2018-08-30 14:32:52 +08:00
|
|
|
#include <stdio.h>
|
|
|
|
#include <inttypes.h>
|
2019-06-26 08:28:49 +08:00
|
|
|
#include <linux/string.h>
|
2018-08-30 14:32:52 +08:00
|
|
|
#include <linux/time64.h>
|
|
|
|
#include <math.h>
|
2019-01-22 20:47:38 +08:00
|
|
|
#include "color.h"
|
2018-08-30 14:32:52 +08:00
|
|
|
#include "evlist.h"
|
|
|
|
#include "evsel.h"
|
|
|
|
#include "stat.h"
|
|
|
|
#include "top.h"
|
|
|
|
#include "thread_map.h"
|
|
|
|
#include "cpumap.h"
|
|
|
|
#include "string2.h"
|
tools perf: Move from sane_ctype.h obtained from git to the Linux's original
We got the sane_ctype.h headers from git and kept using it so far, but
since that code originally came from the kernel sources to the git
sources, perhaps its better to just use the one in the kernel, so that
we can leverage tools/perf/check_headers.sh to be notified when our copy
gets out of sync, i.e. when fixes or goodies are added to the code we've
copied.
This will help with things like tools/lib/string.c where we want to have
more things in common with the kernel, such as strim(), skip_spaces(),
etc so as to go on removing the things that we have in tools/perf/util/
and instead using the code in the kernel, indirectly and removing things
like EXPORT_SYMBOL(), etc, getting notified when fixes and improvements
are made to the original code.
Hopefully this also should help with reducing the difference of code
hosted in tools/ to the one in the kernel proper.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-7k9868l713wqtgo01xxygn12@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-26 04:27:31 +08:00
|
|
|
#include <linux/ctype.h>
|
2018-08-30 14:32:52 +08:00
|
|
|
#include "cgroup.h"
|
|
|
|
#include <math.h>
|
|
|
|
#include <api/fs/fs.h>
|
|
|
|
|
|
|
|
#define CNTR_NOT_SUPPORTED "<not supported>"
|
|
|
|
#define CNTR_NOT_COUNTED "<not counted>"
|
|
|
|
|
|
|
|
static void print_running(struct perf_stat_config *config,
|
|
|
|
u64 run, u64 ena)
|
|
|
|
{
|
|
|
|
if (config->csv_output) {
|
|
|
|
fprintf(config->output, "%s%" PRIu64 "%s%.2f",
|
|
|
|
config->csv_sep,
|
|
|
|
run,
|
|
|
|
config->csv_sep,
|
|
|
|
ena ? 100.0 * run / ena : 100.0);
|
|
|
|
} else if (run != ena) {
|
|
|
|
fprintf(config->output, " (%.2f%%)", 100.0 * run / ena);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_noise_pct(struct perf_stat_config *config,
|
|
|
|
double total, double avg)
|
|
|
|
{
|
|
|
|
double pct = rel_stddev_stats(total, avg);
|
|
|
|
|
|
|
|
if (config->csv_output)
|
|
|
|
fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
|
|
|
|
else if (pct)
|
|
|
|
fprintf(config->output, " ( +-%6.2f%% )", pct);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_noise(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *evsel, double avg)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
struct perf_stat_evsel *ps;
|
|
|
|
|
|
|
|
if (config->run_count == 1)
|
|
|
|
return;
|
|
|
|
|
|
|
|
ps = evsel->stats;
|
|
|
|
print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:51 +08:00
|
|
|
static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel)
|
perf stat: Fix CSV mode column output for non-cgroup events
When using the -x option, perf stat prints CSV-style output with one
event per line. For each event, it prints the count, the unit, the
event name, the cgroup, and a bunch of other event specific fields (such
as insn per cycles).
When you use CSV-style mode, you expect a normalized output where each
event is printed with the same number of fields regardless of what it is
so it can easily be imported into a spreadsheet or parsed.
For instance, if an event does not have a unit, then print an empty
field for it.
Although this approach was implemented for the unit, it was not for the
cgroup.
When mixing cgroup and non-cgroup events, then non-cgroup events would
not show an empty field, instead the next field was printed, make
columns not line up correctly.
This patch fixes the cgroup output issues by forcing an empty field
for non-cgroup events as soon as one event has cgroup.
Before:
<not counted> @ @cycles @foo @ 0 @100.00@@
2531614 @ @cycles @6420922@100.00@ @
foo cgroup lines up with time_running!
After:
<not counted> @ @cycles @foo @0 @100.00@@
2594834 @ @cycles @ @5287372 @100.00@@
Fields line up.
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1541587845-9150-1-git-send-email-eranian@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-07 18:50:45 +08:00
|
|
|
{
|
|
|
|
if (nr_cgroups) {
|
|
|
|
const char *cgrp_name = evsel->cgrp ? evsel->cgrp->name : "";
|
|
|
|
fprintf(config->output, "%s%s", config->csv_sep, cgrp_name);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2018-08-30 14:32:52 +08:00
|
|
|
static void aggr_printout(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *evsel, int id, int nr)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
switch (config->aggr_mode) {
|
|
|
|
case AGGR_CORE:
|
2019-06-05 06:50:42 +08:00
|
|
|
fprintf(config->output, "S%d-D%d-C%*d%s%*d%s",
|
2018-08-30 14:32:52 +08:00
|
|
|
cpu_map__id_to_socket(id),
|
2019-06-05 06:50:42 +08:00
|
|
|
cpu_map__id_to_die(id),
|
2018-08-30 14:32:52 +08:00
|
|
|
config->csv_output ? 0 : -8,
|
|
|
|
cpu_map__id_to_cpu(id),
|
|
|
|
config->csv_sep,
|
|
|
|
config->csv_output ? 0 : 4,
|
|
|
|
nr,
|
|
|
|
config->csv_sep);
|
|
|
|
break;
|
2019-06-05 06:50:42 +08:00
|
|
|
case AGGR_DIE:
|
|
|
|
fprintf(config->output, "S%d-D%*d%s%*d%s",
|
|
|
|
cpu_map__id_to_socket(id << 16),
|
|
|
|
config->csv_output ? 0 : -8,
|
|
|
|
cpu_map__id_to_die(id << 16),
|
|
|
|
config->csv_sep,
|
|
|
|
config->csv_output ? 0 : 4,
|
|
|
|
nr,
|
|
|
|
config->csv_sep);
|
|
|
|
break;
|
2018-08-30 14:32:52 +08:00
|
|
|
case AGGR_SOCKET:
|
|
|
|
fprintf(config->output, "S%*d%s%*d%s",
|
|
|
|
config->csv_output ? 0 : -5,
|
|
|
|
id,
|
|
|
|
config->csv_sep,
|
|
|
|
config->csv_output ? 0 : 4,
|
|
|
|
nr,
|
|
|
|
config->csv_sep);
|
|
|
|
break;
|
|
|
|
case AGGR_NONE:
|
perf stat: Support 'percore' event qualifier
With this patch, we can use the 'percore' event qualifier in perf-stat.
