Skip to content

feat: Separate setup stage in manager #5278

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 10 commits into
base: main
Choose a base branch
from
Draft

feat: Separate setup stage in manager #5278

wants to merge 10 commits into from
+1,810 −1

Conversation

HyeockJinKim
Copy link
Collaborator

resolves #NNN (BA-MMM)

Checklist: (if applicable)

  • Milestone metadata specifying the target backport version
  • Mention to the original issue
  • Installer updates including:
    • Fixtures for db schema changes
    • New mandatory config options
  • Update of end-to-end CLI integration tests in ai.backend.test
  • API server-client counterparts (e.g., manager API -> client SDK)
  • Test case(s) to:
    • Demonstrate the difference of before/after
    • Demonstrate the flow of abstract/conceptual models with a concrete implementation
  • Documentation
    • Contents in the docs directory
    • docstrings in public interfaces and type annotations

@HyeockJinKim
feat: Implement initial setup for Etcd and EventHub provisioners
9b470f5
@HyeockJinKim
feat: Iplement infrastructure provisioners for ETCD, EventHub, databa…
3d631e9 
…se, Redis, and storage management
@HyeockJinKim
feat: Add distributed lock and event producer provisioners with messa…
7b2a7ae 
…ge queue setup
@HyeockJinKim
feat: Add initial implementations for plugins
44c419c
@HyeockJinKim
feat: Add service discovery and repositories provisioners
2894098
@HyeockJinKim
feat: Implement core manager components including AgentRegistry, Idle…
f8bd98e 
…Checker, and SchedulerDispatcher provisioners
@HyeockJinKim
feat: Add background task manager and event dispatcher provisioners w…
c87bc41 
…ith processors setup
@HyeockJinKim
feat: Add StaleSession and StaleKernel sweeper provisioners with task…
8fe6b60 
… management
@HyeockJinKim
refactor: Remove unused kernel hang tolerance logic from StaleKernelS…
8562da5 
…weeperProvisioner
@HyeockJinKim
feat: Implement ManagerSetupStage with comprehensive provisioners and…
954f913 
… resource management
@HyeockJinKim HyeockJinKim requested a review from fregataa July 25, 2025 04:24
@HyeockJinKim HyeockJinKim self-assigned this Jul 25, 2025
@github-actions github-actions bot added size:XL 500~ LoC comp:manager Related to Manager component comp:common Related to Common component labels Jul 25, 2025
github-advanced-security[bot]
github-advanced-security bot found potential problems Jul 25, 2025
View reviewed changes
src/ai/backend/manager/setup/background/sweepers.py
return "stale_session_sweeper"

async def setup(self, spec: StaleSessionSweeperSpec) -> SweeperTask:
# TODO: Resolve type issue and, Use `session_hang_tolerance` from the unified config

Check notice

Code scanning / devskim

A "TODO" or similar was left in source code, possibly indicating incomplete functionality Note

Suspicious comment
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@fregataa fregataa Awaiting requested review from fregataa

Copilot code review Copilot Awaiting requested review from Copilot Copilot will automatically review once the pull request is marked ready for review

Assignees

@HyeockJinKim HyeockJinKim

Labels
comp:common Related to Common component comp:manager Related to Manager component size:XL 500~ LoC
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@HyeockJinKim