From patchwork Sat Jun 29 08:22:48 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christian Loehle X-Patchwork-Id: 13716840 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 943E13BBC9; Sat, 29 Jun 2024 08:22:53 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1719649376; cv=none; b=GFabQH4eSk1StHAd4ad5ia9TuktqtT21S4VJgi5ebCUMkPbDPsGV2TvI28081x4j4xN+oOU/YILbZBaddUB8G2IJ/s+5okkYkb9YlmwlshZD5cWLWs+PWFNpbWT+nYXUvyhLEq9r0JsJIP2NE9jK20n7t73fpi+wYRkDFoIcF7Y= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1719649376; c=relaxed/simple; bh=P8MFF88WFe0wi+HNjE5Y0mEKeKHhp/3xlM7BHh0MSKk=; h=Message-ID:Date:MIME-Version:Subject:To:Cc:References:From: In-Reply-To:Content-Type; b=Gq97fEIJGdStsrZbfipX64fVBdsyv3/2G8tpAS6SN8Se0+7T7sWAHd75/oYxdiwetjNYwLTSeVEDm3mCnw+deHp5pbDv2SDmIOv0Gb3YQRh8H111+r6Pj2Bz4mZuJMkvX+sPTHu5Z3u8U4OmQitysKo4oa2U2RPI8gXFk8eGw4g= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id AB7CD339; Sat, 29 Jun 2024 01:23:17 -0700 (PDT) Received: from [10.1.33.10] (e127648.arm.com [10.1.33.10]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 207403F766; Sat, 29 Jun 2024 01:22:49 -0700 (PDT) Message-ID: Date: Sat, 29 Jun 2024 09:22:48 +0100 Precedence: bulk X-Mailing-List: linux-pm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: [PATCHv4 3/3] cpuidle: teo: Don't count non-existent intercepts To: "Rafael J. Wysocki" Cc: linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org, vincent.guittot@linaro.org, qyousef@layalina.io, peterz@infradead.org, daniel.lezcano@linaro.org, ulf.hansson@linaro.org, anna-maria@linutronix.de, dsmythies@telus.net, kajetan.puchalski@arm.com, lukasz.luba@arm.com, dietmar.eggemann@arm.com References: <20240628095955.34096-1-christian.loehle@arm.com> <20240628095955.34096-4-christian.loehle@arm.com> Content-Language: en-US From: Christian Loehle In-Reply-To: When bailing out early, teo will not query the sleep length anymore since commit 6da8f9ba5a87 ("cpuidle: teo: Skip tick_nohz_get_sleep_length() call in some cases") with an expected sleep_length_ns value of KTIME_MAX. This lead to state0 accumulating lots of 'intercepts' because the actually measured sleep length was < KTIME_MAX, so query the sleep length instead for teo to recognize if it still is in an intercept-likely scenario without alternating between the two modes. Fundamentally we can only do one of the two: 1. Skip sleep_length_ns query when we think intercept is likely 2. Have accurate data if sleep_length_ns is actually intercepted when we believe it is currently intercepted. Previously teo did the former while this patch chooses the latter as the additional time it takes to query the sleep length was found to be negligible and the variants of option 1 (count all unknowns as misses or count all unknown as hits) had significant regressions (as misses had lots of too shallow idle state selections and as hits had terrible performance in intercept-heavy workloads). Fixes: 6da8f9ba5a87 ("cpuidle: teo: Skip tick_nohz_get_sleep_length() call in some cases") Signed-off-by: Christian Loehle --- v4: Skip constraint check if intercept logic selects state0 drivers/cpuidle/governors/teo.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index 200a3598cbcf..6dc44197a80e 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -287,6 +287,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, unsigned int hit_sum = 0; int constraint_idx = 0; int idx0 = 0, idx = -1; + int prev_intercept_idx; s64 duration_ns; int i; @@ -364,6 +365,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * all of the deeper states a shallower idle state is likely to be a * better choice. */ + prev_intercept_idx = idx; if (2 * idx_intercept_sum > cpu_data->total - idx_hit_sum) { int first_suitable_idx = idx; @@ -415,6 +417,15 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, first_suitable_idx = i; } } + if (!idx && prev_intercept_idx) { + /* + * We have to query the sleep length here otherwise we don't + * know after wakeup if our guess was correct. + */ + duration_ns = tick_nohz_get_sleep_length(&delta_tick); + cpu_data->sleep_length_ns = duration_ns; + goto out_tick; + } /* * If there is a latency constraint, it may be necessary to select an