Received-SPF: pass (google.com: domain of linux-kernel+bounces-97125-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 8 Mar 2024 15:59:02 +0200 (EET)
To: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
cc: Fenghua Yu <fenghua.yu@intel.com>, 
    Reinette Chatre <reinette.chatre@intel.com>, Shuah Khan <shuah@kernel.org>, 
    tony.luck@intel.com, "Shaopeng Tan (Fujitsu)" <tan.shaopeng@fujitsu.com>, 
    LKML <linux-kernel@vger.kernel.org>, linux-kselftest@vger.kernel.org
Subject: Re: [PATCH 2/4] selftests/resctrl: SNC support for CMT
In-Reply-To: <6181937a-54b4-8b17-0c24-734764a205d1@linux.intel.com>
Message-ID: <5983d1aa-6e1e-fb49-b95a-429a9decfe7f@linux.intel.com>
References: <cover.1709721159.git.maciej.wieczor-retman@intel.com> <75849cb145429798b21c23b6be4abd7ece9df57b.1709721159.git.maciej.wieczor-retman@intel.com> <6181937a-54b4-8b17-0c24-734764a205d1@linux.intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="8323328-330930196-1709906342=:9765"

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

--8323328-330930196-1709906342=:9765
Content-Type: text/plain; charset=ISO-8859-15
Content-Transfer-Encoding: QUOTED-PRINTABLE

On Fri, 8 Mar 2024, Ilpo J=E4rvinen wrote:

> On Wed, 6 Mar 2024, Maciej Wieczor-Retman wrote:
>=20
> > Cache Monitoring Technology (CMT) works by measuring how much data in L=
3
> > cache is occupied by a given process identified by its Resource
> > Monitoring ID (RMID).
> >=20
> > On systems with Sub-Numa Clusters (SNC) enabled, a process can occupy
> > not only the cache that belongs to its own NUMA node but also pieces of
> > other NUMA nodes' caches that lie on the same socket.
> >=20
> > A simple correction to make the CMT selftest NUMA-aware is to sum value=
s
> > reported by all nodes on the same socket for a given RMID.
> >=20
> > Reported-by: "Shaopeng Tan (Fujitsu)" <tan.shaopeng@fujitsu.com>
> > Closes: https://lore.kernel.org/all/TYAPR01MB6330B9B17686EF426D2C3F308B=
25A@TYAPR01MB6330.jpnprd01.prod.outlook.com/
> > Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
> > ---

> > @@ -828,6 +828,8 @@ int resctrl_val(const struct resctrl_test *test,
> >  =09sleep(1);
> > =20
> >  =09/* Test runs until the callback setup() tells the test to stop. */
> > +=09get_domain_id("L3", uparams->cpu, &res_id);
>=20
> Hardcoding L3 here limits the genericness of this function. You don't eve=
n=20
> need to do it, get_domain_id() does "MB" -> "L3" transformation implicitl=
y=20
> for you so you can just pass test->resource instead.
>=20
> Also, I don't understand why you now again make the naming inconsistent=
=20
> with "res_id".
>=20
> If you based this on top of the patches I just posted, resctl_val()=20
> already the domain_id variable.

Ah, I retract what I said. I see you actually want it only from L3.

> > +     res_id *=3D snc_ways();

I don't understand what this is trying to achieve and how.

--=20
 i.

--8323328-330930196-1709906342=:9765--