Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/5868#discussion_r30110285
--- Diff:
core/src/main/java/org/apache/spark/shuffle/unsafe/UnsafeShuffleWriter.java ---
@@ -0,0 +1,407 @@
+/*
+ * 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.unsafe;
+
+import java.io.*;
+import java.nio.channels.FileChannel;
+import java.util.Iterator;
+import javax.annotation.Nullable;
+
+import scala.Option;
+import scala.Product2;
+import scala.collection.JavaConversions;
+import scala.reflect.ClassTag;
+import scala.reflect.ClassTag$;
+
+import com.google.common.annotations.VisibleForTesting;
+import com.google.common.io.ByteStreams;
+import com.google.common.io.Closeables;
+import com.google.common.io.Files;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import org.apache.spark.*;
+import org.apache.spark.io.CompressionCodec;
+import org.apache.spark.io.CompressionCodec$;
+import org.apache.spark.io.LZFCompressionCodec;
+import org.apache.spark.executor.ShuffleWriteMetrics;
+import org.apache.spark.network.util.LimitedInputStream;
+import org.apache.spark.scheduler.MapStatus;
+import org.apache.spark.scheduler.MapStatus$;
+import org.apache.spark.serializer.SerializationStream;
+import org.apache.spark.serializer.Serializer;
+import org.apache.spark.serializer.SerializerInstance;
+import org.apache.spark.shuffle.IndexShuffleBlockResolver;
+import org.apache.spark.shuffle.ShuffleMemoryManager;
+import org.apache.spark.shuffle.ShuffleWriter;
+import org.apache.spark.storage.BlockManager;
+import org.apache.spark.unsafe.PlatformDependent;
+import org.apache.spark.unsafe.memory.TaskMemoryManager;
+
+public class UnsafeShuffleWriter<K, V> extends ShuffleWriter<K, V> {
+
+ private final Logger logger =
LoggerFactory.getLogger(UnsafeShuffleWriter.class);
+
+ private static final ClassTag<Object> OBJECT_CLASS_TAG =
ClassTag$.MODULE$.Object();
+
+ @VisibleForTesting
+ static final int INITIAL_SORT_BUFFER_SIZE = 4096;
+
+ private final BlockManager blockManager;
+ private final IndexShuffleBlockResolver shuffleBlockResolver;
+ private final TaskMemoryManager memoryManager;
+ private final ShuffleMemoryManager shuffleMemoryManager;
+ private final SerializerInstance serializer;
+ private final Partitioner partitioner;
+ private final ShuffleWriteMetrics writeMetrics;
+ private final int shuffleId;
+ private final int mapId;
+ private final TaskContext taskContext;
+ private final SparkConf sparkConf;
+ private final boolean transferToEnabled;
+
+ private MapStatus mapStatus = null;
+ private UnsafeShuffleExternalSorter sorter = null;
+
+ /** Subclass of ByteArrayOutputStream that exposes `buf` directly. */
+ private static final class MyByteArrayOutputStream extends
ByteArrayOutputStream {
+ public MyByteArrayOutputStream(int size) { super(size); }
+ public byte[] getBuf() { return buf; }
+ }
+
+ private MyByteArrayOutputStream serBuffer;
+ private SerializationStream serOutputStream;
+
+ /**
+ * Are we in the process of stopping? Because map tasks can call stop()
with success = true
+ * and then call stop() with success = false if they get an exception,
we want to make sure
+ * we don't try deleting files, etc twice.
+ */
+ private boolean stopping = false;
+
+ public UnsafeShuffleWriter(
+ BlockManager blockManager,
+ IndexShuffleBlockResolver shuffleBlockResolver,
+ TaskMemoryManager memoryManager,
+ ShuffleMemoryManager shuffleMemoryManager,
+ UnsafeShuffleHandle<K, V> handle,
+ int mapId,
+ TaskContext taskContext,
+ SparkConf sparkConf) {
+ final int numPartitions =
handle.dependency().partitioner().numPartitions();
+ if (numPartitions > PackedRecordPointer.MAXIMUM_PARTITION_ID) {
+ throw new IllegalArgumentException(
+ "UnsafeShuffleWriter can only be used for shuffles with at most " +
+ PackedRecordPointer.MAXIMUM_PARTITION_ID + " reduce partitions");
+ }
+ this.blockManager = blockManager;
+ this.shuffleBlockResolver = shuffleBlockResolver;
+ this.memoryManager = memoryManager;
+ this.shuffleMemoryManager = shuffleMemoryManager;
+ this.mapId = mapId;
+ final ShuffleDependency<K, V, V> dep = handle.dependency();
+ this.shuffleId = dep.shuffleId();
+ this.serializer =
Serializer.getSerializer(dep.serializer()).newInstance();
+ this.partitioner = dep.partitioner();
+ this.writeMetrics = new ShuffleWriteMetrics();
+
taskContext.taskMetrics().shuffleWriteMetrics_$eq(Option.apply(writeMetrics));
+ this.taskContext = taskContext;
+ this.sparkConf = sparkConf;
+ this.transferToEnabled = sparkConf.getBoolean("spark.file.transferTo",
true);
+ }
+
+ public void write(Iterator<Product2<K, V>> records) throws IOException {
--- End diff --
is this only used in testing? maybe document that.
---
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]
