apache / apache/datafusion-ballista

Ballista cluster sharing by multiple users (with fairness of resource allocation)

Open
#13 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Rust
Stars
2.1k
Forks
320
Avg merge
1d 22h
Merged PRs (30d)
66

Description

**Is your feature request related to a problem or challenge? Please describe what you are trying to do.**
Let's say we've an organization that deploys ballista cluster to which multiple users connect to. It'd be great if executor slots can be allocated to the users fairly. If a query has consumed all slots allotted to a user, it can't progress until more slots are generated (say by passage of time).

**Describe the solution you'd like**
Each query execution is associated with some identity, identities are rate limited for the slots and tasks for the identities are queued and consumed at allowed rate (or concurrency)

**Describe alternatives you've considered**

**Additional context**
Add any other context or screenshots about the feature request here.

Contributor guide

Open the contributing guide

Research direction

The issue names no files, tests, or entry points. Start by locating Ballista's query identity, executor-slot, and task-scheduling components, then define how per-identity rate or concurrency limits and queuing should work; done means multiple users receive fair allocation while excess tasks wait.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
distributed-systems
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.