IT数码 购物 网址 头条 软件 日历 阅读 图书馆
TxT小说阅读器
↓语音阅读,小说下载,古典文学↓ 		图片批量下载器
↓批量下载图片,美女图库↓ 		图片自动播放器
↓图片自动播放器↓ 		一键清除垃圾
↓轻轻一点,清除系统垃圾↓
开发: C++知识库 Java知识库 JavaScript Python PHP知识库 人工智能 区块链 大数据 移动开发 嵌入式 开发工具 数据结构与算法 开发测试 游戏开发 网络协议 系统运维
教程: HTML教程 CSS教程 JavaScript教程 Go语言教程 JQuery教程 VUE教程 VUE3教程 Bootstrap教程 SQL数据库教程 C语言教程 C++教程 Java教程 Python教程 Python3教程 C#教程
数码: 电脑 笔记本 显卡 显示器 固态硬盘 硬盘 耳机 手机 iphone vivo oppo 小米 华为 单反 装机 图拉丁
 
   -> 系统运维 -> latency-nice优先级补丁源码分析 -> 正文阅读

[系统运维]latency-nice优先级补丁源码分析

1. 概述

2022年3月11日，Vincent Guittot写道：基于2020年Parth提供的[1-4]系列latency nice相关的patches，他重启了相关工作，提供了新的一组有关latency nice priority的patches。解决了CFS调度器中一个进程是否可以抢占当前正在运行的进程的问题。

2. 设计思想

latency-nice优先级其实和nice值类似，但latency-nice用于表示进程对latency延迟的容忍情况。比如，latency-nice值范围[-20,19]，其中**latency_nice=-20的进程A相比latency_nice=+19的进程B而言，进程A需要更小的延迟特性来维持正常运行，调度器则需要优先考虑运行进程A**。

latency_nice通过从用户态获取latency延迟需求，然后对CFS SCHED_CLASS进行作用，达到控制的目的。

3. 代码实现

[PATCH 1/6]

主要作用：

  • struct task_struct结构体增加变量 int latency_nice；
  • /proc/<pid>/sched文件中显示该进程的 latency_nice；
  • 定义latency_nice取值范围[-20,19]；
  • 定义 DEFAULT_LATENCY_NICE 值为0；
Signed-off-by: Parth Shah <parth@linux.ibm.com>
[rebase]
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/linux/sched.h |  1 +
 kernel/sched/debug.c  |  1 +
 kernel/sched/sched.h  | 18 ++++++++++++++++++
 3 files changed, 20 insertions(+)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 508b91d57470..2aa889a59054 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -779,6 +779,7 @@ struct task_struct {
 	int				static_prio;
 	int				normal_prio;
 	unsigned int			rt_priority;
+	int				latency_nice;
 
 	struct sched_entity		se;
 	struct sched_rt_entity		rt;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 102d6f70e84d..5d76a8927888 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1043,6 +1043,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 #endif
 	P(policy);
 	P(prio);
+	P(latency_nice);
 	if (task_has_dl_policy(p)) {
 		P(dl.runtime);
 		P(dl.deadline);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9b33ba9c3c42..456ad2159eb1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -105,6 +105,24 @@ extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
  */
 #define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
 
+/*
+ * Latency nice is meant to provide scheduler hints about the relative
+ * latency requirements of a task with respect to other tasks.
+ * Thus a task with latency_nice == 19 can be hinted as the task with no
+ * latency requirements, in contrast to the task with latency_nice == -20
+ * which should be given priority in terms of lower latency.
+ */
+#define MAX_LATENCY_NICE	19
+#define MIN_LATENCY_NICE	-20
+
+#define LATENCY_NICE_WIDTH	\
+	(MAX_LATENCY_NICE - MIN_LATENCY_NICE + 1)
+
+/*
+ * Default tasks should be treated as a task with latency_nice = 0.
+ */
+#define DEFAULT_LATENCY_NICE	0
+
 /*
  * Increase resolution of nice-level calculations for 64-bit architectures.
  * The extra resolution improves shares distribution and load balancing of
--

