hadoop分布式复制覆盖不工作

Question

我试图使用org.apache.hadoop.tools.DistCp类将一些文件复制到S3 bucket中。然而，尽管明确地将覆盖标志设置为true，但覆盖功能却无法使用。

复制工作正常，但如果有现有的文件，则不能覆盖。复制映射器会跳过这些文件。我已经明确地将 "overwrite "选项设置为true。

import com.typesafe.scalalogging.LazyLogging
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.tools.{DistCp, DistCpOptions}
import org.apache.hadoop.util.ToolRunner
import scala.collection.JavaConverters._

object  distcptest extends  App with LazyLogging {


  def copytoS3( hdfsSrcFilePathStr: String, s3DestPathStr: String) = {
    val hdfsSrcPathList = List(new Path(hdfsSrcFilePathStr))
    val s3DestPath = new Path(s3DestPathStr)
    val distcpOpt = new DistCpOptions(hdfsSrcPathList.asJava, s3DestPath)

    // Overwriting is not working inspite of explicitly setting it to true.
    distcpOpt.setOverwrite(true)

    val conf: Configuration = new Configuration()
    conf.set("fs.s3n.awsSecretAccessKey", "secret key")
    conf.set("fs.s3n.awsAccessKeyId", "access key")
    conf.set("fs.s3n.impl", "org.apache.hadoop.fs.s3native.NativeS3FileSystem")

    val distCp: DistCp = new DistCp(conf, distcpOpt)
    val filepaths: Array[String] = Array(hdfsSrcFilePathStr, s3DestPathStr)

    try {
      val distCp_result = ToolRunner.run(distCp, filepaths)
      if (distCp_result != 0) {
        logger.error(s"DistCP has failed with - error code = $distCp_result")
      }
    }
    catch {
      case e: Exception => {
        e.printStackTrace()
      }
    }
  }

  copytoS3("hdfs://abc/pqr", "s3n://xyz/wst")
}

Answer 1

我认为问题在于你调用了ToolRunner.run(distCp, filepaths)。

如果你查看DistCp的源代码，在run方法中会覆盖inputOptions，所以传递给constructor的DistCpOptions将无法工作。

  @Override
  public int run(String[] argv) {
    ...

    try {
      inputOptions = (OptionsParser.parse(argv));
      ...
    } catch (Throwable e) {
      ...
    }
    ...
  }