Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 25 Jul 2023 13:59:38 -0400
From:   Steven Rostedt <rostedt@goodmis.org>
To:     Ze Gao <zegao2021@gmail.com>
Cc:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Namhyung Kim <namhyung@kernel.org>,
        Ian Rogers <irogers@google.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Jiri Olsa <jolsa@kernel.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Adrian Hunter <adrian.hunter@intel.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
        linux-trace-kernel@vger.kernel.org, Ze Gao <zegao@tencent.com>
Subject: Re: [RFC PATCH 1/3] sched, tracing: report task state in symbolic
 chars instead
Message-ID: <20230725135938.1e056a02@rorschach.local.home>
In-Reply-To: <20230725072254.32045-2-zegao@tencent.com>
References: <20230725072254.32045-1-zegao@tencent.com>
        <20230725072254.32045-2-zegao@tencent.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Precedence: bulk

On Tue, 25 Jul 2023 15:22:52 +0800
Ze Gao <zegao2021@gmail.com> wrote:

>  #ifdef CREATE_TRACE_POINTS
> -static inline long __trace_sched_switch_state(bool preempt,
> +static inline const char __trace_sched_switch_state(bool preempt,

Does it really need to be "const"?

>  					      unsigned int prev_state,
>  					      struct task_struct *p)
>  {
> @@ -197,13 +198,6 @@ static inline long __trace_sched_switch_state(bool preempt,
>  	BUG_ON(p != current);
>  #endif /* CONFIG_SCHED_DEBUG */
>  
> -	/*
> -	 * Preemption ignores task state, therefore preempted tasks are always
> -	 * RUNNING (we will not have dequeued if state != RUNNING).
> -	 */
> -	if (preempt)
> -		return TASK_REPORT_MAX;
> -
>  	/*
>  	 * task_state_index() uses fls() and returns a value from 0-8 range.
>  	 * Decrement it by 1 (except TASK_RUNNING state i.e 0) before using
> @@ -212,7 +206,16 @@ static inline long __trace_sched_switch_state(bool preempt,
>  	 */
>  	state = __task_state_index(prev_state, p->exit_state);
>  
> -	return state ? (1 << (state - 1)) : state;
> +	/*
> +	 * Preemption ignores task state, therefore preempted tasks are always
> +	 * RUNNING (we will not have dequeued if state != RUNNING).
> +	 * Here, we use 'p' to denote this case and only for this case.
> +	 */
> +	if (preempt)
> +		return 'p';
> +
> +
> +	return task_index_to_char(state);
>  }
>  #endif /* CREATE_TRACE_POINTS */
>  
> @@ -232,7 +235,7 @@ TRACE_EVENT(sched_switch,
>  		__array(	char,	prev_comm,	TASK_COMM_LEN	)
>  		__field(	pid_t,	prev_pid			)
>  		__field(	int,	prev_prio			)
> -		__field(	long,	prev_state			)
> +		__field(	char,	prev_state			)
>  		__array(	char,	next_comm,	TASK_COMM_LEN	)
>  		__field(	pid_t,	next_pid			)
>  		__field(	int,	next_prio			)

This will break userspace. Just because you update libtraceevent
doesn't mean that it will get to all the users of it. There's still
tools that have the old method hard coded and doesn't use the library.

Now, because the old tools still do the parsing of this format, we can
add a new field called prev_state_char that will give you this. Now to
save space, we should change prev_state to int (can't make it short as
there's that test for "+" which does sometimes happen). I believe we
can make prev_prio and next prio into shorts (and possibly chars!).

-- Steve


> @@ -249,22 +252,8 @@ TRACE_EVENT(sched_switch,
>  		/* XXX SCHED_DEADLINE */
>  	),
>  
> -	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
> -		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
> -
> -		(__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
> -		  __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
> -				{ TASK_INTERRUPTIBLE, "S" },
> -				{ TASK_UNINTERRUPTIBLE, "D" },
> -				{ __TASK_STOPPED, "T" },
> -				{ __TASK_TRACED, "t" },
> -				{ EXIT_DEAD, "X" },
> -				{ EXIT_ZOMBIE, "Z" },
> -				{ TASK_PARKED, "P" },
> -				{ TASK_DEAD, "I" }) :
> -		  "R",
> -
> -		__entry->prev_state & TASK_REPORT_MAX ? "+" : "",
> +	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%c ==> next_comm=%s next_pid=%d next_prio=%d",
> +		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
>  		__entry->next_comm, __entry->next_pid, __entry->next_prio)