Re: Re: Re: [PATCH 0/8] Introduce Data Access MONitor (DAMON)

[<sjpark@amazon.com>]

On Mon, 20 Jan 2020 19:14:40 +0100 SeongJae Park <sj38.park@gmail.com> wrote:

> On Mon, 20 Jan 2020 19:55:51 +0300 "Kirill A. Shutemov" <kirill@shutemov.name> wrote:
> 
> > On Mon, Jan 20, 2020 at 05:27:49PM +0100, SeongJae Park wrote:
> > > This patchset introduces a new kernel module for practical monitoring of
> > > data accesses, namely DAMON.
> > 
> > Looks like it's not integrated with perf at all right? Why?
> > Correlating measurements from different domains would help to see the
> > bigger picture.
> 
> Right, it's not integrated with perf.  DAMON provides only its debugfs
> interface.  Also I agree that correlating measurments will be helpful.  I do
> not integrate DAMON with perf with this patchset for following reasons.
> 
> First of all, I think I have no deep understanding of perf, yet.  Partly for
> the reason, I couldn't figure out the best way to integrate DAMON with perf.
> Especially, I couldn't straightforwardly classify DAMON providing information
> into one of the categories of the perf events I know.
> 
> Therefore, rather than integrating DAMON with perf in my arguable way and
> increasing the complexity of the code, I decided to keep the interface as
> simple and flexible as it can be for the first stage.  That said, I believe it
> would be not too hard to integrate DAMON with perf in a future.

I think I was unnecessarily worry about the best way.  I added a tracepoint to
the monitoring result writing logic of DAMON.  Other tracers including perf
would easily integrate DAMON using it, though the tracepoint is not highly
optimized yet.  Will post next version soon.


Thanks,
SeongJae Park

> 
> 
> Thanks,
> SeongJae Park
> 
> > 
> > -- 
> >  Kirill A. Shutemov
> > 
> >