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).

[[email protected]: doc fixlet, per Randy]
  Link: http://lkml.kernel.org/r/[email protected]
[[email protected]: code optimization]
  Link: http://lkml.kernel.org/r/[email protected]
[[email protected]: rename psi_clock() to psi_update_work(), per Peter]
  Link: http://lkml.kernel.org/r/[email protected]
[[email protected]: fix build]
  Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Johannes Weiner <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Tested-by: Daniel Drake <[email protected]>
Tested-by: Suren Baghdasaryan <[email protected]>
Cc: Christopher Lameter <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Enderborg <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Vinayak Menon <[email protected]>
Cc: Randy Dunlap <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/accounting/psi.txt

@@ -0,0 +1,64 @@
+================================
+PSI - Pressure Stall Information
+================================
+
+:Date: April, 2018
+:Author: Johannes Weiner <[email protected]>
+
+When CPU, memory or IO devices are contended, workloads experience
+latency spikes, throughput losses, and run the risk of OOM kills.
+
+Without an accurate measure of such contention, users are forced to
+either play it safe and under-utilize their hardware resources, or
+roll the dice and frequently suffer the disruptions resulting from
+excessive overcommit.
+
+The psi feature identifies and quantifies the disruptions caused by
+such resource crunches and the time impact it has on complex workloads
+or even entire systems.
+
+Having an accurate measure of productivity losses caused by resource
+scarcity aids users in sizing workloads to hardware--or provisioning
+hardware according to workload demand.
+
+As psi aggregates this information in realtime, systems can be managed
+dynamically using techniques such as load shedding, migrating jobs to
+other systems or data centers, or strategically pausing or killing low
+priority or restartable batch jobs.
+
+This allows maximizing hardware utilization without sacrificing
+workload health or risking major disruptions such as OOM kills.
+
+Pressure interface
+==================
+
+Pressure information for each resource is exported through the
+respective file in /proc/pressure/ -- cpu, memory, and io.
+
+The format for CPU is as such:
+
+some avg10=0.00 avg60=0.00 avg300=0.00 total=0
+
+and for memory and IO:
+
+some avg10=0.00 avg60=0.00 avg300=0.00 total=0
+full avg10=0.00 avg60=0.00 avg300=0.00 total=0
+
+The "some" line indicates the share of time in which at least some
+tasks are stalled on a given resource.
+
+The "full" line indicates the share of time in which all non-idle
+tasks are stalled on a given resource simultaneously. In this state
+actual CPU cycles are going to waste, and a workload that spends
+extended time in this state is considered to be thrashing. This has
+severe impact on performance, and it's useful to distinguish this
+situation from a state where some tasks are stalled but the CPU is
+still doing productive work. As such, time spent in this subset of the
+stall state is tracked separately and exported in the "full" averages.
+
+The ratios are tracked as recent trends over ten, sixty, and three
+hundred second windows, which gives insight into short term events as
+well as medium and long term trends. The total absolute stall time is
+tracked and exported as well, to allow detection of latency spikes
+which wouldn't necessarily make a dent in the time averages, or to
+average trends over custom time frames.

include/linux/psi.h

@@ -0,0 +1,28 @@
+#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 */

include/linux/psi_types.h

@@ -0,0 +1,92 @@
+#ifndef _LINUX_PSI_TYPES_H
+#define _LINUX_PSI_TYPES_H
+
+#include <linux/seqlock.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_PSI
+
+/* Tracked task states */
+enum psi_task_count {
+	NR_IOWAIT,
+	NR_MEMSTALL,
+	NR_RUNNING,
+	NR_PSI_TASK_COUNTS,
+};
+
+/* Task state bitmasks */
+#define TSK_IOWAIT	(1 << NR_IOWAIT)
+#define TSK_MEMSTALL	(1 << NR_MEMSTALL)
+#define TSK_RUNNING	(1 << NR_RUNNING)
+
+/* Resources that workloads could be stalled on */
+enum psi_res {
+	PSI_IO,
+	PSI_MEM,
+	PSI_CPU,
+	NR_PSI_RESOURCES,
+};
+
+/*
+ * Pressure states for each resource:
+ *
+ * SOME: Stalled tasks & working tasks
+ * FULL: Stalled tasks & no working tasks
+ */
+enum psi_states {
+	PSI_IO_SOME,
+	PSI_IO_FULL,
+	PSI_MEM_SOME,
+	PSI_MEM_FULL,
+	PSI_CPU_SOME,
+	/* Only per-CPU, to weigh the CPU in the global average: */
+	PSI_NONIDLE,
+	NR_PSI_STATES,
+};
+
+struct psi_group_cpu {
+	/* 1st cacheline updated by the scheduler */
+
+	/* Aggregator needs to know of concurrent changes */
+	seqcount_t seq ____cacheline_aligned_in_smp;
+
+	/* States of the tasks belonging to this group */
+	unsigned int tasks[NR_PSI_TASK_COUNTS];
+
+	/* Period time sampling buckets for each state of interest (ns) */
+	u32 times[NR_PSI_STATES];
+
+	/* Time of last task change in this group (rq_clock) */
+	u64 state_start;
+
+	/* 2nd cacheline updated by the aggregator */
+
+	/* Delta detection against the sampling buckets */
+	u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp;
+};
+
+struct psi_group {
+	/* Protects data updated during an aggregation */
+	struct mutex stat_lock;
+
+	/* Per-cpu task state & time tracking */
+	struct psi_group_cpu __percpu *pcpu;
+
+	/* Periodic aggregation state */
+	u64 total_prev[NR_PSI_STATES - 1];
+	u64 last_update;
+	u64 next_update;
+	struct delayed_work clock_work;
+
+	/* Total stall times and sampled pressure averages */
+	u64 total[NR_PSI_STATES - 1];
+	unsigned long avg[NR_PSI_STATES - 1][3];
+};
+
+#else /* CONFIG_PSI */
+
+struct psi_group { };
+
+#endif /* CONFIG_PSI */
+
+#endif /* _LINUX_PSI_TYPES_H */

