From: Michael wang <wangyun@linux.vnet.ibm.com>
To: Peter Zijlstra <peterz@infradead.org>, Rik van Riel <riel@redhat.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@kernel.org>, Mike Galbraith <efault@gmx.de>,
Alex Shi <alex.shi@linaro.org>, Paul Turner <pjt@google.com>,
Mel Gorman <mgorman@suse.de>,
Daniel Lezcano <daniel.lezcano@linaro.org>
Subject: Re: [ISSUE] sched/cgroup: Does cpu-cgroup still works fine nowadays?
Date: Wed, 14 May 2014 15:36:50 +0800 [thread overview]
Message-ID: <53731D12.7040804@linux.vnet.ibm.com> (raw)
In-Reply-To: <20140513142328.GE2485@laptop.programming.kicks-ass.net>
[-- Attachment #1: Type: text/plain, Size: 3484 bytes --]
Hi, Peter
On 05/13/2014 10:23 PM, Peter Zijlstra wrote:
[snip]
>
> I you want to investigate !spinners, replace the ABC with slightly more
> complex loads like: https://lkml.org/lkml/2012/6/18/212
I've done a little reform, enabled multi-threads and add a mutex,
please check the code below for details.
I built it by:
gcc -o my_tool cgroup_tool.c -lpthread
distro mount cpu-subsys under '/sys/fs/cgroup/cpu', create group like:
mkdir /sys/fs/cgroup/cpu/A
mkdir /sys/fs/cgroup/cpu/B
mkdir /sys/fs/cgroup/cpu/C
and then:
echo $$ > /sys/fs/cgroup/cpu/A/tasks ; ./my_tool -l
echo $$ > /sys/fs/cgroup/cpu/B/tasks ; ./my_tool -l
echo $$ > /sys/fs/cgroup/cpu/C/tasks ; ./my_tool 50
the results in top is around:
A B C
CPU% 550 550 100
While only './my_tool 50' was running, it require around 300%.
And this could also be reproduced by dbench, stress combination like:
echo $$ > /sys/fs/cgroup/cpu/A/tasks ; dbench 6
echo $$ > /sys/fs/cgroup/cpu/B/tasks ; stress -c 6
echo $$ > /sys/fs/cgroup/cpu/C/tasks ; stress -c 6
Now it seems more like a generic problem... will keep investigating, please
let me know if there are any suggestions :)
Regards,
Michael Wang
#include <sys/time.h>
#include <unistd.h>
#include <stdio.h>
#include <pthread.h>
pthread_mutex_t my_mutex;
unsigned long long stamp(void)
{
struct timeval tv;
gettimeofday(&tv, NULL);
return (unsigned long long)tv.tv_sec * 1000000 + tv.tv_usec;
}
void consume(int spin, int total)
{
unsigned long long begin, now;
begin = stamp();
for (;;) {
pthread_mutex_lock(&my_mutex);
now = stamp();
if ((long long)(now - begin) > spin) {
pthread_mutex_unlock(&my_mutex);
usleep(total - spin);
pthread_mutex_lock(&my_mutex);
begin += total;
}
pthread_mutex_unlock(&my_mutex);
}
}
struct my_data {
int spin;
int total;
};
void *my_fn_sleepy(void *arg)
{
struct my_data *data = (struct my_data *)arg;
consume(data->spin, data->total);
return NULL;
}
void *my_fn_loop(void *arg)
{
while (1) {};
return NULL;
}
int main(int argc, char **argv)
{
int period = 100000; /* 100ms */
int frac;
struct my_data data;
pthread_t last_thread;
int thread_num = sysconf(_SC_NPROCESSORS_ONLN) / 2;
void *(*my_fn)(void *arg) = &my_fn_sleepy;
if (thread_num <= 0 || thread_num > 1024) {
fprintf(stderr, "insane processor(half) size %d\n", thread_num);
return -1;
}
if (argc == 2 && !strcmp(argv[1], "-l")) {
my_fn = &my_fn_loop;
printf("loop mode enabled\n");
goto loop_mode;
}
if (argc < 2) {
fprintf(stderr, "%s <frac> [<period>]\n"
" frac -- [1-100] %% of time to burn\n"
" period -- [usec] period of burn/sleep cycle\n",
argv[0]);
return -1;
}
frac = atoi(argv[1]);
if (argc > 2)
period = atoi(argv[2]);
if (frac > 100)
frac = 100;
if (frac < 1)
frac = 1;
data.spin = (period * frac) / 100;
data.total = period;
loop_mode:
pthread_mutex_init(&my_mutex, NULL);
while (thread_num--) {
if (pthread_create(&last_thread, NULL, my_fn, &data)) {
fprintf(stderr, "Create thread failed\n");
return -1;
