Apache DataFusion SQL Query Engine
description = "Null-aware (NOT IN) hash join benchmarks: uncorrelated, non-equality-correlated, and equality-correlated NOT IN across NULL fractions, plus the positive IN shape that must not be null-aware, and multi-column (tuple) NOT IN with and without NULLs"
query_pattern = "q{QUERY_ID_PADDED}.benchmark"
[[options]]
name = "rows"
short = "r"
env = "NAJ_ROWS"
default = "10000"
values = ["10000", "..."]
help = "Rows per table for the correlated and multi-column queries (Q04-Q14). These evaluate the join filter over candidate build x probe pairs, so their cost grows with the square of this value."
[[options]]
name = "large-rows"
short = "l"
env = "NAJ_LARGE_ROWS"
default = "1000000"
values = ["1000000", "..."]
help = "Rows per table for the uncorrelated NOT IN queries (Q01-Q03), whose cost is linear in the table size."
[[examples]]
command = "cargo run --release --bin benchmark_runner -- null_aware_join"
description = "Run all null-aware join queries at the default sizes."
[[examples]]
command = "cargo run --release --bin benchmark_runner -- null_aware_join --query 6"
description = "Run only Q06, the worst case for filter evaluation over NULL build rows."
[[examples]]
command = "cargo run --release --bin benchmark_runner -- null_aware_join -r 20000"
description = "Run with 20,000 rows per table for the correlated queries (~4x the filter work of the default)."