[PATCH 2/6]

主要作用：

  • 0号进程(也叫idle进程/swapper进程)的初始化 latency_nice = 0；
  • 子进程的 latency_nice 继承父进程的 latency_nice值；
  • 子进程如果设置了sched_reset_on_fork，则设置其 latency_nice = 0；
Signed-off-by: Parth Shah <parth@linux.ibm.com>
[rebase]
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 init/init_task.c    | 1 +
 kernel/sched/core.c | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/init/init_task.c b/init/init_task.c
index 73cc8f03511a..2afa249c253b 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -78,6 +78,7 @@ struct task_struct init_task
 	.prio		= MAX_PRIO - 20,
 	.static_prio	= MAX_PRIO - 20,
 	.normal_prio	= MAX_PRIO - 20,
+	.latency_nice	= 0,
 	.policy		= SCHED_NORMAL,
 	.cpus_ptr	= &init_task.cpus_mask,
 	.user_cpus_ptr	= NULL,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1d863d7f6ad7..157eef880d1d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4393,6 +4393,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 */
 	p->prio = current->normal_prio;
 
+	/* Propagate the parent's latency requirements to the child as well */
+	p->latency_nice = current->latency_nice;
+
 	uclamp_fork(p);
 
 	/*
@@ -4409,6 +4412,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
 
+		p->latency_nice = DEFAULT_LATENCY_NICE;
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
 		 * fulfil

[PATCH 3/6]

主要作用：

  • 在sched_attr结构体中增加sched_latency_nice，并且支持通过sched_setattr/sched_getaatr等系统调用来修改/获取；
  • 新增flag标志SCHED_FLAG_LATENCY_NICE，每次系统调用修改sched_latency_nice后会在内核态修改相应的latency_nice/latency_prio；
Signed-off-by: Parth Shah <parth@linux.ibm.com>
[rebase and add a dedicated __setscheduler_latency ]
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/uapi/linux/sched.h       |  4 +++-
 include/uapi/linux/sched/types.h | 19 +++++++++++++++++++
 kernel/sched/core.c              | 26 ++++++++++++++++++++++++++
 tools/include/uapi/linux/sched.h |  4 +++-
 4 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..b2e932c25be6 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ 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_NICE		0x80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ 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_NICE)
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h
index f2c4589d4dbf..0aa4e3b6ed59 100644
--- a/include/uapi/linux/sched/types.h
+++ b/include/uapi/linux/sched/types.h
@@ -10,6 +10,7 @@ struct sched_param {
 
 #define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
 #define SCHED_ATTR_SIZE_VER1	56	/* add: util_{min,max} */
+#define SCHED_ATTR_SIZE_VER2	60	/* add: latency_nice */
 
 /*
  * Extended scheduling parameters data structure.
@@ -98,6 +99,22 @@ struct sched_param {
  * scheduled on a CPU with no more capacity than the specified value.
  *
  * A task utilization boundary can be reset by setting the attribute to -1.
+ *
+ * Latency Tolerance Attributes
+ * ===========================
+ *
+ * A subset of sched_attr attributes allows to specify the relative latency
+ * requirements of a task with respect to the other tasks running/queued in the
+ * system.
+ *
+ * @ sched_latency_nice	task's latency_nice value
+ *
+ * The latency_nice of a task can have any value in a range of
+ * [LATENCY_NICE_MIN..LATENCY_NICE_MAX].
+ *
+ * A task with latency_nice with the value of LATENCY_NICE_MIN can be
+ * taken for a task with lower latency requirements as opposed to the task with
+ * higher latency_nice.
  */
 struct sched_attr {
 	__u32 size;
@@ -120,6 +137,8 @@ struct sched_attr {
 	__u32 sched_util_min;
 	__u32 sched_util_max;
 
+	/* latency requirement hints */
+	__s32 sched_latency_nice;
 };
 
