public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: tip-bot for Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@redhat.com,
	a.p.zijlstra@chello.nl, dave.kleikamp@oracle.com, efault@gmx.de,
	chris.mason@oracle.com, suresh.b.siddha@intel.com,
	tglx@linutronix.de, mingo@elte.hu
Subject: [tip:sched/core] sched: Only queue remote wakeups when crossing cache boundaries
Date: Wed, 21 Dec 2011 03:41:09 -0800	[thread overview]
Message-ID: <tip-518cd62341786aa4e3839810832af2fbc0de1ea4@git.kernel.org> (raw)
In-Reply-To: <1323338531.17673.7.camel@twins>

Commit-ID:  518cd62341786aa4e3839810832af2fbc0de1ea4
Gitweb:     http://git.kernel.org/tip/518cd62341786aa4e3839810832af2fbc0de1ea4
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Wed, 7 Dec 2011 15:07:31 +0100
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Wed, 21 Dec 2011 10:34:44 +0100

sched: Only queue remote wakeups when crossing cache boundaries

Mike reported a 13% drop in netperf TCP_RR performance due to the
new remote wakeup code. Suresh too noticed some performance issues
with it.

Reducing the IPIs to only cross cache domains solves the observed
performance issues.

Reported-by: Suresh Siddha <suresh.b.siddha@intel.com>
Reported-by: Mike Galbraith <efault@gmx.de>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Link: http://lkml.kernel.org/r/1323338531.17673.7.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched/core.c  |   34 +++++++++++++++++++++++++++++++++-
 kernel/sched/fair.c  |   24 +-----------------------
 kernel/sched/sched.h |   42 ++++++++++++++++++++++++++++++++++++------
 3 files changed, 70 insertions(+), 30 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cdf51a2..dba878c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1511,6 +1511,11 @@ static int ttwu_activate_remote(struct task_struct *p, int wake_flags)
 
 }
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+
+static inline int ttwu_share_cache(int this_cpu, int that_cpu)
+{
+	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
+}
 #endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu)
@@ -1518,7 +1523,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 
 #if defined(CONFIG_SMP)
-	if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+	if (sched_feat(TTWU_QUEUE) && !ttwu_share_cache(smp_processor_id(), cpu)) {
 		sched_clock_cpu(cpu); /* sync clocks x-cpu */
 		ttwu_queue_remote(p, cpu);
 		return;
@@ -5744,6 +5749,31 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
 }
 
 /*
+ * Keep a special pointer to the highest sched_domain that has
+ * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
+ * allows us to avoid some pointer chasing select_idle_sibling().
+ *
+ * Also keep a unique ID per domain (we use the first cpu number in
+ * the cpumask of the domain), this allows us to quickly tell if
+ * two cpus are in the same cache domain, see ttwu_share_cache().
+ */
+DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(int, sd_llc_id);
+
+static void update_top_cache_domain(int cpu)
+{
+	struct sched_domain *sd;
+	int id = cpu;
+
+	sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
+	if (sd)
+		id = cpumask_first(sched_domain_span(sd));
+
+	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
+	per_cpu(sd_llc_id, cpu) = id;
+}
+
+/*
  * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
  * hold the hotplug lock.
  */
@@ -5782,6 +5812,8 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	tmp = rq->sd;
 	rcu_assign_pointer(rq->sd, sd);
 	destroy_sched_domains(tmp, cpu);
+
+	update_top_cache_domain(cpu);
 }
 
 /* cpus with isolated domains */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a4d2b7a..2237ffe 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2644,28 +2644,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return idlest;
 }
 
-/**
- * highest_flag_domain - Return highest sched_domain containing flag.
- * @cpu:	The cpu whose highest level of sched domain is to
- *		be returned.
- * @flag:	The flag to check for the highest sched_domain
- *		for the given cpu.
- *
- * Returns the highest sched_domain of a cpu which contains the given flag.
- */
-static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
-{
-	struct sched_domain *sd, *hsd = NULL;
-
-	for_each_domain(cpu, sd) {
-		if (!(sd->flags & flag))
-			break;
-		hsd = sd;
-	}
-
-	return hsd;
-}
-
 /*
  * Try and locate an idle CPU in the sched_domain.
  */
@@ -2696,7 +2674,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	 */
 	rcu_read_lock();
 
-	sd = highest_flag_domain(target, SD_SHARE_PKG_RESOURCES);
+	sd = rcu_dereference(per_cpu(sd_llc, target));
 	for_each_lower_domain(sd) {
 		sg = sd->groups;
 		do {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d8d3613..98c0c26 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -487,6 +487,14 @@ static inline int cpu_of(struct rq *rq)
 
 DECLARE_PER_CPU(struct rq, runqueues);
 
