perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
#include "util.h"
|
|
|
|
#include "../perf.h"
|
|
|
|
#include "parse-options.h"
|
|
|
|
#include "evsel.h"
|
|
|
|
#include "cgroup.h"
|
|
|
|
#include "evlist.h"
|
|
|
|
|
|
|
|
int nr_cgroups;
|
|
|
|
|
|
|
|
static int
|
|
|
|
cgroupfs_find_mountpoint(char *buf, size_t maxlen)
|
|
|
|
{
|
|
|
|
FILE *fp;
|
2011-11-16 22:55:59 +08:00
|
|
|
char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
|
2011-04-08 18:11:06 +08:00
|
|
|
char *token, *saved_ptr = NULL;
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
int found = 0;
|
|
|
|
|
|
|
|
fp = fopen("/proc/mounts", "r");
|
|
|
|
if (!fp)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* in order to handle split hierarchy, we need to scan /proc/mounts
|
|
|
|
* and inspect every cgroupfs mount point to find one that has
|
|
|
|
* perf_event subsystem
|
|
|
|
*/
|
2011-11-16 22:55:59 +08:00
|
|
|
while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %"
|
|
|
|
STR(PATH_MAX)"s %*d %*d\n",
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
mountpoint, type, tokens) == 3) {
|
|
|
|
|
|
|
|
if (!strcmp(type, "cgroup")) {
|
|
|
|
|
|
|
|
token = strtok_r(tokens, ",", &saved_ptr);
|
|
|
|
|
|
|
|
while (token != NULL) {
|
|
|
|
if (!strcmp(token, "perf_event")) {
|
|
|
|
found = 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
token = strtok_r(NULL, ",", &saved_ptr);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (found)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
fclose(fp);
|
|
|
|
if (!found)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
if (strlen(mountpoint) < maxlen) {
|
|
|
|
strcpy(buf, mountpoint);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int open_cgroup(char *name)
|
|
|
|
{
|
2011-11-16 22:55:59 +08:00
|
|
|
char path[PATH_MAX + 1];
|
|
|
|
char mnt[PATH_MAX + 1];
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
int fd;
|
|
|
|
|
|
|
|
|
2011-11-16 22:55:59 +08:00
|
|
|
if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1))
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
return -1;
|
|
|
|
|
2011-11-16 22:55:59 +08:00
|
|
|
snprintf(path, PATH_MAX, "%s/%s", mnt, name);
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
|
|
|
|
fd = open(path, O_RDONLY);
|
|
|
|
if (fd == -1)
|
|
|
|
fprintf(stderr, "no access to cgroup %s\n", path);
|
|
|
|
|
|
|
|
return fd;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int add_cgroup(struct perf_evlist *evlist, char *str)
|
|
|
|
{
|
|
|
|
struct perf_evsel *counter;
|
|
|
|
struct cgroup_sel *cgrp = NULL;
|
|
|
|
int n;
|
|
|
|
/*
|
|
|
|
* check if cgrp is already defined, if so we reuse it
|
|
|
|
*/
|
|
|
|
list_for_each_entry(counter, &evlist->entries, node) {
|
|
|
|
cgrp = counter->cgrp;
|
|
|
|
if (!cgrp)
|
|
|
|
continue;
|
|
|
|
if (!strcmp(cgrp->name, str))
|
|
|
|
break;
|
|
|
|
|
|
|
|
cgrp = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!cgrp) {
|
|
|
|
cgrp = zalloc(sizeof(*cgrp));
|
|
|
|
if (!cgrp)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
cgrp->name = str;
|
|
|
|
|
|
|
|
cgrp->fd = open_cgroup(str);
|
|
|
|
if (cgrp->fd == -1) {
|
|
|
|
free(cgrp);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* find corresponding event
|
|
|
|
* if add cgroup N, then need to find event N
|
|
|
|
*/
|
|
|
|
n = 0;
|
|
|
|
list_for_each_entry(counter, &evlist->entries, node) {
|
|
|
|
if (n == nr_cgroups)
|
|
|
|
goto found;
|
|
|
|
n++;
|
|
|
|
}
|
|
|
|
if (cgrp->refcnt == 0)
|
|
|
|
free(cgrp);
|
|
|
|
|
|
|
|
return -1;
|
|
|
|
found:
|
|
|
|
cgrp->refcnt++;
|
|
|
|
counter->cgrp = cgrp;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void close_cgroup(struct cgroup_sel *cgrp)
|
|
|
|
{
|
|
|
|
if (!cgrp)
|
|
|
|
return;
|
|
|
|
|
|
|
|
/* XXX: not reentrant */
|
|
|
|
if (--cgrp->refcnt == 0) {
|
|
|
|
close(cgrp->fd);
|
|
|
|
free(cgrp->name);
|
|
|
|
free(cgrp);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-09-11 06:15:03 +08:00
|
|
|
int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
|
|
|
|
int unset __maybe_unused)
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
{
|
|
|
|
struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
|
|
|
|
const char *p, *e, *eos = str + strlen(str);
|
|
|
|
char *s;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (list_empty(&evlist->entries)) {
|
|
|
|
fprintf(stderr, "must define events before cgroups\n");
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
p = strchr(str, ',');
|
|
|
|
e = p ? p : eos;
|
|
|
|
|
|
|
|
/* allow empty cgroups, i.e., skip */
|
|
|
|
if (e - str) {
|
|
|
|
/* termination added */
|
|
|
|
s = strndup(str, e - str);
|
|
|
|
if (!s)
|
|
|
|
return -1;
|
|
|
|
ret = add_cgroup(evlist, s);
|
|
|
|
if (ret) {
|
|
|
|
free(s);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
/* nr_cgroups is increased een for empty cgroups */
|
|
|
|
nr_cgroups++;
|
|
|
|
if (!p)
|
|
|
|
break;
|
|
|
|
str = p+1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|