lance-format / lance-format/lance-data-viewer

[bug]: high latency when loading dataset from NFS

Open
#65 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
60
Forks
9
Avg merge
10m
Merged PRs (30d)
4

Description

Container tag

lancedb-0.29.2 (recommended)

Host OS

macos

Lance data source

No response

What happened?

Hi team, I'm actively using lance data viewer in my daily work. I found when loading dataset from remote storage like NFS, the latency is significantly high.
For example, I ran the viewer in San Jose, when hitting the "connect" button to load a 1GiB dataset at Phoenix, it usually takes me 12-15 seconds to see data showing up.

Expected behavior

I expect the initial connect and display to be lightweight, and should't take more than 2 seconds.

Reproduction steps
N/A
Logs or error output

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.

Research direction

Start at the viewer's Connect button and reproduce the reported 12–15 second load for a 1 GiB dataset over NFS, comparing it with local storage. Measure the time until data first appears and identify whether the delay is in connection, remote dataset loading, or initial rendering; done means the initial display meets the reported two-second expectation or the bottleneck is documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
macos, python
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.