+#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
+#define this_rq()		(&__get_cpu_var(runqueues))
+#define task_rq(p)		cpu_rq(task_cpu(p))
+#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+#define raw_rq()		(&__raw_get_cpu_var(runqueues))
+
+#ifdef CONFIG_SMP
+
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
 			      lockdep_is_held(&sched_domains_mutex))
@@ -499,15 +507,37 @@ DECLARE_PER_CPU(struct rq, runqueues);
  * preempt-disabled sections.
  */
 #define for_each_domain(cpu, __sd) \
-	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
+	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
+			__sd; __sd = __sd->parent)
 
 #define for_each_lower_domain(sd) for (; sd; sd = sd->child)
 
-#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
-#define this_rq()		(&__get_cpu_var(runqueues))
-#define task_rq(p)		cpu_rq(task_cpu(p))
-#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
-#define raw_rq()		(&__raw_get_cpu_var(runqueues))
+/**
+ * highest_flag_domain - Return highest sched_domain containing flag.
+ * @cpu:	The cpu whose highest level of sched domain is to
+ *		be returned.
+ * @flag:	The flag to check for the highest sched_domain
+ *		for the given cpu.
+ *
+ * Returns the highest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd, *hsd = NULL;
+
+	for_each_domain(cpu, sd) {
+		if (!(sd->flags & flag))
+			break;
+		hsd = sd;
+	}
+
+	return hsd;
+}
+
+DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(int, sd_llc_id);
+
+#endif /* CONFIG_SMP */
 
 #include "stats.h"
 #include "auto_group.h"

  reply	other threads:[~2011-12-21 11:41 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-12-02  1:07 [patch v3 0/6] nohz idle load balancing patches Suresh Siddha
2011-12-02  1:07 ` [patch v3 1/6] sched, nohz: introduce nohz_flags in the struct rq Suresh Siddha
2011-12-06  9:53   ` [tip:sched/core] sched, nohz: Introduce nohz_flags in 'struct rq' tip-bot for Suresh Siddha
2011-12-06 12:14   ` [patch v3 1/6] sched, nohz: introduce nohz_flags in the struct rq Srivatsa Vaddagiri
2011-12-06 19:26     ` Suresh Siddha
2011-12-06 19:39       ` Peter Zijlstra
2011-12-06 20:24       ` [tip:sched/core] sched, nohz: Set the NOHZ_BALANCE_KICK flag for idle load balancer tip-bot for Suresh Siddha
2011-12-02  1:07 ` [patch v3 2/6] sched, nohz: track nr_busy_cpus in the sched_group_power Suresh Siddha
2011-12-06  9:54   ` [tip:sched/core] sched, nohz: Track " tip-bot for Suresh Siddha
2011-12-02  1:07 ` [patch v3 3/6] sched, nohz: sched group, domain aware nohz idle load balancing Suresh Siddha
2011-12-06  6:37   ` Srivatsa Vaddagiri
2011-12-06 19:19     ` Suresh Siddha
2011-12-06 20:24       ` [tip:sched/core] sched, nohz: Fix the idle cpu check in nohz_idle_balance tip-bot for Suresh Siddha
     [not found]     ` <A75BCAD09CE00A4280CDD4429D85F1F9261B42A1F9@orsmsx501.amr.corp.intel.com>
2011-12-06 19:27       ` [patch v3 3/6] sched, nohz: sched group, domain aware nohz idle load balancing Suresh Siddha
2011-12-06  9:54   ` [tip:sched/core] sched, nohz: Implement " tip-bot for Suresh Siddha
2011-12-02  1:07 ` [patch v3 4/6] sched, nohz: cleanup the find_new_ilb() using sched groups nr_busy_cpus Suresh Siddha
2011-12-06  9:55   ` [tip:sched/core] sched, nohz: Clean up " tip-bot for Suresh Siddha
2011-12-02  1:07 ` [patch v3 5/6] sched, ttwu_queue: queue remote wakeups only when crossing cache domains Suresh Siddha
2011-12-02  3:34   ` Mike Galbraith
2011-12-07 16:23     ` Peter Zijlstra
2011-12-07 19:20       ` Suresh Siddha
2011-12-08  6:06         ` Mike Galbraith
2011-12-08  9:41           ` Peter Zijlstra
2011-12-08  9:29         ` Peter Zijlstra
2011-12-08 19:34           ` Suresh Siddha
2011-12-08 21:50             ` Peter Zijlstra
2011-12-08 21:51               ` Peter Zijlstra
2011-12-08 10:02         ` Peter Zijlstra
2011-12-21 11:41           ` tip-bot for Peter Zijlstra [this message]
2011-12-02  1:07 ` [patch v3 6/6] sched: fix the sched group node allocation for SD_OVERLAP domain 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=tip-518cd62341786aa4e3839810832af2fbc0de1ea4@git.kernel.org \
    --to=a.p.zijlstra@chello.nl \
    --cc=chris.mason@oracle.com \
    --cc=dave.kleikamp@oracle.com \
    --cc=efault@gmx.de \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=mingo@redhat.com \
    --cc=suresh.b.siddha@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