root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000
1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%)
1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%)
1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%)
In this example, we count the event 'ref-cycles' per-core and per-CPU in
one perf stat command-line. From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
|
|
|
if (evsel->percore) {
|
2019-06-05 06:50:42 +08:00
|
|
|
fprintf(config->output, "S%d-D%d-C%*d%s",
|
perf stat: Support 'percore' event qualifier
With this patch, we can use the 'percore' event qualifier in perf-stat.
root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000
1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%)
1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%)
1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%)
In this example, we count the event 'ref-cycles' per-core and per-CPU in
one perf stat command-line. From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
|
|
|
cpu_map__id_to_socket(id),
|
2019-06-05 06:50:42 +08:00
|
|
|
cpu_map__id_to_die(id),
|
perf stat: Support 'percore' event qualifier
With this patch, we can use the 'percore' event qualifier in perf-stat.
root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000
1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%)
1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%)
1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%)
In this example, we count the event 'ref-cycles' per-core and per-CPU in
one perf stat command-line. From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
|
|
|
config->csv_output ? 0 : -5,
|
|
|
|
cpu_map__id_to_cpu(id), config->csv_sep);
|
|
|
|
} else {
|
|
|
|
fprintf(config->output, "CPU%*d%s ",
|
|
|
|
config->csv_output ? 0 : -5,
|
2019-07-21 19:24:05 +08:00
|
|
|
evsel__cpus(evsel)->map[id],
|
perf stat: Support 'percore' event qualifier
With this patch, we can use the 'percore' event qualifier in perf-stat.
root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000
1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%)
1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%)
1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%)
In this example, we count the event 'ref-cycles' per-core and per-CPU in
one perf stat command-line. From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
|
|
|
config->csv_sep);
|
|
|
|
}
|
2018-08-30 14:32:52 +08:00
|
|
|
break;
|
|
|
|
case AGGR_THREAD:
|
|
|
|
fprintf(config->output, "%*s-%*d%s",
|
|
|
|
config->csv_output ? 0 : 16,
|
2019-07-21 19:24:20 +08:00
|
|
|
perf_thread_map__comm(evsel->threads, id),
|
2018-08-30 14:32:52 +08:00
|
|
|
config->csv_output ? 0 : -8,
|
|
|
|
thread_map__pid(evsel->threads, id),
|
|
|
|
config->csv_sep);
|
|
|
|
break;
|
|
|
|
case AGGR_GLOBAL:
|
|
|
|
case AGGR_UNSET:
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
struct outstate {
|
|
|
|
FILE *fh;
|
|
|
|
bool newline;
|
|
|
|
const char *prefix;
|
|
|
|
int nfields;
|
|
|
|
int id, nr;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *evsel;
|
2018-08-30 14:32:52 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
#define METRIC_LEN 35
|
|
|
|
|
|
|
|
static void new_line_std(struct perf_stat_config *config __maybe_unused,
|
|
|
|
void *ctx)
|
|
|
|
{
|
|
|
|
struct outstate *os = ctx;
|
|
|
|
|
|
|
|
os->newline = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void do_new_line_std(struct perf_stat_config *config,
|
|
|
|
struct outstate *os)
|
|
|
|
{
|
|
|
|
fputc('\n', os->fh);
|
|
|
|
fputs(os->prefix, os->fh);
|
|
|
|
aggr_printout(config, os->evsel, os->id, os->nr);
|
|
|
|
if (config->aggr_mode == AGGR_NONE)
|
|
|
|
fprintf(os->fh, " ");
|
|
|
|
fprintf(os->fh, " ");
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_metric_std(struct perf_stat_config *config,
|
|
|
|
void *ctx, const char *color, const char *fmt,
|
|
|
|
const char *unit, double val)
|
|
|
|
{
|
|
|
|
struct outstate *os = ctx;
|
|
|
|
FILE *out = os->fh;
|
|
|
|
int n;
|
|
|
|
bool newline = os->newline;
|
|
|
|
|
|
|
|
os->newline = false;
|
|
|
|
|
|
|
|
if (unit == NULL || fmt == NULL) {
|
|
|
|
fprintf(out, "%-*s", METRIC_LEN, "");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (newline)
|
|
|
|
do_new_line_std(config, os);
|
|
|
|
|
|
|
|
n = fprintf(out, " # ");
|
|
|
|
if (color)
|
|
|
|
n += color_fprintf(out, color, fmt, val);
|
|
|
|
else
|
|
|
|
n += fprintf(out, fmt, val);
|
|
|
|
fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void new_line_csv(struct perf_stat_config *config, void *ctx)
|
|
|
|
{
|
|
|
|
struct outstate *os = ctx;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
fputc('\n', os->fh);
|
|
|
|
if (os->prefix)
|
|
|
|
fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
|
|
|
|
aggr_printout(config, os->evsel, os->id, os->nr);
|
|
|
|
for (i = 0; i < os->nfields; i++)
|
|
|
|
fputs(config->csv_sep, os->fh);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
|
|
|
|
void *ctx,
|
|
|
|
const char *color __maybe_unused,
|
|
|
|
const char *fmt, const char *unit, double val)
|
|
|
|
{
|
|
|
|
struct outstate *os = ctx;
|
|
|
|
FILE *out = os->fh;
|
|
|
|
char buf[64], *vals, *ends;
|
|
|
|
|
|
|
|
if (unit == NULL || fmt == NULL) {
|
|
|
|
fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
snprintf(buf, sizeof(buf), fmt, val);
|
2019-06-26 22:42:03 +08:00
|
|
|
ends = vals = skip_spaces(buf);
|
2018-08-30 14:32:52 +08:00
|
|
|
while (isdigit(*ends) || *ends == '.')
|
|
|
|
ends++;
|
|
|
|
*ends = 0;
|
2019-06-26 08:28:49 +08:00
|
|
|
fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, skip_spaces(unit));
|
2018-08-30 14:32:52 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Filter out some columns that don't work well in metrics only mode */
|
|
|
|
|
|
|
|
static bool valid_only_metric(const char *unit)
|
|
|
|
{
|
|
|
|
if (!unit)
|
|
|
|
return false;
|
|
|
|
if (strstr(unit, "/sec") ||
|
|
|
|
strstr(unit, "hz") ||
|
|
|
|
strstr(unit, "Hz") ||
|
|
|
|
strstr(unit, "CPUs utilized"))
|
|
|
|
return false;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:51 +08:00
|
|
|
static const char *fixunit(char *buf, struct evsel *evsel,
|
2018-08-30 14:32:52 +08:00
|
|
|
const char *unit)
|
|
|
|
{
|
|
|
|
if (!strncmp(unit, "of all", 6)) {
|
|
|
|
snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
|
|
|
|
unit);
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
return unit;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_metric_only(struct perf_stat_config *config,
|
|
|
|
void *ctx, const char *color, const char *fmt,
|
|
|
|
const char *unit, double val)
|
|
|
|
{
|
|
|
|
struct outstate *os = ctx;
|
|
|
|
FILE *out = os->fh;
|
|
|
|
char buf[1024], str[1024];
|
|
|
|
unsigned mlen = config->metric_only_len;
|
|
|
|
|
|
|
|
if (!valid_only_metric(unit))
|
|
|
|
return;
|
|
|
|
unit = fixunit(buf, os->evsel, unit);
|
|
|
|
if (mlen < strlen(unit))
|
|
|
|
mlen = strlen(unit) + 1;
|
|
|
|
|
|
|
|
if (color)
|
|
|
|
mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
|
|
|
|
|
|
|
|
color_snprintf(str, sizeof(str), color ?: "", fmt, val);
|
|
|
|
fprintf(out, "%*s ", mlen, str);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
|
|
|
|
void *ctx, const char *color __maybe_unused,
|
|
|
|
const char *fmt,
|
|
|
|
const char *unit, double val)
|
|
|
|
{
|
|
|
|
struct outstate *os = ctx;
|
|
|
|
FILE *out = os->fh;
|
|
|
|
char buf[64], *vals, *ends;
|
|
|
|
char tbuf[1024];
|
|
|
|
|
|
|
|
if (!valid_only_metric(unit))
|
|
|
|
return;
|
|
|
|
unit = fixunit(tbuf, os->evsel, unit);
|
|
|
|
snprintf(buf, sizeof buf, fmt, val);
|
2019-06-26 22:42:03 +08:00
|
|
|
ends = vals = skip_spaces(buf);
|
2018-08-30 14:32:52 +08:00
|
|
|
while (isdigit(*ends) || *ends == '.')
