Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/6444#discussion_r32785481
--- Diff:
core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeSorterSpillReader.java
---
@@ -0,0 +1,89 @@
+/*
+ * 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.unsafe.sort;
+
+import java.io.*;
+
+import com.google.common.io.ByteStreams;
+
+import org.apache.spark.storage.BlockId;
+import org.apache.spark.storage.BlockManager;
+import org.apache.spark.unsafe.PlatformDependent;
+
+final class UnsafeSorterSpillReader extends UnsafeSorterIterator {
+
+ private final File file;
+ private InputStream in;
+ private DataInputStream din;
+
+ private final byte[] arr = new byte[1024 * 1024]; // TODO: tune this
(maybe grow dynamically)?
+ private int nextRecordLength;
+
+ private long keyPrefix;
+ private final Object baseObject = arr;
+ private final long baseOffset = PlatformDependent.BYTE_ARRAY_OFFSET;
+
+ public UnsafeSorterSpillReader(
+ BlockManager blockManager,
+ File file,
+ BlockId blockId) throws IOException {
+ this.file = file;
+ assert (file.length() > 0);
+ final BufferedInputStream bs = new BufferedInputStream(new
FileInputStream(file));
+ this.in = blockManager.wrapForCompression(blockId, bs);
+ this.din = new DataInputStream(this.in);
+ nextRecordLength = din.readInt();
+ }
+
+ @Override
+ public boolean hasNext() {
+ return (in != null);
+ }
+
+ @Override
+ public void loadNext() throws IOException {
+ keyPrefix = din.readLong();
+ ByteStreams.readFully(in, arr, 0, nextRecordLength);
--- End diff --
Note to self: we need to grow the buffer dynamically in case we're reading
really big records. Add a test for this.
---
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]
