spark编程中设置hadoop的属性

当使用spark进行编程时，如果使用yarn-client方式提交，可以通过以下方式设置hadoop的属性

val conf = new SparkConf()
conf.set("spark.hadoop.yarn.resourcemanager.address", "test01:8050")

源码分析：

当spark任务提交时采用yarn模式，程序会启动YarnClientSchedulerBackend进行调度

  /**
   * Create a Yarn client to submit an application to the ResourceManager.
   * This waits until the application is running.
   */
  override def start() {
    val driverHost = conf.get("spark.driver.host")
    val driverPort = conf.get("spark.driver.port")
    val hostport = driverHost + ":" + driverPort
    sc.ui.foreach { ui => conf.set("spark.driver.appUIAddress", ui.appUIAddress) }

    val argsArrayBuf = new ArrayBuffer[String]()
    argsArrayBuf += ("--arg", hostport)
    argsArrayBuf ++= getExtraClientArguments

    logDebug("ClientArguments called with: " + argsArrayBuf.mkString(" "))
    val args = new ClientArguments(argsArrayBuf.toArray, conf)
    totalExpectedExecutors = args.numExecutors
    client = new Client(args, conf)
    appId = client.submitApplication()

Client创建的时候用到的conf

private[spark] class Client(
    val args: ClientArguments,
    val hadoopConf: Configuration,
    val sparkConf: SparkConf)
  extends Logging {

  import Client._

  def this(clientArgs: ClientArguments, spConf: SparkConf) =
    this(clientArgs, SparkHadoopUtil.get.newConfiguration(spConf), spConf)

SparkHadoopUtil

  def newConfiguration(conf: SparkConf): Configuration = {
    val hadoopConf = new Configuration()

    // Note: this null check is around more than just access to the "conf" object to maintain
    // the behavior of the old implementation of this code, for backwards compatibility.
    if (conf != null) {
      // Explicitly check for S3 environment variables
      if (System.getenv("AWS_ACCESS_KEY_ID") != null &&
          System.getenv("AWS_SECRET_ACCESS_KEY") != null) {
        val keyId = System.getenv("AWS_ACCESS_KEY_ID")
        val accessKey = System.getenv("AWS_SECRET_ACCESS_KEY")

        hadoopConf.set("fs.s3.awsAccessKeyId", keyId)
        hadoopConf.set("fs.s3n.awsAccessKeyId", keyId)
        hadoopConf.set("fs.s3a.access.key", keyId)
        hadoopConf.set("fs.s3.awsSecretAccessKey", accessKey)
        hadoopConf.set("fs.s3n.awsSecretAccessKey", accessKey)
        hadoopConf.set("fs.s3a.secret.key", accessKey)
      }
      // Copy any "spark.hadoop.foo=bar" system properties into conf as "foo=bar"
      conf.getAll.foreach { case (key, value) =>
        if (key.startsWith("spark.hadoop.")) {
          hadoopConf.set(key.substring("spark.hadoop.".length), value)
        }
      }
      val bufferSize = conf.get("spark.buffer.size", "65536")
      hadoopConf.set("io.file.buffer.size", bufferSize)
    }