Mirror of the lttng-dev mailing list
 help / color / mirror / Atom feed
From: "Christophe Bédard via lttng-dev" <lttng-dev@lists.lttng.org>
To: "Sunku, Sai" <sunkusa@amazon.com>
Cc: "lttng-dev@lists.lttng.org" <lttng-dev@lists.lttng.org>
Subject: Re: Call stack context for user space trace points
Date: Mon, 6 Oct 2025 10:22:34 -0700	[thread overview]
Message-ID: <CAAS9doZSjHghJAUechOyNxhwA0DnMJX+Rm=YdbqMPfsSn-u7VQ@mail.gmail.com> (raw)
In-Reply-To: <870C2018-7321-4478-9609-9A75F99468A7@amazon.com>

[-- Attachment #1: Type: text/plain, Size: 1653 bytes --]

Hi,

The userspace callstack context is only available for the kernel domain.

There are potential workarounds and solutions; take a look at the
discussion in this mailing list thread from last year (hit "Next message"):
https://lists.lttng.org/pipermail/lttng-dev/2024-December/030881.html

Regards,

Christophe

On Mon, Oct 6, 2025 at 5:37 AM Sunku, Sai via lttng-dev <
lttng-dev@lists.lttng.org> wrote:

> Hello,
>
>
>
> I have a complex, multithreaded benchmark that emits LTTng trace points at
> various stages. I am trying to trace all malloc calls made by this
> benchmark. I'm specifically trying to get malloc trace points also through
> LTTng so that I can identify when the malloc call was made relative to
> other trace points from the benchmark. I also want to see the stack trace
> for each malloc call so that I can identify where in the benchmark the
> malloc call is coming from.
>
>
>
> If I preload the lttng libc wrapper with
> `LD_PRELOAD=liblttng-ust-libc-wrapper.so`, I'm able to see the trace points
> from malloc calls.
>
>
>
> But when I try to add the callstack-user context with this command `lttng
> add-context --userspace --channel 1 --type callstack-user`, I get an error
> saying "Error: callstack-user: UST invalid context"
>
>
>
> I've successfully added user space stack traces for kernel trace points
> with a similar command `lttng add-context --kernel --type callstack-user`
>
>
>
> Is the callstack-user context only available for kernel trace points? Is
> there another way to get the call stack for malloc calls?
>
>
>
> Thank you,
>
> Sai Sunku
>
>
>

[-- Attachment #2: Type: text/html, Size: 2831 bytes --]

      reply	other threads:[~2025-10-06 17:23 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-06  2:50 Sunku, Sai via lttng-dev
2025-10-06 17:22 ` Christophe Bédard via lttng-dev [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='CAAS9doZSjHghJAUechOyNxhwA0DnMJX+Rm=YdbqMPfsSn-u7VQ@mail.gmail.com' \
    --to=lttng-dev@lists.lttng.org \
    --cc=bedard.christophe@gmail.com \
    --cc=sunkusa@amazon.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