|
|
|
|
ends++;
|
|
|
|
*ends = 0;
|
|
|
|
fprintf(out, "%s%s", vals, config->csv_sep);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void new_line_metric(struct perf_stat_config *config __maybe_unused,
|
|
|
|
void *ctx __maybe_unused)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_metric_header(struct perf_stat_config *config,
|
|
|
|
void *ctx, const char *color __maybe_unused,
|
|
|
|
const char *fmt __maybe_unused,
|
|
|
|
const char *unit, double val __maybe_unused)
|
|
|
|
{
|
|
|
|
struct outstate *os = ctx;
|
|
|
|
char tbuf[1024];
|
|
|
|
|
|
|
|
if (!valid_only_metric(unit))
|
|
|
|
return;
|
|
|
|
unit = fixunit(tbuf, os->evsel, unit);
|
|
|
|
if (config->csv_output)
|
|
|
|
fprintf(os->fh, "%s%s", unit, config->csv_sep);
|
|
|
|
else
|
|
|
|
fprintf(os->fh, "%*s ", config->metric_only_len, unit);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int first_shadow_cpu(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *evsel, int id)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist = evsel->evlist;
|
2018-08-30 14:32:52 +08:00
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!config->aggr_get_id)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (config->aggr_mode == AGGR_NONE)
|
|
|
|
return id;
|
|
|
|
|
|
|
|
if (config->aggr_mode == AGGR_GLOBAL)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
|
2019-07-21 19:24:05 +08:00
|
|
|
int cpu2 = evsel__cpus(evsel)->map[i];
|
2018-08-30 14:32:52 +08:00
|
|
|
|
|
|
|
if (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
|
|
|
|
return cpu2;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void abs_printout(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
int id, int nr, struct evsel *evsel, double avg)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
FILE *output = config->output;
|
|
|
|
double sc = evsel->scale;
|
|
|
|
const char *fmt;
|
|
|
|
|
|
|
|
if (config->csv_output) {
|
|
|
|
fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s";
|
|
|
|
} else {
|
|
|
|
if (config->big_num)
|
|
|
|
fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
|
|
|
|
else
|
|
|
|
fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
|
|
|
|
}
|
|
|
|
|
|
|
|
aggr_printout(config, evsel, id, nr);
|
|
|
|
|
|
|
|
fprintf(output, fmt, avg, config->csv_sep);
|
|
|
|
|
|
|
|
if (evsel->unit)
|
|
|
|
fprintf(output, "%-*s%s",
|
|
|
|
config->csv_output ? 0 : config->unit_width,
|
|
|
|
evsel->unit, config->csv_sep);
|
|
|
|
|
|
|
|
fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
|
|
|
|
|
perf stat: Fix CSV mode column output for non-cgroup events
When using the -x option, perf stat prints CSV-style output with one
event per line. For each event, it prints the count, the unit, the
event name, the cgroup, and a bunch of other event specific fields (such
as insn per cycles).
When you use CSV-style mode, you expect a normalized output where each
event is printed with the same number of fields regardless of what it is
so it can easily be imported into a spreadsheet or parsed.
For instance, if an event does not have a unit, then print an empty
field for it.
Although this approach was implemented for the unit, it was not for the
cgroup.
When mixing cgroup and non-cgroup events, then non-cgroup events would
not show an empty field, instead the next field was printed, make
columns not line up correctly.
This patch fixes the cgroup output issues by forcing an empty field
for non-cgroup events as soon as one event has cgroup.
Before:
<not counted> @ @cycles @foo @ 0 @100.00@@
2531614 @ @cycles @6420922@100.00@ @
foo cgroup lines up with time_running!
After:
<not counted> @ @cycles @foo @0 @100.00@@
2594834 @ @cycles @ @5287372 @100.00@@
Fields line up.
