[PATCH v5 0/2] sched_ext: lockless peek operation for DSQs

Ryan Newton posted 2 patches 1 month, 3 weeks ago
include/linux/sched/ext.h                     |   1 +
kernel/sched/ext.c                            |  58 +++-
tools/sched_ext/include/scx/common.bpf.h      |   1 +
tools/sched_ext/include/scx/compat.bpf.h      |  18 ++
tools/testing/selftests/sched_ext/Makefile    |   1 +
.../selftests/sched_ext/peek_dsq.bpf.c        | 251 ++++++++++++++++++
tools/testing/selftests/sched_ext/peek_dsq.c  | 224 ++++++++++++++++
7 files changed, 552 insertions(+), 2 deletions(-)
create mode 100644 tools/testing/selftests/sched_ext/peek_dsq.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/peek_dsq.c
[PATCH v5 0/2] sched_ext: lockless peek operation for DSQs
Posted by Ryan Newton 1 month, 3 weeks ago
This allows sched_ext schedulers an inexpensive operation to peek
at the first element in a queue (DSQ), without creating an iterator 
and acquiring the lock on that queue.

Note that manual testing has thus far included a modified version of the
example qmap scheduler that exercises peek, as well as a modified
modified LAVD (from the SCX repo) that exercises peek. The attached test
passes >1000 stress tests when run in concurrent VMs, and when run
sequentially on the host kernel. Presently, tested on the below
workstation and server processors.
- AMD Ryzen Threadripper PRO 7975WX 32-Cores
- AMD EPYC 9D64 88-Core Processor

Initial experiments indicate a substantial speedup (on schbench) when
running an SCX scheduler with per-cpu DSQs and peeking each queue to
retrieve the task with the minimum vruntime across all the CPUs.

---
Changes in v5:
 - minor comment tweak requested in review
 - add Reviewed-bys christian.loehle@arm.com

Changes in v4:
 - review comments (from arighi@nvidia.com) addressed, add Reviewed-by
 - make the test much lighter weight with 4 rather than 100 workers
 - link: https://lore.kernel.org/lkml/20251015015712.3996346-1-rrnewton@gmail.com/

Changes in v3:
 - inline helpers and simplify
 - coding style tweaks
 - link: https://lore.kernel.org/lkml/20251006170403.3584204-1-rrnewton@gmail.com/

Changes in v2:
 - make peek() only work for user DSQs and error otherwise
 - added a stress test component to the selftest that performs many peeks
 - responded to review comments from tj@kernel.org and arighi@nvidia.com 
 - link: https://lore.kernel.org/lkml/20251003195408.675527-1-rrnewton@gmail.com/
 
v1 link: https://lore.kernel.org/lkml/20251002025722.3420916-1-rrnewton@gmail.com/

Ryan Newton (2):
  sched_ext: Add lockless peek operation for DSQs
  sched_ext: Add a selftest for scx_bpf_dsq_peek

 include/linux/sched/ext.h                     |   1 +
 kernel/sched/ext.c                            |  58 +++-
 tools/sched_ext/include/scx/common.bpf.h      |   1 +
 tools/sched_ext/include/scx/compat.bpf.h      |  18 ++
 tools/testing/selftests/sched_ext/Makefile    |   1 +
 .../selftests/sched_ext/peek_dsq.bpf.c        | 251 ++++++++++++++++++
 tools/testing/selftests/sched_ext/peek_dsq.c  | 224 ++++++++++++++++
 7 files changed, 552 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/sched_ext/peek_dsq.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/peek_dsq.c

-- 
2.51.0
Re: [PATCH v5 0/2] sched_ext: lockless peek operation for DSQs
Posted by Tejun Heo 1 month, 3 weeks ago
On Wed, Oct 15, 2025 at 11:50:34AM -0400, Ryan Newton wrote:
> Ryan Newton (2):
>   sched_ext: Add lockless peek operation for DSQs
>   sched_ext: Add a selftest for scx_bpf_dsq_peek

Applied to sched_ext/for-6.19.

Thanks.

-- 
tejun