Re: [RFC PATCH v6 3/5] sched, tracing: reorganize fields of switch event struct

[Steven Rostedt]

On Thu,  3 Aug 2023 04:33:50 -0400
Ze Gao <zegao2021@xxxxxxxxx> wrote:

> Report prioritiy and prev_state in 'short' to save some buffer
> space. And also reorder the fields so that we take struct
> alignment into consideration to make the record compact.

If I were to write this, I would have wrote:

  The prev_state field in the sched_switch event is assigned by
  __trace_sched_switch_state(). The largest number that function will return
  is TASK_REPORT_MAX which is just 0x100. There's no reason that the
  prev_state field is a full 32 bits when it is using just 9 bits max. In
  order to save space on the ring buffer, shrink the prev_state to 16 bits
  (short).

  Also, change the positions of the other fields to accommodate the short
  value of prev_state to eliminate any holes that were created in the
  structure.

See the difference?

>  
>  #ifdef CREATE_TRACE_POINTS
> -static inline long __trace_sched_switch_state(bool preempt,
> +static inline short __trace_sched_switch_state(bool preempt,
>  					      unsigned int prev_state,
>  					      struct task_struct *p)
>  {
>  	unsigned int state;
>  
>  #ifdef CONFIG_SCHED_DEBUG
> -	BUG_ON(p != current);
> +	WARN_ON_ONCE(p != current);
>  #endif /* CONFIG_SCHED_DEBUG */

The above needs to be a separate patch.

-- Steve

>  
>  	/*
> @@ -229,23 +229,23 @@ TRACE_EVENT(sched_switch,
>  	TP_ARGS(preempt, prev, next, prev_state),
>  
>  	TP_STRUCT__entry(
> -		__array(	char,	prev_comm,	TASK_COMM_LEN	)
>  		__field(	pid_t,	prev_pid			)
> -		__field(	int,	prev_prio			)
> -		__field(	long,	prev_state			)
> -		__array(	char,	next_comm,	TASK_COMM_LEN	)
>  		__field(	pid_t,	next_pid			)
> -		__field(	int,	next_prio			)
> +		__field(	short,	prev_prio			)
> +		__field(	short,	next_prio			)
> +		__array(	char,	prev_comm,	TASK_COMM_LEN	)
> +		__array(	char,	next_comm,	TASK_COMM_LEN	)
> +		__field(	short,	prev_state			)
>  	),
>  
>  	TP_fast_assign(
> -		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
> -		__entry->prev_pid	= prev->pid;
> -		__entry->prev_prio	= prev->prio;
> -		__entry->prev_state	= __trace_sched_switch_state(preempt, prev_state, prev);
> +		__entry->prev_pid		= prev->pid;
> +		__entry->next_pid		= next->pid;
> +		__entry->prev_prio		= (short) prev->prio;
> +		__entry->next_prio		= (short) next->prio;
>  		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
> -		__entry->next_pid	= next->pid;
> -		__entry->next_prio	= next->prio;
> +		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
> +		__entry->prev_state		= __trace_sched_switch_state(preempt, prev_state, prev);
>  		/* XXX SCHED_DEADLINE */
>  	),
>