Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/7021#discussion_r33739248
--- Diff:
core/src/main/scala/org/apache/spark/util/CheckpointingIterator.scala ---
@@ -0,0 +1,143 @@
+/*
+ * 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.util
+
+import java.io.IOException
+
+import scala.reflect.ClassTag
+
+import org.apache.hadoop.fs.FileSystem
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark._
+import org.apache.spark.broadcast.Broadcast
+import org.apache.spark.rdd.CheckpointRDD
+import org.apache.spark.serializer.SerializationStream
+
+/**
+ * Wrapper around an iterator which writes checkpoint data to HDFS while
running action on
+ * a RDD to support checkpointing RDD.
+ */
+private[spark] class CheckpointingIterator[A: ClassTag, +I <: Iterator[A]](
+ sub: I,
+ path: String,
+ broadcastedConf: Broadcast[SerializableConfiguration],
+ partitionId: Int,
+ context: TaskContext,
+ blockSize: Int = -1) extends Iterator[A] with Logging {
+
+ val env = SparkEnv.get
+ var fs: FileSystem = null
+ val bufferSize = env.conf.getInt("spark.buffer.size", 65536)
+ var serializeStream: SerializationStream = null
+
+ var finalOutputPath: Path = null
+ var tempOutputPath: Path = null
+
+ def init(): this.type = {
+ val outputDir = new Path(path)
+ fs = outputDir.getFileSystem(broadcastedConf.value.value)
+
+ val finalOutputName = CheckpointRDD.splitIdToFile(partitionId)
+ finalOutputPath = new Path(outputDir, finalOutputName)
+ tempOutputPath =
+ new Path(outputDir, "." + finalOutputName + "-attempt-" +
context.attemptNumber)
+
+ if (fs.exists(tempOutputPath)) {
+ // There are more than one iterator of the RDD is consumed.
+ // Don't checkpoint data in this iterator.
+ doCheckpoint = false
+ return this
+ }
+
+ val fileOutputStream = if (blockSize < 0) {
+ fs.create(tempOutputPath, false, bufferSize)
+ } else {
+ // This is mainly for testing purpose
+ fs.create(tempOutputPath, false, bufferSize,
fs.getDefaultReplication, blockSize)
+ }
+ val serializer = env.serializer.newInstance()
+ serializeStream = serializer.serializeStream(fileOutputStream)
+ this
+ }
+
+ def completion(): Unit = {
--- End diff --
what does `completion` mean? Can you add some java docs here and everywhere?
---
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]
