linux/include/linux/psi.h
Johannes Weiner 36b238d571 psi: Optimize switching tasks inside shared cgroups
When switching tasks running on a CPU, the psi state of a cgroup
containing both of these tasks does not change. Right now, we don't
exploit that, and can perform many unnecessary state changes in nested
hierarchies, especially when most activity comes from one leaf cgroup.

This patch implements an optimization where we only update cgroups
whose state actually changes during a task switch. These are all
cgroups that contain one task but not the other, up to the first
shared ancestor. When both tasks are in the same group, we don't need
to update anything at all.

We can identify the first shared ancestor by walking the groups of the
incoming task until we see TSK_ONCPU set on the local CPU; that's the
first group that also contains the outgoing task.

The new psi_task_switch() is similar to psi_task_change(). To allow
code reuse, move the task flag maintenance code into a new function
and the poll/avg worker wakeups into the shared psi_group_change().

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200316191333.115523-3-hannes@cmpxchg.org
2020-03-20 13:06:19 +01:00

66 lines
1.6 KiB
C

#ifndef _LINUX_PSI_H
#define _LINUX_PSI_H
#include <linux/jump_label.h>
#include <linux/psi_types.h>
#include <linux/sched.h>
#include <linux/poll.h>
struct seq_file;
struct css_set;
#ifdef CONFIG_PSI
extern struct static_key_false psi_disabled;
extern struct psi_group psi_system;
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_memstall_tick(struct task_struct *task, int cpu);
void psi_memstall_enter(unsigned long *flags);
void psi_memstall_leave(unsigned long *flags);
int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
#ifdef CONFIG_CGROUPS
int psi_cgroup_alloc(struct cgroup *cgrp);
void psi_cgroup_free(struct cgroup *cgrp);
void cgroup_move_task(struct task_struct *p, struct css_set *to);
struct psi_trigger *psi_trigger_create(struct psi_group *group,
char *buf, size_t nbytes, enum psi_res res);
void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t);
__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
poll_table *wait);
#endif
#else /* CONFIG_PSI */
static inline void psi_init(void) {}
static inline void psi_memstall_enter(unsigned long *flags) {}
static inline void psi_memstall_leave(unsigned long *flags) {}
#ifdef CONFIG_CGROUPS
static inline int psi_cgroup_alloc(struct cgroup *cgrp)
{
return 0;
}
static inline void psi_cgroup_free(struct cgroup *cgrp)
{
}
static inline void cgroup_move_task(struct task_struct *p, struct css_set *to)
{
rcu_assign_pointer(p->cgroups, to);
}
#endif
#endif /* CONFIG_PSI */
#endif /* _LINUX_PSI_H */