 #endif /* _UAPI_LINUX_SCHED_TYPES_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 157eef880d1d..3edba1a38ecb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7219,6 +7219,16 @@ 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);
+
+}
+
+static void __setscheduler_latency(struct task_struct *p,
+		const struct sched_attr *attr)
+{
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+		p->latency_prio = NICE_TO_LATENCY(attr->sched_latency_nice);
+		set_latency_weight(p);
+	}
 }
 
 /*
@@ -7345,6 +7355,13 @@ static int __sched_setscheduler(struct task_struct *p,
 			return retval;
 	}
 
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+		if (attr->sched_latency_nice > MAX_LATENCY_NICE)
+			return -EINVAL;
+		if (attr->sched_latency_nice < MIN_LATENCY_NICE)
+			return -EINVAL;
+	}
+
 	if (pi)
 		cpuset_read_lock();
 
@@ -7379,6 +7396,9 @@ 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_NICE &&
+		    attr->sched_latency_nice != p->latency_nice)
+			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
 		retval = 0;
@@ -7467,6 +7487,7 @@ static int __sched_setscheduler(struct task_struct *p,
 		__setscheduler_params(p, attr);
 		__setscheduler_prio(p, newprio);
 	}
+	__setscheduler_latency(p, attr);
 	__setscheduler_uclamp(p, attr);
 
 	if (queued) {
@@ -7677,6 +7698,9 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr
*a
 	    size < SCHED_ATTR_SIZE_VER1)
 		return -EINVAL;
 
+	if ((attr->sched_flags & SCHED_FLAG_LATENCY_NICE) &&
+	    size < SCHED_ATTR_SIZE_VER2)
+		return -EINVAL;
 	/*
 	 * XXX: Do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
@@ -7914,6 +7938,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *,
uattr,
 	get_params(p, &kattr);
 	kattr.sched_flags &= SCHED_FLAG_ALL;
 
+	kattr.sched_latency_nice = p->latency_nice;
+
 #ifdef CONFIG_UCLAMP_TASK
 	/*
 	 * This could race with another potential updater, but this is fine
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 3bac0a8ceab2..ecc4884bfe4b 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ 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_NICE		0X80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ 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_NICE)
 
 #endif /* _UAPI_LINUX_SCHED_H */
--

[PATCH 4/6]

主要作用：

  • 类似于NICE值系统，使用CAP_SYS_NICE做安全检查，当非root用户尝试减小进程的latency_nice将会返回-EPERM；
Signed-off-by: Parth Shah <parth@linux.ibm.com>
[rebase]
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3edba1a38ecb..8f8b102a75c4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7360,6 +7360,10 @@ static int __sched_setscheduler(struct task_struct *p,
 			return -EINVAL;
 		if (attr->sched_latency_nice < MIN_LATENCY_NICE)
 			return -EINVAL;
+		/* Use the same security checks as NICE */
+		if (attr->sched_latency_nice < p->latency_nice &&
+		    !capable(CAP_SYS_NICE))
+			return -EPERM;
 	}
 
 	if (pi)
--

[PATCH 5/6]

主要作用：

  • 将latency_nice转化为latency_prio，使用优先级来表示对延迟的敏感度，并且引入latency_weight;
  • 进程拥有更大的latency_weight权重（也即更敏感的latency）且其时间片没有用完的情况下，可抢占当前正在运行的进程；
  • 低latency_weight权重的进程只有在唤醒时可以抢占当前进程，以保证一定的公平性，否则只能等tick到来才能获取slice执行；
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/linux/sched.h |  4 ++-
 init/init_task.c      |  2 +-
 kernel/sched/core.c   | 32 +++++++++++++++++++----
 kernel/sched/debug.c  |  2 +-
 kernel/sched/fair.c   | 60 +++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/sched.h  | 12 +++++++++
 6 files changed, 102 insertions(+), 10 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2aa889a59054..9aeb157e819b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -560,6 +560,8 @@ struct sched_entity {
 	unsigned long			runnable_weight;
 #endif
 
