LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Gregory Haskins <ghaskins@novell.com>
To: linux-rt-users@vger.kernel.org
Cc: linux-kernel@vger.kernel.org,
	Gregory Haskins <ghaskins@novell.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Dmitry Adamushko <dmitry.adamushko@gmail.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Ingo Molnar <mingo@elte.hu>, Darren Hart <dvhltc@us.ibm.com>
Subject: [PATCH 03/13] RT: Add a per-cpu rt_overload indication
Date: Tue, 23 Oct 2007 12:50:39 -0400	[thread overview]
Message-ID: <20071023165039.5536.54119.stgit@novell1.haskins.net> (raw)
In-Reply-To: <20071023164156.5536.95573.stgit@novell1.haskins.net>

The system currently evaluates all online CPUs whenever one or more enters
an rt_overload condition.  This suffers from scalability limitations as
the # of online CPUs increases.  So we introduce a cpumask to track
exactly which CPUs need RT balancing.

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
CC: Peter W. Morreale <pmorreale@novell.com>
---

 kernel/sched.c |   12 +++++++++---
 1 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index daeb8ed..e22eec7 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -632,6 +632,7 @@ static inline struct rq *this_rq_lock(void)
 
 #if defined(CONFIG_PREEMPT_RT) && defined(CONFIG_SMP)
 static __cacheline_aligned_in_smp atomic_t rt_overload;
+static cpumask_t rto_cpus;
 #endif
 
 static inline void inc_rt_tasks(struct task_struct *p, struct rq *rq)
@@ -640,8 +641,11 @@ static inline void inc_rt_tasks(struct task_struct *p, struct rq *rq)
 	if (rt_task(p)) {
 		rq->rt_nr_running++;
 # ifdef CONFIG_SMP
-		if (rq->rt_nr_running == 2)
+		if (rq->rt_nr_running == 2) {
+			cpu_set(rq->cpu, rto_cpus);
+			smp_wmb();
 			atomic_inc(&rt_overload);
+		}
 # endif
 	}
 #endif
@@ -654,8 +658,10 @@ static inline void dec_rt_tasks(struct task_struct *p, struct rq *rq)
 		WARN_ON(!rq->rt_nr_running);
 		rq->rt_nr_running--;
 # ifdef CONFIG_SMP
-		if (rq->rt_nr_running == 1)
+		if (rq->rt_nr_running == 1) {
 			atomic_dec(&rt_overload);
+			cpu_clear(rq->cpu, rto_cpus);
+		}
 # endif
 	}
 #endif
@@ -1622,7 +1628,7 @@ static void balance_rt_tasks(struct rq *this_rq, int this_cpu)
 	 */
 	next = pick_next_task(this_rq, this_rq->curr);
 
-	for_each_online_cpu(cpu) {
+	for_each_cpu_mask(cpu, rto_cpus) {
 		if (cpu == this_cpu)
 			continue;
 		src_rq = cpu_rq(cpu);


  parent reply	other threads:[~2007-10-23 17:06 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-10-23 16:50 [PATCH 00/13] Balance RT tasks v5 Gregory Haskins
2007-10-23 16:50 ` [PATCH 01/13] RT: push-rt Gregory Haskins
2007-10-23 16:50 ` [PATCH 02/13] RT: Condense the next-task search into one function Gregory Haskins
2007-10-23 16:50 ` Gregory Haskins [this message]
2007-10-23 16:50 ` [PATCH 04/13] RT: Wrap the RQ notion of priority to make it conditional Gregory Haskins
2007-10-23 16:50 ` [PATCH 05/13] RT: Initialize the priority value Gregory Haskins
2007-10-23 16:50 ` [PATCH 06/13] RT: Maintain the highest RQ priority Gregory Haskins
2007-10-23 16:50 ` [PATCH 07/13] RT: Clean up some of the push-rt logic Gregory Haskins
2007-10-23 16:51 ` [PATCH 08/13] RT: Add support for low-priority wake-up to push_rt feature Gregory Haskins
2007-10-23 16:51 ` [PATCH 09/13] RT: Only dirty a cacheline if the priority is actually changing Gregory Haskins
2007-10-23 16:51 ` [PATCH 10/13] RT: Fixes for push-rt patch Gregory Haskins
2007-10-23 16:51 ` [PATCH 11/13] RT: Condense NORMAL and IDLE priorities Gregory Haskins
2007-10-23 16:51 ` [PATCH 12/13] RT: CPU priority management Gregory Haskins
2007-10-23 16:51 ` [PATCH 13/13] RT: Cache cpus_allowed weight for optimizing migration Gregory Haskins
2007-10-24  0:19   ` Ingo Oeser
2007-10-24  3:20     ` Gregory Haskins

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=20071023165039.5536.54119.stgit@novell1.haskins.net \
    --to=ghaskins@novell.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=dmitry.adamushko@gmail.com \
    --cc=dvhltc@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=rostedt@goodmis.org \
    --subject='Re: [PATCH 03/13] RT: Add a per-cpu rt_overload indication' \
    /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

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).