Bloom filter Join Step I: create benchmark

[Lordworms]

Which issue does this PR close?

part of #7955

Closes #.

Rationale for this change

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

[alamb]

Thanks @Lordworms -- I realize i am very behind on reviews in DataFusion

My first question on these benchmarks is are they measuring the right thing (namely are they dominated by the join time). Have you had a chance to run any profiling (flamegraphs, etc) to confirm these benchmarks are actually join dominated?

[alamb]

Marking as draft as I think this PR is no longer waiting on feedback. Please mark it as ready for review when it is ready for another look

[Lordworms]

for TPCH query 17, when we create 1000000 rows for lineitem and part table, the time spent on join is 50% (the other 80% of time spent on creating parquet files)

[Lordworms]

For the second case, 95% of the time spent on join

[Lordworms]

I think it worth a try to implement join predicate pushdown

[alamb]

I suggest we revive this PR as it seems to have gotten lost / not reviewed 😢

[Lordworms]

I suggest we revive this PR as it seems to have gotten lost / not reviewed 😢

I am still working on the implementation of actual join_pushdown, I'll push a complete PR once it is done

[Lordworms]

I suggest we revive this PR as it seems to have gotten lost / not reviewed 😢

I am still working on the implementation of actual "hash_join build side statistic pushdown", I'll push a complete PR once it is done

[github-actions]

Thank you for your contribution. Unfortunately, this pull request is stale because it has been open 60 days with no activity. Please remove the stale label or comment or this will be closed in 7 days.