+	int				latency_weight;
+
 #ifdef CONFIG_SMP
 	/*
 	 * Per entity load average tracking.
@@ -779,7 +781,7 @@ struct task_struct {
 	int				static_prio;
 	int				normal_prio;
 	unsigned int			rt_priority;
-	int				latency_nice;
+	int				latency_prio;
 
 	struct sched_entity		se;
 	struct sched_rt_entity		rt;
diff --git a/init/init_task.c b/init/init_task.c
index 2afa249c253b..e98c71f24981 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -78,7 +78,7 @@ struct task_struct init_task
 	.prio		= MAX_PRIO - 20,
 	.static_prio	= MAX_PRIO - 20,
 	.normal_prio	= MAX_PRIO - 20,
-	.latency_nice	= 0,
+	.latency_prio	= NICE_WIDTH - 20,
 	.policy		= SCHED_NORMAL,
 	.cpus_ptr	= &init_task.cpus_mask,
 	.user_cpus_ptr	= NULL,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8f8b102a75c4..547b0da01efe 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1241,6 +1241,11 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	}
 }
 
+static void set_latency_weight(struct task_struct *p)
+{
+	p->se.latency_weight = sched_latency_to_weight[p->latency_prio];
+}
+
 #ifdef CONFIG_UCLAMP_TASK
 /*
  * Serializes updates of utilization clamp values
@@ -4394,7 +4399,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->prio = current->normal_prio;
 
 	/* Propagate the parent's latency requirements to the child as well */
-	p->latency_nice = current->latency_nice;
+	p->latency_prio = current->latency_prio;
 
 	uclamp_fork(p);
 
@@ -4412,7 +4417,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
 
-		p->latency_nice = DEFAULT_LATENCY_NICE;
+		p->latency_prio = NICE_TO_LATENCY(0);
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
 		 * fulfilled its duty:
@@ -4420,6 +4425,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
+	/* Once latency_prio is set, update the latency weight */
+	set_latency_weight(p);
+
 	if (dl_prio(p->prio))
 		return -EAGAIN;
 	else if (rt_prio(p->prio))
@@ -7361,7 +7369,7 @@ static int __sched_setscheduler(struct task_struct *p,
 		if (attr->sched_latency_nice < MIN_LATENCY_NICE)
 			return -EINVAL;
 		/* Use the same security checks as NICE */
-		if (attr->sched_latency_nice < p->latency_nice &&
+		if (attr->sched_latency_nice < LATENCY_TO_NICE(p->latency_prio) &&
 		    !capable(CAP_SYS_NICE))
 			return -EPERM;
 	}
@@ -7401,7 +7409,7 @@ static int __sched_setscheduler(struct task_struct *p,
 		if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
 			goto change;
 		if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE &&
-		    attr->sched_latency_nice != p->latency_nice)
+		    attr->sched_latency_nice != LATENCY_TO_NICE(p->latency_prio))
 			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
@@ -7942,7 +7950,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *,
uattr,
 	get_params(p, &kattr);
 	kattr.sched_flags &= SCHED_FLAG_ALL;
 
-	kattr.sched_latency_nice = p->latency_nice;
+	kattr.sched_latency_nice = LATENCY_TO_NICE(p->latency_prio);
 
