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>

4 files changed, 34 insertions, 4 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index faca45ebe62d..7c607479de4a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -22,6 +22,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/page_owner.h>
+#include <linux/psi.h>
 #include "internal.h"
 
 #ifdef CONFIG_COMPACTION
@@ -2068,11 +2069,15 @@ static int kcompactd(void *p)
 	pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
 
 	while (!kthread_should_stop()) {
+		unsigned long pflags;
+
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
 		wait_event_freezable(pgdat->kcompactd_wait,
 				kcompactd_work_requested(pgdat));
 
+		psi_memstall_enter(&pflags);
 		kcompactd_do_work(pgdat);
+		psi_memstall_leave(&pflags);
 	}
 
 	return 0;
diff --git a/mm/filemap.c b/mm/filemap.c
index 01a841f17bf4..41586009fa42 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -37,6 +37,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/rmap.h>
 #include <linux/delayacct.h>
+#include <linux/psi.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -1075,11 +1076,14 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
+	unsigned long pflags;
 	int ret = 0;
 
-	if (bit_nr == PG_locked && !PageSwapBacked(page) &&
+	if (bit_nr == PG_locked &&
 	    !PageUptodate(page) && PageWorkingset(page)) {
-		delayacct_thrashing_start();
+		if (!PageSwapBacked(page))
+			delayacct_thrashing_start();
+		psi_memstall_enter(&pflags);
 		thrashing = true;
 	}
 
@@ -1121,8 +1125,11 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 
 	finish_wait(q, wait);
 
-	if (thrashing)
-		delayacct_thrashing_end();
+	if (thrashing) {
+		if (!PageSwapBacked(page))
+			delayacct_thrashing_end();
+		psi_memstall_leave(&pflags);
+	}
 
 	/*
 	 * A signal could leave PageWaiters set. Clearing it here if
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 20f25d06c00c..f97b5a1700a4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -66,6 +66,7 @@
 #include <linux/ftrace.h>
 #include <linux/lockdep.h>
 #include <linux/nmi.h>
+#include <linux/psi.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -3549,15 +3550,20 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		enum compact_priority prio, enum compact_result *compact_result)
 {
 	struct page *page;
+	unsigned long pflags;
 	unsigned int noreclaim_flag;
 
 	if (!order)
 		return NULL;
 
+	psi_memstall_enter(&pflags);
 	noreclaim_flag = memalloc_noreclaim_save();
+
 	*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
 									prio);
+
 	memalloc_noreclaim_restore(noreclaim_flag);
+	psi_memstall_leave(&pflags);
 
 	if (*compact_result <= COMPACT_INACTIVE)
 		return NULL;
@@ -3756,11 +3762,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 	struct reclaim_state reclaim_state;
 	int progress;
 	unsigned int noreclaim_flag;
+	unsigned long pflags;
 
 	cond_resched();
 
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
+	psi_memstall_enter(&pflags);
 	fs_reclaim_acquire(gfp_mask);
 	noreclaim_flag = memalloc_noreclaim_save();
 	reclaim_state.reclaimed_slab = 0;
@@ -3772,6 +3780,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 	current->reclaim_state = NULL;
 	memalloc_noreclaim_restore(noreclaim_flag);
 	fs_reclaim_release(gfp_mask);
+	psi_memstall_leave(&pflags);
 
 	cond_resched();
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 87e9fef341d2..8ea87586925e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -49,6 +49,7 @@
 #include <linux/prefetch.h>
 #include <linux/printk.h>
 #include <linux/dax.h>
+#include <linux/psi.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -3305,6 +3306,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 {
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
+	unsigned long pflags;
 	int nid;
 	unsigned int noreclaim_flag;
 	struct scan_control sc = {
@@ -3333,9 +3335,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.gfp_mask,
 					    sc.reclaim_idx);
 
+	psi_memstall_enter(&pflags);
 	noreclaim_flag = memalloc_noreclaim_save();
+
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+
 	memalloc_noreclaim_restore(noreclaim_flag);
+	psi_memstall_leave(&pflags);
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -3500,6 +3506,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 	int i;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
+	unsigned long pflags;
 	struct zone *zone;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
@@ -3510,6 +3517,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		.may_swap = 1,
 	};
 
+	psi_memstall_enter(&pflags);
 	__fs_reclaim_acquire();
 
 	count_vm_event(PAGEOUTRUN);
@@ -3611,6 +3619,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 out:
 	snapshot_refaults(NULL, pgdat);
 	__fs_reclaim_release();
+	psi_memstall_leave(&pflags);
 	/*
 	 * Return the order kswapd stopped reclaiming at as
 	 * prepare_kswapd_sleep() takes it into account. If another caller