patches for DPDK stable branches
 help / color / mirror / Atom feed
From: Christian Ehrhardt <christian.ehrhardt@canonical.com>
To: David Hunt <david.hunt@intel.com>
Cc: dpdk stable <stable@dpdk.org>, "Jiang, YuX" <yux.jiang@intel.com>,
	 Richael Zhuang <richael.zhuang@arm.com>
Subject: Re: [dpdk-stable] [19.11.9] test/power: fix CPU frequency when turbo enabled
Date: Mon, 6 Sep 2021 13:00:35 +0200	[thread overview]
Message-ID: <CAATJJ0JPtDAJ+ohL1u8Oe-o9ffSTJsB6dg5vfjSYaHvgrabzCw@mail.gmail.com> (raw)
In-Reply-To: <20210903083736.27922-1-david.hunt@intel.com>

On Fri, Sep 3, 2021 at 10:37 AM David Hunt <david.hunt@intel.com> wrote:
>

x missing proper reference to upstream commit

> On arm platform, the value in "/sys/.../cpuinfo_cur_freq" may not
> be exactly the same as what was set when using CPPC cpufreq driver.
> For other cpufreq driver, no need to round it currently, or else
> this check will fail with turbo enabled. For example, with acpi_cpufreq,
> cpuinfo_cur_freq can be 2401000 which is equal to freqs[0].It should
> not be rounded to 2400000.
>
> This is a version of the patch for 19.11.9 that fixes this issue
> withouth the dependency of having the CPPC support applied first
^^ typo
> (modified version of 29343b9030e38e8c3519ba01cb66724d45b13dc8)

Hi David, thank you for the backport.
I have fixed the typo and reference and made it part of the WIP 19.11 branch at
  https://github.com/cpaelzer/dpdk-stable-queue/commits/19.11

It came too late for 19.11.10 which was released today and this wasn't
urgent enough to reset all the testing.
But you are very early in line for the next release :-)


> Fixes: 606a234c6d360 ("test/power: round CPU frequency to check")
> Cc: stable@dpdk.org
>
> Signed-off-by: David Hunt <david.hunt@intel.com>
> ---
>  app/test/test_power_cpufreq.c | 29 ++++++++++++++++++-----------
>  1 file changed, 18 insertions(+), 11 deletions(-)
>
> diff --git a/app/test/test_power_cpufreq.c b/app/test/test_power_cpufreq.c
> index d0c7e60ca5..51105f35be 100644
> --- a/app/test/test_power_cpufreq.c
> +++ b/app/test/test_power_cpufreq.c
> @@ -55,18 +55,20 @@ check_cur_freq(unsigned int lcore_id, uint32_t idx, bool turbo)
>         FILE *f;
>         char fullpath[PATH_MAX];
>         char buf[BUFSIZ];
> +       enum power_management_env env;
>         uint32_t cur_freq;
> +       uint32_t freq_conv;
>         int ret = -1;
>         int i;
>
>         if (snprintf(fullpath, sizeof(fullpath),
> -               TEST_POWER_SYSFILE_SCALING_FREQ, lcore_id) < 0) {
> +               TEST_POWER_SYSFILE_CPUINFO_FREQ, lcore_id) < 0) {
>                 return 0;
>         }
>         f = fopen(fullpath, "r");
>         if (f == NULL) {
>                 if (snprintf(fullpath, sizeof(fullpath),
> -                       TEST_POWER_SYSFILE_CPUINFO_FREQ, lcore_id) < 0) {
> +                       TEST_POWER_SYSFILE_SCALING_FREQ, lcore_id) < 0) {
>                         return 0;
>                 }
>                 f = fopen(fullpath, "r");
> @@ -80,15 +82,20 @@ check_cur_freq(unsigned int lcore_id, uint32_t idx, bool turbo)
>                         goto fail_all;
>
>                 cur_freq = strtoul(buf, NULL, TEST_POWER_CONVERT_TO_DECIMAL);
> -
> -               /* convert the frequency to nearest 100000 value
> -                * Ex: if cur_freq=1396789 then freq_conv=1400000
> -                * Ex: if cur_freq=800030 then freq_conv=800000
> -                */
> -               unsigned int freq_conv = 0;
> -               freq_conv = (cur_freq + TEST_FREQ_ROUNDING_DELTA)
> -                                       / TEST_ROUND_FREQ_TO_N_100000;
> -               freq_conv = freq_conv * TEST_ROUND_FREQ_TO_N_100000;
> +               freq_conv = cur_freq;
> +
> +               env = rte_power_get_env();
> +
> +               if (env == PM_ENV_PSTATE_CPUFREQ) {
> +                       /* convert the frequency to nearest 100000 value
> +                        * Ex: if cur_freq=1396789 then freq_conv=1400000
> +                        * Ex: if cur_freq=800030 then freq_conv=800000
> +                        */
> +                       unsigned int freq_conv = 0;
> +                       freq_conv = (cur_freq + TEST_FREQ_ROUNDING_DELTA)
> +                                               / TEST_ROUND_FREQ_TO_N_100000;
> +                       freq_conv = freq_conv * TEST_ROUND_FREQ_TO_N_100000;
> +               }
>
>                 if (turbo)
>                         ret = (freqs[idx] <= freq_conv ? 0 : -1);
> --
> 2.17.1
>


-- 
Christian Ehrhardt
Staff Engineer, Ubuntu Server
Canonical Ltd

      reply	other threads:[~2021-09-06 11:01 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-03  8:37 David Hunt
2021-09-06 11:00 ` Christian Ehrhardt [this message]

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=CAATJJ0JPtDAJ+ohL1u8Oe-o9ffSTJsB6dg5vfjSYaHvgrabzCw@mail.gmail.com \
    --to=christian.ehrhardt@canonical.com \
    --cc=david.hunt@intel.com \
    --cc=richael.zhuang@arm.com \
    --cc=stable@dpdk.org \
    --cc=yux.jiang@intel.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;
as well as URLs for NNTP newsgroup(s).