sched: Avoid side-effect of tickless idle on update_cpu_load

tickless idle has a negative side effect on update_cpu_load(), which
in turn can affect load balancing behavior.

update_cpu_load() is supposed to be called every tick, to keep track
of various load indicies. With tickless idle, there are no scheduler
ticks called on the idle CPUs. Idle CPUs may still do load balancing
(with idle_load_balance CPU) using the stale cpu_load. It will also
cause problems when all CPUs go idle for a while and become active
again. In this case loads would not degrade as expected.

This is how rq->nr_load_updates change looks like under different
conditions:

<cpu_num> <nr_load_updates change>
All CPUS idle for 10 seconds (HZ=1000)
0 1621
10 496
11 139
12 875
13 1672
14 12
15 21
1 1472
2 2426
3 1161
4 2108
5 1525
6 701
7 249
8 766
9 1967

One CPU busy rest idle for 10 seconds
0 10003
10 601
11 95
12 966
13 1597
14 114
15 98
1 3457
2 93
3 6679
4 1425
5 1479
6 595
7 193
8 633
9 1687

All CPUs busy for 10 seconds
0 10026
10 10026
11 10026
12 10026
13 10025
14 10025
15 10025
1 10026
2 10026
3 10026
4 10026
5 10026
6 10026
7 10026
8 10026
9 10026

That is update_cpu_load works properly only when all CPUs are busy.
If all are idle, all the CPUs get way lower updates.  And when few
CPUs are busy and rest are idle, only busy and ilb CPU does proper
updates and rest of the idle CPUs will do lower updates.

The patch keeps track of when a last update was done and fixes up
the load avg based on current time.

On one of my test system SPECjbb with warehouse 1..numcpus, patch
improves throughput numbers by ~1% (average of 6 runs).  On another
test system (with different domain hierarchy) there is no noticable
change in perf.

Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <AANLkTilLtDWQsAUrIxJ6s04WTgmw9GuOODc5AOrYsaR5@mail.gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 99 insertions, 6 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index f37a9618fac3..a757f6b11cbd 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -457,6 +457,7 @@ struct rq {
         unsigned long nr_running;
         #define CPU_LOAD_IDX_MAX 5
         unsigned long cpu_load[CPU_LOAD_IDX_MAX];
+        unsigned long last_load_update_tick;
 #ifdef CONFIG_NO_HZ
         u64 nohz_stamp;
         unsigned char in_nohz_recently;
@@ -1803,6 +1804,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
+static void update_cpu_load(struct rq *this_rq);
 
 static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 {
@@ -3050,23 +3052,102 @@ static void calc_load_account_active(struct rq *this_rq)
 }
 
 /*
+ * The exact cpuload at various idx values, calculated at every tick would be
+ * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ *
+ * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
+ * on nth tick when cpu may be busy, then we have:
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *
+ * decay_load_missed() below does efficient calculation of
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ * The calculation is approximated on a 128 point scale.
+ * degrade_zero_ticks is the number of ticks after which load at any
+ * particular idx is approximated to be zero.
+ * degrade_factor is a precomputed table, a row for each load idx.
+ * Each column corresponds to degradation factor for a power of two ticks,
+ * based on 128 point scale.
+ * Example:
+ * row 2, col 3 (=12) says that the degradation at load idx 2 after
+ * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
+ *
+ * With this power of 2 load factors, we can degrade the load n times
+ * by looking at 1 bits in n and doing as many mult/shift instead of
+ * n mult/shifts needed by the exact degradation.
+ */
+#define DEGRADE_SHIFT           7
+static const unsigned char
+                degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const unsigned char
+                degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+                                        {0, 0, 0, 0, 0, 0, 0, 0},
+                                        {64, 32, 8, 0, 0, 0, 0, 0},
+                                        {96, 72, 40, 12, 1, 0, 0},
+                                        {112, 98, 75, 43, 15, 1, 0},
+                                        {120, 112, 98, 76, 45, 16, 2} };
+
+/*
+ * Update cpu_load for any missed ticks, due to tickless idle. The backlog
+ * would be when CPU is idle and so we just decay the old load without
+ * adding any new load.
+ */
+static unsigned long
+decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
+{
+        int j = 0;
+
+        if (!missed_updates)
+                return load;
+
+        if (missed_updates >= degrade_zero_ticks[idx])
+                return 0;
+
+        if (idx == 1)
+                return load >> missed_updates;
+
+        while (missed_updates) {
+                if (missed_updates % 2)
+                        load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
+
+                missed_updates >>= 1;
+                j++;
+        }
+        return load;
+}
+
+/*
  * Update rq->cpu_load[] statistics. This function is usually called every
- * scheduler tick (TICK_NSEC).
+ * scheduler tick (TICK_NSEC). With tickless idle this will not be called
+ * every tick. We fix it up based on jiffies.
  */
 static void update_cpu_load(struct rq *this_rq)
 {
         unsigned long this_load = this_rq->load.weight;
+        unsigned long curr_jiffies = jiffies;
+        unsigned long pending_updates;
         int i, scale;
 
         this_rq->nr_load_updates++;
 
+        /* Avoid repeated calls on same jiffy, when moving in and out of idle */
+        if (curr_jiffies == this_rq->last_load_update_tick)
+                return;
+
+        pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+        this_rq->last_load_update_tick = curr_jiffies;
+
         /* Update our load: */
-        for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
+        this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
+        for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
                 unsigned long old_load, new_load;
 
                 /* scale is effectively 1 << i now, and >> i divides by scale */
 
                 old_load = this_rq->cpu_load[i];
+                old_load = decay_load_missed(old_load, pending_updates - 1, i);
                 new_load = this_load;
                 /*
                  * Round up the averaging division if load is increasing. This
@@ -3074,9 +3155,15 @@ static void update_cpu_load(struct rq *this_rq)
                  * example.
                  */
                 if (new_load > old_load)
-                        new_load += scale-1;
-                this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
+                        new_load += scale - 1;
+
+                this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
         }
+}
+
+static void update_cpu_load_active(struct rq *this_rq)
+{
+        update_cpu_load(this_rq);
 
         calc_load_account_active(this_rq);
 }
@@ -3464,7 +3551,7 @@ void scheduler_tick(void)
 
         raw_spin_lock(&rq->lock);
         update_rq_clock(rq);
-        update_cpu_load(rq);
+        update_cpu_load_active(rq);
         curr->sched_class->task_tick(rq, curr, 0);
         raw_spin_unlock(&rq->lock);
 
@@ -7688,6 +7775,9 @@ void __init sched_init(void)
 
                 for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
                         rq->cpu_load[j] = 0;
+
+                rq->last_load_update_tick = jiffies;
+
 #ifdef CONFIG_SMP
                 rq->sd = NULL;
                 rq->rd = NULL;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index eed35eded602..22b8b4f2b616 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3420,9 +3420,12 @@ static void run_rebalance_domains(struct softirq_action *h)
                         if (need_resched())
                                 break;
 
+                        rq = cpu_rq(balance_cpu);
+                        raw_spin_lock_irq(&rq->lock);
+                        update_cpu_load(rq);
+                        raw_spin_unlock_irq(&rq->lock);
                         rebalance_domains(balance_cpu, CPU_IDLE);
 
-                        rq = cpu_rq(balance_cpu);
                         if (time_after(this_rq->next_balance, rq->next_balance))
                                 this_rq->next_balance = rq->next_balance;
                 }