Loading post…
ClickhouseBenchmark
TPC-H for less than a cent: ClickHouse Cloud vs. Snowflake, Databricks, BigQuery, and Redshift
Summary
ClickHouse Cloud is benchmarked against Snowflake, Databricks, BigQuery, and Redshift on the join-heavy TPC-H workload, with the main comparison using SF100: 100 GB, 866M rows, and 22 queries. Using a single 59-core AWS compute node, the benchmark measures fastest hot runs from three executions with result caching disabled, applies public billing models and comparable Enterprise-tier regional pricing, and publishes scripts, queries, and result files for reproduction. ClickHouse completed SF100 in 19.8 seconds for $0.063 and ranked first on the cost-performance score, while Snowflake Large was faster at 15.9 seconds but cost $0.143; at SF10, ClickHouse ran the workload in 2.9 seconds for $0.009. The results are attributed to two years of join engineering, including faster hash joins, improved planning, correlated subquery support, lazy column replication, runtime filters, and statistics-based join reordering.
Context
The benchmark compares query runtime and compute cost across ClickHouse Cloud, Snowflake, Databricks, BigQuery, and Redshift on join-heavy TPC-H workloads. Directly comparing compute is difficult because the systems use different hardware and capacity models, so the analysis also evaluates cost-performance using each vendor’s public billing model.
Approach / What changed
The comparison runs TPC-H queries on SF100 and SF10, using a fixed single-node ClickHouse Cloud configuration and selected warehouse or serverless capacities for the other systems. Runtime uses the fastest of three hot runs with result caching disabled, while cost applies public billing models and comparable Enterprise-tier regional pricing. The reported engineering improvements include faster hash joins, better planning, correlated subquery support, lazy column replication, runtime filters, and statistics-based join reordering.
Takeaways
On SF100, ClickHouse Cloud completed the 22-query workload in 19.8 seconds for $0.063; Snowflake Large was faster at 15.9 seconds but cost $0.143.
ClickHouse Cloud ranked first on the SF100 cost-performance score, with the nearest tested configurations approximately 2× worse.
At SF10, the same 59-core ClickHouse Cloud node ran all 22 queries over 86M rows in 2.9 seconds for $0.009.
Source and freshness
- Source
- clickhouse.com
- Published
- Added to Yomu
- Last updated
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.