Fixing a bug in reusing database and adding database name as an option

Summary: This diff fixes a bug that disables skipping database loading

Reviewed By: YifanYuan3

Differential Revision: D76067803

Author: marziehlenjaniMeta

benchpress/config/jobs.yml

@@ -480,7 +480,7 @@
   args:
     - 'run'
     - '--dataset-path /flash23/'
-    - '--dataset-name bpc_t93586_s2_synthetic_5GB'
+    - '--dataset-name {dataset_name}'
     - '--warehouse-dir /flash23/warehouse'
     - '--shuffle-dir /flash23/spark_local_dir'
     - '--ipv4 {ipv4}'
@@ -489,6 +489,7 @@
   vars:
     - 'ipv4=0'
     - 'sanity=0'
+    - 'dataset_name=bpc_t93586_s2_synthetic_5GB'
   hooks:
     - hook: copymove
       options:

packages/spark_standalone/templates/runner.py

@@ -52,7 +52,7 @@ def download_dataset(args):
 
 def install_database(args):
     metadata_dir = os.path.join(SPARK_DIR, "spark-2.4.5-bin-hadoop2.7", "metastore_db")
-    database_dir = os.path.join(args.warehouse_dir, f"{args.dataset_name}.db")
+    database_dir = os.path.join(args.warehouse_dir, f"{args.dataset_name.lower()}.db")
     if os.path.exists(metadata_dir) and os.path.exists(database_dir):
         print("Database already created; directly run test")
         return