Edition of Friday 20 November 2026

Distributed, high-performance blob storage on SQLite

Comments on “Distributed, high-performance blob storage on SQLite”

Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked

Zerodha's engineers describe Blobasaur, an open-source Rust server that speaks the Redis protocol and stores JSON blobs in sharded SQLite files, replacing the unmaintained SSDB behind its Kite platform. In the authors' benchmark on a single laptop with tmpfs, 16 shards raised write throughput about 3.3x over one shard (25,324 vs 7,740 ops/s), while reads were unchanged. In production, a three-node cluster reports p99 near 2 ms. Durability is relaxed, and slot rebalancing and failover are not yet implemented. Most figures are self-reported.

Read the original at zerodha.tech. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 16 of 140 with a score of 0.66. The panel rated it highest on new information (0.95) and technical depth (0.93), lowest on audience breadth (0.52). Placed No. 16, No. 25 by score alone: the placement terms moved other stories past it.

AI judgeJudge 2claude-haiku-5-5
Detailed engineering writeup of a production-tested, open-source distributed blob store on SQLite with benchmarks and migration lessons; useful for infra builders, moderate breadth, modest significance, mostly self-reported evidence.
AI judgeJudge 3gpt-5.6-luna
A detailed production engineering account with architecture, benchmarks, operational lessons, migration strategy, and source release. It is highly actionable for storage and infrastructure builders, though significance is limited to a specialized workload and some claims rely on internal measurements.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.66total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.53
  • Reader interest0.80
  • Audience breadth0.52
  • Practical relevance0.77
  • Substantiated0.85
  • Technical depth0.93
  • New information0.95
  • Counts against: Promotional0.10
  • Counts against: Overclaim0.24

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.500.400.690.530.29+0.24+0.127
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.720.800.880.800.16+0.26+0.208
Audience breadthHow many people who build technology does it concern?0.450.550.570.520.12+0.13+0.068
Practical relevanceHow useful is it to someone who builds software or tech products?0.800.700.810.770.11+0.22+0.169
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.950.700.910.850.25+0.05+0.043
Technical depthHow technically substantive is it?1.000.850.930.930.15+0.05+0.046
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.910.950.980.950.07+0.05+0.047
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.070.150.080.100.08−0.19−0.019
OverclaimDo the headline or conclusions claim more than the body supports?0.360.250.120.240.24−0.11−0.027
Sum of contributions+0.663
Claim-check penalty0.000
Total, as published0.663

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #16 on Rubric, 20 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-20/16/"><img src="https://rubric.hrih.si/badge/2026-11-20/16.svg" alt="Ranked #16 on Rubric, 20 Nov 2026" width="245" height="28"></a>

Claim check

Claim check: 1 matches source · 5 no source given · 2 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.

  1. Matches sourceBenchmark result

    SQLite is up to 35% faster than raw filesystem I/O for small blobs.

    The cited source says the same thing.

    The article says

    “For small blobs, SQLite is up to 35% faster than raw filesystem I/O”

    The source says

    “SQLite reads and writes small blobs (for example, thumbnail images) 35% faster¹ than the same blobs can be read from or written to individual files on disk using fread() or…”

    Source cited by the article: sqlite.org/fasterthanfs.html

  2. Couldn’t checkNumber

    Raw files start to beat SQLite above roughly 100 KiB blob size.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “While raw files start to beat SQLite above ~100 KiB”

    The source says

    No passage could be compared.

    Source cited by the article: sqlite.org/fasterthanfs.html

  3. No source givenBenchmark result

    With 16 shards, Blobasaur's write throughput increases 3.3x and median write latency drops from 8.2 ms to 2.1 ms compared with 1 shard.

    The article gives no link or citation for it.

    The article says

    “With 16 shards, write throughput increases 3.3x and median write latency drops from 8.2 ms to 2.1 ms”

    The source says

    No source to compare with.

  4. No source givenBenchmark result

    In the benchmark, 16 shards reached 25,324 ops/s for HSET-only with p99 of 8.3 ms, versus 7,740 ops/s and p99 10.7 ms for 1 shard.

    The article gives no link or citation for it.

    The article says

    “HSET only 7,740 ops/s, p99 10.7 ms 25,324 ops/s, p99 8.3 ms”

    The source says

    No source to compare with.

  5. No source givenNumber

    Over one hour of production HSET traffic, the average payload shrank from 63.6 KiB to 5.5 KiB, about 11x reduction.

    The article gives no link or citation for it.

    The article says

    “Average 63.6 KiB 5.5 KiB about 11x”

    The source says

    No source to compare with.

  6. Couldn’t checkNumber

    Zerodha's Kite trading platform has about 20 million customers.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “our trading platform with ~20 million customers”

    The source says

    No passage could be compared.

    Source cited by the article: zerodha.com/products/kite

  7. No source givenNumber

    With naive hash % num_shards, going from 4 to 5 shards moves about 80% of keys, whereas consistent hashing moves only about 20%.

    The article gives no link or citation for it.

    The article says

    “With naive hash % num_shards, increasing from 4 to 5 shards moves ~80% of keys. With consistent hashing, only ~20% of keys move”

    The source says

    No source to compare with.

  8. No source givenNumber

    In production on a three-node cluster, p99 latency across all commands stays around 2 ms and p50 between 250 and 550 µs over a trading session.

    The article gives no link or citation for it.

    The article says

    “p99 latency across all commands stays around 2 ms on every node, and p50 sits between 250 and 550 µs”

    The source says

    No source to compare with.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 277 pts, front page

Discussion on Hacker News

Recorded for context only, checked 20 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “Distributed, high-performance blob storage on SQLite”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.

  1. Score 0.77

    PostgreSQL 19