From mboxrd@z Thu Jan 1 00:00:00 1970 From: Claudio Scordino Subject: [PATCH v3] cpufreq: schedutil: rate limits for SCHED_DEADLINE Date: Thu, 8 Mar 2018 11:29:10 +0100 Message-ID: <1520504950-8544-1-git-send-email-claudio@evidence.eu.com> Return-path: Sender: linux-kernel-owner@vger.kernel.org To: Peter Zijlstra , "Rafael J . Wysocki" Cc: Claudio Scordino , Ingo Molnar , Patrick Bellasi , Dietmar Eggemann , Morten Rasmussen , Juri Lelli , Viresh Kumar , Vincent Guittot , Todd Kjos , Joel Fernandes , linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org List-Id: linux-pm@vger.kernel.org When the SCHED_DEADLINE scheduling class increases the CPU utilization, we should not wait for the rate limit, otherwise we may miss some deadline. Tests using rt-app on Exynos5422 with up to 10 SCHED_DEADLINE tasks have shown reductions of even 10% of deadline misses with a negligible increase of energy consumption (measured through Baylibre Cape). Signed-off-by: Claudio Scordino CC: Ingo Molnar CC: Patrick Bellasi CC: Dietmar Eggemann CC: Morten Rasmussen CC: Juri Lelli CC: Viresh Kumar CC: Vincent Guittot CC: Todd Kjos CC: Joel Fernandes CC: linux-pm@vger.kernel.org CC: linux-kernel@vger.kernel.org --- Changes from v2: - Rate limit ignored also in case of "fast switch" - Specific routine added --- Changes from v1: - Logic moved from sugov_should_update_freq() to sugov_update_single()/_shared() to not duplicate data structures - Rate limit not ignored in case of "fast switch" --- kernel/sched/cpufreq_schedutil.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 7936f54..13f9cce 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -260,6 +260,17 @@ static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } #endif /* CONFIG_NO_HZ_COMMON */ +/* + * Make sugov_should_update_freq() ignore the rate limit when DL + * has increased the utilization. + */ +static inline +void set_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy) +{ + if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl) + sg_policy->need_freq_update = true; +} + static void sugov_update_single(struct update_util_data *hook, u64 time, unsigned int flags) { @@ -273,6 +284,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, sugov_set_iowait_boost(sg_cpu, time); sg_cpu->last_update = time; + set_dl_rate_limit(sg_cpu, sg_policy); + if (!sugov_should_update_freq(sg_policy, time)) return; @@ -354,6 +367,8 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, raw_spin_lock(&sg_policy->update_lock); + set_dl_rate_limit(sg_cpu, sg_policy); + sugov_get_util(sg_cpu); sg_cpu->flags = flags; -- 2.7.4