Github user srowen commented on the pull request:

    https://github.com/apache/spark/pull/11628#issuecomment-196741708
  
    Here's an alternate take in light of comments above, to illustrate what I'm 
thinking of:
    
    ```
      ...
        val proc = pb.start()
        val env = SparkEnv.get
        val childThreadException = new AtomicReference[Throwable]()
    
        // Start a thread to print the process's stderr to ours
        new Thread(s"stderr reader for $command") {
          override def run(): Unit = {
            val err = proc.getErrorStream
            try {
              for (line <- Source.fromInputStream(err).getLines) {
                // scalastyle:off println
                System.err.println(line)
                // scalastyle:on println
              }
            } catch {
              case t: Throwable => childThreadException.set(t)
            } finally {
              err.close()
            }
          }
        }.start()
    
        // Start a thread to feed the process input from our parent's iterator
        new Thread(s"stdin writer for $command") {
          override def run(): Unit = {
            TaskContext.setTaskContext(context)
            val out = new PrintWriter(proc.getOutputStream)
            try {
              // scalastyle:off println
              // input the pipe context firstly
              if (printPipeContext != null) {
                printPipeContext(out.println)
              }
              for (elem <- firstParent[T].iterator(split, context)) {
                if (printRDDElement != null) {
                  printRDDElement(elem, out.println)
                } else {
                  out.println(elem)
                }
              }
              // scalastyle:on println
            } catch {
              case t: Throwable => childThreadException.set(t)
            } finally {
              out.close()
            }
          }
        }.start()
    
        // Return an iterator that read lines from the process's stdout
        val lines = Source.fromInputStream(proc.getInputStream).getLines()
        new Iterator[String] {
          def next(): String = {
            if (!hasNext()) {
              throw new NoSuchElementException()
            }
            lines.next()
          }
          def hasNext(): Boolean = {
            propagateChildException()
            if (lines.hasNext) {
              true
            } else {
              val exitStatus = proc.waitFor()
              cleanup()
              if (exitStatus != 0) {
                throw new IllegalStateException(s"Subprocess exited with status 
$exitStatus")
              }
              false
            }
          }
          private def cleanup(): Unit = {
            // cleanup task working directory if used
            if (workInTaskDirectory) {
              scala.util.control.Exception.ignoring(classOf[IOException]) {
                Utils.deleteRecursively(new File(taskDirectory))
              }
              logDebug(s"Removed task working directory $taskDirectory")
            }
          }
          private def propagateChildException(): Unit = {
            val t = childThreadException.get()
            if (t != null) {
              proc.destroy()
              cleanup()
              throw t
            }
          }
        }
    ...
    ```


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to