Re: [RFC 3/3] Allow sched_{get,set}attr to change latency_tolerance of the task

[Parth Shah]

On 12/3/19 2:09 PM, Qais Yousef wrote:
> On 11/25/19 15:16, Parth Shah wrote:
>> Introduce the latency_tolerance attribute to sched_attr and provide a
>> mechanism to change the value with the use of sched_setattr/sched_getattr
>> syscall.
>>
>> Also add new flag "SCHED_FLAG_LATENCY_TOLERANCE" to hint the change in
>> latency_tolerance of the task on every sched_setattr syscall.
>>
>> Signed-off-by: Parth Shah <parth@xxxxxxxxxxxxx>
>> ---
>>  include/uapi/linux/sched.h       |  4 +++-
>>  include/uapi/linux/sched/types.h |  2 ++
>>  kernel/sched/core.c              | 15 +++++++++++++++
>>  kernel/sched/sched.h             |  1 +
>>  4 files changed, 21 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
>> index b3105ac1381a..73db430d11b6 100644
>> --- a/include/uapi/linux/sched.h
>> +++ b/include/uapi/linux/sched.h
>> @@ -71,6 +71,7 @@ struct clone_args {
>>  #define SCHED_FLAG_KEEP_PARAMS		0x10
>>  #define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
>>  #define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
>> +#define SCHED_FLAG_LATENCY_TOLERANCE	0x80
>>  
>>  #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
>>  				 SCHED_FLAG_KEEP_PARAMS)
>> @@ -82,6 +83,7 @@ struct clone_args {
>>  			 SCHED_FLAG_RECLAIM		| \
>>  			 SCHED_FLAG_DL_OVERRUN		| \
>>  			 SCHED_FLAG_KEEP_ALL		| \
>> -			 SCHED_FLAG_UTIL_CLAMP)
>> +			 SCHED_FLAG_UTIL_CLAMP		| \
>> +			 SCHED_FLAG_LATENCY_TOLERANCE)
>>  
>>  #endif /* _UAPI_LINUX_SCHED_H */
>> diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h
>> index c852153ddb0d..960774ac0c70 100644
>> --- a/include/uapi/linux/sched/types.h
>> +++ b/include/uapi/linux/sched/types.h
>> @@ -118,6 +118,8 @@ struct sched_attr {
>>  	__u32 sched_util_min;
>>  	__u32 sched_util_max;
>>  
>> +	/* latency requirement hints */
>> +	__s32 sched_latency_tolerance;
>>  };
>>  
>>  #endif /* _UAPI_LINUX_SCHED_TYPES_H */
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index ea7abbf5c1bb..dfd36ec14404 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -4695,6 +4695,9 @@ static void __setscheduler_params(struct task_struct *p,
>>  	p->rt_priority = attr->sched_priority;
>>  	p->normal_prio = normal_prio(p);
>>  	set_load_weight(p, true);
>> +
>> +	/* Change latency tolerance of the task if !SCHED_FLAG_KEEP_PARAMS */
>> +	p->latency_tolerance = attr->sched_latency_tolerance;
>>  }
>>  
>>  /* Actually do priority change: must hold pi & rq lock. */
>> @@ -4852,6 +4855,13 @@ static int __sched_setscheduler(struct task_struct *p,
>>  			return retval;
>>  	}
>>  
>> +	if (attr->sched_flags & SCHED_FLAG_LATENCY_TOLERANCE) {
>> +		if (attr->sched_latency_tolerance > MAX_LATENCY_TOLERANCE)
>> +			return -EINVAL;
>> +		if (attr->sched_latency_tolerance < MIN_LATENCY_TOLERANCE)
>> +			return -EINVAL;
>> +	}
>> +
>>  	if (pi)
>>  		cpuset_read_lock();
>>  
>> @@ -4886,6 +4896,9 @@ static int __sched_setscheduler(struct task_struct *p,
>>  			goto change;
>>  		if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
>>  			goto change;
>> +		if (attr->sched_flags & SCHED_FLAG_LATENCY_TOLERANCE &&
>> +		    attr->sched_latency_tolerance != p->latency_tolerance)
>> +			goto change;
>>  
>>  		p->sched_reset_on_fork = reset_on_fork;
>>  		retval = 0;
>> @@ -5392,6 +5405,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
>>  	else
>>  		kattr.sched_nice = task_nice(p);
>>  
>> +	kattr.sched_latency_tolerance = p->latency_tolerance;
>> +
>>  #ifdef CONFIG_UCLAMP_TASK
>>  	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
>>  	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
>> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
>> index 0db2c1b3361e..bb181175954b 100644
>> --- a/kernel/sched/sched.h
>> +++ b/kernel/sched/sched.h
>> @@ -21,6 +21,7 @@
>>  #include <linux/sched/nohz.h>
>>  #include <linux/sched/numa_balancing.h>
>>  #include <linux/sched/prio.h>
>> +#include <linux/sched/latency_tolerance.h>
> 
> nit: keep in alphabatical order.

ok.

> 
> The series looks good to me except for the 2 minor nits. Thanks for taking care
> of this!

My pleasure. Infact, I'm trying to write patches around what Subhra posted
for reducing wakeup scans https://lkml.org/lkml/2019/8/30/829 and few ideas
from Peter's patch https://lkml.org/lkml/2018/5/30/632. Aim here is to
reduce scans for lower latency_tolerance tasks and will post out soon which
uses this feature.

> 
> Reviewed-by: Qais Yousef <qais.yousef@xxxxxxx>

Thanks. Will add it.

> 
> Cheers
> 
> --
> Qais Yousef
> 
>>  #include <linux/sched/rt.h>
>>  #include <linux/sched/signal.h>
>>  #include <linux/sched/smt.h>
>> -- 
>> 2.17.2
>>