mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
To: "Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>
Cc: Ricardo Neri <ricardo.neri@intel.com>,
	"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
	Ben Segall <bsegall@google.com>,
	Daniel Bristot de Oliveira <bristot@redhat.com>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Len Brown <len.brown@intel.com>, Mel Gorman <mgorman@suse.de>,
	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	Valentin Schneider <vschneid@redhat.com>,
	Lukasz Luba <lukasz.luba@arm.com>,
	Ionela Voinescu <ionela.voinescu@arm.com>,
	Zhao Liu <zhao1.liu@intel.com>,
	"Yuan, Perry" <Perry.Yuan@amd.com>,
	x86@kernel.org,
	"Joel Fernandes (Google)" <joel@joelfernandes.org>,
	linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
	Ricardo Neri <ricardo.neri-calderon@linux.intel.com>,
	"Tim C . Chen" <tim.c.chen@intel.com>,
	Zhao Liu <zhao1.liu@linux.intel.com>
Subject: [PATCH v4 20/24] sched/fair: Introduce sched_smt_siblings_idle()
Date: Mon, 12 Jun 2023 21:24:18 -0700	[thread overview]
Message-ID: <20230613042422.5344-21-ricardo.neri-calderon@linux.intel.com> (raw)
In-Reply-To: <20230613042422.5344-1-ricardo.neri-calderon@linux.intel.com>

X86 needs to know the idle state of the SMT siblings of a CPU to improve
the accuracy of IPCC classification. X86 implements support for IPC classes
in the thermal HFI driver.

Rename is_core_idle() as sched_smt_siblings_idle() and make it available
outside the scheduler code.

Cc: Ben Segall <bsegall@google.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Perry Yuan <Perry.Yuan@amd.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tim C. Chen <tim.c.chen@intel.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Zhao Liu <zhao1.liu@linux.intel.com>
Cc: x86@kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
---
is_core_idle() is no longer an inline function after this patch. To rule
out performance degradation, I compared the execution time of the inline
and non-inline versions on a 4-socket Cascade Lake system using the NUMA
stressor of stress-ng.

I used this test command:

        $ stress-ng --numa 1500 -t 10m

During the test, is_core_idle() was called ~200,000 times. To measure the
execution time, I recorded the value of the TSC counter before and after
calling is_core_idle() and calculated the difference.
value.

I arbitrarily removed outliers (defined as any delta larger than 5000
counts). This required removing ~40 samples.

The table below summarizes the difference in execution time. All values
are expressed in TSC counts, except for the standard deviation, expressed
as a percentage of the average.

                              Average  Median  Std(%) Mode
        TSCdelta inline        668.76     626   67.24   42
        TSCdelta non-inline    677.64     624   67.67   46

The metrics show that both the inline and non-inline versions exhibit
similar performance characteristics.
---
Changes since v3:
 * None

Changes since v2:
 * Brought back this previously dropped patch.
 * Profiled inline vs non-inline is_core_idle(). I found not major penalty.
 * Merged is_core_idle() and sched_smt_siblings_idle() into a single
   function. (Dietmar)

Changes since v1:
 * Dropped this patch.
---
 include/linux/sched.h |  2 ++
 kernel/sched/fair.c   | 13 ++++++++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 719147460ca8..986344ebf2f6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2461,4 +2461,6 @@ static inline void sched_core_fork(struct task_struct *p) { }
 
 extern void sched_set_stop_task(int cpu, struct task_struct *stop);
 
+extern bool sched_smt_siblings_idle(int cpu);
+
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index da3e009eef42..a52589a6c561 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1064,7 +1064,14 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
-static inline bool is_core_idle(int cpu)
+/**
+ * sched_smt_siblings_idle - Check whether SMT siblings of a CPU are idle
+ * @cpu:	The CPU to check
+ *
+ * Returns true if all the SMT siblings of @cpu are idle or @cpu does not have
+ * SMT siblings. The idle state of @cpu is not considered.
+ */
+bool sched_smt_siblings_idle(int cpu)
 {
 #ifdef CONFIG_SCHED_SMT
 	int sibling;
@@ -1767,7 +1774,7 @@ static inline int numa_idle_core(int idle_core, int cpu)
 	 * Prefer cores instead of packing HT siblings
 	 * and triggering future load balancing.
 	 */
-	if (is_core_idle(cpu))
+	if (sched_smt_siblings_idle(cpu))
 		idle_core = cpu;
 
 	return idle_core;
@@ -9652,7 +9659,7 @@ static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
 	if (!sched_smt_active())
 		return true;
 
