From: Babu Moger <babu.moger@amd.com>
To: Ben Horgan <ben.horgan@arm.com>,
Reinette Chatre <reinette.chatre@intel.com>,
Fenghua Yu <fenghuay@nvidia.com>, Tony Luck <tony.luck@intel.com>,
James Morse <james.morse@arm.com>,
Dave Martin <Dave.Martin@arm.com>,
Drew Fustini <fustini@kernel.org>, Chen Yu <yu.c.chen@intel.com>
Cc: Borislav Petkov <bp@alien8.de>,
Thomas Gleixner <tglx@linutronix.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
Peter Newman <peternewman@google.com>,
"x86@kernel.org" <x86@kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [RFC] mpam,x86,fs/resctrl: Generic schema description Proof of Concept
Date: Tue, 4 Aug 2026 09:09:30 -0500 [thread overview]
Message-ID: <e6fabf7e-1b78-4e73-b743-f756e42ee0cf@amd.com> (raw)
In-Reply-To: <618ba724-d734-43d3-b90e-11ba7f31c2b6@arm.com>
Hi Ben,
On 8/4/26 04:11, Ben Horgan wrote:
> Hi Babu,
>
> On 7/22/26 18:02, Babu Moger wrote:
>> Hi Ben,
>>
>> On 7/22/26 05:47, Ben Horgan wrote:
>>> Hi Babu,
>>>
>>> On 7/21/26 21:02, Babu Moger wrote:
>>>> Hi Ben/Reinette,
>>>>
>>>> On 7/21/26 12:30, Reinette Chatre wrote:
>>>>> Hi Ben,
>>>>>
>>>>> On 7/21/26 6:23 AM, Ben Horgan wrote:
>>>>>> On 7/20/26 23:54, Reinette Chatre wrote:
>>>>>>> On 7/20/26 6:30 AM, Ben Horgan wrote:
>>>>> ...>
>>>>>> The former, info/ contains a directory for each allocation scope of each resource.
>>
>>>>>>>
>>>>>>> The other x86 feature to consider is AMD's upcoming "Global" MBA/SMBA that exposes memory
>>>>>>> bandwidth allocation
>>>>>>> in "groups of L3" that I understand could usually be mapped to NODE scope (but it remains
>>>>>>> controlled at L3 scope),
>>>>>>> except for one configuration where it is "SYSTEM"(?) scope.
>>>>>>> Ref.: https://lore.kernel.org/
>>>>>>> lkml/8f77f498b1c77fa8fd8f5d5687f03ae598068544.1776980182.git.babu.moger@amd.com/
>>>>>>
>>>>>> Hmmm, I'm not sure that the scope can be considered to be NODE scope for GMBA. To me it seems
>>>>>> to be
>>>>>> accidental that it maps to the NUMA node but really the scope is just a grouping of L3 instances.
>>>>>> For a control to NUMA scope I would expect the resctrl domains to go offline and online in sync
>>>>>> with
>>>>>> the NUMA nodes. For GMBA it looks like it would just going offline/online based on whether any of
>>>>>> the CPUs and so L3 instances in the group are online. Am I correct here?
>>>>>>
>>>>>> Assuming the domains are on L3 groups rather than NUMA also changes which end of the link the
>>>>>> traffic is regulated and so how cross-NUMA traffic behaves differently. If the domain is an L3
>>>>>> group
>>>>>> then a task running on a CPU affine to that L3 group won't be throttled unless that particular
>>>>>> domain is throttled but with NUMA node domains it may be throttled if it has traffic going to that
>>>>>> domain.
>>>>>
>>>>> I'll defer to Babu for accurate answers about this hardware capability.
>>>>>
>>>>
>>>> To me, Global MBA should be considered a NODE-scoped resource. In some configurations it may appear
>>>> as SYSTEM-scoped, but that is effectively equivalent to a single-node encompassing the entire
>>>> system. In such cases, there is only one schemata entry controlling the whole system.
