Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1612410

RE: [Update][PATCH v3 2/3] cpufreq: intel_pstate: Do not reinit performance limits in ->setpolicy

Path csiph.com!aioe.org!bofh.it!news.nic.it!robomod
From "Doug Smythies" <dsmythies@telus.net>
Newsgroups linux.kernel
Subject RE: [Update][PATCH v3 2/3] cpufreq: intel_pstate: Do not reinit performance limits in ->setpolicy
Date Thu, 30 Mar 2017 00:10:01 +0200
Message-ID <tqtWV-4Sf-17@gated-at.bofh.it> (permalink)
References <tfQ0N-4XF-5@gated-at.bofh.it> <tfZns-2Gn-13@gated-at.bofh.it> <tfZns-2Gn-29@gated-at.bofh.it> <tqtWV-4Sf-19@gated-at.bofh.it>
X-Original-To "'Rafael J. Wysocki'" <rjw@rjwysocki.net>
Dkim-Signature v=1; a=rsa-sha256; c=relaxed/relaxed; d=telus.net; s=neo; t=1490824883; bh=+2pEEhKQ9q53fyJzv5IMfxSfo7QRE8QE4Tv2sT1kr8M=; h=From:To:Cc:References:In-Reply-To:Subject:Date; b=YUhlj/XKKLD6WpeW7pKLCYrxKlHkuVQ5/wLhjePAvYns8LsXMpHy1PnAOCUSrmfu7 3mgsWXJ4Ce9cGQ2xlQ8cC2A6JsxX+aeR03nbmN7rsBiu7z3nTj+3xYe0DGQLcxPZpN u54fFNFKIiL6AKOjDN6eAsai9M/xSYeQmRmQ/BXHuyru5SFS8RhyxsnLHhb0jN6hSQ yHr58pVdW8LxmiEOulslVSpKgSu0c/jae0jx7IcefNYqMz3MS8tMLylpL3+dCCnKsB evMmekR4rg1tCdbazGqA+vc0V2vpXRWnETki9s/C5YMrvmc1AR/TKUVCbOIy7ylwLQ RLAWO555iOeAA==
X-Authority-Analysis v=2.2 cv=ZfTyDodA c=1 sm=1 tr=0 a=zJWegnE7BH9C0Gl4FFgQyA==:117 a=zJWegnE7BH9C0Gl4FFgQyA==:17 a=Pyq9K9CWowscuQLKlpiwfMBGOR0=:19 a=kj9zAlcOel0A:10 a=QyXUC8HyAAAA:8 a=r6Jq5az0UNUJthfbzP4A:9 a=7Zwj6sZBwVKJAoWSPKxL6X1jA+E=:19 a=NTVWMQtJj_o5KP3F:21 a=XEhabr20cNd2vL5B:21 a=CjuIK1q_8ugA:10 a=avl4LiGQNoF5OB0DmCJ7:22
In-Reply-To jZL3cbFe8sVy3jZL4c6fog
MIME-Version 1.0
Content-Type text/plain; charset="us-ascii"
Content-Transfer-Encoding 7bit
X-Mailer Microsoft Office Outlook 12.0
Thread-Index AdKTpXnUUbdikSzzSsGD1w38oPzUpAVLkpjw
Content-Language en-ca
X-Cmae-Envelope MS4wfK2DmiffyajROk7zlJWtqkgRBjerWtBMQctKdY3gSluPeGDpvO44Liu7J8zEjyQXhS0hj0/7tUPZVwcfeB/8bMnmPvHBlyeNN3ZtMFIfk3NZ+Bf716Qy nsMChzMOr4pulF4iTDA2KOHtB8725Zh2a6xl+LehjsBX3hjuNrOKsxDoZsqk7UpzV8QsyFwlF2z1X6qmCHiFrHPrR1cyB72A3Am3W2su3P2YU3oiP61MGTZV tZndiAEvzK4EiYCgkUyXQ0G0qvbjqMOqiMuo547bDdimTJqyefw2MIvXoW2RvMFe
Sender robomod@news.nic.it
List-ID <linux-kernel.vger.kernel.org>
X-Mailing-List linux-kernel@vger.kernel.org
Approved robomod@news.nic.it
Lines 98
Organization linux.* mail to news gateway
X-Original-Cc "'Srinivas Pandruvada'" <srinivas.pandruvada@linux.intel.com>, "'LKML'" <linux-kernel@vger.kernel.org>, "'Linux PM'" <linux-pm@vger.kernel.org>
X-Original-Date Wed, 29 Mar 2017 15:01:17 -0700
X-Original-Message-ID <004101d2a8d7$ff31bb50$fd9531f0$@net>
X-Original-References <2694426.SgxlQuL17D@aspire.rjw.lan> <2326598.n0dkg1GrdM@aspire.rjw.lan> <2188688.SPioTUuSuO@aspire.rjw.lan> jZL3cbFe8sVy3jZL4c6fog
X-Original-Sender linux-kernel-owner@vger.kernel.org
Xref csiph.com linux.kernel:1612410

Show key headers only | View raw


Hi Rafael,

Sorry for the delay, but I didn't notice until today that this
commit causes a regression, at least in my computer.

