On Tue, Apr 01, 2025 at 03:17:01PM -0700, Andrii Nakryiko wrote:
> On Tue, Apr 1, 2025 at 3:12 PM Steven Rostedt wrote:
> >
> > On Tue, 1 Apr 2025 15:04:11 -0700
> > Andrii Nakryiko wrote:
> >
> > > How bad would it be to just move trace_sched_process_exit() then? (and
> > > add group_dead there,
On Tue, Apr 01, 2025 at 11:40:21AM -0700, Andrii Nakryiko wrote:
> It is useful to be able to access current->mm to, say, record a bunch of
> VMA information right before the task exits (e.g., for stack
> symbolization reasons when dealing with short-lived processes that exit
> in the middle of pro
On Wed, Apr 2, 2025 at 12:20 AM Michal Hocko wrote:
>
> On Tue 01-04-25 15:04:11, Andrii Nakryiko wrote:
> > On Tue, Apr 1, 2025 at 2:31 PM Steven Rostedt wrote:
> > >
> > > On Tue, 1 Apr 2025 11:40:21 -0700
> > > Andrii Nakryiko wrote:
> > >
> > > Hi Andrii,
> > >
> > > > It is useful to be ab
On Wed, 2 Apr 2025 09:20:37 +0200
Michal Hocko wrote:
> Is it important to tell the difference between thread and the
> whole process group exiting?
>
> Please keep in mind that even group exit doesn't really imply the mm is
> going away (clone allows CLONE_VM without CLONE_SIGNAL - i.e. mm coul
On Tue 01-04-25 15:04:11, Andrii Nakryiko wrote:
> On Tue, Apr 1, 2025 at 2:31 PM Steven Rostedt wrote:
> >
> > On Tue, 1 Apr 2025 11:40:21 -0700
> > Andrii Nakryiko wrote:
> >
> > Hi Andrii,
> >
> > > It is useful to be able to access current->mm to, say, record a bunch of
> > > VMA information
On Tue 01-04-25 17:34:16, Steven Rostedt wrote:
> On Tue, 1 Apr 2025 17:32:49 -0400
> Steven Rostedt wrote:
>
> > static void exit_mm(void)
> > {
> > struct mm_struct *mm = current->mm;
> >
> > exit_mm_release(current, mm);
> > trace_exit_mm(mm);
> >
> > ??
>
> That should have bee
On Tue, Apr 1, 2025 at 2:31 PM Steven Rostedt wrote:
>
> On Tue, 1 Apr 2025 11:40:21 -0700
> Andrii Nakryiko wrote:
>
> Hi Andrii,
>
> > It is useful to be able to access current->mm to, say, record a bunch of
> > VMA information right before the task exits (e.g., for stack
> > symbolization rea
On Tue, Apr 1, 2025 at 3:12 PM Steven Rostedt wrote:
>
> On Tue, 1 Apr 2025 15:04:11 -0700
> Andrii Nakryiko wrote:
>
> > How bad would it be to just move trace_sched_process_exit() then? (and
> > add group_dead there, as you mentioned)?
>
> I personally don't have an issue with that. In fact, th
On Tue, 1 Apr 2025 15:04:11 -0700
Andrii Nakryiko wrote:
> How bad would it be to just move trace_sched_process_exit() then? (and
> add group_dead there, as you mentioned)?
I personally don't have an issue with that. In fact, the one place I used
the sched_process_exit tracepoint, I had to chang
On Tue, 1 Apr 2025 17:32:49 -0400
Steven Rostedt wrote:
> static void exit_mm(void)
> {
> struct mm_struct *mm = current->mm;
>
> exit_mm_release(current, mm);
> trace_exit_mm(mm);
>
> ??
That should have been:
static void exit_mm(void)
{
struct mm_struct *mm = curre
On Tue, 1 Apr 2025 11:40:21 -0700
Andrii Nakryiko wrote:
Hi Andrii,
> It is useful to be able to access current->mm to, say, record a bunch of
> VMA information right before the task exits (e.g., for stack
> symbolization reasons when dealing with short-lived processes that exit
> in the middle
It is useful to be able to access current->mm to, say, record a bunch of
VMA information right before the task exits (e.g., for stack
symbolization reasons when dealing with short-lived processes that exit
in the middle of profiling session). We currently do have
trace_sched_process_exit() in the e
12 matches
Mail list logo
