[PATCHSET 0/9] perf: Improve cgroup profiling (v1)

From: Namhyung Kim
Date: Wed Aug 28 2019 - 03:31:48 EST

Hello,

This work is to improve cgroup profiling in perf. Currently it only
supports profiling tasks in a specific cgroup and there's no way to
identify which cgroup the current sample belongs to. So I added
PERF_SAMPLE_CGROUP to add cgroup info into each sample. It's a 64-bit
integer having inode number of the cgroup. And kernel also generates
PERF_RECORD_CGROUP event for new groups to correlate the inode number
and cgroup name (path in the cgroup filesystem). The inode number can
be read from userspace easily so it can synthesize the CGROUP event
for existing groups.

Note that this only works for "perf_event" cgroups (obviously) so if
users are still using cgroup-v1 interface, they need to have same
hierarchy for subsystem(s) want to profile with it.

The testing result looks something like this:

[root@qemu build]# ./perf record --all-cgroups ./cgtest
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.009 MB perf.data (150 samples) ]

[root@qemu build]# ./perf report -s cgroup,comm --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 150 of event 'cpu-clock:pppH'
# Event count (approx.): 37500000
#
# Overhead cgroup Command
# ........ .......... .......
#
32.00% /sub/cgrp2 looper2
28.00% /sub/cgrp1 looper1
25.33% /sub looper0
4.00% / cgtest
4.00% /sub cgtest
3.33% /sub/cgrp2 cgtest
2.67% /sub/cgrp1 cgtest
0.67% / looper0


The test program (cgtest) follows.

Thanks,
Namhyung


Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Li Zefan <lizefan@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>


-------8<-----------------------------------------8<----------------
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <sched.h>
#include <errno.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <sys/prctl.h>
#include <sys/mount.h>

char cgbase[] = "/sys/fs/cgroup/perf_event";

void mkcgrp(char *name) {
char buf[256];

snprintf(buf, sizeof(buf), "%s%s", cgbase, name);
if (mkdir(buf, 0755) < 0)
perror("mkdir");
}

void rmcgrp(char *name) {
char buf[256];

snprintf(buf, sizeof(buf), "%s%s", cgbase, name);
if (rmdir(buf) < 0)
perror("rmdir");
}

void setcgrp(char *name) {
char buf[256];
int fd;

snprintf(buf, sizeof(buf), "%s%s/tasks", cgbase, name);

fd = open(buf, O_WRONLY);
if (fd > 0) {
if (write(fd, "0\n", 2) != 2)
perror("write");
close(fd);
}
}

void create_sub_cgroup(int idx) {
char buf[128];

snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
mkcgrp(buf);
}

void remove_sub_cgroup(int idx) {
char buf[128];

snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
rmcgrp(buf);
}

void set_sub_cgroup(int idx) {
char buf[128];

snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
setcgrp(buf);
}

void set_task_name(int idx) {
char buf[16];

snprintf(buf, sizeof(buf), "looper%d", idx);
prctl(PR_SET_NAME, buf, 0, 0, 0);
}

void loop(unsigned max) {
volatile unsigned int count = 1;

while (count++ != max) {
asm volatile ("pause");
}
}

void worker(int idx, unsigned cnt, int new_ns) {
int oldns;

create_sub_cgroup(idx);
set_sub_cgroup(idx);

if (new_ns) {
if (unshare(CLONE_NEWCGROUP) < 0)
perror("unshare");

#if 0 /* FIXME */
if (unshare(CLONE_NEWNS) < 0)
perror("unshare");

if (mount("none", "/sys", NULL, MS_REMOUNT | MS_REC | MS_SLAVE, NULL) < 0)
perror("mount --make-rslave");

sleep(1);
if (umount("/sys/fs/cgroup/perf_event") < 0)
perror("umount");

if (mount("cgroup", "/sys/fs/cgroup/perf_event", "cgroup",
MS_NODEV | MS_NOEXEC | MS_NOSUID, "perf_event") < 0)
perror("mount again");
#endif
}

if (fork() == 0) {
set_task_name(idx);
loop(cnt);
exit(0);
}
wait(NULL);
}

int main(int argc, char *argv[])
{
int i, nr = 2;
int new_ns = 1;
unsigned cnt = 1000000;
int fd;

if (argc > 1)
nr = atoi(argv[1]);
if (argc > 2)
cnt = atoi(argv[2]);
if (argc > 3)
new_ns = atoi(argv[3]);

mkcgrp("/sub");
setcgrp("/sub");

for (i = 0; i < nr; i++) {
if (fork() == 0) {
worker(i+1, cnt, new_ns);
exit(0);
}
}

set_task_name(0);
loop(cnt);

for (i = 0; i < nr; i++)
wait(NULL);

for (i = 0; i < nr; i++)
remove_sub_cgroup(i+1);

setcgrp("/");
rmcgrp("/sub");

return 0;
}
-------8<-----------------------------------------8<----------------


Namhyung Kim (9):
perf/core: Add PERF_RECORD_CGROUP event
perf/core: Add PERF_SAMPLE_CGROUP feature
perf tools: Basic support for CGROUP event
perf tools: Maintain cgroup hierarchy
perf report: Add 'cgroup' sort key
perf record: Support synthesizing cgroup events
perf record: Add --all-cgroups option
perf top: Add --all-cgroups option
perf script: Add --show-cgroup-events option

include/linux/perf_event.h | 1 +
include/uapi/linux/perf_event.h | 18 ++-
kernel/events/core.c | 128 ++++++++++++++++++++++
tools/include/uapi/linux/perf_event.h | 17 ++-
tools/perf/Documentation/perf-record.txt | 5 +-
tools/perf/Documentation/perf-report.txt | 1 +
tools/perf/Documentation/perf-script.txt | 3 +
tools/perf/Documentation/perf-top.txt | 4 +
tools/perf/builtin-diff.c | 1 +
tools/perf/builtin-record.c | 10 ++
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-script.c | 41 +++++++
tools/perf/builtin-top.c | 9 ++
tools/perf/lib/include/perf/event.h | 7 ++
tools/perf/util/cgroup.c | 75 ++++++++++++-
tools/perf/util/cgroup.h | 16 ++-
tools/perf/util/event.c | 133 +++++++++++++++++++++++
tools/perf/util/event.h | 11 ++
tools/perf/util/evsel.c | 12 ++
tools/perf/util/hist.c | 7 ++
tools/perf/util/hist.h | 1 +
tools/perf/util/machine.c | 19 ++++
tools/perf/util/machine.h | 3 +
tools/perf/util/record.h | 1 +
tools/perf/util/session.c | 8 ++
tools/perf/util/sort.c | 31 ++++++
tools/perf/util/sort.h | 2 +
tools/perf/util/tool.h | 2 +
28 files changed, 556 insertions(+), 11 deletions(-)

--
2.23.0.187.g17f5b7556c-goog