Commit f07952b1 authored by Alexander Antonov's avatar Alexander Antonov Committed by Arnaldo Carvalho de Melo
Browse files

perf stat: Basic support for iostat in perf 



Add basic flow for a new iostat mode in perf. Mode is intended to
provide four I/O performance metrics per each PCIe root port: Inbound Read,
Inbound Write, Outbound Read, Outbound Write.

The actual code to compute the metrics and attribute it to
root port is in follow-on patches.

Signed-off-by: default avatarAlexander Antonov <alexander.antonov@linux.intel.com>
Acked-by: default avatarNamhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey V Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210419094147.15909-2-alexander.antonov@linux.intel.com


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent 32daa5d7

tools/perf/builtin-stat.c

+20 −1
Original line number Diff line number Diff line
@@ -68,6 +68,7 @@ 
#include "util/affinity.h"

#include "util/pfm.h"

#include "util/bpf_counter.h"

#include "util/iostat.h"

#include "asm/bug.h"



#include <linux/time64.h>
@@ -212,7 +213,8 @@ static struct perf_stat_config stat_config = { 
	.walltime_nsecs_stats	= &walltime_nsecs_stats,

	.big_num		= true,

	.ctl_fd			= -1,

	.ctl_fd_ack		= -1

	.ctl_fd_ack		= -1,

	.iostat_run		= false,

};



static bool cpus_map_matched(struct evsel *a, struct evsel *b)
@@ -1268,6 +1270,9 @@ static struct option stat_options[] = { 
		     "\t\t\t  Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"

		     "\t\t\t  Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",

		      parse_control_option),

	OPT_CALLBACK_OPTARG(0, "iostat", &evsel_list, &stat_config, "default",

			    "measure I/O performance metrics provided by arch/platform",

			    iostat_parse),

	OPT_END()

};
@@ -2341,6 +2346,17 @@ int cmd_stat(int argc, const char **argv) 
		goto out;

	}



	if (stat_config.iostat_run) {

		status = iostat_prepare(evsel_list, &stat_config);

		if (status)

			goto out;

		if (iostat_mode == IOSTAT_LIST) {

			iostat_list(evsel_list, &stat_config);

			goto out;

		} else if (verbose)

			iostat_list(evsel_list, &stat_config);

	}



	if (add_default_attributes())

		goto out;
@@ -2516,6 +2532,9 @@ int cmd_stat(int argc, const char **argv) 
	perf_stat__exit_aggr_mode();

	evlist__free_stats(evsel_list);

out:

	if (stat_config.iostat_run)

		iostat_release(evsel_list);



	zfree(&stat_config.walltime_run);



	if (smi_cost && smi_reset)

tools/perf/util/Build

+1 −0
Original line number Diff line number Diff line
@@ -102,6 +102,7 @@ perf-y += rwsem.o 
perf-y += thread-stack.o

perf-y += spark.o

perf-y += topdown.o

perf-y += iostat.o

perf-y += stream.o

perf-$(CONFIG_AUXTRACE) += auxtrace.o

perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/

tools/perf/util/iostat.c

0 → 100644
+53 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0

#include "util/iostat.h"

#include "util/debug.h"



enum iostat_mode_t iostat_mode = IOSTAT_NONE;



__weak int iostat_prepare(struct evlist *evlist __maybe_unused,

			  struct perf_stat_config *config __maybe_unused)

{

	return -1;

}



__weak int iostat_parse(const struct option *opt __maybe_unused,

			 const char *str __maybe_unused,

			 int unset __maybe_unused)

{

	pr_err("iostat mode is not supported on current platform\n");

	return -1;

}



__weak void iostat_list(struct evlist *evlist __maybe_unused,

		       struct perf_stat_config *config __maybe_unused)

{

}



__weak void iostat_release(struct evlist *evlist __maybe_unused)

{

}



__weak void iostat_print_header_prefix(struct perf_stat_config *config __maybe_unused)

{

}



__weak void iostat_print_metric(struct perf_stat_config *config __maybe_unused,

				struct evsel *evsel __maybe_unused,

				struct perf_stat_output_ctx *out __maybe_unused)

{

}



__weak void iostat_prefix(struct evlist *evlist __maybe_unused,

			  struct perf_stat_config *config __maybe_unused,

			  char *prefix __maybe_unused,

			  struct timespec *ts __maybe_unused)

{

}



__weak void iostat_print_counters(struct evlist *evlist __maybe_unused,

				  struct perf_stat_config *config __maybe_unused,

				  struct timespec *ts __maybe_unused,

				  char *prefix __maybe_unused,

				  iostat_print_counter_t print_cnt_cb __maybe_unused)

