From patchwork Fri Oct 19 16:17:51 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Vincent Guittot X-Patchwork-Id: 149293 Delivered-To: patch@linaro.org Received: by 2002:a2e:8595:0:0:0:0:0 with SMTP id b21-v6csp3502527lji; Fri, 19 Oct 2018 09:18:04 -0700 (PDT) X-Google-Smtp-Source: ACcGV62E6yzPh7XZPfVqA++NfaCbgAVdujvFtjl/s54FJpV/nhXx2mzfbqc43Qq3OTm5H4ci3/jC X-Received: by 2002:a17:902:930b:: with SMTP id bc11-v6mr35147521plb.101.1539965884775; Fri, 19 Oct 2018 09:18:04 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1539965884; cv=none; d=google.com; s=arc-20160816; b=kyQ6qSE+zw3qD6pS8B6qyUF8MEPzxSBrz46pMiysMaMsiYW4vOlqcZbtn0tbhcDIVt l1/d/Ep9kEv23DSXdYixM8HRg3MT8+GK8AszHd+Kw12FtBZNJj7hDBtNmNIhgdJB24AB vfV/Pbu6aHD9O4ZGHYbyziPXBNWlP/MAnOda/Bm2+8fSw0cXwUtKjTjZlbYYfVZ8Xhmi ho6YYGMgpqKXMOa5lM9zG+ij9c7Rv7eIILU5X/YHvYRa25xx8GzmI1/7FaGiOBrSBbpM EUHIpEX0QImU/gAnFeJTuxj+2ksKhx7aWNcNA1ok+0MQW43PZAev3HTXPIYV4RiiKHR4 m+wg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:references:in-reply-to:message-id:date :subject:cc:to:from:dkim-signature; bh=IvKJhK6xqvP8AgN5D//bnAFpGTeXhswS3ahpoKh9qh8=; b=Us9PdOEy5nB5m6FquPiqs6EhzFHYjiDyrbA5TFnq2J2z9TAT6XHkuB+NvGmdlwSP7c c13ub4e8LOxErzf0r3n23ZdCOaZYxRMzX3qgqZew91r4AMDLKxvS3AH3IIKMR8xUBhje YIhD4zcXtx44AmMbMLi5SKeAicqqEXXhvT+2XfCtWHx3QIpa03hgDSf34Ln2TvZUe7QV 2mFFldAEd+rVUghV+dk3aNWDugGeTK2mnmVAMQQx9CZYiYuXub3Rd42PcjicTP6MkWXd XTJUKX/nrK5WijO6wglfI/gXyH3OTlK8UaIxzSfDNs+qJzsdT1OghL4i+KyxWC7G3lIF 6quQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=MuYg7Kcf; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id be12-v6si24041339plb.347.2018.10.19.09.18.04; Fri, 19 Oct 2018 09:18:04 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=MuYg7Kcf; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727975AbeJTAYt (ORCPT + 32 others); Fri, 19 Oct 2018 20:24:49 -0400 Received: from mail-wr1-f67.google.com ([209.85.221.67]:45198 "EHLO mail-wr1-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727219AbeJTAYt (ORCPT ); Fri, 19 Oct 2018 20:24:49 -0400 Received: by mail-wr1-f67.google.com with SMTP id f17-v6so6270577wrs.12 for ; Fri, 19 Oct 2018 09:18:01 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=IvKJhK6xqvP8AgN5D//bnAFpGTeXhswS3ahpoKh9qh8=; b=MuYg7KcfdKvUCtqSrH117kNvIw17GQVklbSKPDWQDDgl8E76JHBiywQOTjwfNWoWFa gbbOeRFT4tnJLYIoogE5x02Hm79ziJjR3weHTK6+x2L0n936QB4AdGHK0SaS04k+1Hnc cS4hll49DQ8yisgFBFLy+pGuiQZx0APim2t1M= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=IvKJhK6xqvP8AgN5D//bnAFpGTeXhswS3ahpoKh9qh8=; b=Jj6Gq9KYBy8vXCDHuSskDmc3CFRrkHnKcoS80jZ8Qyj7+WFbg6kCjEAxDBapILOP04 5KTOMn/XYtGQ0CYCvR2KorlNNpr0FcfCpJsFJlIoLKb6xJ5U0Jmndg5wBCfqz5DmZjb1 gpRu5tpQXS7CbErrLy2mcTxUMb8pa6kf6F4Aomm4VPgDfFIz5HDd8LAbc2dByq1hvFVU useCLptx0LtPZEFqD4MKEi43zdXifhcbhE/yEaD7ITyFi8cvPjBJioajT/6wpSzInvMF P8RLRzon/6ItM7chNqtSwm4lB4ennHRjQxs21S3ZIedPiv4PxyMFgLKdE0JL1554rq5B xhaQ== X-Gm-Message-State: ABuFfoicnPhNqxhspawaskWAHCATIyiXIUYGre5UA9lsAQ/AADfCtYd5 EYHh03Mh2tGtMptfgjUt/61PBA== X-Received: by 2002:adf:9503:: with SMTP id 3-v6mr36996389wrs.91.1539965879981; Fri, 19 Oct 2018 09:17:59 -0700 (PDT) Received: from localhost.localdomain ([2a01:e0a:f:6020:9024:3180:921a:1e27]) by smtp.gmail.com with ESMTPSA id n11-v6sm17009460wrx.17.2018.10.19.09.17.58 (version=TLS1_2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Fri, 19 Oct 2018 09:17:58 -0700 (PDT) From: Vincent Guittot To: peterz@infradead.org, mingo@kernel.org, linux-kernel@vger.kernel.org Cc: rjw@rjwysocki.net, dietmar.eggemann@arm.com, Morten.Rasmussen@arm.com, patrick.bellasi@arm.com, pjt@google.com, bsegall@google.com, thara.gopinath@linaro.org, Vincent Guittot Subject: [PATCH v4 2/2] sched/fair: update scale invariance of PELT Date: Fri, 19 Oct 2018 18:17:51 +0200 Message-Id: <1539965871-22410-3-git-send-email-vincent.guittot@linaro.