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1541587845-9150-1-git-send-email-eranian@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-07 18:50:45 +08:00
|
|
|
print_cgroup(config, evsel);
|
2018-08-30 14:32:52 +08:00
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:51 +08:00
|
|
|
static bool is_mixed_hw_group(struct evsel *counter)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist = counter->evlist;
|
2018-08-30 14:32:52 +08:00
|
|
|
u32 pmu_type = counter->attr.type;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *pos;
|
2018-08-30 14:32:52 +08:00
|
|
|
|
|
|
|
if (counter->nr_members < 2)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
evlist__for_each_entry(evlist, pos) {
|
|
|
|
/* software events can be part of any hardware group */
|
|
|
|
if (pos->attr.type == PERF_TYPE_SOFTWARE)
|
|
|
|
continue;
|
|
|
|
if (pmu_type == PERF_TYPE_SOFTWARE) {
|
|
|
|
pmu_type = pos->attr.type;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (pmu_type != pos->attr.type)
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void printout(struct perf_stat_config *config, int id, int nr,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, double uval,
|
2018-08-30 14:32:52 +08:00
|
|
|
char *prefix, u64 run, u64 ena, double noise,
|
|
|
|
struct runtime_stat *st)
|
|
|
|
{
|
|
|
|
struct perf_stat_output_ctx out;
|
|
|
|
struct outstate os = {
|
|
|
|
.fh = config->output,
|
|
|
|
.prefix = prefix ? prefix : "",
|
|
|
|
.id = id,
|
|
|
|
.nr = nr,
|
|
|
|
.evsel = counter,
|
|
|
|
};
|
|
|
|
print_metric_t pm = print_metric_std;
|
|
|
|
new_line_t nl;
|
|
|
|
|
|
|
|
if (config->metric_only) {
|
|
|
|
nl = new_line_metric;
|
|
|
|
if (config->csv_output)
|
|
|
|
pm = print_metric_only_csv;
|
|
|
|
else
|
|
|
|
pm = print_metric_only;
|
|
|
|
} else
|
|
|
|
nl = new_line_std;
|
|
|
|
|
|
|
|
if (config->csv_output && !config->metric_only) {
|
|
|
|
static int aggr_fields[] = {
|
|
|
|
[AGGR_GLOBAL] = 0,
|
|
|
|
[AGGR_THREAD] = 1,
|
|
|
|
[AGGR_NONE] = 1,
|
|
|
|
[AGGR_SOCKET] = 2,
|
2019-06-05 06:50:42 +08:00
|
|
|
[AGGR_DIE] = 2,
|
2018-08-30 14:32:52 +08:00
|
|
|
[AGGR_CORE] = 2,
|
|
|
|
};
|
|
|
|
|
|
|
|
pm = print_metric_csv;
|
|
|
|
nl = new_line_csv;
|
|
|
|
os.nfields = 3;
|
|
|
|
os.nfields += aggr_fields[config->aggr_mode];
|
|
|
|
if (counter->cgrp)
|
|
|
|
os.nfields++;
|
|
|
|
}
|
|
|
|
if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
|
|
|
|
if (config->metric_only) {
|
|
|
|
pm(config, &os, NULL, "", "", 0);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
aggr_printout(config, counter, id, nr);
|
|
|
|
|
|
|
|
fprintf(config->output, "%*s%s",
|
|
|
|
config->csv_output ? 0 : 18,
|
|
|
|
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
|
|
|
|
config->csv_sep);
|
|
|
|
|
|
|
|
if (counter->supported) {
|
|
|
|
config->print_free_counters_hint = 1;
|
|
|
|
if (is_mixed_hw_group(counter))
|
|
|
|
config->print_mixed_hw_group_error = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
fprintf(config->output, "%-*s%s",
|
|
|
|
config->csv_output ? 0 : config->unit_width,
|
|
|
|
counter->unit, config->csv_sep);
|
|
|
|
|
|
|
|
fprintf(config->output, "%*s",
|
|
|
|
config->csv_output ? 0 : -25,
|
|
|
|
perf_evsel__name(counter));
|
|
|
|
|
perf stat: Fix CSV mode column output for non-cgroup events
When using the -x option, perf stat prints CSV-style output with one
event per line. For each event, it prints the count, the unit, the
event name, the cgroup, and a bunch of other event specific fields (such
as insn per cycles).
When you use CSV-style mode, you expect a normalized output where each
event is printed with the same number of fields regardless of what it is
so it can easily be imported into a spreadsheet or parsed.
For instance, if an event does not have a unit, then print an empty
field for it.
Although this approach was implemented for the unit, it was not for the
cgroup.
When mixing cgroup and non-cgroup events, then non-cgroup events would
not show an empty field, instead the next field was printed, make
columns not line up correctly.
This patch fixes the cgroup output issues by forcing an empty field
for non-cgroup events as soon as one event has cgroup.
Before:
<not counted> @ @cycles @foo @ 0 @100.00@@
2531614 @ @cycles @6420922@100.00@ @
foo cgroup lines up with time_running!
After:
<not counted> @ @cycles @foo @0 @100.00@@
2594834 @ @cycles @ @5287372 @100.00@@
Fields line up.
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1541587845-9150-1-git-send-email-eranian@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-11-07 18:50:45 +08:00
|
|
|
print_cgroup(config, counter);
|
2018-08-30 14:32:52 +08:00
|
|
|
|
|
|
|
if (!config->csv_output)
|
|
|
|
pm(config, &os, NULL, NULL, "", 0);
|
|
|
|
print_noise(config, counter, noise);
|
|
|
|
print_running(config, run, ena);
|
|
|
|
if (config->csv_output)
|
|
|
|
pm(config, &os, NULL, NULL, "", 0);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!config->metric_only)
|
|
|
|
abs_printout(config, id, nr, counter, uval);
|
|
|
|
|
|
|
|
out.print_metric = pm;
|
|
|
|
out.new_line = nl;
|
|
|
|
out.ctx = &os;
|
|
|
|
out.force_header = false;
|
|
|
|
|
|
|
|
if (config->csv_output && !config->metric_only) {
|
|
|
|
print_noise(config, counter, noise);
|
|
|
|
print_running(config, run, ena);
|
|
|
|
}
|
|
|
|
|
|
|
|
perf_stat__print_shadow_stats(config, counter, uval,
|
|
|
|
first_shadow_cpu(config, counter, id),
|
|
|
|
&out, &config->metric_events, st);
|
|
|
|
if (!config->csv_output && !config->metric_only) {
|
|
|
|
print_noise(config, counter, noise);
|
|
|
|
print_running(config, run, ena);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void aggr_update_shadow(struct perf_stat_config *config,
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
int cpu, s2, id, s;
|
|
|
|
u64 val;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter;
|
2018-08-30 14:32:52 +08:00
|
|
|
|
|
|
|
for (s = 0; s < config->aggr_map->nr; s++) {
|
|
|
|
id = config->aggr_map->map[s];
|
|
|
|
evlist__for_each_entry(evlist, counter) {
|
|
|
|
val = 0;
|
|
|
|
for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
|
|
|
|
s2 = config->aggr_get_id(config, evlist->cpus, cpu);
|
|
|
|
if (s2 != id)
|
|
|
|
continue;
|
|
|
|
val += perf_counts(counter->counts, cpu, 0)->val;
|
|
|
|
}
|
|
|
|
perf_stat__update_shadow_stats(counter, val,
|
|
|
|
first_shadow_cpu(config, counter, id),
|
|
|
|
&rt_stat);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:51 +08:00
|
|
|
static void uniquify_event_name(struct evsel *counter)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
char *new_name;
|
|
|
|
char *config;
|
|
|
|
|
|
|
|
if (counter->uniquified_name ||
|
|
|
|
!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
|
|
|
|
strlen(counter->pmu_name)))
|
|
|
|
return;
|
|
|
|
|
|
|
|
config = strchr(counter->name, '/');
|
|
|
|
if (config) {
|
|
|
|
if (asprintf(&new_name,
|
|
|
|
"%s%s", counter->pmu_name, config) > 0) {
|
|
|
|
free(counter->name);
|
|
|
|
counter->name = new_name;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if (asprintf(&new_name,
|
|
|
|
"%s [%s]", counter->name, counter->pmu_name) > 0) {
|
|
|
|
free(counter->name);
|
|
|
|
counter->name = new_name;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
counter->uniquified_name = true;
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:51 +08:00
|
|
|
static void collect_all_aliases(struct perf_stat_config *config, struct evsel *counter,
|
|
|
|
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
|
2018-08-30 14:32:52 +08:00
|
|
|
bool first),
|
|
|
|
void *data)
|
|
|
|
{
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist = counter->evlist;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *alias;
|
2018-08-30 14:32:52 +08:00
|
|
|
|
2019-07-21 19:24:23 +08:00
|
|
|
alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
|
|
|
|
list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
|
2018-08-30 14:32:52 +08:00
|
|
|
if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
|
|
|
|
alias->scale != counter->scale ||
|
|
|
|
alias->cgrp != counter->cgrp ||
|
|
|
|
strcmp(alias->unit, counter->unit) ||
|
2019-06-25 03:37:09 +08:00
|
|
|
perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter) ||
|
|
|
|
!strcmp(alias->pmu_name, counter->pmu_name))
|
2018-08-30 14:32:52 +08:00
|
|
|
break;
|
|
|
|
alias->merged_stat = true;
|
|
|
|
cb(config, alias, data, false);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-07-21 19:23:51 +08:00
|
|
|
static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
|
|
|
|
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
|
2018-08-30 14:32:52 +08:00
|
|
|
bool first),
|
|
|
|
void *data)
|
|
|
|
{
|
|
|
|
if (counter->merged_stat)
|
|
|
|
return false;
|
|
|
|
cb(config, counter, data, true);
|
|
|
|
if (config->no_merge)
|
|
|
|
uniquify_event_name(counter);
|
|
|
|
else if (counter->auto_merge_stats)
|
|
|
|
collect_all_aliases(config, counter, cb, data);
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct aggr_data {
|
|
|
|
u64 ena, run, val;
|
|
|
|
int id;
|
|
|
|
int nr;
|
|
|
|
int cpu;
|
|
|
|
};
|
|
|
|
|
|
|
|
static void aggr_cb(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, void *data, bool first)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
struct aggr_data *ad = data;
|
|
|
|
int cpu, s2;
|
|
|
|
|
|
|
|
for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
|
|
|
|
struct perf_counts_values *counts;
|
|
|
|
|
2019-07-21 19:24:05 +08:00
|
|
|
s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
|
2018-08-30 14:32:52 +08:00
|
|
|
if (s2 != ad->id)
|
|
|
|
continue;
|
|
|
|
if (first)
|
|
|
|
ad->nr++;
|
|
|
|
counts = perf_counts(counter->counts, cpu, 0);
|
|
|
|
/*
|
|
|
|
* When any result is bad, make them all to give
|
|
|
|
* consistent output in interval mode.
