Skip to content

Apache DataFusion SQL Query Engine

1.5 KB
Raw Blame
# Shared template for every projection_subquery benchmark. Each qNN.benchmark
# includes this template with parameters:
#   QPAD  zero-padded query id / query file stem  (e.g. 01)
#   NAME  criterion display name                  (e.g. q01_in_bare)
# Optional, read by the load script as ${...:-default}:
#   PSQ_ROWS  rows in each of the two tables (default 30000)
#
# The tables are always named `outer_t` and `inner_t`, so the load, the asserts
# and the cleanup are the same for every query.
#
# Every query is an aggregate over the projected subquery result, so the output
# is two numbers and the measurement is the plan and not the result transfer.
# The counts are checked in under results/, so --result-mode validate also
# proves that a change to the decorrelation still returns the same rows. The
# checked-in counts hold for the default PSQ_ROWS only.

load sql_benchmarks/projection_subquery/load/tables.sql

name ${NAME}
group projection_subquery

# Both tables have exactly PSQ_ROWS rows.
assert I
SELECT count(*) = ${PSQ_ROWS:-30000} FROM outer_t;
----
true

assert I
SELECT count(*) = ${PSQ_ROWS:-30000} FROM inner_t;
----
true

# The inner key must keep its NULLs, because three-valued logic is what forces
# the extra mark joins. A load that loses them makes the suite measure the
# wrong plan.
assert I
SELECT count(*) > 0 FROM inner_t WHERE id IS NULL;
----
true

run sql_benchmarks/projection_subquery/queries/q${QPAD}.sql

result sql_benchmarks/projection_subquery/results/${NAME}.csv

cleanup sql_benchmarks/projection_subquery/init/cleanup.sql