Github user jose-torres commented on a diff in the pull request:
https://github.com/apache/spark/pull/21560#discussion_r197930245
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousCoalesceRDD.scala
---
@@ -0,0 +1,108 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.streaming.continuous
+
+import org.apache.spark._
+import org.apache.spark.rdd.{CoalescedRDDPartition, RDD}
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.UnsafeRow
+import org.apache.spark.sql.execution.streaming.continuous.shuffle._
+import org.apache.spark.util.ThreadUtils
+
+case class ContinuousCoalesceRDDPartition(index: Int) extends Partition {
+ // This flag will be flipped on the executors to indicate that the
threads processing
+ // partitions of the write-side RDD have been started. These will run
indefinitely
+ // asynchronously as epochs of the coalesce RDD complete on the read
side.
+ private[continuous] var writersInitialized: Boolean = false
+}
+
+/**
+ * RDD for continuous coalescing. Asynchronously writes all partitions of
`prev` into a local
+ * continuous shuffle, and then reads them in the task thread using
`reader`.
+ */
+class ContinuousCoalesceRDD(
+ context: SparkContext,
+ numPartitions: Int,
+ readerQueueSize: Int,
+ epochIntervalMs: Long,
+ readerEndpointName: String,
+ prev: RDD[InternalRow])
+ extends RDD[InternalRow](context, Nil) {
+
+ override def getPartitions: Array[Partition] =
Array(ContinuousCoalesceRDDPartition(0))
+
+ val readerRDD = new ContinuousShuffleReadRDD(
+ sparkContext,
+ numPartitions,
+ readerQueueSize,
+ prev.getNumPartitions,
+ epochIntervalMs,
+ Seq(readerEndpointName))
+
+ private lazy val threadPool = ThreadUtils.newDaemonFixedThreadPool(
+ prev.getNumPartitions,
+ this.name)
+
+ override def compute(split: Partition, context: TaskContext):
Iterator[InternalRow] = {
+ assert(split.index == 0)
+ // lazy initialize endpoint so writer can send to it
+
readerRDD.partitions(0).asInstanceOf[ContinuousShuffleReadPartition].endpoint
+
+ if
(!split.asInstanceOf[ContinuousCoalesceRDDPartition].writersInitialized) {
+ val rpcEnv = SparkEnv.get.rpcEnv
+ val outputPartitioner = new HashPartitioner(1)
--- End diff --
Repartition would normally imply distributed execution, which isn't
happening here.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
