From e476aac235ecf7f3daf7e74302dfa2a7279ba6f5 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 23 Aug 2021 12:17:00 +0100
Subject: [PATCH] sched/fair: Trigger nohz.next_balance updates when a CPU goes
NOHZ-idle
References: bsc#1189999 (Scheduler functional and performance backports)
Patch-mainline: v5.16-rc1
Git-commit: 7fd7a9e0caba10829b4f8db1aa7711b558681fd4
Consider a system with some NOHZ-idle CPUs, such that
nohz.idle_cpus_mask = S
nohz.next_balance = T
When a new CPU k goes NOHZ idle (nohz_balance_enter_idle()), we end up
with:
nohz.idle_cpus_mask = S \U {k}
nohz.next_balance = T
Note that the nohz.next_balance hasn't changed - it won't be updated until
a NOHZ balance is triggered. This is problematic if the newly NOHZ idle CPU
has an earlier rq.next_balance than the other NOHZ idle CPUs, IOW if:
cpu_rq(k).next_balance < nohz.next_balance
In such scenarios, the existing nohz.next_balance will prevent any NOHZ
balance from happening, which itself will prevent nohz.next_balance from
being updated to this new cpu_rq(k).next_balance. Unnecessary load balance
delays of over 12ms caused by this were observed on an arm64 RB5 board.
Use the new nohz.needs_update flag to mark the presence of newly-idle CPUs
that need their rq->next_balance to be collated into
nohz.next_balance. Trigger a NOHZ_NEXT_KICK when the flag is set.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210823111700.2842997-3-valentin.schneider@arm.com
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/sched/fair.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index dff52398b995..9867fae11c9a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5731,6 +5731,7 @@ static struct {
cpumask_var_t idle_cpus_mask;
atomic_t nr_cpus;
int has_blocked; /* Idle CPUS has blocked load */
+ int needs_update; /* Newly idle CPUs need their next_balance collated */
unsigned long next_balance; /* in jiffy units */
unsigned long next_blocked; /* Next update of blocked load in jiffies */
} nohz ____cacheline_aligned;
@@ -10384,6 +10385,9 @@ static void nohz_balancer_kick(struct rq *rq)
unlock:
rcu_read_unlock();
out:
+ if (READ_ONCE(nohz.needs_update))
+ flags |= NOHZ_NEXT_KICK;
+
if (flags)
kick_ilb(flags);
}
@@ -10480,12 +10484,13 @@ void nohz_balance_enter_idle(int cpu)
/*
* Ensures that if nohz_idle_balance() fails to observe our
* @idle_cpus_mask store, it must observe the @has_blocked
- * store.
+ * and @needs_update stores.
*/
smp_mb__after_atomic();
set_cpu_sd_state_idle(cpu);
+ WRITE_ONCE(nohz.needs_update, 1);
out:
/*
* Each time a cpu enter idle, we assume that it has blocked load and
@@ -10534,13 +10539,17 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
/*
* We assume there will be no idle load after this update and clear
* the has_blocked flag. If a cpu enters idle in the mean time, it will
- * set the has_blocked flag and trig another update of idle load.
+ * set the has_blocked flag and trigger another update of idle load.
* Because a cpu that becomes idle, is added to idle_cpus_mask before
* setting the flag, we are sure to not clear the state and not
* check the load of an idle cpu.
+ *
+ * Same applies to idle_cpus_mask vs needs_update.
*/
if (flags & NOHZ_STATS_KICK)
WRITE_ONCE(nohz.has_blocked, 0);
+ if (flags & NOHZ_NEXT_KICK)
+ WRITE_ONCE(nohz.needs_update, 0);
/*
* Ensures that if we miss the CPU, we must see the has_blocked
@@ -10564,6 +10573,8 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
if (need_resched()) {
if (flags & NOHZ_STATS_KICK)
has_blocked_load = true;
+ if (flags & NOHZ_NEXT_KICK)
+ WRITE_ONCE(nohz.needs_update, 1);
goto abort;
}