-	return sd->flags & SD_SHARE_CPUCAPACITY || is_core_idle(cpu);
+	return sd->flags & SD_SHARE_CPUCAPACITY || sched_smt_siblings_idle(cpu);
 }
 
 /**
-- 
2.25.1


  parent reply	other threads:[~2023-06-13  4:25 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-06-13  4:23 [PATCH v4 00/24] sched: Introduce classes of tasks for load balance Ricardo Neri
2023-06-13  4:23 ` [PATCH v4 01/24] sched/task_struct: Introduce IPC classes of tasks Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 02/24] sched: Add interfaces for IPC classes Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 03/24] sched/core: Initialize the IPC class of a new task Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 04/24] sched/core: Add user_tick as argument to scheduler_tick() Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 05/24] sched/core: Update the IPC class of the current task Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 06/24] sched/fair: Collect load-balancing stats for IPC classes Ricardo Neri
2023-06-14  0:29   ` Ricardo Neri
2023-06-22  9:01   ` Ionela Voinescu
2023-06-24  0:01     ` Ricardo Neri
2023-06-26 19:52       ` Tim Chen
2023-07-06 23:40         ` Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 07/24] sched/fair: Compute IPC class scores for load balancing Ricardo Neri
2023-06-22  9:02   ` Ionela Voinescu
2023-06-25 20:11     ` Ricardo Neri
2023-06-26 21:01       ` Tim Chen
2023-07-06 23:48         ` Ricardo Neri
2023-06-27 15:19       ` Ionela Voinescu
2023-06-13  4:24 ` [PATCH v4 08/24] sched/fair: Use IPCC stats to break ties between asym_packing sched groups Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 09/24] sched/fair: Use IPCC stats to break ties between fully_busy SMT groups Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 10/24] sched/fair: Use IPCC scores to select a busiest runqueue Ricardo Neri
2023-06-22  9:03   ` Ionela Voinescu
2023-06-24  0:25     ` Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 11/24] thermal: intel: hfi: Introduce Intel Thread Director classes Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 12/24] x86/cpufeatures: Add the Intel Thread Director feature definitions Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 13/24] x86/sched: Update the IPC class of the current task Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 14/24] thermal: intel: hfi: Store per-CPU IPCC scores Ricardo Neri
2023-06-29 18:53   ` Rafael J. Wysocki
2023-07-06 23:23     ` Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 15/24] thermal: intel: hfi: Report the IPC class score of a CPU Ricardo Neri
2023-06-29 18:56   ` Rafael J. Wysocki
2023-07-06 23:10     ` Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 16/24] thermal: intel: hfi: Define a default class for unclassified tasks Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 17/24] thermal: intel: hfi: Enable the Intel Thread Director Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 18/24] sched/task_struct: Add helpers for IPC classification Ricardo Neri
2023-06-22 10:20   ` Ionela Voinescu
2023-06-25 20:23     ` Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 19/24] sched/core: Initialize helpers of task classification Ricardo Neri
2023-06-13  4:24 ` Ricardo Neri [this message]
2023-06-13  4:24 ` [PATCH v4 21/24] x86/sched/ipcc: Implement model-specific checks for " Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 22/24] x86/cpufeatures: Add feature bit for HRESET Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 23/24] x86/hreset: Configure history reset Ricardo Neri
2023-06-13  4:24 ` [PATCH v4 24/24] x86/process: Reset hardware history in context switch Ricardo Neri

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=20230613042422.5344-21-ricardo.neri-calderon@linux.intel.com \
    --to=ricardo.neri-calderon@linux.intel.com \
    --cc=Perry.Yuan@amd.com \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=ionela.voinescu@arm.com \
    --cc=joel@joelfernandes.org \
    --cc=juri.lelli@redhat.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=lukasz.luba@arm.com \
    --cc=mgorman@suse.de \
    --cc=peterz@infradead.org \
    --cc=rafael.j.wysocki@intel.com \
    --cc=ravi.v.shankar@intel.com \
    --cc=ricardo.neri@intel.com \
    --cc=rostedt@goodmis.org \
    --cc=srinivas.pandruvada@linux.intel.com \
    --cc=tim.c.chen@intel.com \
    --cc=tim.c.chen@linux.intel.com \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=x86@kernel.org \
    --cc=zhao1.liu@intel.com \
    --cc=zhao1.liu@linux.intel.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

all inboxes | Powered by JetHome®