{

}

tools/perf/util/iostat.h

0 → 100644
+47 −0
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: GPL-2.0 */

/*

 * perf iostat

 *

 * Copyright (C) 2020, Intel Corporation

 *

 * Authors: Alexander Antonov <alexander.antonov@linux.intel.com>

 */



#ifndef _IOSTAT_H

#define _IOSTAT_H



#include <subcmd/parse-options.h>

#include "util/stat.h"

#include "util/parse-events.h"

#include "util/evlist.h"



struct option;

struct perf_stat_config;

struct evlist;

struct timespec;



enum iostat_mode_t {

	IOSTAT_NONE		= -1,

	IOSTAT_RUN		= 0,

	IOSTAT_LIST		= 1

};



extern enum iostat_mode_t iostat_mode;



typedef void (*iostat_print_counter_t)(struct perf_stat_config *, struct evsel *, char *);



int iostat_prepare(struct evlist *evlist, struct perf_stat_config *config);

int iostat_parse(const struct option *opt, const char *str,

		 int unset __maybe_unused);

void iostat_list(struct evlist *evlist, struct perf_stat_config *config);

void iostat_release(struct evlist *evlist);

void iostat_prefix(struct evlist *evlist, struct perf_stat_config *config,

		   char *prefix, struct timespec *ts);

void iostat_print_header_prefix(struct perf_stat_config *config);

void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,

			 struct perf_stat_output_ctx *out);

void iostat_print_counters(struct evlist *evlist,

			   struct perf_stat_config *config, struct timespec *ts,

			   char *prefix, iostat_print_counter_t print_cnt_cb);



#endif /* _IOSTAT_H */

tools/perf/util/stat-display.c

+30 −10
Original line number Diff line number Diff line
@@ -17,6 +17,7 @@ 
#include "cgroup.h"

#include <api/fs/fs.h>

#include "util.h"

#include "iostat.h"



#define CNTR_NOT_SUPPORTED	"<not supported>"

#define CNTR_NOT_COUNTED	"<not counted>"
@@ -310,6 +311,11 @@ static void print_metric_header(struct perf_stat_config *config, 
	struct outstate *os = ctx;

	char tbuf[1024];



	/* In case of iostat, print metric header for first root port only */

	if (config->iostat_run &&

	    os->evsel->priv != os->evsel->evlist->selected->priv)

		return;



	if (!valid_only_metric(unit))

		return;

	unit = fixunit(tbuf, os->evsel, unit);
@@ -958,8 +964,11 @@ static void print_metric_headers(struct perf_stat_config *config, 
	if (config->csv_output) {

		if (config->interval)

			fputs("time,", config->output);

		if (!config->iostat_run)

			fputs(aggr_header_csv[config->aggr_mode], config->output);

	}

	if (config->iostat_run)

		iostat_print_header_prefix(config);



	/* Print metrics headers only */

	evlist__for_each_entry(evlist, counter) {
@@ -989,6 +998,7 @@ static void print_interval(struct perf_stat_config *config, 
	if (config->interval_clear)

		puts(CONSOLE_CLEAR);



	if (!config->iostat_run)

		sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep);



	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
@@ -1025,9 +1035,11 @@ static void print_interval(struct perf_stat_config *config, 
			break;

		case AGGR_GLOBAL:

		default:

			if (!config->iostat_run) {

				fprintf(output, "#           time");

				if (!metric_only)

					fprintf(output, "             counts %*s events\n", unit_width, "unit");

			}

		case AGGR_UNSET:

			break;

		}
@@ -1220,6 +1232,9 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf 
	struct evsel *counter;

	char buf[64], *prefix = NULL;



	if (config->iostat_run)

		evlist->selected = evlist__first(evlist);



	if (interval)

		print_interval(config, evlist, prefix = buf, ts);

	else
@@ -1232,7 +1247,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf 
			print_metric_headers(config, evlist, prefix, false);

		if (num_print_iv++ == 25)

			num_print_iv = 0;

		if (config->aggr_mode == AGGR_GLOBAL && prefix)

		if (config->aggr_mode == AGGR_GLOBAL && prefix && !config->iostat_run)

			fprintf(config->output, "%s", prefix);

	}
@@ -1249,11 +1264,16 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf 
		}

		break;

	case AGGR_GLOBAL:

		if (config->iostat_run)

			iostat_print_counters(evlist, config, ts, prefix = buf,

					      print_counter_aggr);

		else {

			evlist__for_each_entry(evlist, counter) {

				print_counter_aggr(config, counter, prefix);

			}

			if (metric_only)

				fputc('\n', config->output);

		}

		break;

	case AGGR_NONE:

		if (metric_only)