Spark SQL关于性能调优选项详解

import org.apache.commons.lang3.SystemUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.streaming.OutputMode
import org.apache.spark.sql.{DataFrame, SparkSession}
object PerformanceTuneDemo {
	def main(args: Array[String]): Unit = {
		// 构建SparkSession实例对象，设置相关属性参数值
		val sparkConf = new SparkConf()
    		.setAppName(this.getClass.getSimpleName.stripSuffix("$"))
			.set("spark.sql.session.timeZone", "Asia/Shanghai")
			.set("spark.sql.files.maxPartitionBytes", "134217728")
			.set("spark.sql.files.openCostInBytes", "134217728")
			.set("spark.sql.shuffle.partitions", "3")
			.set("spark.sql.autoBroadcastJoinThreshold", "67108864")
		// 构建SparkSession实例对象
		val spark: SparkSession = SparkSession.builder()
    		.config(sparkConf)
			.getOrCreate()
	}
}