Apache
/
hadoop
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

svn merge -c 1468232 FIXES: MAPREDUCE-4974. Optimising the LineRecordReader initialize() method (Gelesh via bobby) 

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-2@1468235 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Joseph Evans 2013-04-15 21:36:31 +00:00
parent 5a98de170c
commit a7fba8fcd7
2 changed files with 12 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
hadoop-mapreduce-project/CHANGES.txt
View File

@ -45,6 +45,9 @@ Release 2.0.5-beta - UNRELEASED
OPTIMIZATIONS
MAPREDUCE-4974. Optimising the LineRecordReader initialize() method
(Gelesh via bobby)
BUG FIXES
MAPREDUCE-4671. AM does not tell the RM about container requests which are

24
hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/input/LineRecordReader.java
View File

@ -52,7 +52,6 @@ public class LineRecordReader extends RecordReader<LongWritable, Text> {
public static final String MAX_LINE_LENGTH =
"mapreduce.input.linerecordreader.line.maxlength";
private CompressionCodecFactory compressionCodecs = null;
private long start;
private long pos;
private long end;
@ -60,9 +59,9 @@ public class LineRecordReader extends RecordReader<LongWritable, Text> {
private FSDataInputStream fileIn;
private Seekable filePosition;
private int maxLineLength;
private LongWritable key = null;
private Text value = null;
private CompressionCodec codec;
private LongWritable key;
private Text value;
private boolean isCompressedInput;
private Decompressor decompressor;
private byte[] recordDelimiterBytes;
@ -81,13 +80,14 @@ public class LineRecordReader extends RecordReader<LongWritable, Text> {
start = split.getStart();
end = start + split.getLength();
final Path file = split.getPath();
compressionCodecs = new CompressionCodecFactory(job);
codec = compressionCodecs.getCodec(file);
// open the file and seek to the start of the split
final FileSystem fs = file.getFileSystem(job);
fileIn = fs.open(file);
if (isCompressedInput()) {
CompressionCodec codec = new CompressionCodecFactory(job).getCodec(file);
if (null!=codec) {
isCompressedInput = true;
decompressor = CodecPool.getDecompressor(codec);
if (codec instanceof SplittableCompressionCodec) {
final SplitCompressionInputStream cIn =
@ -132,19 +132,16 @@ public class LineRecordReader extends RecordReader<LongWritable, Text> {
this.pos = start;
}
private boolean isCompressedInput() {
return (codec != null);
}
private int maxBytesToConsume(long pos) {
return isCompressedInput()
return isCompressedInput
? Integer.MAX_VALUE
: (int) Math.min(Integer.MAX_VALUE, end - pos);
}
private long getFilePosition() throws IOException {
long retVal;
if (isCompressedInput() && null != filePosition) {
if (isCompressedInput && null != filePosition) {
retVal = filePosition.getPos();
} else {
retVal = pos;
@ -166,9 +163,6 @@ public class LineRecordReader extends RecordReader<LongWritable, Text> {
while (getFilePosition() <= end) {
newSize = in.readLine(value, maxLineLength,
Math.max(maxBytesToConsume(pos), maxLineLength));
if (newSize == 0) {
break;
}
pos += newSize;
if (newSize < maxLineLength) {
break;