Fix benchmark script folder references, use data caterer version in docker file for example

Author: pflooky

example/Dockerfile

@@ -1,3 +1,4 @@
-FROM datacatering/data-caterer:0.16.4
+ARG DATA_CATERER_VERSION=0.16.5
+FROM datacatering/data-caterer:${DATA_CATERER_VERSION}
 
 COPY --chown=app:app build/libs/data-caterer-example-0.1.0.jar /opt/app/job.jar

example/benchmark/compare_benchmark_results.sh

@@ -1,12 +1,13 @@
 #!/usr/bin/env bash
 
-SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+RESULTS_DIR="$(cd "$SCRIPT_DIR/results" && pwd)"
 LATEST_VERSION=${1:-0.11.5}
 RESULT_FILE_REGEX="benchmark_results_([0-9\.]+)\.txt"
 
 if [[ -z $2 ]]; then
   echo "No second version to compare against passed into arguments, defaulting to previous version in results"
-  PREVIOUS_VERSION_RESULT_FILE_NAME=$(ls -1 "$SCRIPT_DIR/results" | sort --version-sort | tail -2 | head -1)
+  PREVIOUS_VERSION_RESULT_FILE_NAME=$(ls -1 "$RESULTS_DIR" | sort --version-sort | tail -2 | head -1)
   if [[ $PREVIOUS_VERSION_RESULT_FILE_NAME =~ $RESULT_FILE_REGEX ]]; then
     PREVIOUS_VERSION="${BASH_REMATCH[1]}"
   else
@@ -33,8 +34,8 @@ for plan in "${plans[@]}"; do
   plan_name=$(echo "$plan" | sed 's/io.github.datacatering.plan.benchmark.//')
   echo "Comparing performance for plan: $plan_name"
 
-  latest_version_results=$(cat "$SCRIPT_DIR/results/benchmark_results_${LATEST_VERSION}.txt" | grep "${plan}")
-  previous_version_results=$(cat "$SCRIPT_DIR/results/benchmark_results_${PREVIOUS_VERSION}.txt" | grep "${plan}")
+  latest_version_results=$(cat "$RESULTS_DIR/benchmark_results_${LATEST_VERSION}.txt" | grep "${plan}")
+  previous_version_results=$(cat "$RESULTS_DIR/benchmark_results_${PREVIOUS_VERSION}.txt" | grep "${plan}")
 
   latest_version_average_time=$(echo "$latest_version_results" | awk -F "," '{s+=$4} END {print s/3}')
   previous_version_average_time=$(echo "$previous_version_results" | awk -F "," '{s+=$4} END {print s/3}')

example/benchmark/run_benchmark.sh

@@ -17,7 +17,6 @@ fi
 enable_query_engine_run=${ENABLE_QUERY_ENGINE_RUN:-true}
 enable_data_size_run=${ENABLE_DATA_SIZE_RUN:-true}
 enable_data_sink_run=${ENABLE_DATA_SINK_RUN:-true}
-data_caterer_track=${DATA_CATERER_MANAGEMENT_TRACK:-}
 
 data_caterer_version=$(grep -E "^dataCatererVersion=" "$PROP_FILE" | cut -d= -f2)
 default_job="io.github.datacatering.plan.benchmark.BenchmarkParquetPlanRun"
@@ -64,17 +63,17 @@ run_docker() {
 
     time_taken=$({
       time -p docker run -p 4040:4040 \
-        -v "$(pwd)/build/libs/data-caterer-example-0.1.0.jar:/opt/app/job.jar" \
-        -v "$(pwd)/benchmark/jars/blaze.jar:/opt/app/jars/blaze.jar" \
-        -v "$(pwd)/benchmark/jars/comet.jar:/opt/app/jars/comet.jar" \
-        -v "$(pwd)/benchmark/jars/gluten.jar:/opt/app/jars/gluten.jar" \
+        -v "${EXAMPLE_DIR}/build/libs/data-caterer-example-0.1.0.jar:/opt/app/job.jar" \
+        -v "${EXAMPLE_DIR}/benchmark/jars/blaze.jar:/opt/app/jars/blaze.jar" \
+        -v "${EXAMPLE_DIR}/benchmark/jars/comet.jar:/opt/app/jars/comet.jar" \
+        -v "${EXAMPLE_DIR}/benchmark/jars/gluten.jar:/opt/app/jars/gluten.jar" \
         -v "/tmp:/opt/app/data" \
         -e "PLAN_CLASS=$1" \
         -e "RECORD_COUNT=$2" \
         -e "DEPLOY_MODE=client" \
         -e "$driver_memory" \
         -e "$executor_memory" \
-        -e "DATA_CATERER_MANAGEMENT_TRACK=$data_caterer_track" \
+        -e "DATA_CATERER_VERSION=$data_caterer_version" \
         -e "ADDITIONAL_OPTS=$additional_conf" \
         datacatering/data-caterer:"$data_caterer_version";
     } 2>&1 | grep "real " | sed "$sed_option" "s/^.*real ([0-9\.]+)$/\1/")