Scala 如何正确地将spark rdd结果保存到mysql数据库

目前，我按照以下步骤将spark RDD结果保存到mysql数据库中

import anorm._
import java.sql.Connection
import org.apache.spark.rdd.RDD

val wordCounts: RDD[(String, Int)] = ...

def getDbConnection(dbUrl: String): Connection = {
  Class.forName("com.mysql.jdbc.Driver").newInstance()
  java.sql.DriverManager.getConnection(dbUrl)
}

def using[X <: {def close()}, A](resource : X)(f : X => A): A =
  try { f(resource)
  } finally { resource.close() }

wordCounts.map.foreachPartition(iter => {
  using(getDbConnection(dbUrl)) { implicit conn =>
    iter.foreach { case (word, count) =>
      SQL"insert into WordCount VALUES(word, count)".executeUpdate()
    }
  }
})

---

请检查您正在编写的数据帧的分区数，如果分区太多或太少会影响第二种方法的性能OK，如何检查分区数？dataSet.rdd.getNumPartitions

val sqlContext = new SQLContext(sc)
val wordCountSchema = StructType(List(StructField("word", StringType, nullable = false), StructField("count", IntegerType, nullable = false)))
val wordCountRowRDD = wordCounts.map(p => org.apache.spark.sql.Row(p._1,p._2))
val wordCountDF = sqlContext.createDataFrame(wordCountRowRDD, wordCountSchema)
wordCountDF.registerTempTable("WordCount")
wordCountDF.write.mode("overwrite").jdbc(dbUrl, "WordCount", new java.util.Properties())