lance-format / lance-format/lance
Bench: Lance point lookup vs LMDB
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 7.1k
- Forks
- 852
- Avg merge
- 3d 18h
- Merged PRs (30d)
- 272
Description
Environment
- lance 0.30: https://pypi.org/project/pylance/0.30.0/
- pytest & pytest-benchmark
- ECS instance (volcano engine ecs.r3il.2xlarge)
- CPU: 8vCPU
- Mem: 64GB
- OS: Linux version 5.4.250-9-velinux1u1-amd6
Bench code
Code, designed by @ddupg.
The bench is ran on "memory://test.lance", which means all data is stored in memory.
Bench result
Simple Analysis
- As the batch size increases, the gap between Lance and LMDB narrows.
- With the increase in batch size and value size, version 2.1 shows a performance regression compared to version 2.0.
Future work
Recently, there has been a performance optimization(https://github.com/lancedb/lance/issues/4090) where Lance can benefit a lot in single-point lookup scenarios. I'm going to test it.
Related to https://github.com/lancedb/lance/issues/3983
Contributor guide
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 with the linked benchmark code in ddupg/lance-perf-test and compare its Lance and LMDB point-lookup measurements under the stated memory-backed environment. Read the optimization described in issue #4090 and the related issue #3983, then rerun the benchmark to determine whether the reported performance gap and regression remain.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, rust
- Domain
- databases, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100