From: Lukasz Luba <lukasz.luba@arm.com>
To: Qais Yousef <qyousef@layalina.io>
Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
rafael@kernel.org, dietmar.eggemann@arm.com, rui.zhang@intel.com,
amit.kucheria@verdurent.com, amit.kachhap@gmail.com,
daniel.lezcano@linaro.org, viresh.kumar@linaro.org,
len.brown@intel.com, pavel@ucw.cz, mhiramat@kernel.org,
wvw@google.com
Subject: Re: [PATCH v5 15/23] PM: EM: Optimize em_cpu_energy() and remove division
Date: Mon, 15 Jan 2024 12:36:30 +0000 [thread overview]
Message-ID: <661068a2-7c46-4703-ba4d-5ce1cdf44b3d@arm.com> (raw)
In-Reply-To: <20240115122156.5743y4trhm4tkgs3@airbuntu>
On 1/15/24 12:21, Qais Yousef wrote:
> On 01/10/24 13:53, Lukasz Luba wrote:
>>
>>
>> On 1/4/24 19:23, Qais Yousef wrote:
>>> On 01/02/24 11:47, Lukasz Luba wrote:
>>>>> Did you see a problem or just being extra cautious here?
>>>>
>>>> There is no problem, 'cost' is a private coefficient for EAS only.
>>>
>>> Let me ask differently, what goes wrong if you don't increase the resolution
>>> here? Why is it necessary?
>>>
>>
>>
>> When you have 800mW at CPU capacity 1024, then the value is small (below
>> 1 thousand).
>> Example:
>> power = 800000 uW
>> cost = 800000 / 1024 = 781
>>
>> While I know from past that sometimes OPPs might have close voltage
>> values and a rounding could occur and make some OPPs inefficient
>> while they aren't.
>>
>> This is what would happen when we have the 1x resolution:
>> /sys/kernel/debug/energy_model/cpu4/ps:1008000/cost:551
>> /sys/kernel/debug/energy_model/cpu4/ps:1200000/cost:644
>> /sys/kernel/debug/energy_model/cpu4/ps:1416000/cost:744
>> /sys/kernel/debug/energy_model/cpu4/ps:1512000/cost:851
>> /sys/kernel/debug/energy_model/cpu4/ps:408000/cost:493
>> /sys/kernel/debug/energy_model/cpu4/ps:600000/cost:493
>> /sys/kernel/debug/energy_model/cpu4/ps:816000/cost:493
>> The bottom 3 OPPs have the same 'cost' thus 2 OPPs are in-efficient,
>> which is not true (see below).
>>
>> This is what would happen when we have the 10x resolution:
>> /sys/kernel/debug/energy_model/cpu4/ps:1008000/cost:5513
>> /sys/kernel/debug/energy_model/cpu4/ps:1200000/cost:6443
>> /sys/kernel/debug/energy_model/cpu4/ps:1416000/cost:7447
>> /sys/kernel/debug/energy_model/cpu4/ps:1512000/cost:8514
>> /sys/kernel/debug/energy_model/cpu4/ps:408000/cost:4934
>> /sys/kernel/debug/energy_model/cpu4/ps:600000/cost:4933
>> /sys/kernel/debug/energy_model/cpu4/ps:816000/cost:4934
>> Here the OPP with 600MHz is more efficient than 408MHz,
>> which is true. So only 408MHz will be marked as in-efficient OPP.
>>
>>
>> This is what would happen when we have the 100x resolution:
>> /sys/kernel/debug/energy_model/cpu4/ps:1008000/cost:55137
>> /sys/kernel/debug/energy_model/cpu4/ps:1200000/cost:64433
>> /sys/kernel/debug/energy_model/cpu4/ps:1416000/cost:74473
>> /sys/kernel/debug/energy_model/cpu4/ps:1512000/cost:85140
>> /sys/kernel/debug/energy_model/cpu4/ps:408000/cost:49346
>> /sys/kernel/debug/energy_model/cpu4/ps:600000/cost:49331
>> /sys/kernel/debug/energy_model/cpu4/ps:816000/cost:49346
>> The higher (100x) resolution does not bring that much in
>> practice.
>
> So it seems a uW is not sufficient enough. We moved from mW because of
> resolution already. Shall we make it nW then and multiply by 1000 always? The
> choice of 10 looks arbitrary IMHO
>
No, there is no need of nW in the 'power' field for this.
You've missed the point.