 #ifdef CONFIG_UCLAMP_TASK
 	/*
@@ -10954,6 +10962,20 @@ const u32 sched_prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
+/*
+ * latency weight for wakeup preemption
+ */
+const int sched_latency_to_weight[40] = {
+ /* -20 */      1024,       973,       922,       870,       819,
+ /* -15 */       768,       717,       666,       614,       563,
+ /* -10 */       512,       461,       410,       358,       307,
+ /*  -5 */       256,       205,       154,       102,       51,
+ /*   0 */	   0,       -51,      -102,      -154,      -205,
+ /*   5 */      -256,      -307,      -358,      -410,      -461,
+ /*  10 */      -512,      -563,      -614,      -666,      -717,
+ /*  15 */      -768,      -819,      -870,      -922,      -973,
+};
+
 void call_trace_sched_update_nr_running(struct rq *rq, int count)
 {
         trace_sched_update_nr_running_tp(rq, count);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 5d76a8927888..253e52ec73fb 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1043,7 +1043,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 #endif
 	P(policy);
 	P(prio);
-	P(latency_nice);
+	P(latency_prio);
 	if (task_has_dl_policy(p)) {
 		P(dl.runtime);
 		P(dl.deadline);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5c4bfffe8c2c..506c482a0e48 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5555,6 +5555,35 @@ static int sched_idle_cpu(int cpu)
 }
 #endif
 
+static void set_next_buddy(struct sched_entity *se);
+
+static void check_preempt_from_idle(struct cfs_rq *cfs, struct sched_entity *se)
+{
+	struct sched_entity *next;
+
+	if (se->latency_weight <= 0)
+		return;
+
+	if (cfs->nr_running <= 1)
+		return;
+	/*
+	 * When waking from idle, we don't need to check to preempt at wakeup
+	 * the idle thread and don't set next buddy as a candidate for being
+	 * picked in priority.
+	 * In case of simultaneous wakeup from idle, the latency sensitive tasks
+	 * lost opportunity to preempt non sensitive tasks which woke up
+	 * simultaneously.
+	 */
+
+	if (cfs->next)
+		next = cfs->next;
+	else
+		next = __pick_first_entity(cfs);
+
+	if (next && wakeup_preempt_entity(next, se) == 1)
+		set_next_buddy(se);
+}
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -5648,6 +5677,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!task_new)
 		update_overutilized_status(rq);
 
+	if (rq->curr == rq->idle)
+		check_preempt_from_idle(cfs_rq_of(&p->se), &p->se);
+
 enqueue_throttle:
 	if (cfs_bandwidth_used()) {
 		/*
@@ -5669,8 +5701,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	hrtick_update(rq);
 }
 
-static void set_next_buddy(struct sched_entity *se);
-
 /*
  * The dequeue_task method is called before nr_running is
  * decreased. We remove the task from the rbtree and
@@ -6970,6 +7000,27 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 }
 #endif /* CONFIG_SMP */
 
+static long wakeup_latency_gran(int latency_weight)
+{
+	long thresh = sysctl_sched_latency;
+
+	if (!latency_weight)
+		return 0;
+
+	if (sched_feat(GENTLE_FAIR_SLEEPERS))
+		thresh >>= 1;
+
+	/*
+	 * Clamp the delta to stay in the scheduler period range
+	 * [-sysctl_sched_latency:sysctl_sched_latency]
+	 */
+	latency_weight = clamp_t(long, latency_weight,
+				-1 * NICE_LATENCY_WEIGHT_MAX,
+				NICE_LATENCY_WEIGHT_MAX);
+
+	return (thresh * latency_weight) >> NICE_LATENCY_SHIFT;
+}
+
 static unsigned long wakeup_gran(struct sched_entity *se)
 {
 	unsigned long gran = sysctl_sched_wakeup_granularity;
@@ -7008,6 +7059,10 @@ static int
 wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 {
 	s64 gran, vdiff = curr->vruntime - se->vruntime;
+	int latency_weight = se->latency_weight - curr->latency_weight;
+
+	latency_weight = min(latency_weight, se->latency_weight);
+	vdiff += wakeup_latency_gran(latency_weight);
 
 	if (vdiff <= 0)
 		return -1;
@@ -7117,6 +7172,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int
wake_
 		return;
 
