我发现spark2加载orc文件的速度比spark1慢得多，然后我尝试了一些加速spark2的方法，但没有成功。代码如下：
Spark1.5

val conf = new SparkConf().setAppName("LoadOrc")
      .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
      .set("spark.akka.frameSize", "512")
      .set("spark.akka.timeout","800s")
      .set("spark.storage.blockManagerHeartBeatMs", "300000")
      .set("spark.kryoserializer.buffer.max","1024m")
      .set("spark.executor.extraJavaOptions", "-Djava.util.Arrays.useLegacyMergeSort=true")

    val sc = new SparkContext(conf)

    val hiveContext = new HiveContext(sc)
    val start = System.nanoTime()
    val ret = hiveContext.read.orc(args(0)).count()
    val end = System.nanoTime()
    println(s"count: $ret")
    println(s"Time taken: ${(end - start) / 1000 / 1000} ms")
    sc.stop()

spark用户界面
spark1用户界面
结果

count: 2290811187
Time taken: 401063 ms

Spark2

val spark = SparkSession.builder()
      .appName("LoadOrc")
      .config("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
      .config("spark.akka.frameSize", "512")
      .config("spark.akka.timeout","800s")
      .config("spark.storage.blockManagerHeartBeatMs", "300000")
      .config("spark.kryoserializer.buffer.max","1024m")
      .config("spark.executor.extraJavaOptions", "-Djava.util.Arrays.useLegacyMergeSort=true")
      .enableHiveSupport()
      .getOrCreate()

    println(spark.time(spark.read.format("org.apache.spark.sql.execution.datasources.orc")
      .load(args(0)).count()))

    spark.close()

spark用户界面
spark2用户界面
结果

Time taken: 1384464 ms
2290811187