Github user keypointt commented on a diff in the pull request:
https://github.com/apache/spark/pull/14467#discussion_r79881217
--- Diff: core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala
---
@@ -880,42 +883,70 @@ private class PythonAccumulatorParam(@transient
private val serverHost: String,
* We try to reuse a single Socket to transfer accumulator updates, as
they are all added
* by the DAGScheduler's single-threaded RpcEndpoint anyway.
*/
- @transient var socket: Socket = _
+ @transient private var socket: Socket = _
- def openSocket(): Socket = synchronized {
+ private def openSocket(): Socket = synchronized {
if (socket == null || socket.isClosed) {
socket = new Socket(serverHost, serverPort)
}
socket
}
- override def zero(value: JList[Array[Byte]]): JList[Array[Byte]] = new
JArrayList
+ override def reset(): Unit = {
+ this._acc = Collections.synchronizedList(new JArrayList[Array[Byte]])
+ }
+
+ override def isZero: Boolean = {
+ this._acc.isEmpty
+ }
+
+ override def copyAndReset(): PythonAccumulatorV2 = new
PythonAccumulatorV2(serverHost, serverPort)
+
+ override def copy(): PythonAccumulatorV2 = {
+ val newAcc = new PythonAccumulatorV2(serverHost, serverPort)
+ newAcc._acc.addAll(this._acc)
+ newAcc
+ }
- override def addInPlace(val1: JList[Array[Byte]], val2:
JList[Array[Byte]])
- : JList[Array[Byte]] = synchronized {
+ // This happens on the worker node, where we just want to remember all
the updates
+ override def add(val2: JList[Array[Byte]]): Unit = {
+ _acc.addAll(val2)
+ }
+
+
+ override def merge(other: AccumulatorV2[JList[Array[Byte]], Unit]): Unit
= {
+ val otherPythonAccumulator = other.asInstanceOf[PythonAccumulatorV2]
+ // This conditional isn't strictly speaking needed - merging only
currently happens on the
+ // driver program - but that isn't gauranteed so incase this changes.
if (serverHost == null) {
- // This happens on the worker node, where we just want to remember
all the updates
- val1.addAll(val2)
- val1
+ // We are on the worker
+ add(otherPythonAccumulator._acc)
} else {
// This happens on the master, where we pass the updates to Python
through a socket
val socket = openSocket()
val in = socket.getInputStream
val out = new DataOutputStream(new
BufferedOutputStream(socket.getOutputStream, bufferSize))
- out.writeInt(val2.size)
- for (array <- val2.asScala) {
- out.writeInt(array.length)
- out.write(array)
+ otherPythonAccumulator._acc.synchronized {
+ out.writeInt(otherPythonAccumulator._acc.size)
+ for (array <- otherPythonAccumulator._acc.asScala) {
+ out.writeInt(array.length)
+ out.write(array)
+ }
}
out.flush()
// Wait for a byte from the Python side as an acknowledgement
val byteRead = in.read()
if (byteRead == -1) {
throw new SparkException("EOF reached before Python server
acknowledged")
}
- null
}
}
+
+ /**
+ * Value function - not expected to be called for Python.
+ */
+ def value: Unit = {
--- End diff --
sorry being naive, I'm not getting it why an empty function here?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
