Github user srowen commented on a diff in the pull request:
https://github.com/apache/spark/pull/15408#discussion_r82726120
--- Diff:
core/src/main/java/org/apache/spark/io/NioBasedBufferedFileInputStream.java ---
@@ -0,0 +1,127 @@
+/*
+ * Licensed 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.io;
+
+import org.apache.spark.storage.StorageUtils;
+
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.ByteBuffer;
+import java.nio.channels.FileChannel;
+import java.nio.file.StandardOpenOption;
+
+/**
+ * {@link InputStream} implementation which uses direct buffer
+ * to read a file to avoid extra copy of data between Java and
+ * native memory which happens when using {@link
java.io.BufferedInputStream}.
+ * Unfortunately, this is not something already available in JDK,
+ * {@link sun.nio.ch.ChannelInputStream} supports reading a file using nio,
+ * but does not support buffering.
+ *
+ */
+public final class NioBasedBufferedFileInputStream extends InputStream {
+
+ private static int DEFAULT_BUFFER_SIZE_BYTES = 8192;
+
+ private final ByteBuffer byteBuffer;
+
+ private final FileChannel fileChannel;
+
+ public NioBasedBufferedFileInputStream(File file, int bufferSizeInBytes)
throws IOException {
+ byteBuffer = ByteBuffer.allocateDirect(bufferSizeInBytes);
+ fileChannel = FileChannel.open(file.toPath(), StandardOpenOption.READ);
+ byteBuffer.flip();
+ }
+
+ public NioBasedBufferedFileInputStream(File file) throws IOException {
+ this(file, DEFAULT_BUFFER_SIZE_BYTES);
+ }
+
+ /**
+ * Checks weather data is left to be read from the input stream.
+ * @return true if data is left, false otherwise
+ * @throws IOException
+ */
+ private boolean refill() throws IOException {
+ if (!byteBuffer.hasRemaining()) {
+ byteBuffer.clear();
+ int nRead = fileChannel.read(byteBuffer);
+ if (nRead == -1) {
--- End diff --
Hm,
https://docs.oracle.com/javase/7/docs/api/java/nio/channels/FileChannel.html#read(java.nio.ByteBuffer)
suggests that 0 doesn't mean EOF, just 0 bytes read, but, I'm also not sure
what to do if the channel won't actually give any bytes at this point. I think
that can only happen if the buffer is full but that won't happen here. `<= 0`
seems reasonable AFAIK.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
