linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Milian Wolff <milian.wolff@kdab.com>
To: David Hinkle <david.hinkle@securly.com>
Cc: Hadrien Grasland <grasland@lal.in2p3.fr>,
	linux-perf-users@vger.kernel.org
Subject: Re: Trying to understand some strange samples in a perf profile
Date: Thu, 04 Jan 2018 23:08:17 +0100	[thread overview]
Message-ID: <10526114.Hqjjc3tiqt@agathebauer> (raw)
In-Reply-To: <CAOrDofTn68XiBjEvF=boM94LwfXUt_W-AhCoOsK7aijiOknyfQ@mail.gmail.com>

[-- Attachment #1: Type: text/plain, Size: 1328 bytes --]

On Friday, December 29, 2017 12:31:41 AM CET David Hinkle wrote:
> > - build a minimal "unwinder" application for libunwind e.g.
> > - notify libunwind about all mmap events
> > - install the register and stack state from the per.data file
> > - try to unwind, see what happens
> 
> I'm having some problems with perf dwarf stack unwindings that stop at
> the kernel/userspace boundary and some userspace stacks that aren't
> unwinding at all on 4.9.70 I'd really love to shed some light on.
> Similar situation, in my case the stacks are in libc-2.17.so, which I
> think is symbolized properly (Other traces are unwinding through this
> library fine).  I'm also using libdw for unwinding and not libunwind.
> 
> I'd love to be able to do the above 4 things in an app and see if I
> can figure out why it's not unwinding properly.   Do you have some
> example code that can do that?  If you do now or you write it please
> share.

I don't have anything ready-made, otherwise I'd have shared it already. The 
example code for what needs to be done would be the perf code base. I.e. have 
a look at tools/perf/util/unwind-{libunwind-local,libdw}.c

Cheers

-- 
Milian Wolff | milian.wolff@kdab.com | Senior Software Engineer
KDAB (Deutschland) GmbH, a KDAB Group company
Tel: +49-30-521325470
KDAB - The Qt, C++ and OpenGL Experts

[-- Attachment #2: smime.p7s --]
[-- Type: application/pkcs7-signature, Size: 3826 bytes --]

      reply	other threads:[~2018-01-04 22:08 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-20  9:39 Trying to understand some strange samples in a perf profile Hadrien Grasland
2017-12-21  9:54 ` Milian Wolff
2017-12-21 10:46   ` Hadrien Grasland
2017-12-21 12:47     ` Milian Wolff
2017-12-21 16:02       ` Hadrien Grasland
2017-12-27 22:21         ` Milian Wolff
2017-12-28 23:31       ` David Hinkle
2018-01-04 22:08         ` Milian Wolff [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=10526114.Hqjjc3tiqt@agathebauer \
    --to=milian.wolff@kdab.com \
    --cc=david.hinkle@securly.com \
    --cc=grasland@lal.in2p3.fr \
    --cc=linux-perf-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
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).