Skip to content

Apache DataFusion SQL Query Engine

1.1 KB
Raw Blame
description = "H2O group-by, join, and window SQL benchmarks"

query_pattern = "q{QUERY_ID_PADDED}.benchmark"

[path_replacements]
DATA_DIR = "../../data"

[[options]]
name = "size"
env = "H2O_BENCH_SIZE"
default = "small"
values = ["small", "medium", "big"]
help = "Selects the H2O dataset size."

[[options]]
name = "format"
short = "f"
env = "H2O_FILE_TYPE"
default = "csv"
values = ["csv", "parquet"]
help = "Selects the H2O data format."

[[examples]]
command = "cargo run --release --bin benchmark_runner -- h2o"
description = "Run all H2O queries with the small CSV datasets."

[[examples]]
command = "cargo run --release --bin benchmark_runner -- h2o --query 3 --subgroup window"
description = "Run H2O window query 3."

[[examples]]
command = "cargo run --release --bin benchmark_runner -- h2o --subgroup join --size medium -f parquet"
description = "Run the H2O join queries with the medium Parquet dataset."

[[examples]]
command = "cargo run --release --bin benchmark_runner -- h2o --subgroup window_sorted"
description = "Run the window Top-N sweep over an input that declares its ordering."