hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Chris Douglas (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HADOOP-5281) GzipCodec fails second time it is used in a process
Date Mon, 16 Mar 2009 23:35:50 GMT

     [ https://issues.apache.org/jira/browse/HADOOP-5281?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Chris Douglas updated HADOOP-5281:
----------------------------------

    Description: 
The attached code (GZt.java) raises:
{noformat}
java.io.IOException: incorrect header check
	at org.apache.hadoop.io.compress.zlib.ZlibDecompressor.inflateBytesDirect(Native Method)
	at org.apache.hadoop.io.compress.zlib.ZlibDecompressor.decompress(ZlibDecompressor.java:221)
	at org.apache.hadoop.io.compress.DecompressorStream.decompress(DecompressorStream.java:80)
	at org.apache.hadoop.io.compress.DecompressorStream.read(DecompressorStream.java:74)
	at org.apache.hadoop.io.compress.DecompressorStream.read(DecompressorStream.java:62)
	at java.io.DataInputStream.readByte(DataInputStream.java:248)
	at org.apache.hadoop.io.WritableUtils.readVLong(WritableUtils.java:325)
	at org.apache.hadoop.io.WritableUtils.readVInt(WritableUtils.java:346)
	at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1853)
	at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1876)
	at org.apache.hadoop.io.MapFile$Reader.readIndex(MapFile.java:319)
	at org.apache.hadoop.io.MapFile$Reader.seekInternal(MapFile.java:435)
	at org.apache.hadoop.io.MapFile$Reader.seekInternal(MapFile.java:417)
	at org.apache.hadoop.io.MapFile$Reader.seek(MapFile.java:404)
	at org.apache.hadoop.io.MapFile$Reader.get(MapFile.java:523)
{noformat}

  was:
The following code raises:
java.io.IOException: incorrect header check
	at org.apache.hadoop.io.compress.zlib.ZlibDecompressor.inflateBytesDirect(Native Method)
	at org.apache.hadoop.io.compress.zlib.ZlibDecompressor.decompress(ZlibDecompressor.java:221)
	at org.apache.hadoop.io.compress.DecompressorStream.decompress(DecompressorStream.java:80)
	at org.apache.hadoop.io.compress.DecompressorStream.read(DecompressorStream.java:74)
	at org.apache.hadoop.io.compress.DecompressorStream.read(DecompressorStream.java:62)
	at java.io.DataInputStream.readByte(DataInputStream.java:248)
	at org.apache.hadoop.io.WritableUtils.readVLong(WritableUtils.java:325)
	at org.apache.hadoop.io.WritableUtils.readVInt(WritableUtils.java:346)
	at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1853)
	at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1876)
	at org.apache.hadoop.io.MapFile$Reader.readIndex(MapFile.java:319)
	at org.apache.hadoop.io.MapFile$Reader.seekInternal(MapFile.java:435)
	at org.apache.hadoop.io.MapFile$Reader.seekInternal(MapFile.java:417)
	at org.apache.hadoop.io.MapFile$Reader.seek(MapFile.java:404)
	at org.apache.hadoop.io.MapFile$Reader.get(MapFile.java:523)


{quote}
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.MapFile;
import org.apache.hadoop.io.SequenceFile.CompressionType;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class GZt extends Configured implements Tool {
	private FileSystem fileSystem;

	MapFile.Writer newMap(Path p) throws IOException {
		return new MapFile.Writer(getConf(), fileSystem, p.toString(),
				IntWritable.class, IntWritable.class, CompressionType.BLOCK,
				new GzipCodec(), null);
	}

	@Override
	public int run(String[] args) throws Exception {
		Path p = new Path(args[0]);
		fileSystem = FileSystem.get(getConf());

		fileSystem.mkdirs(p);
		for (int i = 0; i < 2; i++) {
			MapFile.Writer w = newMap(new Path(p, "b" + i));
			for (int j = 0; j < 100; j++) {
				w.append(new IntWritable(j), new IntWritable(j));
			}
			w.close();

		}
		MapFile.Reader rdr = new MapFile.Reader(fileSystem, new Path(p, "b1")
				.toString(), getConf());
		rdr.get(new IntWritable(1), new IntWritable());

		return 0;
	}

	public static void main(String[] args) throws Exception {
		int res = ToolRunner.run(new Configuration(), new GZt(), args);
		System.exit(res);
	}

}
{quote}


Edited description

> GzipCodec fails second time it is used in a process
> ---------------------------------------------------
>
>                 Key: HADOOP-5281
>                 URL: https://issues.apache.org/jira/browse/HADOOP-5281
>             Project: Hadoop Core
>          Issue Type: Bug
>    Affects Versions: 0.19.0
>         Environment: 0.19.0 / Linux / amd64
>            Reporter: Ben Maurer
>            Priority: Blocker
>         Attachments: GZt.java
>
>
> The attached code (GZt.java) raises:
> {noformat}
> java.io.IOException: incorrect header check
> 	at org.apache.hadoop.io.compress.zlib.ZlibDecompressor.inflateBytesDirect(Native Method)
> 	at org.apache.hadoop.io.compress.zlib.ZlibDecompressor.decompress(ZlibDecompressor.java:221)
> 	at org.apache.hadoop.io.compress.DecompressorStream.decompress(DecompressorStream.java:80)
> 	at org.apache.hadoop.io.compress.DecompressorStream.read(DecompressorStream.java:74)
> 	at org.apache.hadoop.io.compress.DecompressorStream.read(DecompressorStream.java:62)
> 	at java.io.DataInputStream.readByte(DataInputStream.java:248)
> 	at org.apache.hadoop.io.WritableUtils.readVLong(WritableUtils.java:325)
> 	at org.apache.hadoop.io.WritableUtils.readVInt(WritableUtils.java:346)
> 	at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1853)
> 	at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1876)
> 	at org.apache.hadoop.io.MapFile$Reader.readIndex(MapFile.java:319)
> 	at org.apache.hadoop.io.MapFile$Reader.seekInternal(MapFile.java:435)
> 	at org.apache.hadoop.io.MapFile$Reader.seekInternal(MapFile.java:417)
> 	at org.apache.hadoop.io.MapFile$Reader.seek(MapFile.java:404)
> 	at org.apache.hadoop.io.MapFile$Reader.get(MapFile.java:523)
> {noformat}

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message