Commit 86dd6c04 authored by Ingo Molnar's avatar Ingo Molnar
Browse files

sched/balancing: Rename scheduler_tick() => sched_tick() 



- Standardize on prefixing scheduler-internal functions defined
  in <linux/sched.h> with sched_*() prefix. scheduler_tick() was
  the only function using the scheduler_ prefix. Harmonize it.

- The other reason to rename it is the NOHZ scheduler tick
  handling functions are already named sched_tick_*().
  Make the 'git grep sched_tick' more meaningful.

Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
Acked-by: default avatarValentin Schneider <vschneid@redhat.com>
Reviewed-by: default avatarShrikanth Hegde <sshegde@linux.ibm.com>
Link: https://lore.kernel.org/r/20240308111819.1101550-3-mingo@kernel.org
parent 70a27d6d

Documentation/scheduler/sched-domains.rst

+2 −2
Original line number Diff line number Diff line
@@ -32,13 +32,13 @@ load of each of its member CPUs, and only when the load of a group becomes 
out of balance are tasks moved between groups.



In kernel/sched/core.c, trigger_load_balance() is run periodically on each CPU

through scheduler_tick(). It raises a softirq after the next regularly scheduled

through sched_tick(). It raises a softirq after the next regularly scheduled

rebalancing event for the current runqueue has arrived. The actual load

balancing workhorse, sched_balance_softirq()->rebalance_domains(), is then run

in softirq context (SCHED_SOFTIRQ).



The latter function takes two arguments: the runqueue of current CPU and whether

the CPU was idle at the time the scheduler_tick() happened and iterates over all

the CPU was idle at the time the sched_tick() happened and iterates over all

sched domains our CPU is on, starting from its base domain and going up the ->parent

chain. While doing that, it checks to see if the current domain has exhausted its

rebalance interval. If so, it runs load_balance() on that domain. It then checks

Documentation/translations/zh_CN/scheduler/sched-domains.rst

+2 −2
Original line number Diff line number Diff line
@@ -34,12 +34,12 @@ CPU共享。任意两个组的CPU掩码的交集不一定为空，如果是这 
调度域中的负载均衡发生在调度组中。也就是说，每个组被视为一个实体。组的负载被定义为它

管辖的每个CPU的负载之和。仅当组的负载不均衡后，任务才在组之间发生迁移。



在kernel/sched/core.c中，trigger_load_balance()在每个CPU上通过scheduler_tick()

在kernel/sched/core.c中，trigger_load_balance()在每个CPU上通过sched_tick()

周期执行。在当前运行队列下一个定期调度再平衡事件到达后，它引发一个软中断。负载均衡真正

的工作由sched_balance_softirq()->rebalance_domains()完成，在软中断上下文中执行

（SCHED_SOFTIRQ）。



后一个函数有两个入参：当前CPU的运行队列、它在scheduler_tick()调用时是否空闲。函数会从

后一个函数有两个入参：当前CPU的运行队列、它在sched_tick()调用时是否空闲。函数会从

当前CPU所在的基调度域开始迭代执行，并沿着parent指针链向上进入更高层级的调度域。在迭代

过程中，函数会检查当前调度域是否已经耗尽了再平衡的时间间隔，如果是，它在该调度域运行

load_balance()。接下来它检查父调度域（如果存在），再后来父调度域的父调度域，以此类推。

include/linux/sched.h

+1 −1
Original line number Diff line number Diff line
@@ -301,7 +301,7 @@ enum { 
	TASK_COMM_LEN = 16,

};



extern void scheduler_tick(void);

extern void sched_tick(void);



#define	MAX_SCHEDULE_TIMEOUT		LONG_MAX

kernel/sched/core.c

+2 −2
Original line number Diff line number Diff line
@@ -5662,7 +5662,7 @@ static inline u64 cpu_resched_latency(struct rq *rq) { return 0; } 
 * This function gets called by the timer code, with HZ frequency.

 * We call it with interrupts disabled.

 */

void scheduler_tick(void)

void sched_tick(void)

{

	int cpu = smp_processor_id();

	struct rq *rq = cpu_rq(cpu);
@@ -6585,7 +6585,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) 
 *      paths. For example, see arch/x86/entry_64.S.

 *

 *      To drive preemption between tasks, the scheduler sets the flag in timer

 *      interrupt handler scheduler_tick().

 *      interrupt handler sched_tick().

 *

 *   3. Wakeups don't really cause entry into schedule(). They add a

 *      task to the run-queue and that's it.

kernel/sched/loadavg.c

+1 −1
Original line number Diff line number Diff line
@@ -379,7 +379,7 @@ void calc_global_load(void) 
}



/*

 * Called from scheduler_tick() to periodically update this CPU's

 * Called from sched_tick() to periodically update this CPU's

 * active count.

 */

void calc_global_load_tick(struct rq *this_rq)