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1539965871-22410-1-git-send-email-vincent.guittot@linaro.org> References: <1539965871-22410-1-git-send-email-vincent.guittot@linaro.org> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The current implementation of load tracking invariance scales the contribution with current frequency and uarch performance (only for utilization) of the CPU. One main result of this formula is that the figures are capped by current capacity of CPU. Another one is that the load_avg is not invariant because not scaled with uarch. The util_avg of a periodic task that runs r time slots every p time slots varies in the range : U * (1-y^r)/(1-y^p) * y^i < Utilization < U * (1-y^r)/(1-y^p) with U is the max util_avg value = SCHED_CAPACITY_SCALE At a lower capacity, the range becomes: U * C * (1-y^r')/(1-y^p) * y^i' < Utilization < U * C * (1-y^r')/(1-y^p) with C reflecting the compute capacity ratio between current capacity and max capacity. so C tries to compensate changes in (1-y^r') but it can't be accurate. Instead of scaling the contribution value of PELT algo, we should scale the running time. The PELT signal aims to track the amount of computation of tasks and/or rq so it seems more correct to scale the running time to reflect the effective amount of computation done since the last update. In order to be fully invariant, we need to apply the same amount of running time and idle time whatever the current capacity. Because running at lower capacity implies that the task will run longer, we have to ensure that the same amount of idle time will be apply when system becomes idle and no idle time has been "stolen". But reaching the maximum utilization value (SCHED_CAPACITY_SCALE) means that the task is seen as an always-running task whatever the capacity of the CPU (even at max compute capacity). In this case, we can discard this "stolen" idle times which becomes meaningless. In order to achieve this time scaling, a new clock_pelt is created per rq. The increase of this clock scales with current capacity when something is running on rq and synchronizes with clock_task when rq is idle. With this mecanism, we ensure the same running and idle time whatever the current capacity. This also enables to simplify the pelt algorithm by removing all references of uarch and frequency and applying the same contribution to utilization and loads. Furthermore, the scaling is done only once per update of clock (update_rq_clock_task()) instead of during each update of sched_entities and cfs/rt/dl_rq of the rq like the current implementation. This is interesting when cgroup are involved as shown in the results below: On a hikey (octo ARM platform). Performance cpufreq governor and only shallowest c-state to remove variance generated by those power features so we only track the impact of pelt algo. each test runs 16 times ./perf bench sched pipe (higher is better) kernel tip/sched/core + patch ops/seconds ops/seconds diff cgroup root 59648(+/- 0.13%) 59785(+/- 0.24%) +0.23% level1 55570(+/- 0.21%) 56003(+/- 0.24%) +0.78% level2 52100(+/- 0.20%) 52788(+/- 0.22%) +1.32% hackbench -l 1000 (lower is better) kernel tip/sched/core + patch duration(sec) duration(sec) diff cgroup root 4.472(+/- 1.86%) 4.346(+/- 2.74%) -2.80% level1 5.039(+/- 11.05%) 4.662(+/- 7.57%) -7.47% level2 5.195(+/- 10.66%) 4.877(+/- 8.90%) -6.12% The responsivness of PELT is improved when CPU is not running at max capacity with this new algorithm. I have put below some examples of duration to reach some typical load values according to the capacity of the CPU with current implementation and with this patch. Util (%) max capacity half capacity(mainline) half capacity(w/ patch) 972 (95%) 138ms not reachable 276ms 486 (47.5%) 30ms 138ms 60ms 256 (25%) 13ms 32ms 26ms On my hikey (octo ARM platform) with schedutil governor, the time to reach max OPP when starting from a null utilization, decreases from 223ms with current scale invariance down to 121ms with the new algorithm. For this test, I have enable arch_scale_freq for arm64. Signed-off-by: Vincent Guittot --- kernel/sched/core.c | 2 +- kernel/sched/deadline.c | 6 ++-- kernel/sched/fair.c | 16 ++++----- kernel/sched/pelt.c | 88 ++++++++++++++++++++++++++++++++++++++++++++----- kernel/sched/pelt.h | 27 +++++++++++++++ kernel/sched/rt.c | 6 ++-- kernel/sched/sched.h | 2 ++ 7 files changed, 123 insertions(+), 24 deletions(-) -- 2.7.4 diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 625bc98..84e5c48 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -181,6 +181,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) update_irq_load_avg(rq, irq_delta + steal); #endif + update_rq_clock_pelt(rq, delta); } void update_rq_clock(struct rq *rq) @@ -205,7 +206,6 @@ void update_rq_clock(struct rq *rq) update_rq_clock_task(rq, delta); } - #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 