Re: [PATCH 4/7] tracing: new format for specialized trace points

[Christoph Hellwig]

On Tue, Mar 10, 2009 at 12:57:14AM -0400, Steven Rostedt wrote:
> Here's the example. The only updated macro in this patch is the
> sched_switch trace point.

Note that we shouldn't keep two variants around long-term, that's
just going to cause confusion.

> The old method looked like this:
> 
>  TRACE_EVENT_FORMAT(sched_switch,
>         TP_PROTO(struct rq *rq, struct task_struct *prev,
>                 struct task_struct *next),
>         TP_ARGS(rq, prev, next),
>         TP_FMT("task %s:%d ==> %s:%d",
>               prev->comm, prev->pid, next->comm, next->pid),
>         TRACE_STRUCT(
>                 TRACE_FIELD(pid_t, prev_pid, prev->pid)
>                 TRACE_FIELD(int, prev_prio, prev->prio)
>                 TRACE_FIELD_SPECIAL(char next_comm[TASK_COMM_LEN],
>                                     next_comm,
>                                     TP_CMD(memcpy(TRACE_ENTRY->next_comm,
>                                                  next->comm,
>                                                  TASK_COMM_LEN)))
>                 TRACE_FIELD(pid_t, next_pid, next->pid)
>                 TRACE_FIELD(int, next_prio, next->prio)
>         ),
>         TP_RAW_FMT("prev %d:%d ==> next %s:%d:%d")
>         );
> 
> The above method is hard to read and requires two format fields.
> 
> The new method:
> 
>  /*
>   * Tracepoint for task switches, performed by the scheduler:
>   *
>   * (NOTE: the 'rq' argument is not used by generic trace events,
>   *        but used by the latency tracer plugin. )
>   */
>  TRACE_EVENT(sched_switch,
> 
> 	TP_PROTO(struct rq *rq, struct task_struct *prev,
> 		 struct task_struct *next),
> 
> 	TP_ARGS(rq, prev, next),
> 
> 	TP_STRUCT__entry(
> 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
> 		__field(	pid_t,	prev_pid			)
> 		__field(	int,	prev_prio			)
> 		__array(	char,	next_comm,	TASK_COMM_LEN	)
> 		__field(	pid_t,	next_pid			)
> 		__field(	int,	next_prio			)
> 	),
> 
> 	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
> 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
> 		__entry->next_comm, __entry->next_pid, __entry->next_prio),
> 
> 	TP_fast_assign(
> 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
> 		__entry->prev_pid	= prev->pid;
> 		__entry->prev_prio	= prev->prio;
> 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
> 		__entry->next_pid	= next->pid;
> 		__entry->next_prio	= next->prio;
> 	)
>  );

While the idea behing it seems like an improvement to me, the
implementation feel actually worse than the old one too me.  I would
expect this to look more like:

struct trace_sched_switch {
	char	prev_comm[TASK_COMM_LEN],
	pid_t	prev_pid,
	int	prev_prio,
	char	next_comm[TASK_COMM_LEN],
	pid_t	next_pid,
	int	next_prio,
}

static void trace_sched_assign(struct trace_sched_switch *dst, struct rq *rq,
		struct task_struct *prev, struct task_struct *next)
{
	memcpy(dst->next_comm, next->comm, TASK_COMM_LEN);
	dst->prev_pid	= prev->pid;
	dst->prev_prio	= prev->prio;
	memcpy(dst->prev_comm, prev->comm, TASK_COMM_LEN);
	dst->next_pid	= next->pid;
	dst->next_prio	= next->prio;
};


TRACE_EVENT(sched_switch,
	trace_proto(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next),
	trace_args(rq, prev, next),
	trace_struct(struct trace_sched_switch),
	trace_assign(trace_sched_assign);

	trace_pretty_print("task %s:%d [%d] ==> %s:%d [%d]",
		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
		__entry->next_comm, __entry->next_pid, __entry->next_prio),
);

--
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/