linux-kernel - Re: [PATCH v3 6/7] perf report: Add --latency flag

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <Z5m2hdR3HZxIdhWR@google.com>
Date: Tue, 28 Jan 2025 21:03:01 -0800
From: Namhyung Kim <namhyung@...nel.org>
To: Dmitry Vyukov <dvyukov@...gle.com>
Cc: irogers@...gle.com, linux-perf-users@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Arnaldo Carvalho de Melo <acme@...nel.org>
Subject: Re: [PATCH v3 6/7] perf report: Add --latency flag

On Mon, Jan 27, 2025 at 10:58:53AM +0100, Dmitry Vyukov wrote:
> Add record/report --latency flag that allows to capture and show
> latency-centric profiles rather than the default CPU-consumption-centric
> profiles. For latency profiles record captures context switch events,
> and report shows Latency as the first column.

It'd be nice if you could add a small example output in the commit
message.

> 
> Signed-off-by: Dmitry Vyukov <dvyukov@...gle.com>
> Cc: Namhyung Kim <namhyung@...nel.org>
> Cc: Arnaldo Carvalho de Melo <acme@...nel.org>
> Cc: Ian Rogers <irogers@...gle.com>
> Cc: linux-perf-users@...r.kernel.org
> Cc: linux-kernel@...r.kernel.org
> ---
[SNIP]
> diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
> index bc4c3acfe7552..2b6023de7a53a 100644
> --- a/tools/perf/util/sort.c
> +++ b/tools/perf/util/sort.c
> @@ -2622,6 +2622,7 @@ struct hpp_dimension {
>  	const char		*name;
>  	struct perf_hpp_fmt	*fmt;
>  	int			taken;
> +	int			was_taken;
>  };
>  
>  #define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], }
> @@ -3513,6 +3514,7 @@ static int __hpp_dimension__add(struct hpp_dimension *hd,
>  		return -1;
>  
>  	hd->taken = 1;
> +	hd->was_taken = 1;
>  	perf_hpp_list__register_sort_field(list, fmt);
>  	return 0;
>  }
> @@ -3547,10 +3549,15 @@ static int __hpp_dimension__add_output(struct perf_hpp_list *list,
>  	return 0;
>  }
>  
> -int hpp_dimension__add_output(unsigned col)
> +int hpp_dimension__add_output(unsigned col, bool implicit)
>  {
> +	struct hpp_dimension *hd;
> +
>  	BUG_ON(col >= PERF_HPP__MAX_INDEX);
> -	return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
> +	hd = &hpp_sort_dimensions[col];
> +	if (implicit && !hd->was_taken)
> +		return 0;

I don't understand why you need 'was_taken' field.  Can it use the
'taken' field?


> +	return __hpp_dimension__add_output(&perf_hpp_list, hd);
>  }
>  
>  int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
> @@ -3809,10 +3816,24 @@ static char *setup_overhead(char *keys)
>  	if (sort__mode == SORT_MODE__DIFF)
>  		return keys;
>  
> -	keys = prefix_if_not_in("overhead", keys);
> -
> -	if (symbol_conf.cumulate_callchain)
> -		keys = prefix_if_not_in("overhead_children", keys);
> +	if (symbol_conf.prefer_latency) {
> +		keys = prefix_if_not_in("overhead", keys);
> +		keys = prefix_if_not_in("latency", keys);
> +		if (symbol_conf.cumulate_callchain) {
> +			keys = prefix_if_not_in("overhead_children", keys);
> +			keys = prefix_if_not_in("latency_children", keys);
> +		}
> +	} else if (!keys || (!strstr(keys, "overhead") &&
> +			!strstr(keys, "latency"))) {
> +		if (symbol_conf.enable_latency)
> +			keys = prefix_if_not_in("latency", keys);
> +		keys = prefix_if_not_in("overhead", keys);
> +		if (symbol_conf.cumulate_callchain) {
> +			if (symbol_conf.enable_latency)
> +				keys = prefix_if_not_in("latency_children", keys);
> +			keys = prefix_if_not_in("overhead_children", keys);
> +		}
> +	}

Do you really need this complexity?  I think it's better to fix the order
of columns in both case.

Thanks,
Namhyung

>  
>  	return keys;
>  }
> diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
> index 11fb15f914093..180d36a2bea35 100644
> --- a/tools/perf/util/sort.h
> +++ b/tools/perf/util/sort.h
> @@ -141,7 +141,7 @@ int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, i
>  
>  bool is_strict_order(const char *order);
>  
> -int hpp_dimension__add_output(unsigned col);
> +int hpp_dimension__add_output(unsigned col, bool implicit);
>  void reset_dimensions(void);
>  int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
>  			struct evlist *evlist,
> diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
> index c5b2e56127e22..cd9aa82c7d5ad 100644
> --- a/tools/perf/util/symbol_conf.h
> +++ b/tools/perf/util/symbol_conf.h
> @@ -49,7 +49,9 @@ struct symbol_conf {
>  			keep_exited_threads,
>  			annotate_data_member,
>  			annotate_data_sample,
> -			skip_empty;
> +			skip_empty,
> +			enable_latency,
> +			prefer_latency;
>  	const char	*vmlinux_name,
>  			*kallsyms_name,
>  			*source_prefix,
> -- 
> 2.48.1.262.g85cc9f2d1e-goog
>