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>

1 files changed, 86 insertions, 0 deletions

diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 8aea199a39b4..4904c4677000 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -55,6 +55,92 @@ static inline void rq_sched_info_depart  (struct rq *rq, unsigned long long delt
 # define   schedstat_val_or_zero(var)	0
 #endif /* CONFIG_SCHEDSTATS */
 
+#ifdef CONFIG_PSI
+/*
+ * PSI tracks state that persists across sleeps, such as iowaits and
+ * memory stalls. As a result, it has to distinguish between sleeps,
+ * where a task's runnable state changes, and requeues, where a task
+ * and its state are being moved between CPUs and runqueues.
+ */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup)
+{
+	int clear = 0, set = TSK_RUNNING;
+
+	if (psi_disabled)
+		return;
+
+	if (!wakeup || p->sched_psi_wake_requeue) {
+		if (p->flags & PF_MEMSTALL)
+			set |= TSK_MEMSTALL;
+		if (p->sched_psi_wake_requeue)
+			p->sched_psi_wake_requeue = 0;
+	} else {
+		if (p->in_iowait)
+			clear |= TSK_IOWAIT;
+	}
+
+	psi_task_change(p, clear, set);
+}
+
+static inline void psi_dequeue(struct task_struct *p, bool sleep)
+{
+	int clear = TSK_RUNNING, set = 0;
+
+	if (psi_disabled)
+		return;
+
+	if (!sleep) {
+		if (p->flags & PF_MEMSTALL)
+			clear |= TSK_MEMSTALL;
+	} else {
+		if (p->in_iowait)
+			set |= TSK_IOWAIT;
+	}
+
+	psi_task_change(p, clear, set);
+}
+
+static inline void psi_ttwu_dequeue(struct task_struct *p)
+{
+	if (psi_disabled)
+		return;
+	/*
+	 * Is the task being migrated during a wakeup? Make sure to
+	 * deregister its sleep-persistent psi states from the old
+	 * queue, and let psi_enqueue() know it has to requeue.
+	 */
+	if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
+		struct rq_flags rf;
+		struct rq *rq;
+		int clear = 0;
+
+		if (p->in_iowait)
+			clear |= TSK_IOWAIT;
+		if (p->flags & PF_MEMSTALL)
+			clear |= TSK_MEMSTALL;
+
+		rq = __task_rq_lock(p, &rf);
+		psi_task_change(p, clear, 0);
+		p->sched_psi_wake_requeue = 1;
+		__task_rq_unlock(rq, &rf);
+	}
+}
+
+static inline void psi_task_tick(struct rq *rq)
+{
+	if (psi_disabled)
+		return;
+
+	if (unlikely(rq->curr->flags & PF_MEMSTALL))
+		psi_memstall_tick(rq->curr, cpu_of(rq));
+}
+#else /* CONFIG_PSI */
+static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
+static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
+static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_task_tick(struct rq *rq) {}
+#endif /* CONFIG_PSI */
+
 #ifdef CONFIG_SCHED_INFO
 static inline void sched_info_reset_dequeued(struct task_struct *t)
 {