>>>>
>>>> Yes, multiple L3 instances are grouped together to form a NODE. Internally, programming is still
>>>> performed at the L3 level, but that implementation detail can be hidden from users and does not need
>>>> to be exposed through the interface.
>>>
>>> We seem to have two things that can both, somewhat reasonably, be called NODE scope in the resctrl
>>> user interface but the behaviour required for an MPAM system and an AMD system appears different
>>> from the point of view of lifecycle of the resctrl domain.
>>>
>>> For MPAM NUMA scope the MSC instance (MPAM hardware interface) is at the memory controller and so
>>> goes on and offline based on whether the NUMA node is offline or online. For AMD NUMA scope it looks
>>> to me that the lifecycle of the resctrl domains would be tied to the CPUs associated with the NUMA
>>> node. To me it does seem odd that a control with a domain associated with an offline NUMA node can
>>> continue to throttle (cross-NUMA) traffic.
>>>
>>> Is there any GLBE Control Domain ID or similar that is exposed to the user, e.g. is sysfs, or is
>>> this just implicitly the NUMA id?
>>>
>> Yes, the GLBE Control Domain ID is exposed to the user. It is essentially equivalent to the NUMA ID.
>
> What's the on/off lifecycle of these nodes? Does it follow the NUMA lifecycle as managed by the NUMA
> node notifiers documented in Documentation/core-api/memory-hotplug.rst or is it just linked to the
> cpu hotplug as is done currently for the resctrl cache based domains.
>
It will follow the CPU hotplug lifecycle, similar to how it is currently
handled for the resctrl cache-based domains.
Thanks,
Babu
next prev parent reply other threads:[~2026-08-04 14:09 UTC|newest]
Thread overview: 108+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-29 18:06 Reinette Chatre
2026-06-02 20:23 ` Babu Moger
2026-06-02 22:56 ` Reinette Chatre
2026-06-03 1:14 ` Moger, Babu
2026-06-03 3:55 ` Reinette Chatre
2026-06-03 14:40 ` Babu Moger
2026-06-02 23:32 ` Chen, Yu C
2026-06-03 3:45 ` Reinette Chatre
2026-06-03 11:53 ` Chen, Yu C
2026-06-04 16:37 ` Reinette Chatre
2026-06-05 15:43 ` Chen, Yu C
2026-06-05 16:20 ` Reinette Chatre
2026-06-03 15:15 ` Ben Horgan
2026-06-03 19:34 ` Drew Fustini
2026-06-04 11:24 ` Ben Horgan
2026-06-04 17:38 ` Drew Fustini
2026-06-12 1:30 ` Shaopeng Tan (Fujitsu)
2026-06-17 15:29 ` Reinette Chatre
2026-06-19 1:42 ` Shaopeng Tan (Fujitsu)
2026-06-22 16:10 ` Reinette Chatre
2026-06-23 5:04 ` Shaopeng Tan (Fujitsu)
2026-06-04 21:05 ` Reinette Chatre
2026-06-05 19:35 ` Drew Fustini
2026-06-06 5:10 ` Drew Fustini
2026-06-06 5:23 ` Drew Fustini
2026-06-04 17:43 ` Reinette Chatre
2026-06-05 14:53 ` Ben Horgan
2026-06-05 15:39 ` Reinette Chatre
2026-06-05 16:37 ` Ben Horgan
2026-06-08 16:16 ` Reinette Chatre
2026-06-09 10:10 ` Ben Horgan
2026-06-09 15:28 ` Reinette Chatre
2026-06-09 16:37 ` Ben Horgan
2026-06-09 17:41 ` Reinette Chatre
