[VL] UnboundedWindowFunctionFrame OOM when partition is large
- Dominant language
- Scala
- Stars
- 1.6k
- Forks
- 657
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 85
Description
### Backend
VL (Velox)
### Bug description
UnboundedWindowFunctionFrame is entire Partition Frame, velox will load the entire partition's data into memory, which may cause OOM.
For example:
```
select *, sum(c1) over () as sum from t
```
### Gluten version
_No response_
### Spark version
None
### Spark configurations
_No response_
### System information
_No response_
### Relevant logs
```bash
```
Contributor guide
Research direction
Start by reproducing the supplied `select *, sum(c1) over () as sum from t` query with a large partition, then trace `UnboundedWindowFunctionFrame` in the Velox backend. Done means the unbounded window no longer loads the entire partition into memory and still returns correct results; add a regression test covering the large-partition case.
Written by the indexing model from the issue text.
Assessment
- Domain
- backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100