Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/1499#discussion_r15543949
--- Diff:
core/src/main/scala/org/apache/spark/shuffle/sort/SortShuffleWriter.scala ---
@@ -0,0 +1,159 @@
+/*
+ * 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.shuffle.sort
+
+import java.io.{BufferedOutputStream, File, FileOutputStream,
DataOutputStream}
+
+import org.apache.spark.{MapOutputTracker, SparkEnv, Logging, TaskContext}
+import org.apache.spark.executor.ShuffleWriteMetrics
+import org.apache.spark.scheduler.MapStatus
+import org.apache.spark.serializer.Serializer
+import org.apache.spark.shuffle.{ShuffleWriter, BaseShuffleHandle}
+import org.apache.spark.storage.ShuffleBlockId
+import org.apache.spark.util.collection.ExternalSorter
+
+private[spark] class SortShuffleWriter[K, V, C](
+ handle: BaseShuffleHandle[K, V, C],
+ mapId: Int,
+ context: TaskContext)
+ extends ShuffleWriter[K, V] with Logging {
+
+ private val dep = handle.dependency
+ private val numPartitions = dep.partitioner.numPartitions
+
+ private val blockManager = SparkEnv.get.blockManager
+ private val ser =
Serializer.getSerializer(dep.serializer.getOrElse(null))
+
+ private val conf = SparkEnv.get.conf
+ private val fileBufferSize = conf.getInt("spark.shuffle.file.buffer.kb",
100) * 1024
+
+ private var sorter: ExternalSorter[K, V, _] = null
+ private var outputFile: File = null
+
+ private var stopping = false
+ private var mapStatus: MapStatus = null
+
+ /** Write a bunch of records to this task's output */
+ override def write(records: Iterator[_ <: Product2[K, V]]): Unit = {
+ val partitions: Iterator[(Int, Iterator[Product2[K, _]])] = {
--- End diff --
can u add inline comment explaining what the tuple represents? (i'm
assuming int represents the partition id?)
---
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.
---