2026-06-10 7:09 ` Chen, Yu C
2026-06-10 14:27 ` Chen, Yu C
2026-06-10 16:13 ` Reinette Chatre
2026-06-10 17:57 ` Chen, Yu C
2026-06-10 18:10 ` Reinette Chatre
2026-06-10 15:59 ` Reinette Chatre
2026-06-10 18:05 ` Chen, Yu C
2026-06-11 3:26 ` Chen, Yu C
2026-06-11 15:45 ` Reinette Chatre
2026-06-26 15:46 ` Chen, Yu C
2026-07-02 14:27 ` Ben Horgan
2026-07-03 9:01 ` Chen, Yu C
2026-07-14 21:37 ` Reinette Chatre
2026-07-15 2:49 ` Chen, Yu C
2026-06-10 4:31 ` Drew Fustini
2026-06-10 15:14 ` Reinette Chatre
2026-06-03 18:46 ` Luck, Tony
2026-06-04 10:02 ` Ben Horgan
2026-06-04 21:42 ` Reinette Chatre
2026-07-08 12:56 ` Chen, Yu C
2026-07-14 21:39 ` Reinette Chatre
2026-06-03 22:14 ` Drew Fustini
2026-06-04 21:47 ` Reinette Chatre
2026-06-05 19:48 ` Drew Fustini
2026-06-15 21:05 ` Moger, Babu
2026-06-17 17:18 ` Reinette Chatre
2026-06-17 20:29 ` Babu Moger
2026-06-24 19:08 ` Fenghua Yu
2026-06-24 22:22 ` Reinette Chatre
2026-06-25 1:26 ` Fenghua Yu
2026-06-25 15:43 ` Reinette Chatre
2026-07-10 20:59 ` Fenghua Yu
2026-07-14 22:06 ` Reinette Chatre
2026-07-15 8:34 ` Ben Horgan
2026-07-15 15:41 ` Reinette Chatre
2026-07-16 14:59 ` Ben Horgan
2026-07-16 16:02 ` Luck, Tony
2026-07-16 16:22 ` Ben Horgan
2026-07-16 17:50 ` Reinette Chatre
2026-07-17 10:27 ` Ben Horgan
2026-07-16 16:04 ` Reinette Chatre
2026-07-16 16:44 ` Ben Horgan
2026-07-16 17:07 ` Reinette Chatre
2026-07-17 12:20 ` Ben Horgan
2026-07-17 16:00 ` Reinette Chatre
2026-07-20 13:30 ` Ben Horgan
2026-07-20 22:54 ` Reinette Chatre
2026-07-21 13:23 ` Ben Horgan
2026-07-21 17:30 ` Reinette Chatre
2026-07-21 20:02 ` Babu Moger
2026-07-22 10:47 ` Ben Horgan
2026-07-22 17:02 ` Babu Moger
2026-08-04 9:11 ` Ben Horgan
2026-08-04 14:09 ` Babu Moger [this message]
2026-08-04 15:11 ` Ben Horgan
2026-08-04 19:51 ` Babu Moger
2026-08-05 6:06 ` Reinette Chatre
2026-08-06 9:24 ` Ben Horgan
2026-08-07 22:53 ` Reinette Chatre
2026-07-22 10:03 ` Ben Horgan
2026-07-22 16:32 ` Reinette Chatre
2026-07-23 7:58 ` Ben Horgan
2026-07-23 15:52 ` Reinette Chatre
2026-07-23 22:08 ` Fenghua Yu
2026-07-27 9:13 ` Ben Horgan
2026-07-17 16:02 ` Chen, Yu C
2026-07-17 16:55 ` Reinette Chatre
2026-07-23 0:17 ` Fenghua Yu
2026-07-23 16:18 ` Reinette Chatre
2026-07-23 22:27 ` Fenghua Yu
2026-07-23 23:31 ` Reinette Chatre
2026-07-02 13:37 ` Ben Horgan
2026-07-02 15:16 ` Fenghua Yu
2026-07-03 13:42 ` Ben Horgan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=e6fabf7e-1b78-4e73-b743-f756e42ee0cf@amd.com \
--to=babu.moger@amd.com \
--cc=Dave.Martin@arm.com \
--cc=ben.horgan@arm.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=fenghuay@nvidia.com \
--cc=fustini@kernel.org \
--cc=james.morse@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peternewman@google.com \
--cc=reinette.chatre@intel.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=x86@kernel.org \
--cc=yu.c.chen@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®