Dev/task local sched cri preempt #656

NamelessOIer · 2025-10-28T07:37:51Z

#656
= #654 + #657
= #650 + #596 + #657
= #625 + #610 + #596 + #657

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Enhance error handling. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Compile error Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> feat: Introduce step to crane fix: Job/Step recovery when ctld/craned down Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: AI comments Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> refactor: Introduce Configured status Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> refactor: ResourcesV2 mongodb serialization Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Remove step id entry if job finish Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Remove db entry if job finish Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Supervisor ctldclient Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> chore: Roll back proto from another branch Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> style: auto format with clang-format. refactor: Fix ai comments. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Solve AI comments Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> refactor: Fix AI comments Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Compile error Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Error status when free step/job rpc failure Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: map out of range Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix dead latch Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> refactor: Job/Step free rpc and cleanup. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Supervisor cleanup Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> style: auto format with clang-format. refactor: Introduce step id for crun/calloc/cfored Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Free jobs when daemon step configure error. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> refactor: Check step status before operate Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> chore: Change supervisor sleep time before send ready to serve reply. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Crun output ignored Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: ExceedTimelimit exit code. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Crun timeout Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Calloc step exec, step req resend timer. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Timer to execute task terminate/change timelimit req. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Suspend req to configuring step. Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> update step status change frequency Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Exit code Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> fix: Calloc Signed-off-by: Li Junlin <xiafeng.li@foxmail.com> feat: Introduce step for job suballocation Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

* doc: Update ubuntu doc * fix: Update GCC installation instructions for improved build process * fix: Specify GCC and G++ compilers in CMake commands for CGroup builds * docs: Fix docs --------- Co-authored-by: Nativu5 <44155313+Nativu5@users.noreply.github.com>

coderabbitai · 2025-10-28T07:38:15Z

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

✨ Finishing touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch dev/task_local_sched_cri_preempt

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

L-Xiafeng and others added 30 commits October 16, 2025 18:43

style: auto format with clang-format.

da687ad

fix: Duplicate ctld server

ac7a21a

Remove duplicate debug log for freeing resource

f42a3f5

refactor

bc3e582

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix comments

9630078

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

feat: local_scheduler

1a4afb3

fix: Lost job steps not terminated, calloc job error.

7fdedd3

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: Status string, remove sleep in CranedClient.cpp

8efbb94

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

refactor step db

c3c1634

style: auto format with clang-format.

290eb58

fix

a47104d

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: update job and step insertion logic to use upsert with filters

1144993

style: auto format with clang-format.

e7b3ef3

update step in mongo db

eb44c05

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: Use unique ptr for FreeStepAllocation_

2567321

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: db mutex

536c4d7

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: thread pool task capture

1647800

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: TerminateOrphanedSteps

5701a9d

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: Handle not existed step in StepStatusChange

b47f876

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: check step is null before check step id

130b6db

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: Fix error in systemd unit file and add doc (#646)

dbe7af4

feat: Add CRI task management support

349e34b

refactor: Refactored

bee32c6

refactor: Refactor helpers

00cd57b

fix: Fix warnings and add logs

72b83f4

fix: Fix CRI container termination

737df87

fix: Fix destruct order

e37de17

refactor: Use rich err in CRI

ca17b61

feat: preempt (Unstable)

a823404

NamelessOIer and others added 4 commits October 28, 2025 17:44

allow disable & bugfix

f73e1c9

feat: Add CPU binding functionality for cgroup v1 and v2

d41551b

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

bugfix

19d7045

refactor.

1150f6c

NamelessOIer force-pushed the dev/task_local_sched_cri_preempt branch from a4e8bc7 to 1150f6c Compare October 30, 2025 16:19

L-Xiafeng and others added 2 commits October 31, 2025 12:37

add cpu bind config

2a22564

Signed-off-by: Li Junlin <xiafeng.li@foxmail.com>

fix: priority bound

d060145

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Dev/task local sched cri preempt #656

Dev/task local sched cri preempt #656

Uh oh!

NamelessOIer commented Oct 28, 2025 •

edited

Loading

Uh oh!

coderabbitai bot commented Oct 28, 2025

Review skipped

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Dev/task local sched cri preempt #656

Are you sure you want to change the base?

Dev/task local sched cri preempt #656

Uh oh!

Conversation

NamelessOIer commented Oct 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

coderabbitai bot commented Oct 28, 2025

Review skipped

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

NamelessOIer commented Oct 28, 2025 •

edited

Loading