Github user aarondav commented on a diff in the pull request:
https://github.com/apache/spark/pull/1499#discussion_r15152216
--- Diff:
core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala ---
@@ -0,0 +1,390 @@
+/*
+ * 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.collection
+
+import java.io._
+import java.util.Comparator
+
+import scala.collection.mutable.ArrayBuffer
+
+import com.google.common.io.ByteStreams
+
+import org.apache.spark.{Aggregator, SparkEnv, Logging, Partitioner}
+import org.apache.spark.serializer.Serializer
+import org.apache.spark.storage.BlockId
+
+/**
+ * Sorts and potentially merges a number of key-value pairs of type (K, V)
to produce key-combiner
+ * pairs of type (K, C). Uses a Partitioner to first group the keys into
partitions, and then
+ * optionally sorts keys within each partition using a custom Comparator.
Can output a single
+ * partitioned file with a different byte range for each partition,
suitable for shuffle fetches.
+ *
+ * If combining is disabled, the type C must equal V -- we'll cast the
objects at the end.
+ *
+ * @param aggregator optional Aggregator with combine functions to use for
merging data
+ * @param partitioner optional partitioner; if given, sort by partition ID
and then key
+ * @param ordering optional ordering to sort keys within each partition
+ * @param serializer serializer to use
+ */
+private[spark] class ExternalSorter[K, V, C](
+ aggregator: Option[Aggregator[K, V, C]] = None,
+ partitioner: Option[Partitioner] = None,
+ ordering: Option[Ordering[K]] = None,
+ serializer: Option[Serializer] = None) extends Logging {
+
+ private val numPartitions = partitioner.map(_.numPartitions).getOrElse(1)
+ private val shouldPartition = numPartitions > 1
+
+ private val blockManager = SparkEnv.get.blockManager
+ private val diskBlockManager = blockManager.diskBlockManager
+ private val ser = Serializer.getSerializer(serializer.getOrElse(null))
+ private val serInstance = ser.newInstance()
+
+ private val conf = SparkEnv.get.conf
+ private val fileBufferSize = conf.getInt("spark.shuffle.file.buffer.kb",
100) * 1024
+ private val serializerBatchSize =
conf.getLong("spark.shuffle.spill.batchSize", 10000)
+
+ private def getPartition(key: K): Int = {
+ if (shouldPartition) partitioner.get.getPartition(key) else 0
+ }
+
+ // Data structures to store in-memory objects before we spill. Depending
on whether we have an
+ // Aggregator set, we either put objects into an AppendOnlyMap where we
combine them, or we
+ // store them in an array buffer.
+ var map = new SizeTrackingAppendOnlyMap[(Int, K), C]
--- End diff --
It appears that we'll either use the map or the buffer throughout the whole
sorting process (rather than switch from one to another). In this case, would
it make sense to put a `val usingMap/shouldCombine = aggregator.isDefined` out
here, and then avoid passing it around elsewhere?
---
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.
---
