public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Suresh Siddha <suresh.b.siddha@intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@elte.hu>, Venki Pallipadi <venki@google.com>,
	Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>,
	Mike Galbraith <efault@gmx.de>
Cc: linux-kernel <linux-kernel@vger.kernel.org>,
	Tim Chen <tim.c.chen@linux.jf.intel.com>,
	alex.shi@intel.com, Suresh Siddha <suresh.b.siddha@intel.com>
Subject: [patch 1/6] sched, nohz: introduce nohz_flags in the struct rq
Date: Fri, 18 Nov 2011 15:03:24 -0800	[thread overview]
Message-ID: <20111118230553.882444396@sbsiddha-desk.sc.intel.com> (raw)
In-Reply-To: 20111118230323.592022417@sbsiddha-desk.sc.intel.com

[-- Attachment #1: introduce_rq_nohz_flags.patch --]
[-- Type: text/plain, Size: 4787 bytes --]

Introduce nohz_flags in the struct rq, which will track two flags for now.

NOHZ_TICK_STOPPED will convey the stop tick status that gets set when
the tick is stopped and cleared during the first busy tick after the tick
is restarted.

NOHZ_BALANCE_KICK will track the need for nohz idle load balance
on this rq.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> 
---
 kernel/sched/core.c  |    5 +++--
 kernel/sched/fair.c  |   40 +++++++++++++++++++++-------------------
 kernel/sched/sched.h |   10 +++++++++-
 3 files changed, 33 insertions(+), 22 deletions(-)

Index: tip/kernel/sched/core.c
===================================================================
--- tip.orig/kernel/sched/core.c
+++ tip/kernel/sched/core.c
@@ -575,7 +575,8 @@ void wake_up_idle_cpu(int cpu)
 
 static inline bool got_nohz_idle_kick(void)
 {
-	return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick;
+	int cpu = smp_processor_id();
+	return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
 }
 
 #else /* CONFIG_NO_HZ */
@@ -6833,7 +6834,7 @@ void __init sched_init(void)
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ
-		rq->nohz_balance_kick = 0;
+		rq->nohz_flags = 0;
 #endif
 #endif
 		init_rq_hrtick(rq);
Index: tip/kernel/sched/fair.c
===================================================================
--- tip.orig/kernel/sched/fair.c
+++ tip/kernel/sched/fair.c
@@ -4866,18 +4866,15 @@ static void nohz_balancer_kick(int cpu)
 			return;
 	}
 
-	if (!cpu_rq(ilb_cpu)->nohz_balance_kick) {
-		cpu_rq(ilb_cpu)->nohz_balance_kick = 1;
-
-		smp_mb();
-		/*
-		 * Use smp_send_reschedule() instead of resched_cpu().
-		 * This way we generate a sched IPI on the target cpu which
-		 * is idle. And the softirq performing nohz idle load balance
-		 * will be run before returning from the IPI.
-		 */
-		smp_send_reschedule(ilb_cpu);
-	}
+	if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)))
+		return;
+	/*
+	 * Use smp_send_reschedule() instead of resched_cpu().
+	 * This way we generate a sched IPI on the target cpu which
+	 * is idle. And the softirq performing nohz idle load balance
+	 * will be run before returning from the IPI.
+	 */
+	smp_send_reschedule(ilb_cpu);
 	return;
 }
 
@@ -4941,6 +4938,8 @@ void select_nohz_load_balancer(int stop_
 			}
 			return;
 		}
+
+		set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
 	} else {
 		if (!cpumask_test_cpu(cpu, nohz.idle_cpus_mask))
 			return;
@@ -5056,8 +5055,9 @@ static void nohz_idle_balance(int this_c
 	struct rq *rq;
 	int balance_cpu;
 
-	if (idle != CPU_IDLE || !this_rq->nohz_balance_kick)
-		return;
+	if (idle != CPU_IDLE ||
+	    !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
+		goto end;
 
 	for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
 		if (balance_cpu == this_cpu)
@@ -5068,10 +5068,8 @@ static void nohz_idle_balance(int this_c
 		 * work being done for other cpus. Next load
 		 * balancing owner will pick it up.
 		 */
-		if (need_resched()) {
-			this_rq->nohz_balance_kick = 0;
+		if (need_resched())
 			break;
-		}
 
 		raw_spin_lock_irq(&this_rq->lock);
 		update_rq_clock(this_rq);
@@ -5085,7 +5083,8 @@ static void nohz_idle_balance(int this_c
 			this_rq->next_balance = rq->next_balance;
 	}
 	nohz.next_balance = this_rq->next_balance;
-	this_rq->nohz_balance_kick = 0;
+end:
+	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
 }
 
