Skip to content

Adjust NUMA imbalance for multiple LLCs

Mel Gorman lkml 5 versions – Applied

Status from this message: The following commit has been merged into the sched/core branch of tip:

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v6 Latest2 patches 10 repliesApplied
  2. v52 patches 4 repliesSuperseded
  3. v42 patches 19 repliesSuperseded
Earlier versions · 2
VersionPostedPatchesRepliesStatus
v32 patches13 repliesSuperseded
v12 patches1 replySuperseded

Changelog since V4 from the cover letter

o Scale imbalance based on the top domain that prefers siblings
o Keep allowed imbalance as 2 up to the point where LLCs can be overloaded

Patches in v6 Applied

#Subject and filesSizeRepliesApplied
1/2sched/fair: Improve consistency of allowed NUMA balance calculationskernel/sched/fair.c+10 -83 replies
2/2sched/fair: Adjust the allowed NUMA imbalance when SD_NUMA spans multiple LLCsinclude/linux/sched/topology.h kernel/sched/fair.c kernel/sched/topology.c+66 -106 replies

Reviews trailers per patch

All 2 patches have a Reviewed-by or Acked-by.

PatchGautham R. ShenoyK Prateek NayakJirka HladkyVincent GuittotSrikar Dronamraju
1/2R-b R-b R-b
2/2R-b T-b T-b R-b R-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 5 reviewers.

Read the v6 thread

Cover letter [PATCH v6 0/2] Adjust NUMA imbalance for multiple LLCs

Changelog sinve v5
o Fix off-by-one error

Changelog since V4
o Scale imbalance based on the top domain that prefers siblings
o Keep allowed imbalance as 2 up to the point where LLCs can be overloaded

Changelog since V3
o Calculate imb_numa_nr for multiple SD_NUMA domains
o Restore behaviour where communicating pairs remain on the same node

Commit 7d2b5dd0bcc4 ("sched/numa: Allow a floating imbalance between NUMA nodes") allowed an imbalance between NUMA nodes such that communicating tasks would not be pulled apart by the load balancer. This works fine when there is a 1:1 relationship between LLC and node but can be suboptimal for multiple LLCs if independent tasks prematurely use CPUs sharing cache.

The series addresses two problems -- inconsistent logic when allowing a NUMA imbalance and sub-optimal performance when there are many LLCs per NUMA node.

 include/linux/sched/topology.h |  1 +
 kernel/sched/fair.c            | 30 ++++++++++---------
 kernel/sched/topology.c        | 53 ++++++++++++++++++++++++++++++++++
 3 files changed, 71 insertions(+), 13 deletions(-)
Signature · 1 line
2.31.1