ClickBench
ClickBench copied to clipboard
ClickHouse
ClickBench: a Benchmark For Analytical Databases
I noticed that for duckdb the CSV file is first uncompressed before loading. https://github.com/ClickHouse/ClickBench/blob/main/duckdb/benchmark.sh#L18C1-L18C5 For Snowflake, we also support faster parallel scanning of uncompressed CSVs. Can we modify the Snowflake...
It should be a drop-in replacement for SQLite. It is written in Rust.
**Intermediate result caching** There are some impressive hot run results from SiriusDB, who have done some cool engineering to integrate GPU accelerated queries with DuckDB. Kudos to them, and it...
Added sync around data loading for ClickHouse and Ursa as their load times are below the theoretical minimum for instances where the whole dataset fits into memory (cf Issue #678)...
There is currently a split in the ClickBench dataset between results that are submitted by vendors, and results that are re-run by maintainers. This is an artificial data integrity issue....
Some systems report load times below the theoretical minimum. For example, [gp2 provides ~250MB/s throughput](https://docs.aws.amazon.com/ebs/latest/userguide/ebs-volume-types.html). With the smallest data size anyone reports being ~10 GB, any load time below 40...
- Closes https://github.com/apache/datafusion/issues/18909 Update DataFusion results for the DataFusion 51 release (TODO add blog URL here when published) I followed the directions in - https://github.com/ClickHouse/ClickBench/blob/main/datafusion/README.md Changes - [x] Update some...
On the default ClickBench configuration of c6a.4xlarge (32 GB RAM). This bug report is for the MariaDB team.
Metadata
Owner
Metadata
ClickBench: a Benchmark For Analytical Databases