datafusion-contrib / datafusion-contrib/datafusion-distributed
[dynamic filtering] dynamic planning stats aren't accurate with dynamic filtering
Open
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 139
- Forks
- 67
- Avg merge
- 3d 1h
- Merged PRs (30d)
- 35
Description
In this plan, the probe SamplerExec overestimates the cost/rows because dynamic filters are not being applied to the DataSourceExec during the sampling period.
stage 3
HashJoinExec
NetworkShuffleExec
NetworkShuffleExec
stage 2 - build
RepartitionExec
SamplerExec
AggregateExec
DataSourceExec
stage 1 - probe
RepartitionExec
SamplerExec
AggregateExec
DataSourceExec
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing the SamplerExec and DataSourceExec interaction in the plan shown, focusing on the sampling period for the probe side. Check how dynamic filters are represented and applied during sampling. Done means the sampler no longer overestimates cost or rows because dynamic filters are omitted from DataSourceExec.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- distributed-systems
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100