[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZeU6_BnXIUs6pCym@debian>
Date: Sun, 3 Mar 2024 19:07:40 -0800
From: fan <nifan.cxl@...il.com>
To: "Ho-Ren (Jack) Chuang" <horenchuang@...edance.com>
Cc: Hao Xiang <hao.xiang@...edance.com>,
Gregory Price <gourry.memverge@...il.com>,
aneesh.kumar@...ux.ibm.com, mhocko@...e.com, tj@...nel.org,
john@...alactic.com, Eishan Mirakhur <emirakhur@...ron.com>,
Vinicius Tavares Petrucci <vtavarespetr@...ron.com>,
Ravis OpenSrc <Ravis.OpenSrc@...ron.com>,
Alistair Popple <apopple@...dia.com>,
"Rafael J. Wysocki" <rafael@...nel.org>,
Len Brown <lenb@...nel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Dave Jiang <dave.jiang@...el.com>,
Dan Williams <dan.j.williams@...el.com>,
Jonathan Cameron <Jonathan.Cameron@...wei.com>,
Huang Ying <ying.huang@...el.com>, linux-acpi@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
"Ho-Ren (Jack) Chuang" <horenc@...edu>,
"Ho-Ren (Jack) Chuang" <horenchuang@...il.com>,
linux-cxl@...r.kernel.org, qemu-devel@...gnu.org
Subject: Re: [PATCH v1 0/1] Improved Memory Tier Creation for CPUless NUMA
Nodes
On Fri, Mar 01, 2024 at 08:22:44AM +0000, Ho-Ren (Jack) Chuang wrote:
> The memory tiering component in the kernel is functionally useless for
> CPUless memory/non-DRAM devices like CXL1.1 type3 memory because the nodes
> are lumped together in the DRAM tier.
> https://lore.kernel.org/linux-mm/PH0PR08MB7955E9F08CCB64F23963B5C3A860A@PH0PR08MB7955.namprd08.prod.outlook.com/T/
Is this the right patchset you want to refer to? It is about node
migration between tiers, how is it related to the context here?
Fan
>
> This patchset automatically resolves the issues. It delays the initialization
> of memory tiers for CPUless NUMA nodes until they obtain HMAT information
> at boot time, eliminating the need for user intervention.
> If no HMAT specified, it falls back to using `default_dram_type`.
>
> Example usecase:
> We have CXL memory on the host, and we create VMs with a new system memory
> device backed by host CXL memory. We inject CXL memory performance attributes
> through QEMU, and the guest now sees memory nodes with performance attributes
> in HMAT. With this change, we enable the guest kernel to construct
> the correct memory tiering for the memory nodes.
>
> Ho-Ren (Jack) Chuang (1):
> memory tier: acpi/hmat: create CPUless memory tiers after obtaining
> HMAT info
>
> drivers/acpi/numa/hmat.c | 3 ++
> include/linux/memory-tiers.h | 6 +++
> mm/memory-tiers.c | 76 ++++++++++++++++++++++++++++++++----
> 3 files changed, 77 insertions(+), 8 deletions(-)
>
> --
> Hao Xiang and Ho-Ren (Jack) Chuang
>
Powered by blists - more mailing lists