[PATCH v2] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

From: Joel Fernandes <joelaf@google.com>
To: linux-kernel@vger.kernel.org
Cc: Joel Fernandes <joelaf@google.com>,
	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
	Len Brown <lenb@kernel.org>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@arm.com>,
	Patrick Bellasi <patrick.bellasi@arm.com>,
	Chris Redpath <Chris.Redpath@arm.com>,
	Steve Muckle <smuckle@google.com>,
	Brendan Jackman <brendan.jackman@arm.com>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Morten Ramussen <morten.rasmussen@arm.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Steven Rostedt <rostedt@goodmis.org>,
	Saravana Kannan <skannan@quicinc.com>,
	Vikram Mulukutla <markivx@codeaurora.org>,
	Rohit Jain <rohit.k.jain@oracle.com>,
	Atish Patra <atish.patra@oracle.com>,
	EAS Dev <eas-dev@lists.linaro.org>,
	Android Kernel <kernel-team@android.com>
Subject: [PATCH v2] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake
Date: Thu, 14 Dec 2017 13:21:58 -0800	[thread overview]
Message-ID: <20171214212158.188190-1-joelaf@google.com> (raw)

capacity_spare_wake in the slow path influences choice of idlest groups,
as we search for groups with maximum spare capacity. In scenarios where
RT pressure is high, a sub optimal group can be chosen and hurt
performance of the task being woken up.

This is fixed in this patch by using capacity_of instead of
capacity_orig_of in capacity_spare_wake. Only change since v1 is change
in commit message.

Tests results from improvements with this change are below. More tests
were also done by myself and Matt Fleming to ensure no degradation in
different benchmarks.

1) Rohit ran barrier.c test (details below) with following improvements:
------------------------------------------------------------------------
This was Rohit's original use case for a patch he posted at [1] however
from his recent tests he showed my patch can replace his slow path
changes [1] and there's no need to selectively scan/skip CPUs in
find_idlest_group_cpu in the slow path to get the improvement he sees.

barrier.c (open_mp code) as a micro-benchmark. It does a number of
iterations and barrier sync at the end of each for loop.

Here barrier,c is running in along with ping on CPU 0 and 1 as:
'ping -l 10000 -q -s 10 -f hostX'

barrier.c can be found at:
http://www.spinics.net/lists/kernel/msg2506955.html

Following are the results for the iterations per second with this
micro-benchmark (higher is better), on a 44 core, 2 socket 88 Threads
Intel x86 machine:
+--------+------------------+---------------------------+
|Threads | Without patch    | With patch                |
|        |                  |                           |
+--------+--------+---------+-----------------+---------+
|        | Mean   | Std Dev | Mean            | Std Dev |
+--------+--------+---------+-----------------+---------+
|1       | 539.36 | 60.16   | 572.54 (+6.15%) | 40.95   |
|2       | 481.01 | 19.32   | 530.64 (+10.32%)| 56.16   |
|4       | 474.78 | 22.28   | 479.46 (+0.99%) | 18.89   |
|8       | 450.06 | 24.91   | 447.82 (-0.50%) | 12.36   |
|16      | 436.99 | 22.57   | 441.88 (+1.12%) | 7.39    |
|32      | 388.28 | 55.59   | 429.4  (+10.59%)| 31.14   |
|64      | 314.62 | 6.33    | 311.81 (-0.89%) | 11.99   |
+--------+--------+---------+-----------------+---------+

2) ping+hackbench test on bare-metal sever (by Rohit)
-----------------------------------------------------
Here hackbench is running in threaded mode along
with, running ping on CPU 0 and 1 as:
'ping -l 10000 -q -s 10 -f hostX'

This test is running on 2 socket, 20 core and 40 threads Intel x86
machine:
Number of loops is 10000 and runtime is in seconds (Lower is better).

+--------------+-----------------+--------------------------+
|Task Groups   | Without patch   |  With patch              |
|              +-------+---------+----------------+---------+
|(Groups of 40)| Mean  | Std Dev |  Mean          | Std Dev |
+--------------+-------+---------+----------------+---------+
|1             | 0.851 | 0.007   |  0.828 (+2.77%)| 0.032   |
|2             | 1.083 | 0.203   |  1.087 (-0.37%)| 0.246   |
|4             | 1.601 | 0.051   |  1.611 (-0.62%)| 0.055   |
|8             | 2.837 | 0.060   |  2.827 (+0.35%)| 0.031   |
|16            | 5.139 | 0.133   |  5.107 (+0.63%)| 0.085   |
|25            | 7.569 | 0.142   |  7.503 (+0.88%)| 0.143   |
+--------------+-------+---------+----------------+---------+

[1] https://patchwork.kernel.org/patch/9991635/

Matt Fleming also ran several different hackbench tests and cyclic test
to santiy-check that the patch doesn't harm other usecases.

Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Matt Fleming <matt@codeblueprint.co.uk>
Tested-by: Rohit Jain <rohit.k.jain@oracle.com>
Signed-off-by: Joel Fernandes <joelaf@google.com>
---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0989676c50e9..832f2ea069ef 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5726,7 +5726,7 @@ static int cpu_util_wake(int cpu, struct task_struct *p);
 
 static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
 {
-	return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
+	return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
 }
 
 /*
-- 
2.15.1.504.g5279b80103-goog
