linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Vitaly Chikunov <vt@altlinux.org>
Cc: Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com>,
	peterz@infradead.org, Ingo Molnar <mingo@redhat.com>,
	linux-kernel@vger.kernel.org,
	"Dmitry V. Levin" <ldv@altlinux.org>
Subject: Re: Should perf version match kernel version?
Date: Wed, 29 Jul 2020 15:28:57 -0300	[thread overview]
Message-ID: <20200729182857.GA433799@kernel.org> (raw)
In-Reply-To: <20200729175704.gsbh4gkbqxas5j2t@altlinux.org>

Em Wed, Jul 29, 2020 at 08:57:04PM +0300, Vitaly Chikunov escreveu:
> On Wed, Jul 29, 2020 at 01:27:32PM -0300, Arnaldo Carvalho de Melo wrote:
> > On July 29, 2020 1:02:20 PM GMT-03:00, peterz@infradead.org wrote:
> > >On Wed, Jul 29, 2020 at 06:56:47PM +0300, Vitaly Chikunov wrote:
> > >> It seems that most distros try to have perf version to match with
> > >> running kernel version. Is is requirement? Would it be better to have
> > >> single perf from kernel mainline to work with any (older) kernel
> > >> version?

> > >> We have different kernel versions in ALT Linux (stable for 4.19, 5.4,
> > >> and 5.7) and I want to understand if we should have three perfs or
> > >> single package will be enough.

> > >We strive to have it all compatible, older perf should work on newer
> > >kernel and newer perf should work on older kernel.

> > >How well it's all tested is another.

> > >Personally I often use a very old perf.

> > Yeah, never was a requirement, if you find some problem using a new perf on an old kernel or the other way around, please report.
> 
> That's great to know. Thanks for the answers!

Having said that, from time to time there are new features such as, say
LBR callgraph stitching, there are kernel and tooling components, so its
important to try and have the latest perf, but yeah, as you said, one
perf package is enough, just keep it uptodate :-)

For other features such as the metric work with 'perf stat', its purely
userspace, and sometimes its purely kernel space, no lockstep.

- Arnaldo

  reply	other threads:[~2020-07-29 18:29 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-29 15:56 Should perf version match kernel version? Vitaly Chikunov
2020-07-29 16:02 ` peterz
2020-07-29 16:27   ` Arnaldo Carvalho de Melo
2020-07-29 17:57     ` Vitaly Chikunov
2020-07-29 18:28       ` Arnaldo Carvalho de Melo [this message]
2020-08-02 11:51       ` Pavel Machek

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=20200729182857.GA433799@kernel.org \
    --to=acme@kernel.org \
    --cc=arnaldo.melo@gmail.com \
    --cc=ldv@altlinux.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=vt@altlinux.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
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).