Commit 0266adf3 authored by Chengming Zhou's avatar Chengming Zhou Committed by Lu Jialin
Browse files

sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure 

mainline inclusion
from mainline-v6.1-rc1
commit 52b1364b
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I8BCV4

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=52b1364ba0b105122d6de0e719b36db705011ac1



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

Now PSI already tracked workload pressure stall information for
CPU, memory and IO. Apart from these, IRQ/SOFTIRQ could have
obvious impact on some workload productivity, such as web service
workload.

When CONFIG_IRQ_TIME_ACCOUNTING, we can get IRQ/SOFTIRQ delta time
from update_rq_clock_task(), in which we can record that delta
to CPU curr task's cgroups as PSI_IRQ_FULL status.

Note we don't use PSI_IRQ_SOME since IRQ/SOFTIRQ always happen in
the current task on the CPU, make nothing productive could run
even if it were runnable, so we only use PSI_IRQ_FULL.

Signed-off-by: default avatarChengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/r/20220825164111.29534-8-zhouchengming@bytedance.com


Conflict:
	Documentation/admin-guide/cgroup-v2.rst
	include/linux/psi_types.h
	kernel/sched/psi.c
	kernel/sched/stats.h
Signed-off-by: default avatarLu Jialin <lujialin4@huawei.com>
parent 78f517b8

Documentation/admin-guide/cgroup-v2.rst

+6 −0
Original line number Diff line number Diff line
@@ -951,6 +951,12 @@ All cgroup core files are prefixed with "cgroup." 
	it's possible to delete a frozen (and empty) cgroup, as well as

	create new sub-cgroups.



irq.pressure

        A read-write nested-keyed file.



        Shows pressure stall information for IRQ/SOFTIRQ. See

        :ref:`Documentation/accounting/psi.rst <psi>` for details.



Controllers

===========

include/linux/psi.h

+1 −0
Original line number Diff line number Diff line
@@ -21,6 +21,7 @@ void psi_init(void); 
void psi_task_change(struct task_struct *task, int clear, int set);

void psi_task_switch(struct task_struct *prev, struct task_struct *next,

		     bool sleep);

void psi_account_irqtime(struct task_struct *task, u32 delta);



void psi_memstall_enter(unsigned long *flags);

void psi_memstall_leave(unsigned long *flags);

include/linux/psi_types.h

+8 −2
Original line number Diff line number Diff line
@@ -63,7 +63,10 @@ enum psi_res { 
	PSI_IO,

	PSI_MEM,

	PSI_CPU,

	NR_PSI_RESOURCES = 3,

#ifdef CONFIG_IRQ_TIME_ACCOUNTING

	PSI_IRQ,

#endif

	NR_PSI_RESOURCES,

};



/*
@@ -98,9 +101,12 @@ enum psi_states { 
	PSI_MEM_FULL,

	PSI_CPU_SOME,

	PSI_CPU_FULL,

#ifdef CONFIG_IRQ_TIME_ACCOUNTING

	PSI_IRQ_FULL,

#endif

	/* Only per-CPU, to weigh the CPU in the global average: */

	PSI_NONIDLE,

	NR_PSI_STATES = 7,

	NR_PSI_STATES,

};

#endif

kernel/cgroup/cgroup.c

+26 −0
Original line number Diff line number Diff line
@@ -3751,6 +3751,23 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, 
	return cgroup_pressure_write(of, buf, nbytes, PSI_CPU);

}



#ifdef CONFIG_IRQ_TIME_ACCOUNTING

static int cgroup_irq_pressure_show(struct seq_file *seq, void *v)

{

	struct cgroup *cgrp = seq_css(seq)->cgroup;

	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;



	return psi_show(seq, psi, PSI_IRQ);

}



static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,

					 char *buf, size_t nbytes,

					 loff_t off)

{

	return cgroup_pressure_write(of, buf, nbytes, PSI_IRQ);

}

#endif



static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,

					  poll_table *pt)

{
@@ -5155,6 +5172,15 @@ static struct cftype cgroup_base_files[] = { 
		.poll = cgroup_pressure_poll,

		.release = cgroup_pressure_release,

	},

#ifdef CONFIG_IRQ_TIME_ACCOUNTING

	{

		.name = "irq.pressure",

		.seq_show = cgroup_irq_pressure_show,

		.write = cgroup_irq_pressure_write,

		.poll = cgroup_pressure_poll,

		.release = cgroup_pressure_release,

	},

#endif

#endif /* CONFIG_PSI */

	{ }	/* terminate */

};

kernel/sched/core.c

+1 −0
Original line number Diff line number Diff line
@@ -629,6 +629,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) 


	rq->prev_irq_time += irq_delta;

	delta -= irq_delta;

	psi_account_irqtime(rq->curr, irq_delta);

#endif

#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING

	if (static_key_false((&paravirt_steal_rq_enabled))) {