All of lore.kernel.org
 help / color / mirror / Atom feed
From: Zefan Li <lizefan@huawei.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>,
	Mike Galbraith <umgwanakikbuti@gmail.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Stefan Bader <stefan.bader@canonical.com>
Subject: Re: [PATCH] sched, autogroup: Fix failure when writing to cpu.rt_runtime_us
Date: Fri, 6 Feb 2015 09:30:51 +0800	[thread overview]
Message-ID: <54D4194B.2040808@huawei.com> (raw)
In-Reply-To: <20150205142527.GI5029@twins.programming.kicks-ass.net>

On 2015/2/5 22:25, Peter Zijlstra wrote:
> On Thu, Feb 05, 2015 at 04:33:24PM +0800, Zefan Li wrote:
>> This is how to reproduce the bug:
>>
>> int main() {
>>     struct sched_param param = {.sched_priority=1};
>>
>>     if (fork() > 0)
>>         exit(0);
>>
>>     setsid();
>>
>>     if (sched_setscheduler(0, SCHED_RR, &param) < 0){
>>         perror("failed to sched_setscheduler()");
>>         return -1;
>>     }
>>

btw, if you move setscheduler() abvoe fork(), changing rt_runtime
will succeed.

>>     while(1)
>>         ;
>> }
>>
>>   # ./test
>>   # mount -t cgroup -o cpu xxx /cgroup
>>   # cat /cgroup/cpu.rt_runtime_us
>>   950000
>>   # echo 940000 > /cgroup/cpu.rt_runtime_us
>>   Device or Resource busy
> 
> That's -EBUSY, but you're changing an -EPERM condition. Neither your
> patch nor explanation of the matter make sense.
> 

I'm not changing the -EPERM condition. I'm adding an else condition which
resets p->sched_task_group.

After running the test program, we have:

  root
   |
  autogroup   <-- the RT test program is now here

root.rt_runtime = 950000
autogroup.rt_runtime = 0

Now if you try to change the rt_runtime of the root cgroup, it returns
-EBUSY.

That comes from:

static int tg_rt_schedulable(struct task_group *tg, void *data)
(
	...
        if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
                return -EBUSY;
	...
}

static inline int tg_has_rt_tasks(struct task_group *tg)
{
        struct task_struct *g, *p;

        for_each_process_thread(g, p) {
                if (rt_task(p) && task_group(p) == tg)
                        return 1;
        }

        return 0;
}

here tg == autogroup, p == the test program, and task_group(p)
returns autogroup, which is wrong.

See this commit:

commit f44937718ce3b8360f72f6c68c9481712517a867
Author: Mike Galbraith <efault@gmx.de>
Date:   Thu Jan 13 04:54:50 2011 +0100

    sched, autogroup: Fix CONFIG_RT_GROUP_SCHED sched_setscheduler() failure
...
+       /*
+        * Autogroup RT tasks are redirected to the root task group
	...
+        * the policy change to proceed.  Thereafter, task_group()
+        * returns &root_task_group, ...
+        */



  reply	other threads:[~2015-02-06  1:31 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-02-05  8:33 [PATCH] sched, autogroup: Fix failure when writing to cpu.rt_runtime_us Zefan Li
2015-02-05 14:25 ` Peter Zijlstra
2015-02-06  1:30   ` Zefan Li [this message]
2015-02-06 10:58     ` Peter Zijlstra
2015-02-07  7:02       ` Zefan Li
2015-02-09 11:22         ` Peter Zijlstra
2015-02-09 11:27           ` Peter Zijlstra
2015-02-18 17:09             ` [tip:sched/core] sched/rt: Avoid obvious configuration fail tip-bot for Peter Zijlstra
2015-02-10  1:26           ` [PATCH] sched, autogroup: Fix failure when writing to cpu.rt_runtime_us Zefan Li
2015-02-18 17:09           ` [tip:sched/core] sched/autogroup: Fix failure to set cpu.rt_runtime_us tip-bot for Peter Zijlstra

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=54D4194B.2040808@huawei.com \
    --to=lizefan@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=stefan.bader@canonical.com \
    --cc=umgwanakikbuti@gmail.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.