}
}
printf("Threads never stop, CTRL + C to terminate\n");
pthread_join(last_thread, NULL);
pthread_mutex_destroy(&my_mutex); //won't happen
return 0;
}
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
[-- Attachment #2: cgroup_tool.c --]
[-- Type: text/x-csrc, Size: 2042 bytes --]
#include <sys/time.h>
#include <unistd.h>
#include <stdio.h>
#include <pthread.h>
pthread_mutex_t my_mutex;
unsigned long long stamp(void)
{
struct timeval tv;
gettimeofday(&tv, NULL);
return (unsigned long long)tv.tv_sec * 1000000 + tv.tv_usec;
}
void consume(int spin, int total)
{
unsigned long long begin, now;
begin = stamp();
for (;;) {
pthread_mutex_lock(&my_mutex);
now = stamp();
if ((long long)(now - begin) > spin) {
pthread_mutex_unlock(&my_mutex);
usleep(total - spin);
pthread_mutex_lock(&my_mutex);
begin += total;
}
pthread_mutex_unlock(&my_mutex);
}
}
struct my_data {
int spin;
int total;
};
void *my_fn_sleepy(void *arg)
{
struct my_data *data = (struct my_data *)arg;
consume(data->spin, data->total);
return NULL;
}
void *my_fn_loop(void *arg)
{
while (1) {};
return NULL;
}
int main(int argc, char **argv)
{
int period = 100000; /* 100ms */
int frac;
struct my_data data;
pthread_t last_thread;
int thread_num = sysconf(_SC_NPROCESSORS_ONLN) / 2;
void *(*my_fn)(void *arg) = &my_fn_sleepy;
if (thread_num <= 0 || thread_num > 1024) {
fprintf(stderr, "insane processor(half) size %d\n", thread_num);
return -1;
}
if (argc == 2 && !strcmp(argv[1], "-l")) {
my_fn = &my_fn_loop;
printf("loop mode enabled\n");
goto loop_mode;
}
if (argc < 2) {
fprintf(stderr, "%s <frac> [<period>]\n"
" frac -- [1-100] %% of time to burn\n"
" period -- [usec] period of burn/sleep cycle\n",
argv[0]);
return -1;
}
frac = atoi(argv[1]);
if (argc > 2)
period = atoi(argv[2]);
if (frac > 100)
frac = 100;
if (frac < 1)
frac = 1;
data.spin = (period * frac) / 100;
data.total = period;
loop_mode:
pthread_mutex_init(&my_mutex, NULL);
while (thread_num--) {
if (pthread_create(&last_thread, NULL, my_fn, &data)) {
fprintf(stderr, "Create thread failed\n");
return -1;
}
}
printf("Threads never stop, CTRL + C to terminate\n");
pthread_join(last_thread, NULL);
pthread_mutex_destroy(&my_mutex); //won't happen
return 0;
}
next prev parent reply other threads:[~2014-05-14 7:37 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-05-13 3:34 [ISSUE] sched/cgroup: Does cpu-cgroup still works fine nowadays? Michael wang
2014-05-13 9:47 ` Peter Zijlstra
2014-05-13 13:36 ` Rik van Riel
2014-05-13 14:23 ` Peter Zijlstra
2014-05-14 3:27 ` Michael wang
2014-05-14 7:36 ` Michael wang [this message]
2014-05-14 9:44 ` Peter Zijlstra
2014-05-15 3:46 ` Michael wang
2014-05-15 8:35 ` Peter Zijlstra
2014-05-15 8:46 ` Michael wang
2014-05-15 9:06 ` Peter Zijlstra
2014-05-15 9:35 ` Michael wang
2014-05-15 11:57 ` Peter Zijlstra
2014-05-16 2:23 ` Michael wang
2014-05-16 2:51 ` Mike Galbraith
2014-05-16 4:24 ` Michael wang
2014-05-16 7:54 ` Peter Zijlstra
2014-05-16 8:15 ` Michael wang
2014-06-10 8:56 ` Michael wang
2014-06-10 12:12 ` Peter Zijlstra
2014-06-11 6:13 ` Michael wang
2014-06-11 8:24 ` Peter Zijlstra
2014-06-11 9:18 ` Michael wang
2014-06-23 9:42 ` Peter Zijlstra
2014-06-24 3:10 ` Michael wang
2014-05-16 7:48 ` Peter Zijlstra
2014-05-14 3:21 ` Michael wang
2014-05-14 3:16 ` Michael wang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=53731D12.7040804@linux.vnet.ibm.com \
--to=wangyun@linux.vnet.ibm.com \
--cc=alex.shi@linaro.org \
--cc=daniel.lezcano@linaro.org \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=riel@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.