Skip to content

docs: correct the scheduler design's table-count assumption - #365

Merged
beinan merged 1 commit into
lance-format:mainfrom
beinan:docs/correct-scale-assumptions
Oct 9, 2026
Merged

beinan merged 1 commit into
lance-format:mainfrom
beinan:docs/correct-scale-assumptions

Conversation

@beinan

@beinan beinan commented Oct 9, 2026

Copy link
Copy Markdown
Collaborator

Part of #333. Follow-up to #364.

Review round 5 measured production: 13,405 tables, ~354 with pending, 318 generic, 6 masters. The design assumed "tens → low hundreds active" — wrong by two orders of magnitude — and that assumption directly produced the unpaged etcd reads and 1-byte reservations fixed in #364.

Corrects §2 (workload table, with the error acknowledged), §4.5 (per-cycle cost now stated with paging and measured at production shape), §6 (when the single leader would need watch-driven folding or sharding), and marks backlog open question 1 answered.

Docs only; typos clean.

🤖 Generated with Claude Code

Review round 5 measured production: 13,405 tables, ~354 with pending
WAL, 318 generic, 6 masters. The design assumed tens to low hundreds of
active tables, two orders of magnitude off, and that assumption drove
the unpaged etcd reads and the token byte reservations fixed in lance-format#364.
Correct §2, §4.5 and §6, and mark the first open question answered.

Refs lance-format#333.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@beinan
beinan merged commit ecddd6f into lance-format:main Oct 9, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant