Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/21977#discussion_r208120759
--- Diff:
core/src/main/scala/org/apache/spark/api/python/PythonRunner.scala ---
@@ -60,14 +61,26 @@ private[spark] object PythonEvalType {
*/
private[spark] abstract class BasePythonRunner[IN, OUT](
funcs: Seq[ChainedPythonFunctions],
- bufferSize: Int,
- reuseWorker: Boolean,
evalType: Int,
- argOffsets: Array[Array[Int]])
+ argOffsets: Array[Array[Int]],
+ conf: SparkConf)
extends Logging {
require(funcs.length == argOffsets.length, "argOffsets should have the
same length as funcs")
+ private val bufferSize = conf.getInt("spark.buffer.size", 65536)
+ private val reuseWorker = conf.getBoolean("spark.python.worker.reuse",
true)
+ private val memoryMb = {
+ val allocation = conf.get(PYSPARK_EXECUTOR_MEMORY)
+ if (reuseWorker) {
--- End diff --
maybe here
https://github.com/apache/spark/blob/628c7b517969c4a7ccb26ea67ab3dd61266073ca/core/src/main/scala/org/apache/spark/api/python/PythonWorkerFactory.scala#L89?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
