Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

MAPREDUCE-7494. File stream leak when LineRecordReader is interrupted #7119

Open
wants to merge 1 commit into
base: branch-3.4
Choose a base branch
from
+44 −37
Open

MAPREDUCE-7494. File stream leak when LineRecordReader is interrupted #7119

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions ...hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/LineRecordReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,6 +302,8 @@ public synchronized void close() throws IOException {
try {
if (in != null) {
in.close();
} else if (fileIn != null) {
fileIn.close();
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why not do this in finally ?

}
} finally {
if (decompressor != null) {
Expand Down
79 changes: 42 additions & 37 deletions ...uce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/input/LineRecordReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,48 +98,53 @@ public void initialize(InputSplit genericSplit,
MRJobConfig.INPUT_FILE_OPTION_PREFIX,
MRJobConfig.INPUT_FILE_MANDATORY_PREFIX);
fileIn = FutureIO.awaitFuture(builder.build());

CompressionCodec codec = new CompressionCodecFactory(job).getCodec(file);
if (null!=codec) {
isCompressedInput = true;
decompressor = CodecPool.getDecompressor(codec);
if (codec instanceof SplittableCompressionCodec) {
final SplitCompressionInputStream cIn =
((SplittableCompressionCodec)codec).createInputStream(
fileIn, decompressor, start, end,
SplittableCompressionCodec.READ_MODE.BYBLOCK);
in = new CompressedSplitLineReader(cIn, job,
this.recordDelimiterBytes);
start = cIn.getAdjustedStart();
end = cIn.getAdjustedEnd();
filePosition = cIn;
} else {
if (start != 0) {
// So we have a split that is only part of a file stored using
// a Compression codec that cannot be split.
throw new IOException("Cannot seek in " +
codec.getClass().getSimpleName() + " compressed stream");
}

in = new SplitLineReader(codec.createInputStream(fileIn,
decompressor), job, this.recordDelimiterBytes);
try {
CompressionCodec codec = new CompressionCodecFactory(job).getCodec(file);
if (null!=codec) {
isCompressedInput = true;
decompressor = CodecPool.getDecompressor(codec);
if (codec instanceof SplittableCompressionCodec) {
final SplitCompressionInputStream cIn =
((SplittableCompressionCodec)codec).createInputStream(
fileIn, decompressor, start, end,
SplittableCompressionCodec.READ_MODE.BYBLOCK);
in = new CompressedSplitLineReader(cIn, job,
this.recordDelimiterBytes);
start = cIn.getAdjustedStart();
end = cIn.getAdjustedEnd();
filePosition = cIn;
} else {
if (start != 0) {
// So we have a split that is only part of a file stored using
// a Compression codec that cannot be split.
throw new IOException("Cannot seek in " +
codec.getClass().getSimpleName() + " compressed stream");
}

in = new SplitLineReader(codec.createInputStream(fileIn,
decompressor), job, this.recordDelimiterBytes);
filePosition = fileIn;
}
} else {
fileIn.seek(start);
in = new UncompressedSplitLineReader(
fileIn, job, this.recordDelimiterBytes, split.getLength());
filePosition = fileIn;
}
} else {
fileIn.seek(start);
in = new UncompressedSplitLineReader(
fileIn, job, this.recordDelimiterBytes, split.getLength());
filePosition = fileIn;
}
// If this is not the first split, we always throw away first record
// because we always (except the last split) read one extra line in
// next() method.
if (start != 0) {
start += in.readLine(new Text(), 0, maxBytesToConsume(start));
// If this is not the first split, we always throw away first record
// because we always (except the last split) read one extra line in
// next() method.
if (start != 0) {
start += in.readLine(new Text(), 0, maxBytesToConsume(start));
}
this.pos = start;
} catch (Exception e) {
fileIn.close();
throw e;
}
this.pos = start;
}


private int maxBytesToConsume(long pos) {
return isCompressedInput
Expand Down