From: Steven Rostedt <rostedt@goodmis.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com>,
Steven Rostedt <rostedt@kernel.org>,
linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
bpf@vger.kernel.org, x86@kernel.org,
Masami Hiramatsu <mhiramat@kernel.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Josh Poimboeuf <jpoimboe@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Andrii Nakryiko <andrii@kernel.org>,
Indu Bhagat <indu.bhagat@oracle.com>,
"Jose E. Marchesi" <jemarch@gnu.org>,
Beau Belgrave <beaub@linux.microsoft.com>,
Jens Remus <jremus@linux.ibm.com>,
Andrew Morton <akpm@linux-foundation.org>,
Florian Weimer <fweimer@redhat.com>, Sam James <sam@gentoo.org>,
Kees Cook <kees@kernel.org>,
"Carlos O'Donell" <codonell@redhat.com>
Subject: Re: [PATCH v6 5/6] tracing: Show inode and device major:minor in deferred user space stacktrace
Date: Fri, 29 Aug 2025 17:18:55 -0400 [thread overview]
Message-ID: <20250829171855.64f2cbfc@gandalf.local.home> (raw)
In-Reply-To: <CAHk-=wh8QVL4rb_17+6NfxW=AF-HS0WarMmq-nYm42akG0-Gbg@mail.gmail.com>
On Fri, 29 Aug 2025 13:54:08 -0700
Linus Torvalds <torvalds@linux-foundation.org> wrote:
> On Fri, 29 Aug 2025 at 11:11, Steven Rostedt <rostedt@goodmis.org> wrote:
> >
> > The idea is this (pseudo code):
> >
> > user_stack_trace() {
> > foreach vma in each stack frame:
> > key = hash(vma->vm_file);
> > if (!lookup(key)) {
> > trace_file_map(key, generate_path(vma), generate_buildid(vma));
> > add_into_hash(key);
> > }
> > }
>
> I see *zero* advantage to this. It's only doing stupid things that
> cost extra, and only because you don't want to do the smart thing that
> I've explained extensively that has *NONE* of these overheads.
>
> Just do the parsing at parse time. End of story.
What does "parsing at parse time" mean?
>
> Or don't do this at all. Justy forget the whole thing entirely. Throw
> the patch that started this all away, and just DON'T DO THIS.
Maybe we are talking past each other.
When I get a user space stack trace, I get the virtual addresses of each of
the user space functions. This is saved into an user stack trace event in
the ring buffer that usually gets mapped right to a file for post
processing.
I still do the:
user_stack_trace() {
foreach addr each stack frame
vma = vma_lookup(mm, addr);
callchain[i++] = (addr - vma->vm_start) + (vma->vm_pgoff << PAGE_SHIFT);
Are you saying that this shouldn't be done either? And to just record the
the virtual address in the chain and the vma->vm_start and
vma->vm_pgoff in another event? Where the post processing could do the
math? This other event could also record the path and build id.
The question is, when do I record this vma event? How do I know it's new?
I can't rely too much on other events (like mmap) and such as those events
may have occurred before the tracing started. I have to have some way to
know if the vma has been saved previously, which was why I had the hash
lookup, and only add vma's on new instances.
My main question is, when do I record the vma data event?