|
|
|
|
*/
|
|
|
|
if (counts->ena == 0 || counts->run == 0 ||
|
|
|
|
counter->counts->scaled == -1) {
|
|
|
|
ad->ena = 0;
|
|
|
|
ad->run = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
ad->val += counts->val;
|
|
|
|
ad->ena += counts->ena;
|
|
|
|
ad->run += counts->run;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-04-12 21:59:48 +08:00
|
|
|
static void print_counter_aggrdata(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, int s,
|
2019-04-12 21:59:48 +08:00
|
|
|
char *prefix, bool metric_only,
|
|
|
|
bool *first)
|
|
|
|
{
|
|
|
|
struct aggr_data ad;
|
|
|
|
FILE *output = config->output;
|
|
|
|
u64 ena, run, val;
|
|
|
|
int id, nr;
|
|
|
|
double uval;
|
|
|
|
|
|
|
|
ad.id = id = config->aggr_map->map[s];
|
|
|
|
ad.val = ad.ena = ad.run = 0;
|
|
|
|
ad.nr = 0;
|
|
|
|
if (!collect_data(config, counter, aggr_cb, &ad))
|
|
|
|
return;
|
|
|
|
|
|
|
|
nr = ad.nr;
|
|
|
|
ena = ad.ena;
|
|
|
|
run = ad.run;
|
|
|
|
val = ad.val;
|
|
|
|
if (*first && metric_only) {
|
|
|
|
*first = false;
|
|
|
|
aggr_printout(config, counter, id, nr);
|
|
|
|
}
|
|
|
|
if (prefix && !metric_only)
|
|
|
|
fprintf(output, "%s", prefix);
|
|
|
|
|
|
|
|
uval = val * counter->scale;
|
|
|
|
printout(config, id, nr, counter, uval, prefix,
|
|
|
|
run, ena, 1.0, &rt_stat);
|
|
|
|
if (!metric_only)
|
|
|
|
fputc('\n', output);
|
|
|
|
}
|
|
|
|
|
2018-08-30 14:32:52 +08:00
|
|
|
static void print_aggr(struct perf_stat_config *config,
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist,
|
2018-08-30 14:32:52 +08:00
|
|
|
char *prefix)
|
|
|
|
{
|
|
|
|
bool metric_only = config->metric_only;
|
|
|
|
FILE *output = config->output;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter;
|
2019-04-12 21:59:48 +08:00
|
|
|
int s;
|
2018-08-30 14:32:52 +08:00
|
|
|
bool first;
|
|
|
|
|
|
|
|
if (!(config->aggr_map || config->aggr_get_id))
|
|
|
|
return;
|
|
|
|
|
|
|
|
aggr_update_shadow(config, evlist);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* With metric_only everything is on a single line.
|
|
|
|
* Without each counter has its own line.
|
|
|
|
*/
|
|
|
|
for (s = 0; s < config->aggr_map->nr; s++) {
|
|
|
|
if (prefix && metric_only)
|
|
|
|
fprintf(output, "%s", prefix);
|
|
|
|
|
|
|
|
first = true;
|
|
|
|
evlist__for_each_entry(evlist, counter) {
|
2019-04-12 21:59:48 +08:00
|
|
|
print_counter_aggrdata(config, counter, s,
|
|
|
|
prefix, metric_only,
|
|
|
|
&first);
|
2018-08-30 14:32:52 +08:00
|
|
|
}
|
|
|
|
if (metric_only)
|
|
|
|
fputc('\n', output);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cmp_val(const void *a, const void *b)
|
|
|
|
{
|
|
|
|
return ((struct perf_aggr_thread_value *)b)->val -
|
|
|
|
((struct perf_aggr_thread_value *)a)->val;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct perf_aggr_thread_value *sort_aggr_thread(
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter,
|
2018-08-30 14:32:52 +08:00
|
|
|
int nthreads, int ncpus,
|
|
|
|
int *ret,
|
|
|
|
struct target *_target)
|
|
|
|
{
|
|
|
|
int cpu, thread, i = 0;
|
|
|
|
double uval;
|
|
|
|
struct perf_aggr_thread_value *buf;
|
|
|
|
|
|
|
|
buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
|
|
|
|
if (!buf)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
for (thread = 0; thread < nthreads; thread++) {
|
|
|
|
u64 ena = 0, run = 0, val = 0;
|
|
|
|
|
|
|
|
for (cpu = 0; cpu < ncpus; cpu++) {
|
|
|
|
val += perf_counts(counter->counts, cpu, thread)->val;
|
|
|
|
ena += perf_counts(counter->counts, cpu, thread)->ena;
|
|
|
|
run += perf_counts(counter->counts, cpu, thread)->run;
|
|
|
|
}
|
|
|
|
|
|
|
|
uval = val * counter->scale;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Skip value 0 when enabling --per-thread globally,
|
|
|
|
* otherwise too many 0 output.
