This is an automated email from the ASF dual-hosted git repository.
dheres pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 94fd86ab82 Add topk_tpch benchmark (#16410)
94fd86ab82 is described below
commit 94fd86ab82aa4fff135352b1025706e255db6f5e
Author: Daniël Heres <danielhe...@gmail.com>
AuthorDate: Sat Jun 14 16:06:56 2025 +0200
Add topk_tpch benchmark (#16410)
* Add topk benchmark
* Add topk benchmark
* Add topk benchmark
---
benchmarks/README.md | 9 +++++++++
benchmarks/bench.sh | 17 +++++++++++++++++
2 files changed, 26 insertions(+)
diff --git a/benchmarks/README.md b/benchmarks/README.md
index b19b3385af..01da886ffb 100644
--- a/benchmarks/README.md
+++ b/benchmarks/README.md
@@ -510,6 +510,15 @@ See [`sort_tpch.rs`](src/sort_tpch.rs) for more details.
./bench.sh run sort_tpch
```
+### TopK TPCH
+
+In addition, topk_tpch is available from the bench.sh script:
+
+```bash
+./bench.sh run topk_tpch
+```
+
+
## IMDB
Run Join Order Benchmark (JOB) on IMDB dataset.
diff --git a/benchmarks/bench.sh b/benchmarks/bench.sh
index 837e8c6c9b..f1780f8844 100755
--- a/benchmarks/bench.sh
+++ b/benchmarks/bench.sh
@@ -236,6 +236,10 @@ main() {
# same data as for tpch
data_tpch "1"
;;
+ topk_tpch)
+ # same data as for tpch
+ data_tpch "1"
+ ;;
*)
echo "Error: unknown benchmark '$BENCHMARK' for data
generation"
usage
@@ -361,6 +365,9 @@ main() {
sort_tpch)
run_sort_tpch
;;
+ topk_tpch)
+ run_topk_tpch
+ ;;
*)
echo "Error: unknown benchmark '$BENCHMARK' for run"
usage
@@ -981,6 +988,16 @@ run_sort_tpch() {
debug_run $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path
"${TPCH_DIR}" -o "${RESULTS_FILE}"
}
+# Runs the sort tpch integration benchmark with limit 100 (topk)
+run_topk_tpch() {
+ TPCH_DIR="${DATA_DIR}/tpch_sf1"
+ RESULTS_FILE="${RESULTS_DIR}/run_topk_tpch.json"
+ echo "RESULTS_FILE: ${RESULTS_FILE}"
+ echo "Running topk tpch benchmark..."
+
+ $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path
"${TPCH_DIR}" -o "${RESULTS_FILE}" --limit 100
+}
+
compare_benchmarks() {
BASE_RESULTS_DIR="${SCRIPT_DIR}/results"
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@datafusion.apache.org
For additional commands, e-mail: commits-h...@datafusion.apache.org