997ea7b..68cb4dc 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1761,7 +1761,7 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) deadline_queue_push_tasks(rq); if (rq->curr->sched_class != &dl_sched_class) - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); return p; } @@ -1770,7 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1787,7 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) { update_curr_dl(rq); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); /* * Even when we have runtime, update_curr_dl() might have resulted in us * not being the leftmost task anymore. In that case NEED_RESCHED will diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0969ce3..5677254 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -764,7 +764,7 @@ void post_init_entity_util_avg(struct sched_entity *se) * such that the next switched_to_fair() has the * expected state. */ - se->avg.last_update_time = cfs_rq_clock_task(cfs_rq); + se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq); return; } } @@ -3400,7 +3400,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s /* Update task and its cfs_rq load average */ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { - u64 now = cfs_rq_clock_task(cfs_rq); + u64 now = cfs_rq_clock_pelt(cfs_rq); struct rq *rq = rq_of(cfs_rq); int cpu = cpu_of(rq); int decayed; @@ -7285,7 +7285,7 @@ static void update_blocked_averages(int cpu) if (throttled_hierarchy(cfs_rq)) continue; - if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq)) + if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) update_tg_load_avg(cfs_rq, 0); /* Propagate pending load changes to the parent, if any: */ @@ -7306,8 +7306,8 @@ static void update_blocked_averages(int cpu) } curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); /* Don't need periodic decay once load/util_avg are null */ if (others_have_blocked(rq)) @@ -7377,11 +7377,11 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index 35475c0..48f4f07 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -30,6 +30,72 @@ #include "pelt.h" /* + * The clock_pelt scales the time to reflect the effective amount of + * computation done during the running delta time but then sync back to + * clock_task when rq is idle. + * + * + * absolute time | 1| 2| 3| 4| 5| 6| 7| 8| 9|10|11|12|13|14|15|16 + * @ max capacity ------******---------------******--------------- + * @ half capacity ------************---------************--------- + * clock pelt | 1| 2| 3| 4| 7| 8| 9| 10| 11|14|15|16 + * + */ +void update_rq_clock_pelt(struct rq *rq, s64 delta) +{ + + if (is_idle_task(rq->curr)) { + u32 divider = (LOAD_AVG_MAX - 1024 + rq->cfs.avg.period_contrib) << SCHED_CAPACITY_SHIFT; + u32 overload = rq->cfs.avg.util_sum + LOAD_AVG_MAX; + overload += rq->avg_rt.util_sum; + overload += rq->avg_dl.util_sum; + + /* + * Reflecting some stolen time makes sense only if the idle + * phase would be present at max capacity. As soon as the + * utilization of a rq has reached the maximum value, it is + * considered as an always runnnig rq without idle time to + * steal. This potential idle time is considered as lost in + * this case. We keep track of this lost idle time compare to + * rq's clock_task. + */ + if (overload >= divider) + rq->lost_idle_time += rq_clock_task(rq) - rq->clock_pelt; + + + /* The rq is idle, we can sync to clock_task */ + rq->clock_pelt = rq_clock_task(rq); + + + } else { + /* + * When a rq runs at a lower compute capacity, it will need + * more time to do the same amount of work than at max + * capacity: either because it takes more time to compute the + * same amount of work or because taking more time means + * sharing more often the CPU between entities. + * In order to be invariant, we scale the delta to reflect how + * much work has been really done. + * Running at lower capacity also means running longer to do + * the same amount of work and this results in stealing some + * idle time that will disturb the load signal compared to + * max capacity; This stolen idle time will be automaticcally + * reflected when the rq will be idle and the clock will be + * synced with rq_clock_task. + */ + + /* + * scale the elapsed time to reflect the real amount of + * computation + */ + delta = cap_scale(delta, arch_scale_freq_capacity(cpu_of(rq))); + delta = cap_scale(delta, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + + rq->clock_pelt += delta; + } +} + +/* * Approximate: * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) */ @@ -106,16 +172,12 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) * n=1 */ static __always_inline u32 -accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, +accumulate_sum(u64 delta, struct sched_avg *sa, unsigned long load, unsigned long runnable, int running) { - unsigned long scale_freq, scale_cpu; u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ u64 periods; - scale_freq = arch_scale_freq_capacity(cpu); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); - delta += sa->period_contrib; periods = delta / 1024; /* A period is 1024us (~1ms) */ @@ -137,13 +199,12 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, } sa->period_contrib = delta; - contrib = cap_scale(contrib, scale_freq); if (load) sa->load_sum += load * contrib; if (runnable) sa->runnable_load_sum += runnable * contrib; if (running) - sa->util_sum += contrib * scale_cpu; + sa->util_sum += contrib << SCHED_CAPACITY_SHIFT; return periods; } @@ -221,7 +282,7 @@ ___update_load_sum(u64 now, int cpu, struct sched_avg *sa, * Step 1: accumulate *_sum since last_update_time. If we haven't * crossed period boundaries, finish. */ - if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) + if (!accumulate_sum(delta, sa, load, runnable, running)) return 0; return 1; @@ -371,12 +432,21 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) int update_irq_load_avg(struct rq *rq, u64 running) { int ret = 0; + + /* + * We can't use clock_pelt because irq time is not accounted in + * clock_task. Instead we directly scale the running time to + * reflect the real amount of computation + */ + running = cap_scale(running, arch_scale_freq_capacity(cpu_of(rq))); + running = cap_scale(running, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + /* * We know the time that has been used by interrupt since last update * but we don't when. Let be pessimistic and assume that interrupt has * happened just before the update. This is not so far from reality * because interrupt will most probably wake up task and trig an update - * of rq clock during which the metric si updated. + * of rq clock during which the metric is updated. * We start to decay with normal context time and then we add the * interrupt context time. * We can safely remove running from rq->clock because diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index d2894db..b4ce173 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -42,6 +42,29 @@ static inline void cfs_se_util_change(struct sched_avg *avg) WRITE_ONCE(avg->util_est.enqueued, enqueued); } +void update_rq_clock_pelt(struct rq *rq, s64 delta); + +static inline u64 rq_clock_pelt(struct rq *rq) +{ + return rq->clock_pelt - rq->lost_idle_time; +} + +#ifdef CONFIG_CFS_BANDWIDTH +/* rq->task_clock normalized against any time this cfs_rq has spent throttled */ +static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) +{ + if (unlikely(cfs_rq->throttle_count)) + return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time; + + return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; +} +#else +static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) +{ + return rq_clock_pelt(rq_of(cfs_rq)); +} +#endif + #else static inline int @@ -67,6 +90,10 @@ update_irq_load_avg(struct rq *rq, u64 running) { return 0; } + +static inline void +update_rq_clock_pelt(struct rq *rq, s64 delta) {} + #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2e2955a..f62f2d5 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1584,7 +1584,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * rt task */ if (rq->curr->sched_class != &rt_sched_class) - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); return p; } @@ -1593,7 +1593,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1); /* * The previous task needs to be made eligible for pushing @@ -2324,7 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1); watchdog(rq, p); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3990818..d987f50 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -848,6 +848,8 @@ struct rq { unsigned int clock_update_flags; u64 clock; u64 clock_task; + u64 clock_pelt; + unsigned long lost_idle_time; atomic_t nr_iowait;