Received-SPF: pass (google.com: domain of linux-kernel+bounces-208410-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 17:55:23 +0300 (EEST)
To: Reinette Chatre <reinette.chatre@intel.com>
cc: linux-kselftest@vger.kernel.org, Shuah Khan <shuah@kernel.org>, 
    =?ISO-8859-15?Q?Maciej_Wiecz=F3r-Retman?= <maciej.wieczor-retman@intel.com>, 
    Babu Moger <babu.moger@amd.com>, Fenghua Yu <fenghua.yu@intel.com>, 
    LKML <linux-kernel@vger.kernel.org>, 
    Shuah Khan <skhan@linuxfoundation.org>
Subject: Re: [PATCH v6 02/16] selftests/resctrl: Calculate resctrl FS derived
 mem bw over sleep(1) only
In-Reply-To: <3d6587a4-3e39-449b-a108-9f6893d4a405@intel.com>
Message-ID: <aac572c5-b130-9c3a-d991-7477ba552cfa@linux.intel.com>
References: <20240607125316.7089-1-ilpo.jarvinen@linux.intel.com> <20240607125316.7089-3-ilpo.jarvinen@linux.intel.com> <3d6587a4-3e39-449b-a108-9f6893d4a405@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="8323328-1374148641-1718031323=:1540"

  This message is in MIME format.  The first part should be readable text,
  while the remaining parts are likely unreadable without MIME-aware tools.

--8323328-1374148641-1718031323=:1540
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: QUOTED-PRINTABLE

On Fri, 7 Jun 2024, Reinette Chatre wrote:
> On 6/7/24 5:53 AM, Ilpo J=C3=A4rvinen wrote:
> > For MBM/MBA tests, measure_vals() calls get_mem_bw_imc() that performs
> > the measurement over a duration of sleep(1) call. The memory bandwidth
> > numbers from IMC are derived over this duration. The resctrl FS derived
> > memory bandwidth, however, is calculated inside measure_vals() and only
> > takes delta between the previous value and the current one which
> > besides the actual test, also samples inter-test noise.
> >=20
> > Rework the logic in measure_vals() and get_mem_bw_imc() such that the
> > resctrl FS memory bandwidth section covers much shorter duration
> > closely matching that of the IMC perf counters to improve measurement
> > accuracy.
> >=20
> > For the second read after rewind() to return a fresh value, also
> > newline has to be consumed by the fscanf().
> >=20
> > Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
> > Signed-off-by: Ilpo J=C3=A4rvinen <ilpo.jarvinen@linux.intel.com>
> > Tested-by: Babu Moger <babu.moger@amd.com>
> > ---
> >=20
> > v6:
> > - Adjust closing/rollback of the IMC perf
> > - Move the comment in measure_vals() to function level
> > - Capitalize MBM
> > - binded to -> bound to
>=20
> This change does not match the patch.
>=20
> > v5:
> > - Open mem bw file once and use rewind()
> > - Read \n from the mem bw file to allow rewind to return a new value.
> > v4:
> > - Open resctrl mem bw file (twice) beforehand to avoid opening it durin=
g
> >    the test
> > v3:
> > - Don't drop Return: entry from perf_open_imc_mem_bw() func comment
> > ---
> >   tools/testing/selftests/resctrl/resctrl_val.c | 141 +++++++++++------=
-
> >   1 file changed, 91 insertions(+), 50 deletions(-)
> >=20
> > diff --git a/tools/testing/selftests/resctrl/resctrl_val.c
> > b/tools/testing/selftests/resctrl/resctrl_val.c
> > index f55f5989de72..1575c5c09ac7 100644
> > --- a/tools/testing/selftests/resctrl/resctrl_val.c
> > +++ b/tools/testing/selftests/resctrl/resctrl_val.c
> > @@ -306,18 +306,13 @@ static void perf_close_imc_mem_bw(void)
> >   }
> >     /*
> > - * get_mem_bw_imc:=09Memory band width as reported by iMC counters
> > - * @cpu_no:=09=09CPU number that the benchmark PID is binded to
> > - * @bw_report:=09=09Bandwidth report type (reads, writes)
> > - *
> > - * Memory B/W utilized by a process on a socket can be calculated usin=
g
> > - * iMC counters. Perf events are used to read these counters.
> > + * perf_open_imc_mem_bw - Open perf fds for IMCs
> > + * @cpu_no: CPU number that the benchmark PID is bounded to
>=20
> "is bounded to" -> "is bound to"?
>=20
> Just the one nitpick from me. The patch looks good to me. Thank you
> very much.
>=20
> | Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>

I'll correct this in v7. I guess it's because I now make these corrections=
=20
"twice", once for the per patch changelog bullet and then the actual=20
change which unfortunately means my brains switch to repeated actions mode=
=20
=3D> autotype without thinking.

Earlier when I made the version changelogs only into 00/xx, I actually=20
read through the diff of diffs against the previous version in order to=20
find out what to write into the changelog. I ended up catching many error=
=20
like this in that stage. Now it's just mostly copying the pre-existing=20
entries from per patch changelogs (and less attention is obviously paid on=
=20
looking the diff of diffs because I no longer need to derive information
out of them).


--=20
 i.

--8323328-1374148641-1718031323=:1540--