Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/21200#discussion_r185372507
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/continuous/ContinuousWriteRDD.scala
---
@@ -0,0 +1,80 @@
+/*
+ * 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.{Partition, SparkEnv, TaskContext}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.catalyst.InternalRow
+import
org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask.{logError,
logInfo}
+import org.apache.spark.sql.sources.v2.writer.{DataWriter,
DataWriterFactory, WriterCommitMessage}
+import org.apache.spark.util.Utils
+
+class ContinuousWriteRDD(var prev: RDD[InternalRow], writeTask:
DataWriterFactory[InternalRow])
+ extends RDD[Unit](prev) {
+
+ override val partitioner = prev.partitioner
+
+ override def getPartitions: Array[Partition] = prev.partitions
+
+ override def compute(split: Partition, context: TaskContext):
Iterator[Unit] = {
+ val epochCoordinator = EpochCoordinatorRef.get(
+
context.getLocalProperty(ContinuousExecution.EPOCH_COORDINATOR_ID_KEY),
+ SparkEnv.get)
+ var currentEpoch =
context.getLocalProperty(ContinuousExecution.START_EPOCH_KEY).toLong
+
+ do {
+ var dataWriter: DataWriter[InternalRow] = null
+ // write the data and commit this writer.
+ Utils.tryWithSafeFinallyAndFailureCallbacks(block = {
+ try {
+ val dataIterator = prev.compute(split, context)
+ dataWriter = writeTask.createDataWriter(
+ context.partitionId(), context.attemptNumber(), currentEpoch)
+ while (dataIterator.hasNext) {
+ dataWriter.write(dataIterator.next())
+ }
+ logInfo(s"Writer for partition ${context.partitionId()} " +
+ s"in epoch $currentEpoch is committing.")
+ val msg = dataWriter.commit()
+ epochCoordinator.send(
+ CommitPartitionEpoch(context.partitionId(), currentEpoch, msg)
+ )
+ logInfo(s"Writer for partition ${context.partitionId()} " +
+ s"in epoch $currentEpoch committed.")
+ currentEpoch += 1
--- End diff --
I am having trouble tracking how the currentEpoch is updated and used. Is
this field `currentEpoch` used anywhere outside this class? The
`ContinuousQueuedDataReader` also has currentEpoch being incremented. I am
confused on what is used where.
Cant we converge the different flags to a common thread-local variable that
is initialized using the local property, incremented at one place (say, by this
writer class) and used everywhere?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