|
|
|
|
*/
|
|
|
|
if (uval == 0.0 && target__has_per_thread(_target))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
buf[i].counter = counter;
|
|
|
|
buf[i].id = thread;
|
|
|
|
buf[i].uval = uval;
|
|
|
|
buf[i].val = val;
|
|
|
|
buf[i].run = run;
|
|
|
|
buf[i].ena = ena;
|
|
|
|
i++;
|
|
|
|
}
|
|
|
|
|
|
|
|
qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
|
|
|
|
|
|
|
|
if (ret)
|
|
|
|
*ret = i;
|
|
|
|
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_aggr_thread(struct perf_stat_config *config,
|
|
|
|
struct target *_target,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, char *prefix)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
FILE *output = config->output;
|
|
|
|
int nthreads = thread_map__nr(counter->threads);
|
|
|
|
int ncpus = cpu_map__nr(counter->cpus);
|
|
|
|
int thread, sorted_threads, id;
|
|
|
|
struct perf_aggr_thread_value *buf;
|
|
|
|
|
|
|
|
buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
|
|
|
|
if (!buf) {
|
|
|
|
perror("cannot sort aggr thread");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (thread = 0; thread < sorted_threads; thread++) {
|
|
|
|
if (prefix)
|
|
|
|
fprintf(output, "%s", prefix);
|
|
|
|
|
|
|
|
id = buf[thread].id;
|
|
|
|
if (config->stats)
|
|
|
|
printout(config, id, 0, buf[thread].counter, buf[thread].uval,
|
|
|
|
prefix, buf[thread].run, buf[thread].ena, 1.0,
|
|
|
|
&config->stats[id]);
|
|
|
|
else
|
|
|
|
printout(config, id, 0, buf[thread].counter, buf[thread].uval,
|
|
|
|
prefix, buf[thread].run, buf[thread].ena, 1.0,
|
|
|
|
&rt_stat);
|
|
|
|
fputc('\n', output);
|
|
|
|
}
|
|
|
|
|
|
|
|
free(buf);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct caggr_data {
|
|
|
|
double avg, avg_enabled, avg_running;
|
|
|
|
};
|
|
|
|
|
|
|
|
static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, void *data,
|
2018-08-30 14:32:52 +08:00
|
|
|
bool first __maybe_unused)
|
|
|
|
{
|
|
|
|
struct caggr_data *cd = data;
|
|
|
|
struct perf_stat_evsel *ps = counter->stats;
|
|
|
|
|
|
|
|
cd->avg += avg_stats(&ps->res_stats[0]);
|
|
|
|
cd->avg_enabled += avg_stats(&ps->res_stats[1]);
|
|
|
|
cd->avg_running += avg_stats(&ps->res_stats[2]);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Print out the results of a single counter:
|
|
|
|
* aggregated counts in system-wide mode
|
|
|
|
*/
|
|
|
|
static void print_counter_aggr(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, char *prefix)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
bool metric_only = config->metric_only;
|
|
|
|
FILE *output = config->output;
|
|
|
|
double uval;
|
|
|
|
struct caggr_data cd = { .avg = 0.0 };
|
|
|
|
|
|
|
|
if (!collect_data(config, counter, counter_aggr_cb, &cd))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (prefix && !metric_only)
|
|
|
|
fprintf(output, "%s", prefix);
|
|
|
|
|
|
|
|
uval = cd.avg * counter->scale;
|
|
|
|
printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
|
|
|
|
cd.avg, &rt_stat);
|
|
|
|
if (!metric_only)
|
|
|
|
fprintf(output, "\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
static void counter_cb(struct perf_stat_config *config __maybe_unused,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, void *data,
|
2018-08-30 14:32:52 +08:00
|
|
|
bool first __maybe_unused)
|
|
|
|
{
|
|
|
|
struct aggr_data *ad = data;
|
|
|
|
|
|
|
|
ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
|
|
|
|
ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
|
|
|
|
ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Print out the results of a single counter:
|
|
|
|
* does not use aggregated count in system-wide
|
|
|
|
*/
|
|
|
|
static void print_counter(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, char *prefix)
|
2018-08-30 14:32:52 +08:00
|
|
|
{
|
|
|
|
FILE *output = config->output;
|
|
|
|
u64 ena, run, val;
|
|
|
|
double uval;
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
|
|
|
|
struct aggr_data ad = { .cpu = cpu };
|
|
|
|
|
|
|
|
if (!collect_data(config, counter, counter_cb, &ad))
|
|
|
|
return;
|
|
|
|
val = ad.val;
|
|
|
|
ena = ad.ena;
|
|
|
|
run = ad.run;
|
|
|
|
|
|
|
|
if (prefix)
|
|
|
|
fprintf(output, "%s", prefix);
|
|
|
|
|
|
|
|
uval = val * counter->scale;
|
|
|
|
printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
|
|
|
|
&rt_stat);
|
|
|
|
|
|
|
|
fputc('\n', output);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_no_aggr_metric(struct perf_stat_config *config,
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist,
|
2018-08-30 14:32:52 +08:00
|
|
|
char *prefix)
|
|
|
|
{
|
|
|
|
int cpu;
|
|
|
|
int nrcpus = 0;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter;
|
2018-08-30 14:32:52 +08:00
|
|
|
u64 ena, run, val;
|
|
|
|
double uval;
|
|
|
|
|
|
|
|
nrcpus = evlist->cpus->nr;
|
|
|
|
for (cpu = 0; cpu < nrcpus; cpu++) {
|
|
|
|
bool first = true;
|
|
|
|
|
|
|
|
if (prefix)
|
|
|
|
fputs(prefix, config->output);
|
|
|
|
evlist__for_each_entry(evlist, counter) {
|
|
|
|
if (first) {
|
|
|
|
aggr_printout(config, counter, cpu, 0);
|
|
|
|
first = false;
|
|
|
|
}
|
|
|
|
val = perf_counts(counter->counts, cpu, 0)->val;
|
|
|
|
ena = perf_counts(counter->counts, cpu, 0)->ena;
|
|
|
|
run = perf_counts(counter->counts, cpu, 0)->run;
|
|
|
|
|
|
|
|
uval = val * counter->scale;
|
|
|
|
printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
|
|
|
|
&rt_stat);
|
|
|
|
}
|
|
|
|
fputc('\n', config->output);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int aggr_header_lens[] = {
|
2019-06-05 06:50:42 +08:00
|
|
|
[AGGR_CORE] = 24,
|
|
|
|
[AGGR_DIE] = 18,
|
2018-08-30 14:32:52 +08:00
|
|
|
[AGGR_SOCKET] = 12,
|
|
|
|
[AGGR_NONE] = 6,
|
|
|
|
[AGGR_THREAD] = 24,
|
|
|
|
[AGGR_GLOBAL] = 0,
|
|
|
|
};
|
|
|
|
|
|
|
|
static const char *aggr_header_csv[] = {
|
|
|
|
[AGGR_CORE] = "core,cpus,",
|
2019-06-05 06:50:42 +08:00
|
|
|
[AGGR_DIE] = "die,cpus",
|
2018-08-30 14:32:52 +08:00
|
|
|
[AGGR_SOCKET] = "socket,cpus",
|
|
|
|
[AGGR_NONE] = "cpu,",
|
|
|
|
[AGGR_THREAD] = "comm-pid,",
|
|
|
|
[AGGR_GLOBAL] = ""
|
|
|
|
};
|
|
|
|
|
|
|
|
static void print_metric_headers(struct perf_stat_config *config,
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist,
|
2018-08-30 14:32:52 +08:00
|
|
|
const char *prefix, bool no_indent)
|
|
|
|
{
|
|
|
|
struct perf_stat_output_ctx out;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter;
