dask-sql icon indicating copy to clipboard operation
dask-sql copied to clipboard

[ENH] Join reordering improvements

Open sarahyurick opened this issue 2 years ago • 0 comments

https://github.com/dask-contrib/dask-sql/pull/1027 added basic join reordering functionality. However, there are several things that need to be fixed and improved upon in the future:

  • [ ] Probably the biggest improvement we need is to support join filters correctly. This should allow us to run query 72, which is expected to have the largest performance gain with join reordering. Other queries affected include queries 75 and 93
  • [ ] Ideally, the fact_dimension_ratio should be 0.3, but queries 17, 25, 29, and 85 currently fail without a stricter ratio. This suggests that more work needs to be done with reordering fact-to-fact joins
  • [ ] Check for deterministic filter expressions
  • [ ] Add Rust tests
  • [x] Consider exposing parameters to the user

sarahyurick avatar Mar 01 '23 21:03 sarahyurick