linux-kernel - Re: [PATCH] sched: add a tuning knob to allow changing RR tmeslice

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20130123144646.6221097e@redhat.com>
Date:	Wed, 23 Jan 2013 14:46:46 -0600
From:	Clark Williams <williams@...hat.com>
To:	Steven Rostedt <rostedt@...dmis.org>
Cc:	Peter Zijlstra <peterz@...radead.org>,
	LKML <linux-kernel@...r.kernel.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...e.hu>
Subject: Re: [PATCH] sched: add a tuning knob to allow changing RR tmeslice

On Wed, 23 Jan 2013 15:09:38 -0500
Steven Rostedt <rostedt@...dmis.org> wrote:

> On Thu, 2012-11-08 at 14:27 -0600, Clark Williams wrote:
> > Subject: [PATCH] sched: add a tuning knob to allow changing RR timeslice
> > 
> > User wanted a facility simliar to the ability on Solaris to adjust
> > the SCHED_RR timeslice value. Add a /proc/sys/kernel scheduler knob
> > named sched_rr_timeslice_ms which allows global changing of the SCHED_RR
> > timeslice value. User visable value is in milliseconds but is stored as
> > jiffies.  Setting to 0 (zero) resets to the default (currently 100ms).
> > 
> 
> Hmm, has this been ignored?
> 
> I guess the real question, is it still needed (or wanted)?
> 

Yes, we've got a couple of customers that have been asking for it. 

> -- Steve
> 
> > Patch against tip/master, currently 3.7-rc3.
> > 
> > Signed-off-by: Clark Williams <williams@...hat.com>
> > ---
> >  include/linux/sched.h |  6 +++++-
> >  kernel/sched.c        | 19 +++++++++++++++++++
> >  kernel/sched_rt.c     |  4 ++--
> >  kernel/sysctl.c       |  8 ++++++++
> >  4 files changed, 34 insertions(+), 3 deletions(-)
> > 
> > diff --git a/include/linux/sched.h b/include/linux/sched.h
> > index 12317b6..214bf27 100644
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -2097,11 +2097,15 @@ static inline unsigned int get_sysctl_timer_migration(void)
> >  #endif
> >  extern unsigned int sysctl_sched_rt_period;
> >  extern int sysctl_sched_rt_runtime;
> > -
> >  int sched_rt_handler(struct ctl_table *table, int write,
> >  		void __user *buffer, size_t *lenp,
> >  		loff_t *ppos);
> >  
> > +extern int sched_rr_timeslice;
> > +extern int sched_rr_handler(struct ctl_table *table, int write,
> > +		void __user *buffer, size_t *lenp,
> > +		loff_t *ppos);
> > +
> >  #ifdef CONFIG_SCHED_AUTOGROUP
> >  extern unsigned int sysctl_sched_autogroup_enabled;
> >  
> > diff --git a/kernel/sched.c b/kernel/sched.c
> > index cdf9484..c63c3a4 100644
> > --- a/kernel/sched.c
> > +++ b/kernel/sched.c
> > @@ -120,6 +120,7 @@
> >   * Timeslices get refilled after they expire.
> >   */
> >  #define DEF_TIMESLICE		(100 * HZ / 1000)
> > +int sched_rr_timeslice = DEF_TIMESLICE;
> >  
> >  /*
> >   * single value that denotes runtime == period, ie unlimited time.
> > @@ -9614,6 +9615,24 @@ static int sched_rt_global_constraints(void)
> >  }
> >  #endif /* CONFIG_RT_GROUP_SCHED */
> >  
> > +int sched_rr_handler(struct ctl_table *table, int write,
> > +		void __user *buffer, size_t *lenp,
> > +		loff_t *ppos)
> > +{
> > +	int ret;
> > +	static DEFINE_MUTEX(mutex);
> > +
> > +	mutex_lock(&mutex);
> > +	ret = proc_dointvec(table, write, buffer, lenp, ppos);
> > +	/* make sure that internally we keep jiffies */
> > +	/* also, writing zero resets timeslice to default */
> > +	if (!ret && write) 
> > +		sched_rr_timeslice = sched_rr_timeslice <= 0 ? 
> > +			DEF_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
> > +	mutex_unlock(&mutex);
> > +	return ret;
> > +}
> > +
> >  int sched_rt_handler(struct ctl_table *table, int write,
> >  		void __user *buffer, size_t *lenp,
> >  		loff_t *ppos)
> > diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
> > index c108b9c..799dd09 100644
> > --- a/kernel/sched_rt.c
> > +++ b/kernel/sched_rt.c
> > @@ -1791,7 +1791,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
> >  	if (--p->rt.time_slice)
> >  		return;
> >  
> > -	p->rt.time_slice = DEF_TIMESLICE;
> > +	p->rt.time_slice = sched_rr_timeslice;
> >  
> >  	/*
> >  	 * Requeue to the end of queue if we are not the only element
> > @@ -1819,7 +1819,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
> >  	 * Time slice is 0 for SCHED_FIFO tasks
> >  	 */
> >  	if (task->policy == SCHED_RR)
> > -		return DEF_TIMESLICE;
> > +		return sched_rr_timeslice;
> >  	else
> >  		return 0;
> >  }
> > diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> > index ea7ec7f..10b1129 100644
> > --- a/kernel/sysctl.c
> > +++ b/kernel/sysctl.c
> > @@ -362,6 +362,14 @@ static struct ctl_table kern_table[] = {
> >  		.mode		= 0644,
> >  		.proc_handler	= sched_rt_handler,
> >  	},
> > +	{
> > +		.procname	= "sched_rr_timeslice_ms",
> > +		.data		= &sched_rr_timeslice,
> > +		.maxlen		= sizeof(int),
> > +		.mode		= 0644,
> > +		.proc_handler	= sched_rr_handler,
> > +	},
> > +
> >  #ifdef CONFIG_SCHED_AUTOGROUP
> >  	{
> >  		.procname	= "sched_autogroup_enabled",
> 
> 

Download attachment "signature.asc" of type "application/pgp-signature" (199 bytes)