Subject	sched: Scale cache-aware aggregation at LLC granularity
Author	wujianyong@hygon.cn
Date	2026-08-27 12:27:54 +0000 UTC
Version	Version 2
Cc	akpm@linux-foundation.org bsegall@google.com david@kernel.org dietmar.eggemann@arm.com huangsj@hygon.cn jianyong.wu@outlook.com juri.lelli@redhat.com justin.he@arm.com kprateek.nayak@amd.com linux-kernel@vger.kernel.org linux-mm@kvack.org mgorman@suse.de mingo@redhat.com pauld@redhat.com peterz@infradead.org rostedt@goodmis.org sshegde@linux.ibm.com tim.c.chen@linux.intel.com vincent.guittot@linaro.org vschneid@redhat.com wangfengyu@hygon.cn wujianyong@hygon.cn xiaowu.417@qq.com yingzhiwei@hygon.cn yu.c.chen@intel.com zhongyuan@hygon.cn

Patches (23)

Name	Content [All]
[RFC PATCH v2 01/23] sched/topology: Add llc_to_node() to translate LLC id to NUMA node	[Body]
[RFC PATCH v2 02/23] sched/topology: Introduce a NUMA distance matrix with unique distance values	[Body]
[RFC PATCH v2 03/23] sched/topology: Introduce a macro to traverse node	[Body]
[RFC PATCH v2 04/23] sched/topology: Introduce a method to calculate the llc distance	[Body]
[RFC PATCH v2 05/23] sched/topology: Introduce a macro to traverse LLC inside node	[Body]
[RFC PATCH v2 06/23] sched/topology: Add sd_node for the NODE sched domain	[Body]
[RFC PATCH v2 07/23] sched/cache: Prioritize preferred NUMA node selection over LLC selection	[Body]
[RFC PATCH v2 08/23] sched/topology: Introduce a per-CPU tasks NUMA preferred counter	[Body]
[RFC PATCH v2 09/23] sched/cache: Account percpu sd task NUMA preference	[Body]
[RFC PATCH v2 10/23] sched/topology: Add per-sd scratch for the load balance affinity score	[Body]
[RFC PATCH v2 11/23] sched/cache: Introduce helpers for task migration decisions	[Body]
[RFC PATCH v2 12/23] sched/cache: Introduce rq affinity gain calculation	[Body]
[RFC PATCH v2 13/23] sched/cache: Pick optimal src rq/group using affinity promotion metric	[Body]
[RFC PATCH v2 14/23] sched/cache: Drop prefer_sibling restriction for llc_balance	[Body]
[RFC PATCH v2 15/23] sched/cache: Judge migration eligibility in LLC granularity	[Body]
[RFC PATCH v2 16/23] sched/cache: Allow un-throttled active balance to spread out of a full LLC	[Body]
[RFC PATCH v2 17/23] sched/fair: Fine-granularity NUMA balancing	[Body]
[RFC PATCH v2 18/23] sched/cache: Scan all prefer nodes in thread group	[Body]
[RFC PATCH v2 19/23] sched/cache: Remove preferred LLC/node check no longer needed	[Body]
[RFC PATCH v2 20/23] sched/cache: Estimate utilization of the whole thread group	[Body]
[RFC PATCH v2 21/23] sched/cache: Spread workloads within an estimated LLC range	[Body]
[RFC PATCH v2 22/23] sched/cache: Walk the preferred node from the preferred LLC	[Body]
[RFC PATCH v2 23/23] sched/debug: Print task preferred LLC for scheduler debugging	[Body]

Sessions