Commit c51ad919 authored by Zhao Wenhui's avatar Zhao Wenhui
Browse files

sched/fair: Introduce multiple qos level 

hulk inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I737X1



-------------------------------

Expand qos_level from {-1,0} to [-2, 2], to distinguish the tasks expected
to be with extremely high or low priority level. Using qos_level_weight
to reweight the shares when calculating group's weight. Meanwhile,
set offline task's schedule policy to SCHED_IDLE so that it can be
preempted at check_preempt_wakeup.

Signed-off-by: default avatarZhao Wenhui <zhaowenhui8@huawei.com>
parent 22ff6706

arch/arm64/configs/openeuler_defconfig

+1 −0
Original line number Diff line number Diff line
@@ -140,6 +140,7 @@ CONFIG_CGROUP_WRITEBACK=y 
CONFIG_CGROUP_V1_WRITEBACK=y

CONFIG_CGROUP_SCHED=y

CONFIG_QOS_SCHED=y

CONFIG_QOS_SCHED_MULTILEVEL=y

CONFIG_QOS_SCHED_DYNAMIC_AFFINITY=y

CONFIG_QOS_SCHED_SMT_EXPELLER=y

CONFIG_FAIR_GROUP_SCHED=y

arch/x86/configs/openeuler_defconfig

+1 −0
Original line number Diff line number Diff line
@@ -158,6 +158,7 @@ CONFIG_CGROUP_WRITEBACK=y 
CONFIG_CGROUP_V1_WRITEBACK=y

CONFIG_CGROUP_SCHED=y

CONFIG_QOS_SCHED=y

CONFIG_QOS_SCHED_MULTILEVEL=y

CONFIG_QOS_SCHED_DYNAMIC_AFFINITY=y

CONFIG_QOS_SCHED_SMT_EXPELLER=y

CONFIG_FAIR_GROUP_SCHED=y

include/linux/sched/sysctl.h

+4 −0
Original line number Diff line number Diff line
@@ -83,6 +83,10 @@ extern unsigned int sysctl_overload_detect_period; 
extern unsigned int sysctl_offline_wait_interval;

#endif



#ifdef CONFIG_QOS_SCHED_MULTILEVEL

extern unsigned int sysctl_qos_level_weights[];

#endif



#ifdef CONFIG_QOS_SCHED_PRIO_LB

extern unsigned int sysctl_sched_prio_load_balance_enabled;

#endif

init/Kconfig

+9 −0
Original line number Diff line number Diff line
@@ -977,6 +977,15 @@ config QOS_SCHED 


    default n



config QOS_SCHED_MULTILEVEL

	bool "Multiple qos level task scheduling"

	depends on QOS_SCHED

	default n

	help

	  This feature enable multiple qos level on task scheduling.

	  Expand the qos_level to [-2,2] to distinguish the tasks expected

	  to be with extremely high or low priority level.



config QOS_SCHED_SMT_EXPELLER

	bool "Qos smt expeller"

	depends on SCHED_SMT

kernel/sched/core.c

+14 −6
Original line number Diff line number Diff line
@@ -6431,7 +6431,7 @@ static int __sched_setscheduler(struct task_struct *p, 
	 * other than SCHED_IDLE, the online task preemption and cpu resource

	 * isolation will be invalid, so return -EINVAL in this case.

	 */

	if (unlikely(task_group(p)->qos_level == -1 && !idle_policy(policy))) {

	if (unlikely(is_offline_level(task_group(p)->qos_level) && !idle_policy(policy))) {

		retval = -EINVAL;

		goto unlock;

	}
@@ -8556,7 +8556,7 @@ static void sched_change_qos_group(struct task_struct *tsk, struct task_group *t 
	 */

	if (!(tsk->flags & PF_EXITING) &&

	    !task_group_is_autogroup(tg) &&

	    (tg->qos_level == -1)) {

	    (is_offline_level(tg->qos_level))) {

		attr.sched_priority = 0;

		attr.sched_policy = SCHED_IDLE;

		__setscheduler_params(tsk, &attr);
@@ -8584,7 +8584,7 @@ void sched_move_offline_task(struct task_struct *p) 
{

	struct offline_args *args;



	if (unlikely(task_group(p)->qos_level != -1))

	if (unlikely(!is_offline_level(task_group(p)->qos_level)))

		return;



	args = kmalloc(sizeof(struct offline_args), GFP_ATOMIC);
@@ -9457,7 +9457,7 @@ static int tg_change_scheduler(struct task_group *tg, void *data) 
	struct cgroup_subsys_state *css = &tg->css;



	tg->qos_level = qos_level;

	if (qos_level == -1)

	if (is_offline_level(qos_level))

		policy = SCHED_IDLE;

	else

		policy = SCHED_NORMAL;
@@ -9479,19 +9479,27 @@ static int cpu_qos_write(struct cgroup_subsys_state *css, 
	if (!tg->se[0])

		return -EINVAL;



#ifdef CONFIG_QOS_SCHED_MULTILEVEL

	if (qos_level > QOS_LEVEL_HIGH_EX || qos_level < QOS_LEVEL_OFFLINE_EX)

#else

	if (qos_level != -1 && qos_level != 0)

#endif

		return -EINVAL;



	if (tg->qos_level == qos_level)

		goto done;



#ifdef CONFIG_QOS_SCHED_MULTILEVEL

	if (!is_normal_level(tg->qos_level))

#else

	if (tg->qos_level == -1 && qos_level == 0)

#endif

		return -EINVAL;



	cpus_read_lock();

	if (qos_level == -1)

	if (is_offline_level(qos_level))

		cfs_bandwidth_usage_inc();

	else

	else if (is_offline_level(tg->qos_level) && !is_offline_level(qos_level))

		cfs_bandwidth_usage_dec();

	cpus_read_unlock();