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>

3 files changed, 130 insertions, 0 deletions

diff --git a/include/linux/psi.h b/include/linux/psi.h
new file mode 100644
index 000000000000..b0daf050de58
--- /dev/null
+++ b/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 */
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
new file mode 100644
index 000000000000..2cf422db5d18
--- /dev/null
+++ b/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 */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index adfb3f9a7597..b8fcc6b3080c 100644
--- a/include/linux/sched.h
+++ b/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 */