include/linux/sched.h

@@ -25,6 +25,7 @@
 #include <linux/latencytop.h>
 #include <linux/sched/prio.h>
 #include <linux/signal_types.h>
+#include <linux/psi_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
 #include <linux/rseq.h>
@@ -706,6 +707,10 @@ struct task_struct {
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
 	unsigned			sched_remote_wakeup:1;
+#ifdef CONFIG_PSI
+	unsigned			sched_psi_wake_requeue:1;
+#endif
+
 	/* Force alignment to the next boundary: */
 	unsigned			:0;
 
@@ -965,6 +970,10 @@ struct task_struct {
 	kernel_siginfo_t		*last_siginfo;
 
 	struct task_io_accounting	ioac;
+#ifdef CONFIG_PSI
+	/* Pressure stall state */
+	unsigned int			psi_flags;
+#endif
 #ifdef CONFIG_TASK_XACCT
 	/* Accumulated RSS usage: */
 	u64				acct_rss_mem1;
@@ -1391,6 +1400,7 @@ extern struct pid *cad_pid;
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
+#define PF_MEMSTALL		0x01000000	/* Stalled due to lack of memory */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MUTEX_TESTER		0x20000000	/* Thread belongs to the rt mutex tester */

init/Kconfig

@@ -490,6 +490,21 @@ config TASK_IO_ACCOUNTING
 
 	  Say N if unsure.
 
+config PSI
+	bool "Pressure stall information tracking"
+	help
+	  Collect metrics that indicate how overcommitted the CPU, memory,
+	  and IO capacity are in the system.
+
+	  If you say Y here, the kernel will create /proc/pressure/ with the
+	  pressure statistics files cpu, memory, and io. These will indicate
+	  the share of walltime in which some or all tasks in the system are
+	  delayed due to contention of the respective resource.
+
+	  For more details see Documentation/accounting/psi.txt.
+
+	  Say N if unsure.
+
 endmenu # "CPU/Task time and stats accounting"
 
 config CPU_ISOLATION

kernel/fork.c

@@ -1822,6 +1822,10 @@ static __latent_entropy struct task_struct *copy_process(
 
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
+#ifdef CONFIG_PSI
+	p->psi_flags = 0;
+#endif
+
 	task_io_accounting_init(&p->ioac);
 	acct_clear_integrals(p);
 

kernel/sched/Makefile

@@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o
 obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
 obj-$(CONFIG_MEMBARRIER) += membarrier.o
 obj-$(CONFIG_CPU_ISOLATION) += isolation.o
+obj-$(CONFIG_PSI) += psi.o

kernel/sched/core.c

@@ -722,8 +722,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & ENQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	if (!(flags & ENQUEUE_RESTORE))
+	if (!(flags & ENQUEUE_RESTORE)) {
 		sched_info_queued(rq, p);
+		psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+	}
 
 	p->sched_class->enqueue_task(rq, p, flags);
 }
@@ -733,8 +735,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & DEQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	if (!(flags & DEQUEUE_SAVE))
+	if (!(flags & DEQUEUE_SAVE)) {
 		sched_info_dequeued(rq, p);
+		psi_dequeue(p, flags & DEQUEUE_SLEEP);
+	}
 
 	p->sched_class->dequeue_task(rq, p, flags);
 }
@@ -2037,6 +2041,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
+		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
 
@@ -3051,6 +3056,7 @@ void scheduler_tick(void)
 	curr->sched_class->task_tick(rq, curr, 0);
 	cpu_load_update_active(rq);
 	calc_global_load_tick(rq);
+	psi_task_tick(rq);
 
 	rq_unlock(rq, &rf);
 
@@ -6067,6 +6073,8 @@ void __init sched_init(void)
 
 	init_schedstats();
 
+	psi_init();
+
 	scheduler_running = 1;
 }