@@ -32,6 +32,7 @@ import org.apache.spark.sql.SparkSession
3232 * Default: spark.default.parallelism
3333 * --size: specify the size of the dataset that should be loaded into Spark.
3434 * Default: sf_001
35+ * Available options: sf_01, sf_1, sf_3, sf_5, sf_10
3536 * --filesystem-url: optional arguments to specify filesystem master node URL.
3637 * Default: file://
3738 * --log-operators: boolean whether or not to log individual physical operators.
@@ -87,9 +88,10 @@ object Benchmark {
8788 println("""
8889 Available flags:
8990 --num-partitions: specify the number of partitions the data should be split into.
90- Default: 2 * number of executors if exists, 4 otherwise
91+ Default: spark.default.parallelism
9192 --size: specify the size of the dataset that should be loaded into Spark.
9293 Default: sf_001
94+ Available options: sf_01, sf_1, sf_3, sf_5, sf_10
9395 --filesystem-url: optional arguments to specify filesystem master node URL.
9496 Default: file://
9597 --log-operators: boolean whether or not to log individual physical operators.
@@ -111,7 +113,9 @@ object Benchmark {
111113 this .numPartitions = numPartitions.toInt
112114 }
113115 case Array (" --size" size : String ) => {
114- if (size == " sf_001" || size == " sf_01" || size == " sf_1"
116+ if (
117+ size == " sf_001" || size == " sf_01" || size == " sf_1" || size == " sf_3" || size == " sf_5" || size == " sf_10"
118+ ) {
115119 this .size = size
116120 } else {
117121 println(s " Given size is not supported: $size" )
0 commit comments