LoginSign Up
← Back to all sparks
Q

QuestDB

DEVOPS
Velocity6.3

High-performance time-series database for real-time analytics

questdb.io ↗

QuestDB 10.0 collapses ingest and egress into one binary protocol, then aims at agent-run notebooks.

time-serieswire-protocolapache-arrowbenchmarksdatabase-internals
◆Current state
QuestDB's feed mixes release notes, engineering deep dives and customer stories, and the through-line for the past month has been QWP — its own binary columnar wire protocol. It shipped in 10.0, was benchmarked against InfluxDB Line Protocol on ingestion and against ClickHouse and TimescaleDB on Arrow reads, and now has a standalone explainer covering bidirectional dataframe transfer and built-in failover. Between the protocol posts sit JIT compiler internals and production references from banks and exchanges.
◆Where it's heading
The protocol work is the thread that matters. QuestDB has been positioning against InfluxDB Line Protocol on ingestion throughput for a while, and 10.0 turned that from a benchmark argument into the default path both in and out of the database. The follow-up posts are consolidation rather than new capability: the same protocol re-explained for a different reader each time, which is what a project does when it needs an ecosystem to adopt a format. Live views and agent-driven notebooks remain the less-proven half of the release.
◆Prediction
Expect client libraries and third-party connectors to be the next visible work, since a proprietary wire protocol is only worth its switching cost once the dataframe tools speak it. Whether live views leave beta is not something these entries settle.

◆Recent moves

  1. 2d ago

    QWP: QuestDB's own binary wire protocol for ingestion and queries

    A standalone explainer for QWP, the protocol already shipped in 10.0 two weeks ago. It restates the bidirectional Arrow story and adds framing on built-in failover, but nothing new reaches users here.

    View source ↗
  2. 12d ago

    Streaming 500 million rows into Apache Arrow in 2.3 seconds

    A benchmark post streaming 500 million rows into Arrow against ClickHouse and TimescaleDB, with three measurement artifacts stripped out first. Supporting material for the QWP argument rather than a release.

    View source ↗
  3. 13d ago

    QuestDB 10.0: QWP, one binary streaming protocol for writes and Arrow reads

    ⚡ SPARK

    The major-version release that turns QuestDB's protocol argument into shipped default behaviour: QWP carries writes in and Arrow out through one client, alongside live views in beta and agent-driven notebooks. It also lays the storage foundation Enterprise 4.0 is said to build cold storage on, so the Enterprise track now depends on this release.

    View source ↗
  4. 14d ago

    Introducing QuestDB's new binary ingestion protocol: QWP

    The first public benchmark for QWP as an ingestion protocol: 33 million rows per second on one machine at a million series, roughly 3.6x line protocol over a network. It set up the throughput claim that 10.0 then shipped as the default path.

    View source ↗
  5. 1mo ago

    Transaction Cost Analysis with QuestDB and Polars: VWAP, Slippage and Markout

    A worked transaction-cost-analysis pipeline computing VWAP, slippage and markout in QuestDB SQL with Polars on top. Applied content aimed at the trading audience, not a product change.

    View source ↗
  6. 1mo ago

    HDFC Bank uses QuestDB for mule account detection across all major 25+ banking channels

    A customer story: HDFC Bank runs mule-account detection on QuestDB at 5,000 to 7,000 transactions per second on a single instance. Reference material rather than a release.

    View source ↗