 	update_curr(cfs_rq_of(se));
+
 	if (wakeup_preempt_entity(se, pse) == 1) {
 		/*
 		 * Bias pick_next to pick the sched entity that is
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 456ad2159eb1..dd92aa9c36f9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -122,6 +122,17 @@ extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
  * Default tasks should be treated as a task with latency_nice = 0.
  */
 #define DEFAULT_LATENCY_NICE	0
+#define DEFAULT_LATENCY_PRIO	(DEFAULT_LATENCY_NICE + LATENCY_NICE_WIDTH/2)
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static latency [ 0..39 ],
+ * and back.
+ */
+#define NICE_TO_LATENCY(nice)	((nice) + DEFAULT_LATENCY_PRIO)
+#define LATENCY_TO_NICE(prio)	((prio) - DEFAULT_LATENCY_PRIO)
+#define NICE_LATENCY_SHIFT	(SCHED_FIXEDPOINT_SHIFT)
+#define NICE_LATENCY_WEIGHT_MAX	(1L << NICE_LATENCY_SHIFT)
 
 /*
  * Increase resolution of nice-level calculations for 64-bit architectures.
@@ -2098,6 +2109,7 @@ static_assert(WF_TTWU == SD_BALANCE_WAKE);
 
 extern const int		sched_prio_to_weight[40];
 extern const u32		sched_prio_to_wmult[40];
+extern const int		sched_latency_to_weight[40];
 
 /*
  * {de,en}queue flags:
--

[PATCH 6/6]

主要作用：

  • 组调度中，进程可以设置其latency_prio优先级，以便抢占当前进程，而其group组的latency优先级还是原来值；在task group中设置一个latency域，实现该功能。
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/core.c  | 41 +++++++++++++++++++++++++++++++++++++++++
 kernel/sched/fair.c  | 32 ++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |  4 ++++
 3 files changed, 77 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 547b0da01efe..e0668652dd24 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10635,6 +10635,30 @@ static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
 {
 	return sched_group_set_idle(css_tg(css), idle);
 }
+
+static s64 cpu_latency_read_s64(struct cgroup_subsys_state *css,
+			       struct cftype *cft)
+{
+	return css_tg(css)->latency_prio;
+}
+
+static int cpu_latency_write_s64(struct cgroup_subsys_state *css,
+				struct cftype *cft, s64 latency_prio)
+{
+	return sched_group_set_latency(css_tg(css), latency_prio);
+}
+
+static s64 cpu_latency_nice_read_s64(struct cgroup_subsys_state *css,
+			       struct cftype *cft)
+{
+	return LATENCY_TO_NICE(css_tg(css)->latency_prio);
+}
+
+static int cpu_latency_nice_write_s64(struct cgroup_subsys_state *css,
+				struct cftype *cft, s64 latency_nice)
+{
+	return sched_group_set_latency(css_tg(css), NICE_TO_LATENCY(latency_nice));
+}
 #endif
 
 static struct cftype cpu_legacy_files[] = {
@@ -10649,6 +10673,11 @@ static struct cftype cpu_legacy_files[] = {
 		.read_s64 = cpu_idle_read_s64,
 		.write_s64 = cpu_idle_write_s64,
 	},
+	{
+		.name = "latency",
+		.read_s64 = cpu_latency_read_s64,
+		.write_s64 = cpu_latency_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
@@ -10866,6 +10895,18 @@ static struct cftype cpu_files[] = {
 		.read_s64 = cpu_idle_read_s64,
 		.write_s64 = cpu_idle_write_s64,
 	},
+	{
+		.name = "latency",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = cpu_latency_read_s64,
+		.write_s64 = cpu_latency_write_s64,
+	},
+	{
+		.name = "latency.nice",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = cpu_latency_nice_read_s64,
+		.write_s64 = cpu_latency_nice_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 506c482a0e48..cbccef025089 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11496,6 +11496,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group
*parent)
 		goto err;
 
 	tg->shares = NICE_0_LOAD;
+	tg->latency_prio = DEFAULT_LATENCY_PRIO;
 
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
@@ -11594,6 +11595,7 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	}
 
 	se->my_q = cfs_rq;
+	se->latency_weight = sched_latency_to_weight[tg->latency_prio];
 	/* guarantee group entities always have weight */
 	update_load_set(&se->load, NICE_0_LOAD);
 	se->parent = parent;
@@ -11724,6 +11726,36 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 	return 0;
 }
 