|
2018-08-30 14:32:52 +08:00
|
|
|
struct outstate os = {
|
|
|
|
.fh = config->output
|
|
|
|
};
|
|
|
|
|
|
|
|
if (prefix)
|
|
|
|
fprintf(config->output, "%s", prefix);
|
|
|
|
|
|
|
|
if (!config->csv_output && !no_indent)
|
|
|
|
fprintf(config->output, "%*s",
|
|
|
|
aggr_header_lens[config->aggr_mode], "");
|
|
|
|
if (config->csv_output) {
|
|
|
|
if (config->interval)
|
|
|
|
fputs("time,", config->output);
|
|
|
|
fputs(aggr_header_csv[config->aggr_mode], config->output);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Print metrics headers only */
|
|
|
|
evlist__for_each_entry(evlist, counter) {
|
|
|
|
os.evsel = counter;
|
|
|
|
out.ctx = &os;
|
|
|
|
out.print_metric = print_metric_header;
|
|
|
|
out.new_line = new_line_metric;
|
|
|
|
out.force_header = true;
|
|
|
|
os.evsel = counter;
|
|
|
|
perf_stat__print_shadow_stats(config, counter, 0,
|
|
|
|
0,
|
|
|
|
&out,
|
|
|
|
&config->metric_events,
|
|
|
|
&rt_stat);
|
|
|
|
}
|
|
|
|
fputc('\n', config->output);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_interval(struct perf_stat_config *config,
|
2019-07-21 19:23:52 +08:00
|
|
|
struct evlist *evlist,
|
2018-08-30 14:32:52 +08:00
|
|
|
char *prefix, struct timespec *ts)
|
|
|
|
{
|
|
|
|
bool metric_only = config->metric_only;
|
|
|
|
unsigned int unit_width = config->unit_width;
|
|
|
|
FILE *output = config->output;
|
|
|
|
static int num_print_interval;
|
|
|
|
|
|
|
|
if (config->interval_clear)
|
|
|
|
puts(CONSOLE_CLEAR);
|
|
|
|
|
|
|
|
sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
|
|
|
|
|
|
|
|
if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
|
|
|
|
switch (config->aggr_mode) {
|
|
|
|
case AGGR_SOCKET:
|
|
|
|
fprintf(output, "# time socket cpus");
|
|
|
|
if (!metric_only)
|
|
|
|
fprintf(output, " counts %*s events\n", unit_width, "unit");
|
|
|
|
break;
|
2019-06-05 06:50:42 +08:00
|
|
|
case AGGR_DIE:
|
|
|
|
fprintf(output, "# time die cpus");
|
|
|
|
if (!metric_only)
|
|
|
|
fprintf(output, " counts %*s events\n", unit_width, "unit");
|
|
|
|
break;
|
2018-08-30 14:32:52 +08:00
|
|
|
case AGGR_CORE:
|
2019-06-05 06:50:42 +08:00
|
|
|
fprintf(output, "# time core cpus");
|
2018-08-30 14:32:52 +08:00
|
|
|
if (!metric_only)
|
|
|
|
fprintf(output, " counts %*s events\n", unit_width, "unit");
|
|
|
|
break;
|
|
|
|
case AGGR_NONE:
|
|
|
|
fprintf(output, "# time CPU ");
|
|
|
|
if (!metric_only)
|
|
|
|
fprintf(output, " counts %*s events\n", unit_width, "unit");
|
|
|
|
break;
|
|
|
|
case AGGR_THREAD:
|
|
|
|
fprintf(output, "# time comm-pid");
|
|
|
|
if (!metric_only)
|
|
|
|
fprintf(output, " counts %*s events\n", unit_width, "unit");
|
|
|
|
break;
|
|
|
|
case AGGR_GLOBAL:
|
|
|
|
default:
|
|
|
|
fprintf(output, "# time");
|
|
|
|
if (!metric_only)
|
|
|
|
fprintf(output, " counts %*s events\n", unit_width, "unit");
|
|
|
|
case AGGR_UNSET:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if ((num_print_interval == 0 || config->interval_clear) && metric_only)
|
|
|
|
print_metric_headers(config, evlist, " ", true);
|
|
|
|
if (++num_print_interval == 25)
|
|
|
|
num_print_interval = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_header(struct perf_stat_config *config,
|
|
|
|
struct target *_target,
|
|
|
|
int argc, const char **argv)
|
|
|
|
{
|
|
|
|
FILE *output = config->output;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
fflush(stdout);
|
|
|
|
|
|
|
|
if (!config->csv_output) {
|
|
|
|
fprintf(output, "\n");
|
|
|
|
fprintf(output, " Performance counter stats for ");
|
|
|
|
if (_target->system_wide)
|
|
|
|
fprintf(output, "\'system wide");
|
|
|
|
else if (_target->cpu_list)
|
|
|
|
fprintf(output, "\'CPU(s) %s", _target->cpu_list);
|
|
|
|
else if (!target__has_task(_target)) {
|
|
|
|
fprintf(output, "\'%s", argv ? argv[0] : "pipe");
|
|
|
|
for (i = 1; argv && (i < argc); i++)
|
|
|
|
fprintf(output, " %s", argv[i]);
|
|
|
|
} else if (_target->pid)
|
|
|
|
fprintf(output, "process id \'%s", _target->pid);
|
|
|
|
else
|
|
|
|
fprintf(output, "thread id \'%s", _target->tid);
|
|
|
|
|
|
|
|
fprintf(output, "\'");
|
|
|
|
if (config->run_count > 1)
|
|
|
|
fprintf(output, " (%d runs)", config->run_count);
|
|
|
|
fprintf(output, ":\n\n");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int get_precision(double num)
|
|
|
|
{
|
|
|
|
if (num > 1)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
return lround(ceil(-log10(num)));
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_table(struct perf_stat_config *config,
|
|
|
|
FILE *output, int precision, double avg)
|
|
|
|
{
|
|
|
|
char tmp[64];
|
|
|
|
int idx, indent = 0;
|
|
|
|
|
|
|
|
scnprintf(tmp, 64, " %17.*f", precision, avg);
|
|
|
|
while (tmp[indent] == ' ')
|
|
|
|
indent++;
|
|
|
|
|
|
|
|
fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
|
|
|
|
|
|
|
|
for (idx = 0; idx < config->run_count; idx++) {
|
|
|
|
double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
|
|
|
|
int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
|
|
|
|
|
|
|
|
fprintf(output, " %17.*f (%+.*f) ",
|
|
|
|
precision, run, precision, run - avg);
|
|
|
|
|
|
|
|
for (h = 0; h < n; h++)
|
|
|
|
fprintf(output, "#");
|
|
|
|
|
|
|
|
fprintf(output, "\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
fprintf(output, "\n%*s# Final result:\n", indent, "");
|
|
|
|
}
|
|
|
|
|
|
|
|
static double timeval2double(struct timeval *t)
|
|
|
|
{
|
|
|
|
return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void print_footer(struct perf_stat_config *config)
|
|
|
|
{
|
|
|
|
double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
|
|
|
|
FILE *output = config->output;
|
|
|
|
int n;
|
|
|
|
|
|
|
|
if (!config->null_run)
|
|
|
|
fprintf(output, "\n");
|
|
|
|
|
|
|
|
if (config->run_count == 1) {
|
|
|
|
fprintf(output, " %17.9f seconds time elapsed", avg);
|
|
|
|
|
|
|
|
if (config->ru_display) {
|
|
|
|
double ru_utime = timeval2double(&config->ru_data.ru_utime);
|
|
|
|
double ru_stime = timeval2double(&config->ru_data.ru_stime);
|
|
|
|
|
|
|
|
fprintf(output, "\n\n");
|
|
|
|
fprintf(output, " %17.9f seconds user\n", ru_utime);
|
|
|
|
fprintf(output, " %17.9f seconds sys\n", ru_stime);
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
|
|
|
|
/*
|
|
|
|
* Display at most 2 more significant
|
|
|
|
* digits than the stddev inaccuracy.
