Re: [RFC PATCH 11/16] sched/qos: Add rampup multiplier QoS

[Ricardo Neri <ricardo.neri-calderon@linux.intel.com>]

On Tue, Aug 20, 2024 at 05:35:07PM +0100, Qais Yousef wrote:
> Bursty tasks are hard to predict. To use resources efficiently, the
> system would like to be exact as much as possible. But this poses
> a challenge for these bursty tasks that need to get access to more
> resources quickly.
> 
> The new SCHED_QOS_RAMPUP_MULTIPLIER allows userspace to do that. As the
> name implies, it only helps them to transition to a higher performance
> state when they get _busier_. That is perfectly periodic tasks by
> definition are not going through a transition and will run at a constant
> performance level. It is the tasks that need to transition from one
> periodic state to another periodic state that is at a higher level that
> this rampup_multiplier will help with. It also slows down the ewma decay
> of util_est which should help those bursty tasks to keep their faster
> rampup.
> 
> This should work complimentary with uclamp. uclamp tells the system
> about min and max perf requirements which can be applied immediately.
> 
> rampup_multiplier is about reactiveness of the task to change.
> Specifically to a change for a higher performance level. The task might
> necessary need to have a min perf requirements, but it can have sudden
> burst of changes that require higher perf level and it needs the system
> to provide this faster.
> 
> TODO: update the sched_qos docs
> 
> Signed-off-by: Qais Yousef <qyousef@layalina.io>
> ---
>  include/linux/sched.h      |  7 ++++
>  include/uapi/linux/sched.h |  2 ++
>  kernel/sched/core.c        | 66 ++++++++++++++++++++++++++++++++++++++
>  kernel/sched/fair.c        |  6 ++--
>  kernel/sched/syscalls.c    | 38 ++++++++++++++++++++--
>  5 files changed, 115 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 2e8c5a9ffa76..a30ee43a25fb 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -404,6 +404,11 @@ struct sched_info {
>  #endif /* CONFIG_SCHED_INFO */
>  };
>  
> +struct sched_qos {
> +	DECLARE_BITMAP(user_defined, SCHED_QOS_MAX);
> +	unsigned int rampup_multiplier;
> +};
> +
>  /*
>   * Integer metrics need fixed point arithmetic, e.g., sched/fair
>   * has a few: load, load_avg, util_avg, freq, and capacity.
> @@ -882,6 +887,8 @@ struct task_struct {
>  
>  	struct sched_info		sched_info;
>  
> +	struct sched_qos		sched_qos;
> +
>  	struct list_head		tasks;
>  #ifdef CONFIG_SMP
>  	struct plist_node		pushable_tasks;
> diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
> index 67ef99f64ddc..0baba91ba5b8 100644
> --- a/include/uapi/linux/sched.h
> +++ b/include/uapi/linux/sched.h
> @@ -104,6 +104,8 @@ struct clone_args {
>  };
>  
>  enum sched_qos_type {
> +	SCHED_QOS_RAMPUP_MULTIPLIER,
> +	SCHED_QOS_MAX,
>  };
>  #endif
>  
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index c91e6a62c7ab..54faa845cb29 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -152,6 +152,8 @@ __read_mostly int sysctl_resched_latency_warn_once = 1;
>   */
>  const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
>  
> +unsigned int sysctl_sched_qos_default_rampup_multiplier	= 1;
> +
>  __read_mostly int scheduler_running;
>  
>  #ifdef CONFIG_SCHED_CORE
> @@ -4488,6 +4490,47 @@ static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
>  #endif /* CONFIG_SCHEDSTATS */
>  
>  #ifdef CONFIG_SYSCTL
> +static void sched_qos_sync_sysctl(void)
> +{
> +	struct task_struct *g, *p;
> +
> +	guard(rcu)();
> +	for_each_process_thread(g, p) {
> +		struct rq_flags rf;
> +		struct rq *rq;
> +
> +		rq = task_rq_lock(p, &rf);
> +		if (!test_bit(SCHED_QOS_RAMPUP_MULTIPLIER, p->sched_qos.user_defined))
> +			p->sched_qos.rampup_multiplier = sysctl_sched_qos_default_rampup_multiplier;
> +		task_rq_unlock(rq, p, &rf);
> +	}
> +}
> +
> +static int sysctl_sched_qos_handler(struct ctl_table *table, int write,
> +				    void *buffer, size_t *lenp, loff_t *ppos)
> +{
> +	unsigned int old_rampup_mult;
> +	int result;
> +
> +	old_rampup_mult = sysctl_sched_qos_default_rampup_multiplier;
> +
> +	result = proc_dointvec(table, write, buffer, lenp, ppos);
> +	if (result)
> +		goto undo;
> +	if (!write)
> +		return 0;
> +
> +	if (old_rampup_mult != sysctl_sched_qos_default_rampup_multiplier) {
> +		sched_qos_sync_sysctl();
> +	}
> +
> +	return 0;
> +
> +undo:
> +	sysctl_sched_qos_default_rampup_multiplier = old_rampup_mult;
> +	return result;
> +}
> +
>  static struct ctl_table sched_core_sysctls[] = {
>  #ifdef CONFIG_SCHEDSTATS
>  	{
> @@ -4534,6 +4577,13 @@ static struct ctl_table sched_core_sysctls[] = {
>  		.extra2		= SYSCTL_FOUR,
>  	},
>  #endif /* CONFIG_NUMA_BALANCING */
> +	{
> +		.procname	= "sched_qos_default_rampup_multiplier",
> +		.data           = &sysctl_sched_qos_default_rampup_multiplier,
> +		.maxlen         = sizeof(unsigned int),

IIUC, user space needs to select a value between 0 and (2^32 - 1). Does
this mean that it will need fine-tuning for each product and application?

Could there be some translation to a fewer number of QoS levels that are
qualitatively?

Also, I think about Intel processors. They work with hardware-controlled
performance scaling. The proposed interface would help us to communicate
per-task multipliers to hardware, but they would be used as hints to
hardware and not acted upon by the kernel to scale frequency.