Skip to content

Add SQL based benchmarking #21707

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Omega359 wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Add SQL based benchmarking #21707

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5ef261f
Add a sql based benchmark framework with tpch as the initial benchmar…
Omega359 Apr 17, 2026
dd498c2
Merge remote-tracking branch 'upstream/main' into new_sql_benchmark
Omega359 Apr 17, 2026
1561e99
Code cleanup, improvements and added tests. AI assistance was used fo…
Omega359 Apr 18, 2026
74e3b16
Merge branch 'main' into new_sql_benchmark
Omega359 Apr 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
118 changes: 23 additions & 95 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 3 additions & 1 deletion benchmarks/.gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
data
results
data_csv
./results/
venv
!sql_benchmarks/**/results/
8 changes: 7 additions & 1 deletion benchmarks/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,8 @@ mimalloc_extended = ["libmimalloc-sys/extended"]
arrow = { workspace = true }
async-trait = "0.1"
bytes = { workspace = true }
clap = { version = "4.5.60", features = ["derive"] }
clap = { version = "4.6.0", features = ["derive", "env"] }
criterion = { workspace = true, features = ["html_reports"] }
datafusion = { workspace = true, default-features = true }
datafusion-common = { workspace = true, default-features = true }
env_logger = { workspace = true }
Expand All @@ -62,3 +63,8 @@ tokio-util = { version = "0.7.17" }

[dev-dependencies]
datafusion-proto = { workspace = true }
tempfile = { workspace = true }

[[bench]]
harness = false
name = "sql"
29 changes: 17 additions & 12 deletions benchmarks/bench.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ BENCHMARK=all
DATAFUSION_DIR=${DATAFUSION_DIR:-$SCRIPT_DIR/..}
DATA_DIR=${DATA_DIR:-$SCRIPT_DIR/data}
CARGO_COMMAND=${CARGO_COMMAND:-"cargo run --release"}
SQL_CARGO_COMMAND=${SQL_CARGO_COMMAND:-"cargo bench --bench sql"}
PREFER_HASH_JOIN=${PREFER_HASH_JOIN:-true}
SIMULATE_LATENCY=${SIMULATE_LATENCY:-false}

Expand Down Expand Up @@ -685,14 +686,16 @@ run_tpch() {
echo "Internal error: Scale factor not specified"
exit 1
fi
TPCH_DIR="${DATA_DIR}/tpch_sf${SCALE_FACTOR}"

RESULTS_FILE="${RESULTS_DIR}/tpch_sf${SCALE_FACTOR}.json"
echo "RESULTS_FILE: ${RESULTS_FILE}"
FORMAT=$2
echo "Running tpch benchmark..."

FORMAT=$2
debug_run $CARGO_COMMAND --bin dfbench -- tpch --iterations 5 --path "${TPCH_DIR}" --scale-factor "${SCALE_FACTOR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format ${FORMAT} -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}
debug_run env BENCH_NAME=tpch \
BENCH_SIZE="${SCALE_FACTOR}" \
PREFER_HASH_JOIN="${PREFER_HASH_JOIN}" \
TPCH_FILE_TYPE="${FORMAT}" \
SIMULATE_LATENCY="${SIMULATE_LATENCY}" \
${QUERY_ARG} \
bash -c "$SQL_CARGO_COMMAND"
}

# Runs the tpch in memory (needs tpch parquet data)
Expand All @@ -702,13 +705,15 @@ run_tpch_mem() {
echo "Internal error: Scale factor not specified"
exit 1
fi
TPCH_DIR="${DATA_DIR}/tpch_sf${SCALE_FACTOR}"

RESULTS_FILE="${RESULTS_DIR}/tpch_mem_sf${SCALE_FACTOR}.json"
echo "RESULTS_FILE: ${RESULTS_FILE}"
echo "Running tpch_mem benchmark..."
# -m means in memory
debug_run $CARGO_COMMAND --bin dfbench -- tpch --iterations 5 --path "${TPCH_DIR}" --scale-factor "${SCALE_FACTOR}" --prefer_hash_join "${PREFER_HASH_JOIN}" -m --format parquet -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}

debug_run env BENCH_NAME=tpch \
BENCH_SIZE="${SCALE_FACTOR}" \
TPCH_FILE_TYPE="mem" \
PREFER_HASH_JOIN="${PREFER_HASH_JOIN}" \
SIMULATE_LATENCY="${SIMULATE_LATENCY}" \
${QUERY_ARG} \
bash -c "$SQL_CARGO_COMMAND"
}

# Runs the tpcds benchmark
Expand Down
Loading
Loading