Re: [PATCH 02/13] sched_ext: Make slice values tunable and use shorter slice in bypass mode

[Andrea Righi <arighi@nvidia.com>]

On Mon, Nov 10, 2025 at 08:03:45AM +0100, Andrea Righi wrote:
> Hi Tejun,
> 
> On Sun, Nov 09, 2025 at 08:31:01AM -1000, Tejun Heo wrote:
> > There have been reported cases of bypass mode not making forward progress fast
> > enough. The 20ms default slice is unnecessarily long for bypass mode where the
> > primary goal is ensuring all tasks can make forward progress.
> > 
> > Introduce SCX_SLICE_BYPASS set to 5ms and make the scheduler automatically
> > switch to it when entering bypass mode. Also make both the default and bypass
> > slice values tunable through module parameters (slice_dfl_us and
> > slice_bypass_us, adjustable between 100us and 100ms) to make it easier to test
> > whether slice durations are a factor in problem cases. Note that the configured
> > values are applied through bypass mode switching and thus are guaranteed to
> > apply only during scheduler [un]load operations.
> 
> IIRC Changwoo suggested to introduce a tunable to change the default time
> slice in the past.
> 
> I agree that slice_bypass_us can be a tunable in sysfs, but I think it'd be
> nicer if the default time slice would be a property of sched_ext_ops, is
> there any reason to not do that?

Moreover (not necessarily for this patchset, we can add this later), should
we turn SCX_SLICE_DFL into a special value (e.g., 0) and have the
schedulers that currently rely on it automatically pick up the new global
default time slice internally?

Thanks,
-Andrea

> 
> Thanks,
> -Andrea
> 
> > 
> > Cc: Dan Schatzberg <schatzberg.dan@gmail.com>
> > Cc: Emil Tsalapatis <etsal@meta.com>
> > Signed-off-by: Tejun Heo <tj@kernel.org>
> > ---
> >  include/linux/sched/ext.h | 11 +++++++++++
> >  kernel/sched/ext.c        | 37 ++++++++++++++++++++++++++++++++++---
> >  2 files changed, 45 insertions(+), 3 deletions(-)
> > 
> > diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
> > index eb776b094d36..9f5b0f2be310 100644
> > --- a/include/linux/sched/ext.h
> > +++ b/include/linux/sched/ext.h
> > @@ -17,7 +17,18 @@
> >  enum scx_public_consts {
> >  	SCX_OPS_NAME_LEN	= 128,
> >  
> > +	/*
> > +	 * %SCX_SLICE_DFL is used to refill slices when the BPF scheduler misses
> > +	 * to set the slice for a task that is selected for execution.
> > +	 * %SCX_EV_REFILL_SLICE_DFL counts the number of times the default slice
> > +	 * refill has been triggered.
> > +	 *
> > +	 * %SCX_SLICE_BYPASS is used as the slice for all tasks in the bypass
> > +	 * mode. As mkaing forward progress for all tasks is the main goal of
> > +	 * the bypass mode, a shorter slice is used.
> > +	 */
> >  	SCX_SLICE_DFL		= 20 * 1000000,	/* 20ms */
> > +	SCX_SLICE_BYPASS	=  5 * 1000000, /*  5ms */
> >  	SCX_SLICE_INF		= U64_MAX,	/* infinite, implies nohz */
> >  };
> >  
> > diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
> > index cf8d86a2585c..2ce226018dbe 100644
> > --- a/kernel/sched/ext.c
> > +++ b/kernel/sched/ext.c
> > @@ -143,6 +143,35 @@ static struct scx_dump_data scx_dump_data = {
> >  /* /sys/kernel/sched_ext interface */
> >  static struct kset *scx_kset;
> >  
> > +/*
> > + * Parameter that can be adjusted through /sys/module/sched_ext/parameters.
> > + * There usually is no reason to modify these as normal scheduler opertion
> > + * shouldn't be affected by them. The knobs are primarily for debugging.
> > + */
> > +static u64 scx_slice_dfl = SCX_SLICE_DFL;
> > +static unsigned int scx_slice_dfl_us = SCX_SLICE_DFL / NSEC_PER_USEC;
> > +static unsigned int scx_slice_bypass_us = SCX_SLICE_BYPASS / NSEC_PER_USEC;
> > +
> > +static int set_slice_us(const char *val, const struct kernel_param *kp)
> > +{
> > +	return param_set_uint_minmax(val, kp, 100, 100 * USEC_PER_MSEC);
> > +}
> > +
> > +static const struct kernel_param_ops slice_us_param_ops = {
> > +	.set = set_slice_us,
> > +	.get = param_get_uint,
> > +};
> > +
> > +#undef MODULE_PARAM_PREFIX
> > +#define MODULE_PARAM_PREFIX	"sched_ext."
> > +
> > +module_param_cb(slice_dfl_us, &slice_us_param_ops, &scx_slice_dfl_us, 0600);
> > +MODULE_PARM_DESC(slice_dfl_us, "default slice in microseconds, applied on [un]load (100us to 100ms)");
> > +module_param_cb(slice_bypass_us, &slice_us_param_ops, &scx_slice_bypass_us, 0600);
> > +MODULE_PARM_DESC(slice_bypass_us, "bypass slice in microseconds, applied on [un]load (100us to 100ms)");
> > +
> > +#undef MODULE_PARAM_PREFIX
> > +
> >  #define CREATE_TRACE_POINTS
> >  #include <trace/events/sched_ext.h>
> >  
> > @@ -919,7 +948,7 @@ static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
> >  
> >  static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p)
> >  {
> > -	p->scx.slice = SCX_SLICE_DFL;
> > +	p->scx.slice = scx_slice_dfl;
> >  	__scx_add_event(sch, SCX_EV_REFILL_SLICE_DFL, 1);
> >  }
> >  
> > @@ -2892,7 +2921,7 @@ void init_scx_entity(struct sched_ext_entity *scx)
> >  	INIT_LIST_HEAD(&scx->runnable_node);
> >  	scx->runnable_at = jiffies;
> >  	scx->ddsp_dsq_id = SCX_DSQ_INVALID;
> > -	scx->slice = SCX_SLICE_DFL;
> > +	scx->slice = scx_slice_dfl;
> >  }
> >  
> >  void scx_pre_fork(struct task_struct *p)
> > @@ -3770,6 +3799,7 @@ static void scx_bypass(bool bypass)
> >  		WARN_ON_ONCE(scx_bypass_depth <= 0);
> >  		if (scx_bypass_depth != 1)
> >  			goto unlock;
> > +		scx_slice_dfl = scx_slice_bypass_us * NSEC_PER_USEC;
> >  		bypass_timestamp = ktime_get_ns();
> >  		if (sch)
> >  			scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1);
> > @@ -3778,6 +3808,7 @@ static void scx_bypass(bool bypass)
> >  		WARN_ON_ONCE(scx_bypass_depth < 0);
> >  		if (scx_bypass_depth != 0)
> >  			goto unlock;
> > +		scx_slice_dfl = scx_slice_dfl_us * NSEC_PER_USEC;
> >  		if (sch)
> >  			scx_add_event(sch, SCX_EV_BYPASS_DURATION,
> >  				      ktime_get_ns() - bypass_timestamp);
> > @@ -4776,7 +4807,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
> >  			queue_flags |= DEQUEUE_CLASS;
> >  
> >  		scoped_guard (sched_change, p, queue_flags) {
> > -			p->scx.slice = SCX_SLICE_DFL;
> > +			p->scx.slice = scx_slice_dfl;
> >  			p->sched_class = new_class;
> >  		}
> >  	}
> > -- 
> > 2.51.1
> >