next prev parent reply other threads:[~2024-01-15 12:35 UTC|newest]
Thread overview: 99+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-29 11:08 [PATCH v5 00/23] Introduce runtime modifiable Energy Model Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 01/23] PM: EM: Add missing newline for the message log Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 02/23] PM: EM: Refactor em_cpufreq_update_efficiencies() arguments Lukasz Luba
2023-12-17 17:58 ` Qais Yousef
2023-12-19 10:30 ` Lukasz Luba
2023-12-28 16:59 ` Qais Yousef
2024-01-02 9:40 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 03/23] PM: EM: Find first CPU active while updating OPP efficiency Lukasz Luba
2023-12-17 17:58 ` Qais Yousef
2023-12-19 10:53 ` Lukasz Luba
2023-12-28 17:13 ` Qais Yousef
2024-01-02 9:42 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 04/23] PM: EM: Refactor em_pd_get_efficient_state() to be more flexible Lukasz Luba
2023-12-12 18:49 ` Dietmar Eggemann
2023-12-19 10:58 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 05/23] PM: EM: Refactor a new function em_compute_costs() Lukasz Luba
2023-12-17 17:58 ` Qais Yousef
2023-12-19 10:59 ` Lukasz Luba
2023-12-28 17:14 ` Qais Yousef
2024-01-02 9:43 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 06/23] PM: EM: Check if the get_cost() callback is present in em_compute_costs() Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 07/23] PM: EM: Refactor how the EM table is allocated and populated Lukasz Luba
2023-12-12 18:50 ` Dietmar Eggemann
2023-12-19 13:19 ` Lukasz Luba
2023-12-17 17:59 ` Qais Yousef
2023-11-29 11:08 ` [PATCH v5 08/23] PM: EM: Introduce runtime modifiable table Lukasz Luba
2023-12-12 18:50 ` Dietmar Eggemann
2023-12-19 11:33 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 09/23] PM: EM: Use runtime modified EM for CPUs energy estimation in EAS Lukasz Luba
2023-12-17 17:59 ` Qais Yousef
2023-12-19 4:03 ` Xuewen Yan
2023-12-19 8:32 ` Lukasz Luba
2023-12-28 17:32 ` Qais Yousef
2024-01-02 11:17 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 10/23] PM: EM: Add API for memory allocations for new tables Lukasz Luba
2023-12-17 17:59 ` Qais Yousef
2023-12-19 8:45 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 11/23] PM: EM: Add API for updating the runtime modifiable EM Lukasz Luba
2023-12-12 18:50 ` Dietmar Eggemann
2023-12-20 8:06 ` Lukasz Luba
2024-01-04 15:45 ` Dietmar Eggemann
2024-01-04 16:55 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 12/23] PM: EM: Add helpers to read under RCU lock the EM table Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 13/23] PM: EM: Add performance field to struct em_perf_state Lukasz Luba
2023-12-17 18:00 ` Qais Yousef
2023-12-20 8:21 ` Lukasz Luba
2023-12-28 17:45 ` Qais Yousef
2023-11-29 11:08 ` [PATCH v5 14/23] PM: EM: Support late CPUs booting and capacity adjustment Lukasz Luba
2023-12-12 18:50 ` Dietmar Eggemann
2023-12-20 8:23 ` Lukasz Luba
2023-12-17 18:00 ` Qais Yousef
2024-01-02 11:39 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 15/23] PM: EM: Optimize em_cpu_energy() and remove division Lukasz Luba
2023-12-12 18:50 ` Dietmar Eggemann
2023-12-20 8:42 ` Lukasz Luba
2024-01-04 16:30 ` Dietmar Eggemann
2024-01-04 16:56 ` Lukasz Luba
2023-12-28 18:06 ` Qais Yousef
2024-01-02 11:47 ` Lukasz Luba
2024-01-04 19:23 ` Qais Yousef
2024-01-10 13:53 ` Lukasz Luba
2024-01-15 12:21 ` Qais Yousef
2024-01-15 12:36 ` Lukasz Luba [this message]
2024-01-16 13:10 ` Qais Yousef
2024-01-16 15:34 ` Lukasz Luba
2024-01-16 19:33 ` Qais Yousef
2023-11-29 11:08 ` [PATCH v5 16/23] powercap/dtpm_cpu: Use new Energy Model interface to get table Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 17/23] powercap/dtpm_devfreq: " Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 18/23] drivers/thermal/cpufreq_cooling: Use new Energy Model interface Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 19/23] drivers/thermal/devfreq_cooling: " Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 20/23] PM: EM: Change debugfs configuration to use runtime EM table data Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 21/23] PM: EM: Remove old table Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 22/23] PM: EM: Add em_dev_compute_costs() as API for device drivers Lukasz Luba
2023-12-12 18:50 ` Dietmar Eggemann
2023-12-17 18:03 ` Qais Yousef
2023-12-18 11:56 ` Lukasz Luba
2023-12-20 11:14 ` Lukasz Luba
2023-11-29 11:08 ` [PATCH v5 23/23] Documentation: EM: Update with runtime modification design Lukasz Luba
2023-12-12 18:51 ` Dietmar Eggemann
2023-12-19 9:35 ` Lukasz Luba
2023-12-19 4:42 ` Xuewen Yan
2023-12-19 8:47 ` Lukasz Luba
2023-12-19 6:22 ` Xuewen Yan
2023-12-19 9:32 ` Lukasz Luba
2023-12-20 2:08 ` Xuewen Yan
2023-12-20 7:57 ` Lukasz Luba
2023-12-12 18:48 ` [PATCH v5 00/23] Introduce runtime modifiable Energy Model Dietmar Eggemann
2023-12-13 9:23 ` Lukasz Luba
2023-12-13 11:34 ` Dietmar Eggemann
2023-12-13 11:45 ` Rafael J. Wysocki
2023-12-13 12:20 ` Lukasz Luba
2023-12-12 18:49 ` Rafael J. Wysocki
2023-12-13 9:32 ` Lukasz Luba
2023-12-13 13:40 ` Hongyan Xia
2023-12-13 13:16 ` Lukasz Luba
2023-12-17 18:22 ` Qais Yousef
2023-12-19 10:22 ` Lukasz Luba
2023-12-28 18:41 ` Qais Yousef
2024-01-02 12:12 ` Lukasz Luba
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=661068a2-7c46-4703-ba4d-5ce1cdf44b3d@arm.com \
--to=lukasz.luba@arm.com \
--cc=amit.kachhap@gmail.com \
--cc=amit.kucheria@verdurent.com \
--cc=daniel.lezcano@linaro.org \
--cc=dietmar.eggemann@arm.com \
--cc=len.brown@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mhiramat@kernel.org \
--cc=pavel@ucw.cz \
--cc=qyousef@layalina.io \
--cc=rafael@kernel.org \
--cc=rui.zhang@intel.com \
--cc=viresh.kumar@linaro.org \
--cc=wvw@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®