You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by vanzin <gi...@git.apache.org> on 2018/04/25 22:42:55 UTC
[GitHub] spark pull request #21066: [SPARK-23977][CLOUD][WIP] Add commit protocol bin...
Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/21066#discussion_r184223981
--- Diff: hadoop-cloud/src/hadoop-3/main/scala/org/apache/spark/internal/io/cloud/PathOutputCommitProtocol.scala ---
@@ -0,0 +1,260 @@
+/*
+ * 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.internal.io.cloud
+
+import java.io.IOException
+
+import org.apache.hadoop.fs.Path
+import org.apache.hadoop.mapreduce.{JobContext, TaskAttemptContext}
+import org.apache.hadoop.mapreduce.lib.output.{FileOutputCommitter, PathOutputCommitter, PathOutputCommitterFactory}
+
+import org.apache.spark.internal.io.{FileCommitProtocol, HadoopMapReduceCommitProtocol}
+import org.apache.spark.internal.io.FileCommitProtocol.TaskCommitMessage
+
+/**
+ * Spark Commit protocol for Path Output Committers.
+ * This committer will work with the `FileOutputCommitter` and subclasses.
+ * All implementations *must* be serializable.
+ *
+ * Rather than ask the `FileOutputFormat` for a committer, it uses the
+ * `org.apache.hadoop.mapreduce.lib.output.PathOutputCommitterFactory` factory
+ * API to create the committer.
+ * This is what [[org.apache.hadoop.mapreduce.lib.output.FileOutputFormat]] does,
+ * but as [[HadoopMapReduceCommitProtocol]] still uses the original
+ * `org.apache.hadoop.mapred.FileOutputFormat` binding
+ * subclasses do not do this, overrides those subclasses to using the
+ * factory mechanism now supported in the base class.
+ *
+ * In `setupCommitter` the factory is bonded to and the committer for
+ * the destination path chosen.
+ *
+ * @constructor Instantiate. dynamic partition overwrite is not supported,
+ * so that committers for stores which do not support rename
+ * will not get confused.
+ * @param jobId job
+ * @param destination destination
+ * @param dynamicPartitionOverwrite does the caller want support for dynamic
+ * partition overwrite. If so, it will be
+ * refused.
+ * @throws IOException when an unsupported dynamicPartitionOverwrite option is supplied.
+ */
+class PathOutputCommitProtocol(
+ jobId: String,
+ destination: String,
+ dynamicPartitionOverwrite: Boolean = false)
+ extends HadoopMapReduceCommitProtocol(
+ jobId,
+ destination,
+ false) with Serializable {
+
+ @transient var committer: PathOutputCommitter = _
--- End diff --
`private`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org