Linux-rt-users archive mirror
 help / color / mirror / Atom feed

From: Rodrigo Queiro <rodrigoq@google.com>
To: linux-rt-users@vger.kernel.org
Subject: Alternative to updating has_smi_counter?
Date: Mon, 19 Feb 2024 12:36:12 +0100	[thread overview]
Message-ID: <CAMnS4ZDigjkexNdJT3ZhLcmAMeodTKsPi+b91sSjE5sky7ZfqQ@mail.gmail.com> (raw)

Hi all,

I observed that `cyclictest --smi` doesn't work on Raptor Lake CPUs
(including 13th gen Intel Core CPUs). I assume that this could be
resolved by extending the switch statements in has_smi_counter(). Last
time this was done, the author changed the structure to better match
turbostat.c, but that has since been refactored to a table/struct
approach that is less easily copied.

I also notice that if family == 6, all listed CPUs support the SMI
counter, both in cyclictest.c and turbostat.c. Only unrecognized CPUs
cause has_smi_counter() to return 0 if family == 6, even though it is
more likely that the CPU is newer than the list in cyclictest.c, as
opposed to a CPU from 2008 or earlier.

What do you think about removing the checks on the model number, and
assuming that all processors with family == 6 support the Nehalem
MSRs, including the SMI counter? Any user running a recent cyclictest
on pre-Nehalem hardware could still run without --smi to prevent
seeing bogus SMI counts.

Thanks in advance,
Rodrigo

next             reply	other threads:[~2024-02-19 11:36 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-19 11:36 Rodrigo Queiro [this message]
2024-02-19 13:21 ` Alternative to updating has_smi_counter? Daniel Bristot de Oliveira
2024-03-12 10:43   ` Rodrigo Queiro
2024-03-12 10:46     ` Daniel Bristot de Oliveira
2024-03-12 12:01     ` Metin Kaya

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=CAMnS4ZDigjkexNdJT3ZhLcmAMeodTKsPi+b91sSjE5sky7ZfqQ@mail.gmail.com \
    --to=rodrigoq@google.com \
    --cc=linux-rt-users@vger.kernel.org \
    /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

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 read-only IMAP folder(s) and NNTP newsgroup(s).