datafusion-contrib / datafusion-contrib/liquid-cache

Add more real world benchmark

Open
#338 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Rust
Stars
452
Forks
51
Avg merge
3h 10m
Merged PRs (30d)
12

Description

Currently we have tpc-h and clickbench running in ci, while they are good benchmark they have their own problems:

  1. TPC-H is all synthetic data, the strings are not realistic, so it's irrelevant to our new work.
  2. ClickBench queries are a bit too simple, especially the filters

A few options:

  • Add TPC-DS -- but this is still synthetic data, but probably the filters/aggregations are more complex.
  • Add JOB -- the data is real, the queries seem to be legit. but it is more join order focused. Maybe we can extract the parts of the query plan that runs on liquid cache?
  • Investigate SQLStorm-- 1. they use real world dataset (StackOverflow dataset), 2. they seems to contain semantically relevant queries.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No repository files, tests, or entry points are named. Start by examining the existing TPC-H and ClickBench CI benchmarks, then compare the proposed TPC-DS, JOB, and SQLStorm options. Done means selecting and integrating a real-world benchmark with queries and data that exercise the cache meaningfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust, sql
Domain
data-engineering, performance
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.