Benchmark randomness vs performance tradeoff

Open
#4 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Stale
Tech stack
python
Domain
data-engineering, performance

Research direction

Start with the cited paper and inspect annbatch's block-based loader; the issue names no files, tests, or benchmark entry points. Define measurements for on-disk chunk size, read throughput, and randomness, then document the chunk-size threshold and its performance tradeoff.

Written by the indexing model from the issue text.

Description

It is clear (see https://arxiv.org/pdf/2506.01883) that there is a tradeoff in block-based loaders between randomness and read throughput. Generally, more randomness entails less read throughput.

  • At what chunk size on-disk does either pre-shuffling become unnecessary? Is this chunk size performant and what is the tradeoff?
Dominant language
Python
Stars
68
Forks
6
Avg merge
7h 24m
Merged PRs (30d)
6

Contributor guide

Open the contributing guide

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.

More from scverse/annbatch

All issues in scverse/annbatch

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.