Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/21428#discussion_r194958139
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/shuffle/RPCContinuousShuffleWriter.scala
---
@@ -0,0 +1,54 @@
+/*
+ * 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.shuffle
+
+import org.apache.spark.Partitioner
+import org.apache.spark.rpc.RpcEndpointRef
+import org.apache.spark.sql.catalyst.expressions.UnsafeRow
+
+/**
+ * A [[ContinuousShuffleWriter]] sending data to
[[RPCContinuousShuffleReader]] instances.
+ *
+ * @param writerId The partition ID of this writer.
+ * @param outputPartitioner The partitioner on the reader side of the
shuffle.
+ * @param endpoints The [[RPCContinuousShuffleReader]] endpoints
to write to. Indexed by
+ * partition ID within outputPartitioner.
+ */
+class RPCContinuousShuffleWriter(
+ writerId: Int,
+ outputPartitioner: Partitioner,
+ endpoints: Array[RpcEndpointRef]) extends ContinuousShuffleWriter {
+
+ if (outputPartitioner.numPartitions != 1) {
+ throw new IllegalArgumentException("multiple readers not yet
supported")
+ }
+
+ if (outputPartitioner.numPartitions != endpoints.length) {
+ throw new IllegalArgumentException(s"partitioner size
${outputPartitioner.numPartitions} did " +
+ s"not match endpoint count ${endpoints.length}")
+ }
+
+ def write(epoch: Iterator[UnsafeRow]): Unit = {
+ while (epoch.hasNext) {
+ val row = epoch.next()
+
endpoints(outputPartitioner.getPartition(row)).askSync[Unit](ReceiverRow(writerId,
row))
+ }
+
+ endpoints.foreach(_.askSync[Unit](ReceiverEpochMarker(writerId)))
--- End diff --
As far as I understand, the code here is to send a ReceiverEpochMarker to
each endpoint and wait for all of them to response. You can send
`ReceiverEpochMarker`s in parallel rather than send and wait one by one.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
