Re: [PATCH v4 1/3] perf sched: Suppress latency table output when trace samples are missing

On Wed, Jul 29, 2026 at 03:00:38PM +0000, [email protected] wrote:
> --- Patch [1]: [PATCH v4 1/3] perf sched: Suppress latency table output when trace samples are missing ---
> commit e9be5c25be0368a795779cd7fdb10479f3b3c099
> Author: Aaron Tomlin <[email protected]>
> 
> perf sched: Suppress latency table output when trace samples are missing
> 
> This commit updates perf_sched__read_events() to abort early and return an
> error when trace samples are missing. It also adds callbacks in cmd_sched()
> to support pipe mode streams and adds a null check in map_switch_event().
> 
> > diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
> > index 7fd63a9db4574..fabd99a18aad4 100644
> > --- a/tools/perf/builtin-sched.c
> > +++ b/tools/perf/builtin-sched.c
> 
> [ ... ]
> 
> > @@ -2001,7 +2001,7 @@ static int perf_sched__read_events(struct perf_sched *sched)
> >  		.mode  = PERF_DATA_MODE_READ,
> >  		.force = sched->force,
> >  	};
> > -	int rc = -1;
> > +	int rc = -1, err;
> >  
> >  	session = perf_session__new(&data, &sched->tool);
> >  	if (IS_ERR(session)) {
> > @@ -2018,18 +2018,25 @@ static int perf_sched__read_events(struct perf_sched *sched)
> >  	if (perf_session__set_tracepoints_handlers(session, handlers))
> >  		goto out_delete;
> 
> [Severity: Medium]
> Does setting the tracepoint handlers before processing events work for
> pipe mode?
> 
> Since the evlist is empty in pipe mode until events are processed, it appears
> perf_session__set_tracepoints_handlers() won't set up the handlers.
> 
> When samples later arrive in perf_sched__process_tracepoint_sample():
> 
>     if (evsel->handler != NULL) {
>         tracepoint_handler f = evsel->handler;
>         err = f(tool, sample, machine);
>     }
> 
> Will they be silently dropped because evsel->handler is NULL?
> 
> > -	if (perf_session__has_traces(session, "record -R")) {
> > -		int err = perf_session__process_events(session);
> > -		if (err) {
> > -			pr_err("Failed to process events, error %d", err);
> > -			goto out_delete;
> > -		}
> > +	if (!perf_data__is_pipe(session->data) &&
> > +	    !perf_session__has_traces(session, "record -R"))
> > +		goto out_delete;
> >  
> > -		sched->nr_events      = session->evlist->stats.nr_events[0];
> > -		sched->nr_lost_events = session->evlist->stats.total_lost;
> > -		sched->nr_lost_chunks = session->evlist->stats.nr_events[PERF_RECORD_LOST];
> > +	err = perf_session__process_events(session);
> 
> [ ... ]
> 
> > @@ -5167,6 +5174,9 @@ int cmd_sched(int argc, const char **argv)
> >  	sched.tool.namespaces	 = perf_event__process_namespaces;
> >  	sched.tool.lost		 = perf_event__process_lost;
> >  	sched.tool.fork		 = perf_sched__process_fork_event;
> > +	sched.tool.attr		 = perf_event__process_attr;
> > +	sched.tool.tracing_data	 = perf_event__process_tracing_data;
> > +	sched.tool.build_id	 = perf_event__process_build_id;
> 
> [Severity: Medium]
> Does this code omit the feature callback required for pipe mode?
> 
> Without registering perf_event__process_feature to tool.feature, it seems
> feature events from the pipe stream will be silently dropped, leaving
> struct perf_env unpopulated.
> 
> >  
> >  	argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands,
> >  					sched_usage, PARSE_OPT_STOP_AT_NON_OPTION);

Hi Namhyung, Arnaldo, Ian,

This feedback is valid.

In pipe mode, header attributes arrive dynamically during event processing,
meaning session->evlist starts empty prior to perf_session__process_events().
Calling perf_session__set_tracepoints_handlers() upfront resulted in zero
handlers being attached, causing incoming tracepoint samples to be silently
dropped (i.e., evsel->handler == NULL).

I will resolve this in the next iteration.

Kind regards,
-- 
Aaron Tomlin