I have not figured out exactly what is wrong, as I must
admit I am finding these policy interactions difficult
to follow.

On 2017.03.02 14:29 Rafael J. Wysocki wrote:
>From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
>
> If the current P-state selection algorithm is set to "performance"
> in intel_pstate_set_policy(), the limits may be initialized from

... [cut] ...

Going back to kernel 4.11-rc1 I get this after boot**:

$ uname -a
Linux s15 4.11.0-rc1-stock #217 SMP Sun Mar 5 15:34:38 PST 2017 x86_64 x86_64 x86_64 GNU/Linux

$ grep . /sys/devices/system/cpu/intel_pstate/*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100  <<< Correct
/sys/devices/system/cpu/intel_pstate/min_perf_pct:43   <<< Correct
/sys/devices/system/cpu/intel_pstate/no_turbo:0
/sys/devices/system/cpu/intel_pstate/num_pstates:23
/sys/devices/system/cpu/intel_pstate/status:active
/sys/devices/system/cpu/intel_pstate/turbo_pct:18

$ grep . /sys/devices/system/cpu/cpu0/cpufreq/*
/sys/devices/system/cpu/cpu0/cpufreq/affected_cpus:0
grep: /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq: Permission denied
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq:3800000  <<< Correct
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_min_freq:1600000  <<< Correct
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_transition_latency:4294967295
/sys/devices/system/cpu/cpu0/cpufreq/related_cpus:0
/sys/devices/system/cpu/cpu0/cpufreq/scaling_available_governors:performance powersave
/sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq:1600805
/sys/devices/system/cpu/cpu0/cpufreq/scaling_driver:intel_pstate
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:powersave  <<< Notice
/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq:3800000  <<< Correct
/sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq:1600000  <<< Correct
/sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed:<unsupported>

$ sudo rdmsr --bitfield 15:8 -d -a 0x199 <<< Requested P-States
16
16
17
17
16
16
16
16

Going back to kernel 4.11-rc2 I get this after boot**:

~$ uname -a
Linux s15 4.11.0-rc2-stock #218 SMP Sun Mar 12 23:57:44 PDT 2017 x86_64 x86_64 x86_64 GNU/Linux

$ grep . /sys/devices/system/cpu/intel_pstate/*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100  <<< Correct
/sys/devices/system/cpu/intel_pstate/min_perf_pct:100  <<< Incorrect
/sys/devices/system/cpu/intel_pstate/no_turbo:0
/sys/devices/system/cpu/intel_pstate/num_pstates:23
/sys/devices/system/cpu/intel_pstate/status:active
/sys/devices/system/cpu/intel_pstate/turbo_pct:18

$ grep . /sys/devices/system/cpu/cpu0/cpufreq/*
/sys/devices/system/cpu/cpu0/cpufreq/affected_cpus:0
grep: /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq: Permission denied
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq:3800000  <<< Correct
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_min_freq:1600000  <<< Correct
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_transition_latency:4294967295
/sys/devices/system/cpu/cpu0/cpufreq/related_cpus:0
/sys/devices/system/cpu/cpu0/cpufreq/scaling_available_governors:performance powersave
/sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq:1600805
/sys/devices/system/cpu/cpu0/cpufreq/scaling_driver:intel_pstate
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:powersave  <<< Notice
/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq:3800000  <<< Correct
/sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq:3800000  <<< Incorrect
/sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed:<unsupported>

$ sudo rdmsr --bitfield 15:8 -d -a 0x199  <<< Requested P-States
38   <<<< All are pinned, system is idle
38
38
38
38
38
38
38

**: After boot means > 1 minute after boot, because my distro (Ubtunu)
starts up using the performance governor and then changes to powersave
after 1 minute.

... Doug

Back to linux.kernel | Previous | Next | Find similar | Unroll thread


Thread

RE: [Update][PATCH v3 2/3] cpufreq: intel_pstate: Do not reinit performance limits in ->setpolicy "Doug Smythies" <dsmythies@telus.net> - 2017-03-30 00:10 +0200

csiph-web