linux-next/include/linux/psi.h

#ifndef _LINUX_PSI_H
#define _LINUX_PSI_H

#include <linux/psi_types.h>
#include <linux/sched.h>

#ifdef CONFIG_PSI

extern bool psi_disabled;

void psi_init(void);

void psi_task_change(struct task_struct *task, int clear, int set);

void psi_memstall_tick(struct task_struct *task, int cpu);
void psi_memstall_enter(unsigned long *flags);
void psi_memstall_leave(unsigned long *flags);

#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) {}

#endif /* CONFIG_PSI */

#endif /* _LINUX_PSI_H */
psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Daniel Drake <drake@endlessm.com> Tested-by: Suren Baghdasaryan <surenb@google.com> Cc: Christopher Lameter <cl@linux.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <jweiner@fb.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Enderborg <peter.enderborg@sony.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 2018-10-26 15:06:27 -07:00			`#ifndef _LINUX_PSI_H`
			`#define _LINUX_PSI_H`

			`#include <linux/psi_types.h>`
			`#include <linux/sched.h>`

			`#ifdef CONFIG_PSI`

			`extern bool psi_disabled;`

			`void psi_init(void);`

			`void psi_task_change(struct task_struct *task, int clear, int set);`

			`void psi_memstall_tick(struct task_struct *task, int cpu);`
			`void psi_memstall_enter(unsigned long *flags);`
			`void psi_memstall_leave(unsigned long *flags);`

			`#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) {}`

			`#endif /* CONFIG_PSI */`

			`#endif /* _LINUX_PSI_H */`