debug cargo command in bench script (#16236)

Author: 2010YOUY01

benchmarks/bench.sh

@@ -28,6 +28,12 @@ set -e
 # https://stackoverflow.com/questions/59895/how-do-i-get-the-directory-where-a-bash-script-is-located-from-within-the-script
 SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
 
+# Execute command and also print it, for debugging purposes
+debug_run() {
+    set -x
+    "$@"
+    set +x
+}
 
 # Set Defaults
 COMMAND=
@@ -435,10 +441,7 @@ run_tpch() {
     echo "Running tpch benchmark..."
     # Optional query filter to run specific query
     QUERY=$([ -n "$ARG3" ] && echo "--query $ARG3" || echo "")
-    # debug the target command
-    set -x
-    $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}" $QUERY
-    set +x
+    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
 }
 
 # Runs the tpch in memory
@@ -455,35 +458,32 @@ run_tpch_mem() {
     echo "Running tpch_mem benchmark..."
     # Optional query filter to run specific query
     QUERY=$([ -n "$ARG3" ] && echo "--query $ARG3" || echo "")
-    # debug the target command
-    set -x
     # -m means in memory
-    $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" -m --format parquet -o "${RESULTS_FILE}" $QUERY
-    set +x
+    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
 }
 
 # Runs the cancellation benchmark
 run_cancellation() {
     RESULTS_FILE="${RESULTS_DIR}/cancellation.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running cancellation benchmark..."
-    $CARGO_COMMAND --bin dfbench -- cancellation --iterations 5 --path "${DATA_DIR}/cancellation" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- cancellation --iterations 5 --path "${DATA_DIR}/cancellation" -o "${RESULTS_FILE}"
 }
 
 # Runs the parquet filter benchmark
 run_parquet() {
     RESULTS_FILE="${RESULTS_DIR}/parquet.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running parquet filter benchmark..."
-    $CARGO_COMMAND --bin parquet -- filter --path "${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 5 -o "${RESULTS_FILE}"
 }
 
 # Runs the sort benchmark
 run_sort() {
     RESULTS_FILE="${RESULTS_DIR}/sort.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running sort benchmark..."
-    $CARGO_COMMAND --bin parquet -- sort --path "${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 5 -o "${RESULTS_FILE}"
 }
 
 
@@ -537,23 +537,23 @@ run_clickbench_1() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_1.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (1 file) benchmark..."
-    $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet"  --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet"  --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
 }
 
  # Runs the clickbench benchmark with the partitioned parquet files
 run_clickbench_partitioned() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_partitioned.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (partitioned, 100 files) benchmark..."
-    $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits_partitioned" --queries-path "${SCRIPT_DIR}/queries/clickbench/queries.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${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
 run_clickbench_extended() {
     RESULTS_FILE="${RESULTS_DIR}/clickbench_extended.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running clickbench (1 file) extended benchmark..."
-    $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${DATA_DIR}/hits.parquet" --queries-path "${SCRIPT_DIR}/queries/clickbench/extended.sql" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- clickbench  --iterations 5 --path "${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)
@@ -668,7 +668,7 @@ run_imdb() {
     RESULTS_FILE="${RESULTS_DIR}/imdb.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running imdb benchmark..."
-    $CARGO_COMMAND --bin imdb -- benchmark datafusion --iterations 5 --path "${IMDB_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin imdb -- benchmark datafusion --iterations 5 --path "${IMDB_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}"
 }
 
 data_h2o() {
@@ -859,7 +859,7 @@ run_h2o() {
     QUERY_FILE="${SCRIPT_DIR}/queries/h2o/${RUN_Type}.sql"
 
     # Run the benchmark using the dynamically constructed file path and query file
-    $CARGO_COMMAND --bin dfbench -- h2o \
+    debug_run $CARGO_COMMAND --bin dfbench -- h2o \
         --iterations 3 \
         --path "${H2O_DIR}/${FILE_NAME}" \
         --queries-path "${QUERY_FILE}" \
@@ -910,7 +910,7 @@ h2o_runner() {
     # Set the query file name based on the RUN_Type
     QUERY_FILE="${SCRIPT_DIR}/queries/h2o/${RUN_Type}.sql"
 
-    $CARGO_COMMAND --bin dfbench -- h2o \
+    debug_run $CARGO_COMMAND --bin dfbench -- h2o \
         --iterations 3 \
         --join-paths "${H2O_DIR}/${X_TABLE_FILE_NAME},${H2O_DIR}/${SMALL_TABLE_FILE_NAME},${H2O_DIR}/${MEDIUM_TABLE_FILE_NAME},${H2O_DIR}/${LARGE_TABLE_FILE_NAME}" \
         --queries-path "${QUERY_FILE}" \
@@ -940,7 +940,7 @@ 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.
-    $CARGO_COMMAND --bin external_aggr -- benchmark --partitions 4 --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin external_aggr -- benchmark --partitions 4 --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
 }
 
 # Runs the sort integration benchmark
@@ -950,7 +950,7 @@ run_sort_tpch() {
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running sort tpch benchmark..."
 
-    $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
+    debug_run $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
 }