From: Nicholas Piggin <npiggin@gmail.com>
To: Thomas Gleixner <tglx@linutronix.de>,
Frederic Weisbecker <fweisbec@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
linux-kernel@vger.kernel.org
Subject: [PATCH 4/4] nohz_full: Allow the boot CPU to be full nohz
Date: Thu, 4 Apr 2019 22:07:04 +1000 [thread overview]
Message-ID: <20190404120704.18479-5-npiggin@gmail.com> (raw)
In-Reply-To: <20190404120704.18479-1-npiggin@gmail.com>
Allow the boot CPU to be full nohz, and have it take the do_timer duty
temporarily during boot.
nohz_full has been successful at significantly reducing jitter for a
large supercomputer customer, but their job control system requires
CPU0 to be for housekeeping.
This will cause suspend / kexec freeze to occur on a non-boot CPU,
so the option may need to be made conditional by arch?
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
kernel/time/tick-common.c | 50 +++++++++++++++++++++++++++++++++++----
kernel/time/tick-sched.c | 27 +++++++++++----------
2 files changed, 60 insertions(+), 17 deletions(-)
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 529143b4c8d2..31146c13226e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -46,6 +46,14 @@ ktime_t tick_period;
* procedure also covers cpu hotplug.
*/
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
+ * tick_do_timer_cpu and it should be taken over by an eligible secondary
+ * when one comes online.
+ */
+static int tick_do_timer_boot_cpu __read_mostly = -1;
+#endif
/*
* Debugging: see timer_list.c
@@ -167,6 +175,26 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
}
}
+#ifdef CONFIG_NO_HZ_FULL
+static void giveup_do_timer(void *info)
+{
+ int cpu = *(unsigned int *)info;
+
+ WARN_ON(tick_do_timer_cpu != smp_processor_id());
+
+ tick_do_timer_cpu = cpu;
+}
+
+static void tick_take_do_timer_from_boot(void)
+{
+ int cpu = smp_processor_id();
+ int from = tick_do_timer_boot_cpu;
+
+ if (from >= 0 && from != cpu)
+ smp_call_function_single(from, giveup_do_timer, &cpu, 1);
+}
+#endif
+
/*
* Setup the tick device
*/
@@ -186,12 +214,26 @@ static void tick_setup_device(struct tick_device *td,
* this cpu:
*/
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
- if (!tick_nohz_full_cpu(cpu))
- tick_do_timer_cpu = cpu;
- else
- tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+ tick_do_timer_cpu = cpu;
+
tick_next_period = ktime_get();
tick_period = NSEC_PER_SEC / HZ;
+#ifdef CONFIG_NO_HZ_FULL
+ /*
+ * The boot CPU may be nohz_full, in which case set
+ * tick_do_timer_boot_cpu so the first housekeeping
+ * secondary that comes up will take do_timer from
+ * us.
+ */
+ if (tick_nohz_full_cpu(cpu))
+ tick_do_timer_boot_cpu = cpu;
+
+ } else if (tick_do_timer_boot_cpu != -1 &&
+ !tick_nohz_full_cpu(cpu)) {
+ tick_take_do_timer_from_boot();
+ tick_do_timer_boot_cpu = -1;
+ WARN_ON(tick_do_timer_cpu != cpu);
+#endif
}
/*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6fa52cd6df0b..c0105bf4ecd9 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -121,10 +121,14 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
* into a long sleep. If two CPUs happen to assign themselves to
* this duty, then the jiffies update is still serialized by
* jiffies_lock.
+ *
+ * If nohz_full is enabled, this should not happen because the
+ * tick_do_timer_cpu never relinquishes.
*/
- if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
- && !tick_nohz_full_cpu(cpu))
+ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+ WARN_ON(tick_nohz_full_running);
tick_do_timer_cpu = cpu;
+ }
#endif
/* Check, if the jiffies need an update */
@@ -395,8 +399,8 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
static int tick_nohz_cpu_down(unsigned int cpu)
{
/*
- * The boot CPU handles housekeeping duty (unbound timers,
- * workqueues, timekeeping, ...) on behalf of full dynticks
+ * The tick_do_timer_cpu CPU handles housekeeping duty (unbound
+ * timers, workqueues, timekeeping, ...) on behalf of full dynticks
* CPUs. It must remain online when nohz full is enabled.
*/
if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
@@ -423,14 +427,6 @@ void __init tick_nohz_init(void)
return;
}
- cpu = smp_processor_id();
-
- if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
- pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n",
- cpu);
- cpumask_clear_cpu(cpu, tick_nohz_full_mask);
- }
-
for_each_cpu(cpu, tick_nohz_full_mask)
context_tracking_cpu_set(cpu);
@@ -904,8 +900,13 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
/*
* Boot safety: make sure the timekeeping duty has been
* assigned before entering dyntick-idle mode,
+ * tick_do_timer_cpu is TICK_DO_TIMER_BOOT
*/
- if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT))
+ return false;
+
+ /* Should not happen for nohz-full */
+ if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
return false;
}
--
2.20.1
next prev parent reply other threads:[~2019-04-04 12:07 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-04 12:07 [PATCH 0/4] Allow CPU0 to be nohz full Nicholas Piggin
2019-04-04 12:07 ` [PATCH 1/4] sched/core: allow the remote scheduler tick to be started on CPU0 Nicholas Piggin
2019-04-04 12:07 ` [PATCH 2/4] kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze Nicholas Piggin
2019-04-04 12:07 ` [PATCH 3/4] kernel/sched/isolation: require a present CPU in housekeeping mask Nicholas Piggin
2019-04-04 12:07 ` Nicholas Piggin [this message]
2019-04-04 14:36 ` [PATCH 0/4] Allow CPU0 to be nohz full Thomas Gleixner
2019-04-04 16:02 ` Nicholas Piggin
2019-04-05 17:54 ` Thomas Gleixner
2019-04-09 9:21 ` Nicholas Piggin
2019-04-11 15:42 ` Paul E. McKenney
2019-04-12 3:16 ` Nicholas Piggin
2019-04-12 11:30 ` Paul E. McKenney
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190404120704.18479-5-npiggin@gmail.com \
--to=npiggin@gmail.com \
--cc=fweisbec@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).