Re: CPU scheduler weirdness?

[Marton Balint]

On Fri, 4 Sep 2009, Mike Galbraith wrote:

> On Thu, 2009-09-03 at 23:57 +0200, Marton Balint wrote:
>
> > > > In the meantime, I updated my original C program and also created a kernel
> > > > module (schedtest_mod.c) which causes the same scheduling problems as the
> > > > kernel module of my TV card. The kernel module is a skeleton of the
> > > > infrared sensor polling code in cx88-input.c. It uses
> > > > schedule_delayed_work, this seems to cause the problem. The C program
> > > > (schedtest.c) is also updated, it now detects the number of CPU cores, from
> > > > now, what you can set as a command line parameter is the CPU core number,
> > > > on which the schedtest processes will not quit. (previously this was always
> > > > the last core).
> > > >
> > > > So to reproduce the bug on a dual core system, compile and insert the
> > > > kernel module (schedtest_mod.c). Then check dmesg, it should contain on
> > > > which CPU core is the delayed_work running. You should use the CPU core id
> > > > of the _other_ CPU core as a command line parameter to the updated
> > > > schedtest program.
> > > >
> > > > And by the way, thank you guys for the help so far, hopefully we'll get to
> > > > the bottom of this :)
> > >
> > > I reproduced the bug with the previously provided kernel module and C program
> > > on a different computer (it's a laptop with a core2 duo P8400 CPU), and also
> > > bisected the bug to this commit:
> > >
> > > sched: fine-tune SD_MC_INIT:
> > > 14800984706bf6936bbec5187f736e928be5c218
> > >
> > > If I add again the removed SD_BALANCE_NEWIDLE to flags, then everything works
> > > as expected. So what would be the correct fix for this bug? Revert the patch?
> > > Or just add SD_BALANCE_NEWIDLE to flags?
>
> Or, figure out what's going weird with that module loaded.

The problem is most likely caused by scheduled_delayed_work, a work 
function is called every time a CPU wakes up.

> > Ingo, Peter, could any of you guys have a look at the commit that caused
> > this bug? Is it OK to revert it? Or a fix somewhere else is necessary? I'm
> > pushing this because I hope that this bug will get fixed in the upcoming
> > stable kernel...
>
> Where does your schedtest.c and schedtest_mod.c live?

They were attached to one of my previous mails, i'm inlining them here to 
make the discussion easier. Thanks for looking into this.

Regards,
  Marton


schedtest_mod.c
-------------------
#include <linux/module.h>
#include <linux/init.h>
#include <linux/workqueue.h>
#include <asm/smp.h>

static int i;
static struct delayed_work d_work;

static void schedtest_work(struct work_struct *work)
{
	schedule_delayed_work(&d_work, msecs_to_jiffies(1));
	if (i++ % 500 == 0) {
		printk(KERN_DEBUG "schedtest: I am on CPU %d.\n", get_cpu());
		put_cpu();
	}
}

static int __init schedtest_init_module(void)
{
	INIT_DELAYED_WORK(&d_work, schedtest_work);
	schedule_delayed_work(&d_work, 0);
	return 0;
}

static void __exit schedtest_cleanup_module(void)
{
	cancel_delayed_work_sync(&d_work);
}

module_init(schedtest_init_module);
module_exit(schedtest_cleanup_module);

MODULE_LICENSE("GPL");



schedtest.c:
--------------------

#define _GNU_SOURCE
#include <utmpx.h>
#include <sys/time.h>
#include <unistd.h>

/* Usage: ./schedtest <cpu core to test> */

int miliseconds() {
  struct timeval tv;
  gettimeofday(&tv, 0);
  return tv.tv_usec/1000;
}

int main(int argc, char *argv[]) {
  int lives = 1000, time, lasttime, childs, cores, core_to_test;
  cores = sysconf(_SC_NPROCESSORS_ONLN);
  childs = cores * 2;
  if (argc > 1)
    core_to_test = atoi(argv[1]);
  else
    core_to_test = cores-1;
  while (childs-- && !fork());
  while (lives) {
    time = miliseconds();
    if (lasttime != time && sched_getcpu() != core_to_test)
       lives--;
    lasttime = time;
  }
  return 0;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/