Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/6397#discussion_r31003641
--- Diff:
core/src/main/scala/org/apache/spark/shuffle/sort/BypassMergeSortShuffleWriter.scala
---
@@ -0,0 +1,132 @@
+/*
+ * 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.{File, FileInputStream, FileOutputStream}
+
+import org.apache.spark._
+import org.apache.spark.executor.ShuffleWriteMetrics
+import org.apache.spark.serializer.Serializer
+import org.apache.spark.storage.{BlockId, BlockManager, BlockObjectWriter}
+import org.apache.spark.util.Utils
+import org.apache.spark.util.collection._
+
+/**
+ * This class handles sort-based shuffle's `bypassMergeSort` write path,
which is used for shuffles
+ * for which no Ordering and no Aggregator is given and the number of
partitions is
+ * less than `spark.shuffle.sort.bypassMergeThreshold`.
+ *
+ * This path used to be part of [[ExternalSorter]] but was refactored into
its own class in order to
+ * reduce code complexity; see SPARK-7855 for more details.
+ *
+ * There have been proposals to completely remove this code path; see
SPARK-6026 for details.
+ */
+private[spark] class BypassMergeSortShuffleWriter[K, V](
+ conf: SparkConf,
+ blockManager: BlockManager,
+ partitioner: Partitioner,
+ writeMetrics: ShuffleWriteMetrics,
+ serializer: Serializer)
+ extends Logging with SortShuffleFileWriter[K, V] {
+
+ private[this] val numPartitions = partitioner.numPartitions
+
+ /** Array of file writers for each partition */
+ private[this] var partitionWriters: Array[BlockObjectWriter] = _
+
+ def insertAll(records: Iterator[_ <: Product2[K, V]]): Unit = {
--- End diff --
override
---
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]
