Re: [RFC PATCH v2 18/28] mm/damon: trace probe_hits

[SeongJae Park]

On Wed, 13 May 2026 20:32:37 -0400 Steven Rostedt <rostedt@xxxxxxxxxxx> wrote:

> On Wed, 13 May 2026 17:06:10 -0700
> SeongJae Park <sj@xxxxxxxxxx> wrote:
> 
> > Btw, if you don't mind, may I ask your opinion about the name having '_v2'
> > suffix?  I chose that as an RFC phase temporal name that doesn't break the
> > compatibility, planning to give it a better name later.  But I start feeling
> > just extending the original one might be another option because tracepoints are
> > not strict stable ABI to my understanding, and the change of the TP_prink
> > format should be simple enough (append the probe_hits= part) that the user
> > space could reasonably deal with.
> 
> It's only a stable ABI if some useful userspace tooling depends on it.
> Otherwise, feel free to change.

Makes perfect sense, thank you Steven!

> 
> Nothing really should be parsing the TP_printk() format part as it is
> really inefficient to do so. That's why I created libtraceevent and
> libtracefs to do the parsing of the raw data for you.

I will try to make DAMON user-space tool directly uses those.  At the moment,
it is lazily parsing trace-cmd or perf outputs.


Thanks,
SJ

[...]