))
+	if (consume_global_dsq(rq)) {
+		if (scx_rq_bypassing(rq))
+			__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
 		goto has_tasks;
+	}
 
 	if (!SCX_HAS_OP(dispatch) || scx_rq_bypassing(rq) || !scx_rq_online(rq))
 		goto no_tasks;
@@ -2899,10 +2910,16 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 			rq->scx.flags |= SCX_RQ_BAL_KEEP;
 			goto has_tasks;
 		}
-		if (rq->scx.local_dsq.nr)
+		if (rq->scx.local_dsq.nr) {
+			if (scx_rq_bypassing(rq))
+				__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
 			goto has_tasks;
-		if (consume_global_dsq(rq))
+		}
+		if (consume_global_dsq(rq)) {
+			if (scx_rq_bypassing(rq))
+				__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
 			goto has_tasks;
+		}
 
 		/*
 		 * ops.dispatch() can trap us in this loop by repeatedly
@@ -5001,6 +5018,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 	scx_dump_event(s, &events, SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE);
 	scx_dump_event(s, &events, SCX_EV_DISPATCH_KEEP_LAST);
 	scx_dump_event(s, &events, SCX_EV_ENQ_SKIP_EXITING);
+	scx_dump_event(s, &events, SCX_EV_BYPASS_DISPATCH);
 	scx_dump_event(s, &events, SCX_EV_BYPASS_ACTIVATE);
 
 	if (seq_buf_has_overflowed(&s) && dump_len >= sizeof(trunc_marker))
@@ -7138,6 +7156,7 @@ __bpf_kfunc void scx_bpf_events(struct scx_event_stats *events,
 		scx_agg_event(&e_sys, e_cpu, SCX_EV_SELECT_CPU_FALLBACK);
 		scx_agg_event(&e_sys, e_cpu, SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE);
 		scx_agg_event(&e_sys, e_cpu, SCX_EV_DISPATCH_KEEP_LAST);
+		scx_agg_event(&e_sys, e_cpu, SCX_EV_BYPASS_DISPATCH);
 		scx_agg_event(&e_sys, e_cpu, SCX_EV_BYPASS_ACTIVATE);
 	}
 
-- 
2.48.1

Hello,

On Fri, Jan 31, 2025 at 04:09:34PM +0900, Changwoo Min wrote:
...
> @@ -2869,11 +2874,17 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
>  	}
>  
>  	/* if there already are tasks to run, nothing to do */
> -	if (rq->scx.local_dsq.nr)
> +	if (rq->scx.local_dsq.nr) {
> +		if (scx_rq_bypassing(rq))
> +			__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
>  		goto has_tasks;
> +	}
>  
> -	if (consume_global_dsq(rq))
> +	if (consume_global_dsq(rq)) {
> +		if (scx_rq_bypassing(rq))
> +			__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);

Hmm... Wouldn't it be easier to count it from select_task_rq_scx() and
do_enqueue_task()? The latter already has scx_rq_bypassing() condition and
the former one can easily cache bypassing test result and use that in the
else block.

> @@ -2899,10 +2910,16 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
>  			rq->scx.flags |= SCX_RQ_BAL_KEEP;
>  			goto has_tasks;
>  		}
> -		if (rq->scx.local_dsq.nr)
> +		if (rq->scx.local_dsq.nr) {
> +			if (scx_rq_bypassing(rq))
> +				__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
>  			goto has_tasks;
> -		if (consume_global_dsq(rq))
> +		}
> +		if (consume_global_dsq(rq)) {
> +			if (scx_rq_bypassing(rq))
> +				__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
>  			goto has_tasks;
> +		}

The above can happen while bypass mode is being turned on but once on
control doesn't even reach here, right?

Thanks.

-- 
tejun

Hello,

On 25. 2. 3. 02:33, Tejun Heo wrote:
> Hello,
> 
> On Fri, Jan 31, 2025 at 04:09:34PM +0900, Changwoo Min wrote:
> ...
>> @@ -2869,11 +2874,17 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
>>   	}
>>   
>>   	/* if there already are tasks to run, nothing to do */
>> -	if (rq->scx.local_dsq.nr)
>> +	if (rq->scx.local_dsq.nr) {
>> +		if (scx_rq_bypassing(rq))
>> +			__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
>>   		goto has_tasks;
>> +	}
>>   
>> -	if (consume_global_dsq(rq))
>> +	if (consume_global_dsq(rq)) {
>> +		if (scx_rq_bypassing(rq))
>> +			__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
> 
> Hmm... Wouldn't it be easier to count it from select_task_rq_scx() and
> do_enqueue_task()? The latter already has scx_rq_bypassing() condition and
> the former one can easily cache bypassing test result and use that in the
> else block.

That makes sense. I will change the code as you suggested.

> 
>> @@ -2899,10 +2910,16 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
>>   			rq->scx.flags |= SCX_RQ_BAL_KEEP;
>>   			goto has_tasks;
>>   		}
>> -		if (rq->scx.local_dsq.nr)
>> +		if (rq->scx.local_dsq.nr) {
>> +			if (scx_rq_bypassing(rq))
>> +				__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
>>   			goto has_tasks;
>> -		if (consume_global_dsq(rq))
>> +		}
>> +		if (consume_global_dsq(rq)) {
>> +			if (scx_rq_bypassing(rq))
>> +				__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
>>   			goto has_tasks;
>> +		}
> 
> The above can happen while bypass mode is being turned on but once on
> control doesn't even reach here, right?

You are right. I will clean this up.

Regards,
Changwoo Min