Skip to content

RFC autonuma: Optimize memory placement in memory tiering system

Huang, Ying linux-mm lkml oe-kbuild-all 1 version In review

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 RFC Latest8 patches 4 repliesIn review

v2 from the cover letter

- Addressed comments for V1.

- Rebased on v5.5.

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/8autonuma: Add NUMA_BALANCING_MEMORY_TIERING modeinclude/linux/sched/sysctl.h kernel/sched/core.c kernel/sysctl.c+12 -90 replies
2/8autonuma, memory tiering: Rate limit NUMA migration throughputinclude/linux/mmzone.h include/linux/sched/sysctl.h kernel/sched/fair.c +2 more+86 -02 replies
3/8autonuma, memory tiering: Use kswapd to demote cold pages to PMEMmm/migrate.c mm/vmscan.c+24 -92 replies
4/8autonuma, memory tiering: Skip to scan fastest memorymm/huge_memory.c mm/mprotect.c+34 -100 replies
5/8autonuma, memory tiering: Only promote page if accessed twicemm/huge_memory.c mm/memory.c mm/mprotect.c+45 -150 replies
6/8autonuma, memory tiering: Select hotter pages to promote to fast memory nodeinclude/linux/mempolicy.h include/linux/mm_types.h include/linux/sched/numa_balancing.h +6 more+108 -200 replies
7/8autonuma, memory tiering: Double hot threshold for write hint page faultinclude/linux/sched/numa_balancing.h kernel/sched/fair.c mm/memory.c+6 -00 replies
8/8autonuma, memory tiering: Adjust hot threshold automaticallyinclude/linux/mmzone.h kernel/sched/fair.c+39 -40 replies

Reviews trailers per patch

No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.

Read the v1 thread

Cover letter [RFC -V2 0/8] autonuma: Optimize memory placement in memory tiering system

From: Huang Ying <[email protected]>

With the advent of various new memory types, there may be multiple memory types in one system, e.g. DRAM and PMEM (persistent memory). Because the performance and cost of the different types of memory may be different, the memory subsystem of the machine could be called the memory tiering system.

After commit c221c0b0308f ("device-dax: "Hotplug" persistent memory for use like normal RAM"), the PMEM could be used as the cost-effective volatile memory in separate NUMA nodes. In a typical memory tiering system, there are CPUs, DRAM and PMEM in each physical NUMA node. The CPUs and the DRAM will be put in one logical node, while the PMEM will be put in another (faked) logical node.

To optimize the system overall performance, the hot pages should be placed in DRAM node. To do that, we need to identify the hot pages in the PMEM node and migrate them to DRAM node via NUMA migration.

While in autonuma, there are a set of existing mechanisms to identify the pages recently accessed by the CPUs in a node and migrate the pages to the node. So we can reuse these mechanisms to build mechanisms to optimize page placement in the memory tiering system. This has been implemented in this patchset.

At the other hand, the cold pages should be placed in PMEM node. So, we also need to identify the cold pages in the DRAM node and migrate them to PMEM node.

In the following patchset,

[PATCH 0/4] [RFC] Migrate Pages in lieu of discard
https://lore.kernel.org/linux-mm/[email protected]/

A mechanism to demote the cold DRAM pages to PMEM node under memory pressure is implemented. Based on that, the cold DRAM pages can be demoted to PMEM node proactively to free some memory space on DRAM node. And this frees space on DRAM node for the hot PMEM pages to be migrated to. This has been implemented in this patchset too.

The patchset is based on the following not-yet-merged patchset (after being rebased to v5.5):

[PATCH 0/4] [RFC] Migrate Pages in lieu of discard
https://lore.kernel.org/linux-mm/[email protected]/

This is part of a larger patch set. If you want to apply these or play with them, I'd suggest using the tree from below,

https://github.com/hying-caritas/linux/commits/autonuma-r2

With all above optimization, the score of pmbench memory accessing benchmark with 80:20 read/write ratio and normal access address distribution improves 116% on a 2 socket Intel server with Optane DC Persistent Memory.

Changelog:

v2:

- Addressed comments for V1.

- Rebased on v5.5.

Best Regards,
Huang, Ying