 /*
@@ -5106,6 +5105,9 @@ static inline int nohz_kick_needed(struc
 	int ret;
 	int first_pick_cpu, second_pick_cpu;
 
+	if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))))
+		clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
+
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
@@ -5173,7 +5175,7 @@ void trigger_load_balance(struct rq *rq,
 	    likely(!on_null_domain(cpu)))
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ
-	else if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
+	if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
 		nohz_balancer_kick(cpu);
 #endif
 }
Index: tip/kernel/sched/sched.h
===================================================================
--- tip.orig/kernel/sched/sched.h
+++ tip/kernel/sched/sched.h
@@ -371,7 +371,7 @@ struct rq {
 	unsigned long last_load_update_tick;
 #ifdef CONFIG_NO_HZ
 	u64 nohz_stamp;
-	unsigned char nohz_balance_kick;
+	unsigned long nohz_flags;
 #endif
 	int skip_clock_update;
 
@@ -1062,3 +1062,11 @@ extern void init_rt_rq(struct rt_rq *rt_
 extern void unthrottle_offline_cfs_rqs(struct rq *rq);
 
 extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
+
+#ifdef CONFIG_NO_HZ
+enum rq_nohz_flag_bits {
+	NOHZ_TICK_STOPPED,
+	NOHZ_BALANCE_KICK,
+};
+#define nohz_flags(cpu)		(&cpu_rq(cpu)->nohz_flags)
+#endif /* CONFIG_NO_HZ */



  reply	other threads:[~2011-11-18 23:10 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-11-18 23:03 [patch 0/6] sched, nohz: load balancing patches Suresh Siddha
2011-11-18 23:03 ` Suresh Siddha [this message]
2011-11-24 10:24   ` [patch 1/6] sched, nohz: introduce nohz_flags in the struct rq Peter Zijlstra
2011-11-28 23:59     ` Suresh Siddha
2011-11-29  9:47       ` Peter Zijlstra
2011-11-18 23:03 ` [patch 2/6] sched, nohz: track nr_busy_cpus in the sched_group_power Suresh Siddha
2011-11-18 23:03 ` [patch 3/6] sched, nohz: sched group, domain aware nohz idle load balancing Suresh Siddha
2011-11-24 11:47   ` Peter Zijlstra
2011-11-28 23:51     ` Suresh Siddha
2011-11-29  9:44       ` Peter Zijlstra
2011-12-01  1:03         ` Suresh Siddha
2011-12-01  1:17         ` Suresh Siddha
2011-12-01  8:36           ` Peter Zijlstra
2011-11-24 11:53   ` Peter Zijlstra
2011-11-28 23:58     ` Suresh Siddha
2011-11-29  9:45       ` Peter Zijlstra
2011-11-18 23:03 ` [patch 4/6] sched, nohz: cleanup the find_new_ilb() using sched groups nr_busy_cpus Suresh Siddha
2011-11-18 23:03 ` [patch 5/6] sched: disable sched feature TTWU_QUEUE by default Suresh Siddha
2011-11-19  4:30   ` Mike Galbraith
2011-11-19  4:41     ` Mike Galbraith
2011-11-18 23:03 ` [patch 6/6] sched: fix the sched group node allocation for SD_OVERLAP domain Suresh Siddha
2011-12-06  9:51   ` [tip:sched/core] sched: Fix the sched group node allocation for SD_OVERLAP domains tip-bot for Suresh Siddha

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=20111118230553.882444396@sbsiddha-desk.sc.intel.com \
    --to=suresh.b.siddha@intel.com \
    --cc=alex.shi@intel.com \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=peterz@infradead.org \
    --cc=tim.c.chen@linux.jf.intel.com \
    --cc=vatsa@linux.vnet.ibm.com \
    --cc=venki@google.com \
    /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