SciTS: A Benchmark for Time-Series Databases in Scientific Experiments and Industrial Internet of Things

TL;DR

This paper introduces SciTS, a comprehensive benchmark designed to evaluate the performance of various time-series databases in handling large-scale scientific and industrial IoT data, focusing on ingestion and query latency.

Contribution

The paper presents SciTS, a flexible benchmark that assesses how different storage engine designs impact time-series database performance in scientific and IIoT contexts.

Findings

InfluxDB shows superior ingestion performance.

TimescaleDB offers balanced query latency.

PostgreSQL underperforms compared to specialized time-series databases.

Abstract

Time-series data has an increasingly growing usage in Industrial Internet of Things (IIoT) and large-scale scientific experiments. Managing time-series data needs a storage engine that can keep up with their constantly growing volumes while providing an acceptable query latency. While traditional ACID databases favor consistency over performance, many time-series databases with novel storage engines have been developed to provide better ingestion performance and lower query latency. To understand how the unique design of a time-series database affects its performance, we design SciTS, a highly extensible and parameterizable benchmark for time-series data. The benchmark studies the data ingestion capabilities of time-series databases especially as they grow larger in size. It also studies the latencies of 5 practical queries from the scientific experiments use case. We use SciTS to evaluate the performance of 4 databases of 4 distinct storage engines: ClickHouse, InfluxDB, TimescaleDB, and PostgreSQL.