lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230613042422.5344-8-ricardo.neri-calderon@linux.intel.com>
Date:   Mon, 12 Jun 2023 21:24:05 -0700
From:   Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
To:     "Peter Zijlstra (Intel)" <peterz@...radead.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Vincent Guittot <vincent.guittot@...aro.org>
Cc:     Ricardo Neri <ricardo.neri@...el.com>,
        "Ravi V. Shankar" <ravi.v.shankar@...el.com>,
        Ben Segall <bsegall@...gle.com>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Len Brown <len.brown@...el.com>, Mel Gorman <mgorman@...e.de>,
        "Rafael J. Wysocki" <rafael.j.wysocki@...el.com>,
        Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Valentin Schneider <vschneid@...hat.com>,
        Lukasz Luba <lukasz.luba@....com>,
        Ionela Voinescu <ionela.voinescu@....com>,
        Zhao Liu <zhao1.liu@...el.com>,
        "Yuan, Perry" <Perry.Yuan@....com>, x86@...nel.org,
        "Joel Fernandes (Google)" <joel@...lfernandes.org>,
        linux-kernel@...r.kernel.org, linux-pm@...r.kernel.org,
        Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>,
        "Tim C . Chen" <tim.c.chen@...el.com>,
        Zhao Liu <zhao1.liu@...ux.intel.com>
Subject: [PATCH v4 07/24] sched/fair: Compute IPC class scores for load balancing

When using IPCC scores to break ties between two scheduling groups, it is
necessary to consider both the current score and the score that would
result after load balancing.

Compute the combined IPC class score of a scheduling group and the local
scheduling group. Compute both the current score and the prospective score.

Collect IPCC statistics only for asym_packing and fully_busy scheduling
groups. These are the only cases that use IPCC scores.

These IPCC statistics are used during idle load balancing. The candidate
scheduling group will have one fewer busy CPU after load balancing. This
observation is important for cores with SMT support.

The IPCC score of scheduling groups composed of SMT siblings needs to
consider that the siblings share CPU resources. When computing the total
IPCC score of the scheduling group, divide the score of each sibling by
the number of busy siblings.

Cc: Ben Segall <bsegall@...gle.com>
Cc: Daniel Bristot de Oliveira <bristot@...hat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@....com>
Cc: Ionela Voinescu <ionela.voinescu@....com>
Cc: Joel Fernandes (Google) <joel@...lfernandes.org>
Cc: Len Brown <len.brown@...el.com>
Cc: Lukasz Luba <lukasz.luba@....com>
Cc: Mel Gorman <mgorman@...e.de>
Cc: Perry Yuan <Perry.Yuan@....com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
Cc: Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Tim C. Chen <tim.c.chen@...el.com>
Cc: Valentin Schneider <vschneid@...hat.com>
Cc: Zhao Liu <zhao1.liu@...ux.intel.com>
Cc: x86@...nel.org
Cc: linux-pm@...r.kernel.org
Cc: linux-kernel@...r.kernel.org
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
---
Changes since v3:
 * None

Changes since v2:
 * Also collect IPCC stats for fully_busy sched groups.
 * Restrict use of IPCC stats to SD_ASYM_PACKING. (Ionela)
 * Handle errors of arch_get_ipcc_score(). (Ionela)

Changes since v1:
 * Implemented cleanups and reworks from PeterZ. I took all his
   suggestions, except the computation of the  IPC score before and after
   load balancing. We are computing not the average score, but the *total*.
 * Check for the SD_SHARE_CPUCAPACITY to compute the throughput of the SMT
   siblings of a physical core.
 * Used the new interface names.
 * Reworded commit message for clarity.
---
 kernel/sched/fair.c | 68 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c0cab5e501b6..a51c65c9335f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9114,6 +9114,8 @@ struct sg_lb_stats {
 	unsigned long min_score; /* Min(score(rq->curr->ipcc)) */
 	unsigned short min_ipcc; /* Class of the task with the minimum IPCC score in the rq */
 	unsigned long sum_score; /* Sum(score(rq->curr->ipcc)) */
+	long ipcc_score_after; /* Prospective IPCC score after load balancing */
+	unsigned long ipcc_score_before; /* IPCC score before load balancing */
 #endif
 };
 
@@ -9452,6 +9454,62 @@ static void update_sg_lb_ipcc_stats(int dst_cpu, struct sg_lb_stats *sgs,
 	}
 }
 
+static void update_sg_lb_stats_scores(struct sg_lb_stats *sgs,
+				      struct sched_group *sg,
+				      struct lb_env *env)
+{
+	unsigned long score_on_dst_cpu, before;
+	int busy_cpus;
+	long after;
+
+	if (!sched_ipcc_enabled())
+		return;
+
+	/*
+	 * IPCC scores are only useful during idle load balancing. For now,
+	 * only asym_packing uses IPCC scores.
+	 */
+	if (!(env->sd->flags & SD_ASYM_PACKING) ||
+	    env->idle == CPU_NOT_IDLE)
+		return;
+
+	/*
+	 * IPCC scores are used to break ties only between these types of
+	 * groups.
+	 */
+	if (sgs->group_type != group_fully_busy &&
+	    sgs->group_type != group_asym_packing)
+		return;
+
+	busy_cpus = sgs->group_weight - sgs->idle_cpus;
+
+	/* No busy CPUs in the group. No tasks to move. */
+	if (!busy_cpus)
+		return;
+
+	score_on_dst_cpu = arch_get_ipcc_score(sgs->min_ipcc, env->dst_cpu);
+
+	/*
+	 * Do not use IPC scores. sgs::ipcc_score_{after, before} will be zero
+	 * and not used.
+	 */
+	if (IS_ERR_VALUE(score_on_dst_cpu))
+		return;
+
+	before = sgs->sum_score;
+	after = before - sgs->min_score;
+
+	/* SMT siblings share throughput. */
+	if (busy_cpus > 1 && sg->flags & SD_SHARE_CPUCAPACITY) {
+		before /= busy_cpus;
+		/* One sibling will become idle after load balance. */
+		after /= busy_cpus - 1;
+	}
+
+	sgs->ipcc_score_after = after + score_on_dst_cpu;
+	sgs->ipcc_score_before = before;
+}
+
 #else /* CONFIG_IPC_CLASSES */
 static void update_sg_lb_ipcc_stats(int dst_cpu, struct sg_lb_stats *sgs,
 				    struct rq *rq)
@@ -9461,6 +9519,13 @@ static void update_sg_lb_ipcc_stats(int dst_cpu, struct sg_lb_stats *sgs,
 static void init_rq_ipcc_stats(struct sg_lb_stats *sgs)
 {
 }
+
+static void update_sg_lb_stats_scores(struct sg_lb_stats *sgs,
+				      struct sched_group *sg,
+				      struct lb_env *env)
+{
+}
+
 #endif /* CONFIG_IPC_CLASSES */
 
 /**
@@ -9620,6 +9685,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 	sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs);
 
+	if (!local_group)
+		update_sg_lb_stats_scores(sgs, group, env);
+
 	/* Computing avg_load makes sense only when group is overloaded */
 	if (sgs->group_type == group_overloaded)
 		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
-- 
2.25.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