-- Steve
next prev parent reply other threads:[~2025-08-29 21:18 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-28 18:03 [PATCH v6 0/6] tracing: Deferred unwinding of user space stack traces Steven Rostedt
2025-08-28 18:03 ` [PATCH v6 1/6] tracing: Do not bother getting user space stacktraces for kernel threads Steven Rostedt
2025-08-28 18:03 ` [PATCH v6 2/6] tracing: Rename __dynamic_array() to __dynamic_field() for ftrace events Steven Rostedt
2025-08-28 18:03 ` [PATCH v6 3/6] tracing: Implement deferred user space stacktracing Steven Rostedt
2025-08-28 18:03 ` [PATCH v6 4/6] tracing: Have deferred user space stacktrace show file offsets Steven Rostedt
2025-08-28 18:03 ` [PATCH v6 5/6] tracing: Show inode and device major:minor in deferred user space stacktrace Steven Rostedt
2025-08-28 18:39 ` Linus Torvalds
2025-08-28 18:58 ` Arnaldo Carvalho de Melo
2025-08-28 19:02 ` Mathieu Desnoyers
2025-08-28 19:18 ` Linus Torvalds
2025-08-28 20:04 ` Arnaldo Carvalho de Melo
2025-08-28 20:37 ` Linus Torvalds
2025-08-28 20:17 ` Steven Rostedt
2025-08-28 20:27 ` Arnaldo Carvalho de Melo
2025-08-28 20:42 ` Linus Torvalds
2025-08-28 20:51 ` Steven Rostedt
2025-08-28 21:00 ` Arnaldo Carvalho de Melo
2025-08-28 21:27 ` Steven Rostedt
2025-08-29 16:27 ` Sam James
2025-08-28 20:38 ` Linus Torvalds
2025-08-28 20:48 ` Steven Rostedt
2025-08-28 21:06 ` Linus Torvalds
2025-08-28 21:17 ` Steven Rostedt
2025-08-28 22:10 ` Linus Torvalds
2025-08-28 22:44 ` Steven Rostedt
2025-08-29 15:06 ` Steven Rostedt
2025-08-29 15:47 ` Linus Torvalds
2025-08-29 16:07 ` Linus Torvalds
2025-08-29 16:33 ` Steven Rostedt
2025-08-29 16:42 ` Linus Torvalds
2025-08-29 16:50 ` Linus Torvalds
2025-08-29 17:02 ` Steven Rostedt
2025-08-29 17:13 ` Linus Torvalds
2025-08-29 17:57 ` Arnaldo Carvalho de Melo
2025-08-29 20:51 ` Linus Torvalds
2025-08-29 16:57 ` Steven Rostedt
2025-08-29 17:02 ` Linus Torvalds
2025-08-29 17:52 ` Steven Rostedt
2025-08-29 16:19 ` Steven Rostedt
2025-08-29 16:28 ` Linus Torvalds
2025-08-29 16:49 ` Steven Rostedt
2025-08-29 16:59 ` Linus Torvalds
2025-08-29 17:17 ` Arnaldo Carvalho de Melo
2025-08-29 17:33 ` Linus Torvalds
2025-08-29 18:11 ` Steven Rostedt
2025-08-29 20:54 ` Linus Torvalds
2025-08-29 21:18 ` Steven Rostedt [this message]
2025-08-29 22:40 ` Linus Torvalds
2025-08-29 23:09 ` Steven Rostedt
2025-08-29 23:42 ` Steven Rostedt
2025-08-30 0:36 ` Steven Rostedt
2025-08-30 0:44 ` Steven Rostedt
2025-08-30 0:45 ` Linus Torvalds
2025-08-30 1:20 ` Steven Rostedt
2025-08-30 1:26 ` Steven Rostedt
2025-08-30 18:31 ` Steven Rostedt
2025-08-30 19:03 ` Arnaldo Carvalho de Melo
2025-08-30 19:03 ` Linus Torvalds
2025-09-08 21:42 ` Steven Rostedt
2025-09-08 23:09 ` Linus Torvalds
2025-09-08 23:26 ` Linus Torvalds
2025-09-09 1:18 ` Steven Rostedt
2025-08-28 18:03 ` [PATCH v6 6/6] tracing: Add an event to map the inodes to their file names Steven Rostedt
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=20250829171855.64f2cbfc@gandalf.local.home \
--to=rostedt@goodmis.org \
--cc=acme@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=andrii@kernel.org \
--cc=arnaldo.melo@gmail.com \
--cc=beaub@linux.microsoft.com \
--cc=bpf@vger.kernel.org \
--cc=codonell@redhat.com \
--cc=fweimer@redhat.com \
--cc=indu.bhagat@oracle.com \
--cc=jemarch@gnu.org \
--cc=jolsa@kernel.org \
--cc=jpoimboe@kernel.org \
--cc=jremus@linux.ibm.com \
--cc=kees@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@kernel.org \
--cc=sam@gentoo.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=x86@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
all inboxes | Powered by JetHome®