Datafusion benchmark script patch

bench_sh.patch

diff --git a/benchmarks/bench.sh b/benchmarks/bench.sh
index b34c646c5..d8742c25f 100755
--- a/benchmarks/bench.sh
+++ b/benchmarks/bench.sh
@@ -43,6 +43,7 @@ DATA_DIR=${DATA_DIR:-$SCRIPT_DIR/data}
 CARGO_COMMAND=${CARGO_COMMAND:-"cargo run --release"}
 PREFER_HASH_JOIN=${PREFER_HASH_JOIN:-true}
 VIRTUAL_ENV=${VIRTUAL_ENV:-$SCRIPT_DIR/venv}
+ITERATIONS=50

 usage() {
     echo "
@@ -446,7 +447,7 @@ run_tpch() {
     echo "Running tpch benchmark..."
     # Optional query filter to run specific query                                                      QUERY=$([ -n "$ARG3" ] && echo "--query $ARG3" || echo "")
-    debug_run $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}" $QUERY
+    debug_run $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations $ITERATIONS --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}" $QUERY
 }

 # Runs the tpch in memory
@@ -464,7 +465,7 @@ run_tpch_mem() {
     # Optional query filter to run specific query
     QUERY=$([ -n "$ARG3" ] && echo "--query $ARG3" || echo "")                                         # -m means in memory
-    debug_run $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" -m --format parquet -o "${RESULTS_FILE}" $QUERY         +    debug_run $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations $ITERATIONS --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" -m --format parquet -o "${RESULTS_FILE}" $QUERY
 }

 # Runs the cancellation benchmark
@@ -472,7 +473,7 @@ run_cancellation() {
     RESULTS_FILE="${RESULTS_DIR}/cancellation.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running cancellation benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- cancellation --iterations 5 --path "${DATA_DIR}/cancellation" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- cancellation --iterations $ITERATIONS --path "${DATA_DIR}/cancellation" -o "${RESULTS_FILE}"
 }

 # Runs the parquet filter benchmark
@@ -480,7 +481,7 @@ run_parquet() {
     RESULTS_FILE="${RESULTS_DIR}/parquet.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running parquet filter benchmark..."
-    debug_run $CARGO_COMMAND --bin parquet -- filter --path "${DATA_DIR}" --scale-factor 1.0 --iterations 5 -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin parquet -- filter --path "${DATA_DIR}" --scale-factor 1.0 --iterations $ITERATIONS -o "${RESULTS_FILE}"
 }

 # Runs the sort benchmark
@@ -488,7 +489,7 @@ run_sort() {
     RESULTS_FILE="${RESULTS_DIR}/sort.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running sort benchmark..."
-    debug_run $CARGO_COMMAND --bin parquet -- sort --path "${DATA_DIR}" --scale-factor 1.0 --iterations 5 -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin parquet -- sort --path "${DATA_DIR}" --scale-factor 1.0 --iterations $ITERATIONS -o "${RESULTS_FILE}"
 }


@@ -542,7 +543,7 @@ run_clickbench_1() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_1.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (1 file) benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet"  --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations $ITERATIONS --path "${DATA_DIR}/hits.parquet"  --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
 }

  # Runs the clickbench benchmark with the partitioned parquet files
@@ -550,7 +551,7 @@ run_clickbench_partitioned() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_partitioned.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (partitioned, 100 files) benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits_partitioned" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations $ITERATIONS --path "${DATA_DIR}/hits_partitioned" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
 }

 # Runs the clickbench "extended" benchmark with a single large parquet file                       @@ -558,7 +559,7 @@ run_clickbench_extended() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_extended.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (1 file) extended benchmark..."
-    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet" --queries-path "${SCRIPT_DIR}/queries/clickbench/extended.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations $ITERATIONS --path "${DATA_DIR}/hits.parquet" --queries-path "${SCRIPT_DIR}/queries/clickbench/extended.sql" -o "${RESULTS_FILE}"
 }

 # Downloads the csv.gz files IMDB datasets from Peter Boncz's homepage(one of the JOB paper authors)
@@ -673,7 +674,7 @@ run_imdb() {
     RESULTS_FILE="${RESULTS_DIR}/imdb.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running imdb benchmark..."
-    debug_run $CARGO_COMMAND --bin imdb -- benchmark datafusion --iterations 5 --path "${IMDB_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin imdb -- benchmark datafusion --iterations $ITERATIONS --path "${IMDB_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}"
 }

 data_h2o() {
@@ -945,7 +946,7 @@ run_external_aggr() {
     # number-of-partitions), and by default `--partitions` is set to number of
     # CPU cores, we set a constant number of partitions to prevent this
     # benchmark to fail on some machines.
-    debug_run $CARGO_COMMAND --bin external_aggr -- benchmark --partitions 4 --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin external_aggr -- benchmark --partitions 4 --iterations $ITERATIONS --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
 }

 # Runs the sort integration benchmark
@@ -955,7 +956,7 @@ run_sort_tpch() {
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running sort tpch benchmark..."

-    debug_run $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations $ITERATIONS --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
 }


@@ -1000,3 +1001,4 @@ setup_venv() {

 # And start the process up
 main
+