+int sched_group_set_latency(struct task_group *tg, long latency_prio)
+{
+	int i;
+
+	if (tg == &root_task_group)
+		return -EINVAL;
+
+	if (latency_prio < 0 ||
+	    latency_prio > LATENCY_NICE_WIDTH)
+		return -EINVAL;
+
+	mutex_lock(&shares_mutex);
+
+	if (tg->latency_prio == latency_prio) {
+		mutex_unlock(&shares_mutex);
+		return 0;
+	}
+
+	tg->latency_prio = latency_prio;
+
+	for_each_possible_cpu(i) {
+		struct sched_entity *se = tg->se[i];
+
+		WRITE_ONCE(se->latency_weight, sched_latency_to_weight[latency_prio]);
+	}
+
+	mutex_unlock(&shares_mutex);
+	return 0;
+}
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
 void free_fair_sched_group(struct task_group *tg) { }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index dd92aa9c36f9..885d1c809329 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -429,6 +429,8 @@ struct task_group {
 
 	/* A positive value indicates that this is a SCHED_IDLE group. */
 	int			idle;
+	/* latency priority of the group. */
+	int			latency_prio;
 
 #ifdef	CONFIG_SMP
 	/*
@@ -542,6 +544,8 @@ extern int sched_group_set_shares(struct task_group *tg, unsigned long
shares);
 
 extern int sched_group_set_idle(struct task_group *tg, long idle);
 
+extern int sched_group_set_latency(struct task_group *tg, long latency);
+
 #ifdef CONFIG_SMP
 extern void set_task_rq_fair(struct sched_entity *se,
 			     struct cfs_rq *prev, struct cfs_rq *next);
--

4. 总结

latency-nice值其实和现有的nice值系统十分类似，个人认为latency-nice是对Linux实时性较差的一个补充解决方案。而且该方案是一个十分有价值的参考，设想一下：你的定制系统如果需要对某类业务的实时响应十分严格，就可以参考latency-nice这种方法定制你想要的优先级系统。
  系统运维 最新文章
配置小型公司网络WLAN基本业务（AC通过三层
如何在交付运维过程中建立风险底线意识，提
快速传输大文件，怎么通过网络传大文件给对
从游戏服务端角度分析移动同步（状态同步）
MySQL使用MyCat实现分库分表
如何用DWDM射频光纤技术实现200公里外的站点
国内顺畅下载k8s.gcr.io的镜像
自动化测试appium
ctfshow ssrf
Linux操作系统学习之实用指令（Centos7/8均
上一篇文章      下一篇文章      查看所有文章
加:2022-04-06 16:28:46  更:2022-04-06 16:29:45 
 
开发: C++知识库 Java知识库 JavaScript Python PHP知识库 人工智能 区块链 大数据 移动开发 嵌入式 开发工具 数据结构与算法 开发测试 游戏开发 网络协议 系统运维
教程: HTML教程 CSS教程 JavaScript教程 Go语言教程 JQuery教程 VUE教程 VUE3教程 Bootstrap教程 SQL数据库教程 C语言教程 C++教程 Java教程 Python教程 Python3教程 C#教程
数码: 电脑 笔记本 显卡 显示器 固态硬盘 硬盘 耳机 手机 iphone vivo oppo 小米 华为 单反 装机 图拉丁

360图书馆 购物 三丰科技 阅读网 日历 万年历 2024年11日历 -2024/11/15 21:20:51-

图片自动播放器
↓图片自动播放器↓ 		TxT小说阅读器
↓语音阅读,小说下载,古典文学↓ 		一键清除垃圾
↓轻轻一点,清除系统垃圾↓ 		图片批量下载器
↓批量下载图片,美女图库↓
  网站联系: qq:121756557 email:121756557@qq.com  IT数码