History[04][05]

QuestDB started as a side project in 2013 by Vlad Ilyushchenko who applied principles from low latency techniques found in the financial services industry. QuestDB is backed by YCombinator.

Concurrency Control[06]

QuestDB uses a single writer model. The writer re-orders timestamps on the fly. Multi-publisher, single consumer queue provides concurrent write access.

Data Model[07]

QuestDB uses a relational model with column-based storage model.

Foreign Keys

Hardware Acceleration

SIMD optimised analytics.

Indexes[08]

Indexing is available for symbol columns. Index support for other types will be added over time.

Isolation Levels

Joins[09]

QuestDB supports the following types of joins: INNER, OUTER, CROSS, ASOF and SPLICE. FULL joins are not yet implemented and are on our roadmap. All supported join types can be combined in a single SQL statement.

Logging

Parallel Execution

Multi threaded SQL execution.

Query Compilation

Query Execution[10]

SIMD-based vector execution of queries.

Query Interface[11]

QuestDB enhances ANSI SQL with time series extensions to manipulate time stamped data.

Storage Architecture[12]

Memory mapped files data access.

Storage Model[07]

QuestDB uses a column-based storage model. Data is stored in tables with each column stored in its own file and its own native format. New data is appended to the bottom of each column to allow data to be organically retrieved in the same order that it was ingested.

Storage Organization

Stored Procedures

System Architecture

Views