|
|
|
|
*/
|
|
|
|
int precision = get_precision(sd) + 2;
|
|
|
|
|
|
|
|
if (config->walltime_run_table)
|
|
|
|
print_table(config, output, precision, avg);
|
|
|
|
|
|
|
|
fprintf(output, " %17.*f +- %.*f seconds time elapsed",
|
|
|
|
precision, avg, precision, sd);
|
|
|
|
|
|
|
|
print_noise_pct(config, sd, avg);
|
|
|
|
}
|
|
|
|
fprintf(output, "\n\n");
|
|
|
|
|
|
|
|
if (config->print_free_counters_hint &&
|
|
|
|
sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
|
|
|
|
n > 0)
|
|
|
|
fprintf(output,
|
|
|
|
"Some events weren't counted. Try disabling the NMI watchdog:\n"
|
|
|
|
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
|
|
|
|
" perf stat ...\n"
|
|
|
|
" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
|
|
|
|
|
|
|
|
if (config->print_mixed_hw_group_error)
|
|
|
|
fprintf(output,
|
|
|
|
"The events in group usually have to be from "
|
|
|
|
"the same PMU. Try reorganizing the group.\n");
|
|
|
|
}
|
|
|
|
|
perf stat: Support 'percore' event qualifier
With this patch, we can use the 'percore' event qualifier in perf-stat.
root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000
1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%)
1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%)
1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%)
In this example, we count the event 'ref-cycles' per-core and per-CPU in
one perf stat command-line. From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
|
|
|
static void print_percore(struct perf_stat_config *config,
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter, char *prefix)
|
perf stat: Support 'percore' event qualifier
With this patch, we can use the 'percore' event qualifier in perf-stat.
root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000
1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%)
1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%)
1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%)
In this example, we count the event 'ref-cycles' per-core and per-CPU in
one perf stat command-line. From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
|
|
|
{
|
|
|
|
bool metric_only = config->metric_only;
|
|
|
|
FILE *output = config->output;
|
|
|
|
int s;
|
|
|
|
bool first = true;
|
|
|
|
|
|
|
|
if (!(config->aggr_map || config->aggr_get_id))
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (s = 0; s < config->aggr_map->nr; s++) {
|
|
|
|
if (prefix && metric_only)
|
|
|
|
fprintf(output, "%s", prefix);
|
|
|
|
|
|
|
|
print_counter_aggrdata(config, counter, s,
|
|
|
|
prefix, metric_only,
|
|
|
|
&first);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (metric_only)
|
|
|
|
fputc('\n', output);
|
|
|
|
}
|
|
|
|
|
2018-08-30 14:32:52 +08:00
|
|
|
void
|
2019-07-21 19:23:52 +08:00
|
|
|
perf_evlist__print_counters(struct evlist *evlist,
|
2018-08-30 14:32:52 +08:00
|
|
|
struct perf_stat_config *config,
|
|
|
|
struct target *_target,
|
|
|
|
struct timespec *ts,
|
|
|
|
int argc, const char **argv)
|
|
|
|
{
|
|
|
|
bool metric_only = config->metric_only;
|
|
|
|
int interval = config->interval;
|
2019-07-21 19:23:51 +08:00
|
|
|
struct evsel *counter;
|
2018-08-30 14:32:52 +08:00
|
|
|
char buf[64], *prefix = NULL;
|
|
|
|
|
|
|
|
if (interval)
|
|
|
|
print_interval(config, evlist, prefix = buf, ts);
|
|
|
|
else
|
|
|
|
print_header(config, _target, argc, argv);
|
|
|
|
|
|
|
|
if (metric_only) {
|
|
|
|
static int num_print_iv;
|
|
|
|
|
|
|
|
if (num_print_iv == 0 && !interval)
|
|
|
|
print_metric_headers(config, evlist, prefix, false);
|
|
|
|
if (num_print_iv++ == 25)
|
|
|
|
num_print_iv = 0;
|
|
|
|
if (config->aggr_mode == AGGR_GLOBAL && prefix)
|
|
|
|
fprintf(config->output, "%s", prefix);
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (config->aggr_mode) {
|
|
|
|
case AGGR_CORE:
|
2019-06-05 06:50:42 +08:00
|
|
|
case AGGR_DIE:
|
2018-08-30 14:32:52 +08:00
|
|
|
case AGGR_SOCKET:
|
|
|
|
print_aggr(config, evlist, prefix);
|
|
|
|
break;
|
|
|
|
case AGGR_THREAD:
|
|
|
|
evlist__for_each_entry(evlist, counter) {
|
|
|
|
print_aggr_thread(config, _target, counter, prefix);
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case AGGR_GLOBAL:
|
|
|
|
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)
|
|
|
|
print_no_aggr_metric(config, evlist, prefix);
|
|
|
|
else {
|
|
|
|
evlist__for_each_entry(evlist, counter) {
|
perf stat: Support 'percore' event qualifier
With this patch, we can use the 'percore' event qualifier in perf-stat.
root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000
1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%)
1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%)
1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%)
1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%)
1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%)
In this example, we count the event 'ref-cycles' per-core and per-CPU in
one perf stat command-line. From the output, we can see:
S0-C0 = CPU0 + CPU4
S0-C1 = CPU1 + CPU5
S0-C2 = CPU2 + CPU6
S0-C3 = CPU3 + CPU7
So the result is expected (tiny difference is ignored).
Note that, the 'percore' event qualifier needs to use with option '-A'.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 21:59:49 +08:00
|
|
|
if (counter->percore)
|
|
|
|
print_percore(config, counter, prefix);
|
|
|
|
else
|
|
|
|
print_counter(config, counter, prefix);
|
2018-08-30 14:32:52 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case AGGR_UNSET:
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!interval && !config->csv_output)
|
|
|
|
print_footer(config);
|
|
|
|
|
|
|
|
fflush(config->output);
|
|
|
|
}
|