[PACH OLK-5.10 v5 05/20] sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure

29 Nov 2023

From: Chengming Zhou zhouchengming@bytedance.com
mainline inclusion
from mainline-v6.1-rc1
commit 52b1364ba0b105122d6de0e719b36db705011ac1
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I8BCV4
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
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: Chengming Zhou zhouchengming@bytedance.com
Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org
Acked-by: Johannes 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: Lu Jialin lujialin4@huawei.com
---
 Documentation/admin-guide/cgroup-v2.rst |  6 ++
 include/linux/psi.h                     |  1 +
 include/linux/psi_types.h               | 10 +++-
 kernel/cgroup/cgroup.c                  | 26 +++++++++
 kernel/sched/core.c                     |  1 +
 kernel/sched/psi.c                      | 74 ++++++++++++++++++++++++-
 kernel/sched/stats.h                    |  1 +
 7 files changed, 115 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 394fb18c9e3d..20c35c289253 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -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
 ===========
diff --git a/include/linux/psi.h b/include/linux/psi.h
index 86635a5630ba..9e15596968d0 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -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);
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 9b3988ee2ce8..668f67b56464 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -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
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3d778636f2e8..45c422808340 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -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 */
 };
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 201d75a786e0..eb3353b90b8d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -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))) {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 800d11f9898c..7c255aabc8ac 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -925,6 +925,36 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
    }
 }
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+void psi_account_irqtime(struct task_struct *task, u32 delta)
+{
+	int cpu = task_cpu(task);
+	void *iter = NULL;
+	struct psi_group *group;
+	struct psi_group_cpu *groupc;
+	u64 now;
+
+	if (!task->pid)
+		return;
+
+	now = cpu_clock(cpu);
+
+	while ((group = iterate_groups(task, &iter))) {
+		groupc = per_cpu_ptr(group->pcpu, cpu);
+
+		write_seqcount_begin(&groupc->seq);
+
+		record_times(groupc, now);
+		groupc->times[PSI_IRQ_FULL] += delta;
+
+		write_seqcount_end(&groupc->seq);
+
+		if (group->poll_states & (1 << PSI_IRQ_FULL))
+			psi_schedule_poll_work(group, 1);
+	}
+}
+#endif
+
 /**
  * psi_memstall_enter - mark the beginning of a memory stall section
  * @flags: flags to handle nested sections
@@ -1083,6 +1113,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 {
+	bool only_full = false;
    int full;
    u64 now;
@@ -1097,7 +1128,11 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
    	group->avg_next_update = update_averages(group, now);
    mutex_unlock(&group->avgs_lock);
-	for (full = 0; full < 2; full++) {
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	only_full = res == PSI_IRQ;
+#endif
+
+	for (full = 0; full < 2 - only_full; full++) {
    	unsigned long avg[3] = { 0, };
    	u64 total = 0;
    	int w;
@@ -1111,7 +1146,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
    	}
seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
-			   full ? "full" : "some",
+			   full || only_full ? "full" : "some",
    		   LOAD_INT(avg[0]), LOAD_FRAC(avg[0]),
    		   LOAD_INT(avg[1]), LOAD_FRAC(avg[1]),
    		   LOAD_INT(avg[2]), LOAD_FRAC(avg[2]),
@@ -1140,6 +1175,11 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
    else
    	return ERR_PTR(-EINVAL);
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	if (res == PSI_IRQ && --state != PSI_IRQ_FULL)
+		return ERR_PTR(-EINVAL);
+#endif
+
    if (state >= PSI_NONIDLE)
    	return ERR_PTR(-EINVAL);
@@ -1423,6 +1463,33 @@ static const struct proc_ops psi_cpu_proc_ops = {
    .proc_release	= psi_fop_release,
 };
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+static int psi_irq_show(struct seq_file *m, void *v)
+{
+	return psi_show(m, &psi_system, PSI_IRQ);
+}
+
+static int psi_irq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, psi_irq_show, NULL);
+}
+
+static ssize_t psi_irq_write(struct file *file, const char __user *user_buf,
+			     size_t nbytes, loff_t *ppos)
+{
+	return psi_write(file, user_buf, nbytes, PSI_IRQ);
+}
+
+static const struct proc_ops psi_irq_proc_ops = {
+	.proc_open	= psi_irq_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= psi_irq_write,
+	.proc_poll	= psi_fop_poll,
+	.proc_release	= psi_fop_release,
+};
+#endif
+
 static int __init psi_proc_init(void)
 {
    if (psi_enable) {
@@ -1430,7 +1497,10 @@ static int __init psi_proc_init(void)
    	proc_create("pressure/io", 0, NULL, &psi_io_proc_ops);
    	proc_create("pressure/memory", 0, NULL, &psi_memory_proc_ops);
    	proc_create("pressure/cpu", 0, NULL, &psi_cpu_proc_ops);
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+		proc_create("pressure/irq", 0, NULL, &psi_irq_proc_ops);
    }
+#endif
    return 0;
 }
 module_init(psi_proc_init);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index b8b4e5b2694e..874d8c6e6750 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -170,6 +170,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {}
 static inline void psi_sched_switch(struct task_struct *prev,
    			    struct task_struct *next,
    			    bool sleep) {}
+static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {}
 #endif /* CONFIG_PSI */
#ifdef CONFIG_SCHED_INFO
-- 
2.34.1


    

2024

2023

2022

2021

2020

2019

[PACH OLK-5.10 v5 05/20] sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure