linux-rt-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: John Kacur <jkacur@redhat.com>
To: Tomas Glozar <tglozar@redhat.com>
Cc: linux-rt-users@vger.kernel.org
Subject: Re: [PATCH v2 3/3] rteval: Support run-on-isolcpus in cyclictest
Date: Fri, 15 Sep 2023 15:12:40 -0400 (EDT)	[thread overview]
Message-ID: <aa9abe34-5aa-ace0-dba1-7324562d967@redhat.com> (raw)
In-Reply-To: <20230811095228.200772-4-tglozar@redhat.com>



On Fri, 11 Aug 2023, Tomas Glozar wrote:

> If --measurement-run-on-isolcpus is enabled, add isolated CPUs to the
> cpumask for the case when --measurement-cpulist is not specified. If
> both options are specified, display a warning.
> 
> Signed-off-by: Tomas Glozar <tglozar@redhat.com>
> ---
>  rteval/modules/measurement/cyclictest.py | 12 ++++++++++--
>  1 file changed, 10 insertions(+), 2 deletions(-)
> 
> diff --git a/rteval/modules/measurement/cyclictest.py b/rteval/modules/measurement/cyclictest.py
> index ace8db4..4d7fcf2 100644
> --- a/rteval/modules/measurement/cyclictest.py
> +++ b/rteval/modules/measurement/cyclictest.py
> @@ -214,6 +214,7 @@ class Cyclictest(rtevalModulePrototype):
>          self.__cpus = []
>          self.__cyclicdata = {}
>          self.__sparse = False
> +        self.__run_on_isolcpus = bool(self.__cfg.setdefault('run-on-isolcpus', False))
>  
>          if self.__cfg.cpulist:
>              self.__cpulist = self.__cfg.cpulist
> @@ -224,14 +225,21 @@ class Cyclictest(rtevalModulePrototype):
>              self.__cpulist = collapse_cpulist(self.__cpus)
>              self.__cpus = [str(c) for c in self.__cpus]
>              self.__sparse = True
> +            if self.__run_on_isolcpus:
> +                self._log(Log.WARN, "ignoring --measurement-run-on-isolcpus, since cpulist is specified")
>          else:
>              self.__cpus = SysTopology().online_cpus_str()
>              # Get the cpuset from the environment
>              cpuset = os.sched_getaffinity(0)
>              # Convert the elements to strings
>              cpuset = [str(c) for c in cpuset]
> -            # Only include cpus that are in the cpuset
> -            self.__cpus = [c for c in self.__cpus if c in cpuset]
> +            # Get isolated CPU list
> +            isolcpus = [str(c) for c in SysTopology().isolated_cpus()]
> +            # Only include cpus that are in the cpuset and isolated CPUs if run_on_isolcpus is enabled
> +            self.__cpus = [c for c in self.__cpus if c in cpuset or self.__run_on_isolcpus and c in isolcpus]
> +            if self.__run_on_isolcpus:
> +                self.__sparse = True
> +                self.__cpulist = collapse_cpulist(self.__cpus)
>  
>          # Sort the list of cpus to align with the order reported by cyclictest
>          self.__cpus.sort(key=int)
> -- 
> 2.41.0
> 
> 
Signed-off-by: John Kacur <jkacur@redhat.com>
--

I'm including this but we might need to finess the model.
Right now this is the intersection of isolated cpus plus the mask if 
given.
Other possibilities would be for the mask to override the isolated cpus, 
but perhaps we want the user to indicate, are we adding to the isolated 
cpus to include more cpus, are we subtracing, etc


      reply	other threads:[~2023-09-15 19:14 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-08-11  9:52 [PATCH v2 0/3] rteval: Add cmdline option to run measurements on isolcpus by default Tomas Glozar
2023-08-11  9:52 ` [PATCH v2 1/3] rteval: Allow arguments specific to module group Tomas Glozar
2023-09-15 18:58   ` John Kacur
2023-08-11  9:52 ` [PATCH v2 2/3] rteval: Add run_on_isolcpus option to measurements Tomas Glozar
2023-09-15 19:01   ` John Kacur
2023-09-15 19:06   ` John Kacur
2023-08-11  9:52 ` [PATCH v2 3/3] rteval: Support run-on-isolcpus in cyclictest Tomas Glozar
2023-09-15 19:12   ` John Kacur [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=aa9abe34-5aa-ace0-dba1-7324562d967@redhat.com \
    --to=jkacur@redhat.com \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=tglozar@redhat.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).