Re: [lttng-dev] Record stacktraces at userspace tracing domain

2024-12-02 Thread Christophe Bédard via lttng-dev
Hi, I did the same thing a while ago, i.e., trigger tracepoints on malloc/free/etc. using liblttng-ust-libc-wrapper and collect userspace callstack information (so that the indirect calls to malloc/free can be removed from an application). There is a userspace callstack context implementation her

Re: [lttng-dev] How to report a bug?

2020-08-14 Thread Christophe Bédard via lttng-dev
Hi, You have to register for an account first (top right corner): https://bugs.lttng.org/account/register Once your account is created and you've logged in, you can open a new issue by clicking on "new issue" (or using this link: https://bugs.lttng.org/projects/urcu/issues/new) Christophe On T

Re: [lttng-dev] get function names with lttng-ust-cyg-profile

2020-06-26 Thread Christophe Bédard via lttng-dev
Hi, On Tue, 23 Jun 2020 at 21:45, Liu, Changcheng wrote: > Do you know how to print the call site function_name/offset? > For example: > 11 getchar(); > 12 > 13 x = add3(x); > Currently, it only shows call_site address instead of function name with > o

Re: [lttng-dev] get function names with lttng-ust-cyg-profile

2020-06-23 Thread Christophe Bédard via lttng-dev
Hi, Babeltrace is doing exactly what it should as far as I know. > yes, but babeltrace *can* provide the information if: * ip and vpid contexts are enabled (for userspace), e.g. $ lttng add-context --userspace --type=ip --type=vpid * LTTng state dump events are enabled, e.g. $ lttng enable-ev

Re: [lttng-dev] Correctly using callstack-user context

2020-05-13 Thread Christophe Bédard via lttng-dev
On Wed, 13 May 2020 at 10:18, Genevieve Bastien via lttng-dev < lttng-dev@lists.lttng.org> wrote: > We had a very very experimental branch with it, using backtrace first, > then unwind. But it is not suggested, not performant. It's far from the > correct desired implementation, for which Mathieu c

Re: [lttng-dev] Correctly using callstack-user context

2020-05-13 Thread Christophe Bédard via lttng-dev
On Tue, 12 May 2020 at 08:27, Mathieu Desnoyers < mathieu.desnoy...@efficios.com> wrote: > How does your test program issue the system call ? Is it directly with > syscall() (see syscall(2) man page), or > does it call into libc ? Is your entire libc compiled with > -fno-omit-frame-pointer ? > In

[lttng-dev] Correctly using callstack-user context

2020-05-11 Thread Christophe Bédard via lttng-dev
Hi, As part of a big software safety certification effort, we are looking into making sure that some functions of our API do not allocate memory and do not use any blocking syscalls. This part is done and is working (using kmem_mm_page_{alloc,free} for memory allocations for now). However, if we

Re: [lttng-dev] gcc plugin for instrumenting individual functions

2019-07-30 Thread Christophe Bédard
Hi, On Mon, 29 Jul 2019 at 21:23, Jonathan Rajotte-Julien < jonathan.rajotte-jul...@efficios.com> wrote: > Hi, > > For those at home wondering why this would be relevant to lttng, > lttng-ust comes with a utility shared object allowing you to leverage the > -finstrument-function sites to hook ltt

[lttng-dev] gcc plugin for instrumenting individual functions

2019-07-29 Thread Christophe Bédard
Hi, Sharing this just in case it can help someone! gcc only lets you disable instrumentation, using the `no_instrument_function` attribute, or by matching file names. It does not let you explicitly choose the individual functions you want to instrument. I've searched many times for a way to do i

Re: [lttng-dev] What is _prev_state in sched_switch?

2019-07-29 Thread Christophe Bédard
Hi, Re-sending since I previously used an email address not subscribed to the ML. On Mon, 29 Jul 2019 at 11:08, Ravindra Kumar Meena wrote: > Okay. The above link was somewhat helpful but I still didn't get what is > the meaning of {0, 1, 1026, 4096} values in _prev_state. > > In babeltrace out