[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <aXUIoSSL2hZPKf0p@x1>
Date: Sat, 24 Jan 2026 10:00:01 -0800
From: Drew Fustini <fustini@...nel.org>
To: Reinette Chatre <reinette.chatre@...el.com>
Cc: Paul Walmsley <pjw@...nel.org>, Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>, Alexandre Ghiti <alex@...ti.fr>,
Radim Krčmář <rkrcmar@...tanamicro.com>,
Samuel Holland <samuel.holland@...ive.com>,
Adrien Ricciardi <aricciardi@...libre.com>,
Nicolas Pitre <npitre@...libre.com>,
Kornel Dulęba <mindal@...ihalf.com>,
Atish Patra <atish.patra@...ux.dev>,
Atish Kumar Patra <atishp@...osinc.com>,
Vasudevan Srinivasan <vasu@...osinc.com>,
Ved Shanbhogue <ved@...osinc.com>,
yunhui cui <cuiyunhui@...edance.com>,
Chen Pei <cp0613@...ux.alibaba.com>,
Liu Zhiwei <zhiwei_liu@...ux.alibaba.com>,
Weiwei Li <liwei1518@...il.com>, guo.wenjia23@....com.cn,
liu.qingtao2@....com.cn, Conor Dooley <conor+dt@...nel.org>,
Krzysztof Kozlowski <krzk+dt@...nel.org>,
Rob Herring <robh+dt@...nel.org>, Tony Luck <tony.luck@...el.com>,
Babu Moger <babu.moger@....com>,
Peter Newman <peternewman@...gle.com>,
Fenghua Yu <fenghua.yu@...el.com>,
James Morse <james.morse@....com>, Ben Horgan <ben.horgan@....com>,
Dave Martin <Dave.Martin@....com>, devicetree@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-riscv@...ts.infradead.org,
x86@...nel.org, Conor Dooley <conor.dooley@...rochip.com>
Subject: Re: [PATCH RFC 00/19] RISC-V: QoS: add CBQRI resctrl interface
On Thu, Jan 22, 2026 at 02:31:06PM -0800, Reinette Chatre wrote:
> Hi Drew,
>
> On 1/19/26 8:14 PM, Drew Fustini wrote:
> > - No MBM (bandwidth monitoring)
> > - MBA schema works ok for the CBQRI-enabled memory controllers, but
> > resctrl does not currently have solution for representing MBM for
> > bandwidth resources that are not associated with a L3 cache.
> > - For the old CBQRI proof-of-concept RFC, two separate domains were
> > created for each memory controller: one for MB (allocation) and one
> > for MBM (monitoring).
> > - The monitoring domains had to pretend that these memory controllers
> > were L3 caches which is not the case. I have removed this as it was
> > too complicated and not the right solution.
> > - Fenghua Yu talked about a similar problem last month at LPC in the
> > resctrl BoF during the "MBA/MBM on CPU-less Memory Node" topic:
> > https://lpc.events/event/19/contributions/2093/
> > - I hope to work with resctrl developers on finding a solution.
>
> Specific to this open, could you please consider [1] that proposes a way for
> resctrl to handle allocation and monitoring of resources at different scope?
Thank you for pointing that out. I think that the different scope for
bandwidth monitoring would fit CBQRI well. I will reply in that other
thread.
-Drew
Powered by blists - more mailing lists