From: Jason Low <jason.low2@hp.com>
To: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>,
"peterz@infradead.org" <peterz@infradead.org>,
"mingo@kernel.org" <mingo@kernel.org>,
Daniel Lezcano <daniel.lezcano@linaro.org>,
"riel@redhat.com" <riel@redhat.com>,
"vincent.guittot@linaro.org" <vincent.guittot@linaro.org>,
"srikar@linux.vnet.ibm.com" <srikar@linux.vnet.ibm.com>,
"pjt@google.com" <pjt@google.com>,
"benh@kernel.crashing.org" <benh@kernel.crashing.org>,
"efault@gmx.de" <efault@gmx.de>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"iamjoonsoo.kim@lge.com" <iamjoonsoo.kim@lge.com>,
"svaidy@linux.vnet.ibm.com" <svaidy@linux.vnet.ibm.com>,
"tim.c.chen@linux.intel.com" <tim.c.chen@linux.intel.com>,
jason.low2@hp.com
Subject: Re: sched: Improve load balancing in the presence of idle CPUs
Date: Tue, 07 Apr 2015 17:07:46 -0700 [thread overview]
Message-ID: <1428451666.2556.84.camel@j-VirtualBox> (raw)
In-Reply-To: <1428449300.2556.79.camel@j-VirtualBox>
On Tue, 2015-04-07 at 16:28 -0700, Jason Low wrote:
> Okay, so perhaps we can also try continuing nohz load balancing if we
> find that there are overloaded CPUs in the system.
Something like the following.
---
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fdae26e..d636bf7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7620,6 +7620,16 @@ out:
}
#ifdef CONFIG_NO_HZ_COMMON
+static inline bool nohz_kick_needed(struct rq *rq);
+
+static inline void pass_nohz_balance(struct rq *this_rq, int this_cpu)
+{
+ clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
+ nohz.next_balance = jiffies;
+ if (nohz_kick_needed(this_rq))
+ nohz_balancer_kick();
+}
+
/*
* In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
* rebalancing for all the cpus for whom scheduler ticks are stopped.
@@ -7631,8 +7641,10 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
int balance_cpu;
if (idle != CPU_IDLE ||
- !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
- goto end;
+ !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu))) {
+ pass_nohz_balance(this_rq, this_cpu);
+ return;
+ }
for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
if (balance_cpu == this_cpu || !idle_cpu(balance_cpu))
@@ -7643,8 +7655,10 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
* work being done for other cpus. Next load
* balancing owner will pick it up.
*/
- if (need_resched())
- break;
+ if (need_resched()) {
+ pass_nohz_balance(this_rq, this_cpu);
+ return;
+ }
rq = cpu_rq(balance_cpu);
@@ -7664,7 +7678,6 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
this_rq->next_balance = rq->next_balance;
}
nohz.next_balance = this_rq->next_balance;
-end:
clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
}
@@ -7687,7 +7700,7 @@ static inline bool nohz_kick_needed(struct rq *rq)
int nr_busy, cpu = rq->cpu;
bool kick = false;
- if (unlikely(rq->idle_balance))
+ if (unlikely(idle_cpu(cpu)))
return false;
/*
@@ -7707,7 +7720,7 @@ static inline bool nohz_kick_needed(struct rq *rq)
if (time_before(now, nohz.next_balance))
return false;
- if (rq->nr_running >= 2)
+ if (rq->nr_running >= 2 || rq->rd->overload)
return true;
rcu_read_lock();
@@ -7757,16 +7770,14 @@ static void run_rebalance_domains(struct softirq_action *h)
enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;
+ rebalance_domains(this_rq, idle);
+
/*
* If this cpu has a pending nohz_balance_kick, then do the
* balancing on behalf of the other idle cpus whose ticks are
- * stopped. Do nohz_idle_balance *before* rebalance_domains to
- * give the idle cpus a chance to load balance. Else we may
- * load balance only within the local sched_domain hierarchy
- * and abort nohz_idle_balance altogether if we pull some load.
+ * stopped.
*/
nohz_idle_balance(this_rq, idle);
- rebalance_domains(this_rq, idle);
}
/*
next prev parent reply other threads:[~2015-04-08 0:07 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-30 18:55 sched: Improve load balancing in the presence of idle CPUs Jason Low
2015-03-31 8:37 ` Preeti U Murthy
2015-03-31 18:54 ` Jason Low
2015-04-01 6:49 ` Preeti U Murthy
2015-04-01 17:04 ` Morten Rasmussen
2015-04-02 3:30 ` Jason Low
2015-04-02 8:49 ` Morten Rasmussen
2015-04-02 5:59 ` Jason Low
2015-04-02 8:42 ` Preeti U Murthy
2015-04-02 9:17 ` Morten Rasmussen
2015-04-02 17:22 ` Jason Low
2015-04-03 22:35 ` Tim Chen
2015-04-07 17:42 ` Jason Low
2015-04-07 19:39 ` Tim Chen
2015-04-07 20:24 ` Jason Low
2015-04-04 9:59 ` Preeti U Murthy
2015-04-07 23:28 ` Jason Low
2015-04-08 0:07 ` Jason Low [this message]
2015-04-08 11:12 ` Srikar Dronamraju
2015-04-08 21:22 ` Jason Low
2015-04-10 8:37 ` Srikar Dronamraju
2015-04-13 18:55 ` Jason Low
2015-04-13 20:54 ` Jason Low
2015-04-09 2:39 ` Jason Low
2015-04-09 7:02 ` Srikar Dronamraju
2015-04-09 22:49 ` Jason Low
2015-04-13 6:16 ` Preeti U Murthy
2015-04-13 22:49 ` Jason Low
2015-04-14 2:59 ` Jason Low
2015-04-02 2:11 ` Jason Low
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=1428451666.2556.84.camel@j-VirtualBox \
--to=jason.low2@hp.com \
--cc=benh@kernel.crashing.org \
--cc=daniel.lezcano@linaro.org \
--cc=efault@gmx.de \
--cc=iamjoonsoo.kim@lge.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=morten.rasmussen@arm.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=preeti@linux.vnet.ibm.com \
--cc=riel@redhat.com \
--cc=srikar@linux.vnet.ibm.com \
--cc=svaidy@linux.vnet.ibm.com \
--cc=tim.c.chen@linux.intel.com \
--cc=vincent.guittot@linaro.org \
/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).