hadoop mapreduce:java.lang.unsatifiedLinkError:org.apache.hadoop.util.nativecodeloader.buildsupportssnappy()z

ct3nt3jp  于 2021-06-04  发布在  Hadoop
关注(0)|答案(6)|浏览(515)

我正在尝试从map reduce作业编写一个snappy块压缩序列文件。我使用的是hadoop2.0.0-cdh4.5.0和snappyjava1.0.4.1
这是我的密码:

package jinvestor.jhouse.mr;

import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.Arrays;
import java.util.List;

import jinvestor.jhouse.core.House;
import jinvestor.jhouse.core.util.HouseAvroUtil;
import jinvestor.jhouse.download.HBaseHouseDAO;

import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocatedFileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RemoteIterator;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.SnappyCodec;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.mahout.math.DenseVector;
import org.apache.mahout.math.NamedVector;
import org.apache.mahout.math.VectorWritable;

/**
 * Produces mahout vectors from House entries in HBase.
 * 
 * @author Michael Scott Knapp
 * 
 */
public class HouseVectorizer {

    private final Configuration configuration;
    private final House minimumHouse;
    private final House maximumHouse;

    public HouseVectorizer(final Configuration configuration,
            final House minimumHouse, final House maximumHouse) {
        this.configuration = configuration;
        this.minimumHouse = minimumHouse;
        this.maximumHouse = maximumHouse;
    }

    public void vectorize() throws IOException, ClassNotFoundException, InterruptedException {
        JobConf jobConf = new JobConf();
        jobConf.setMapOutputKeyClass(LongWritable.class);
        jobConf.setMapOutputValueClass(VectorWritable.class);

        // we want the vectors written straight to HDFS,
        // the order does not matter.
        jobConf.setNumReduceTasks(0);

        Path outputDir = new Path("/home/cloudera/house_vectors");
        FileSystem fs = FileSystem.get(configuration);
        if (fs.exists(outputDir)) {
            fs.delete(outputDir, true);
        }

        FileOutputFormat.setOutputPath(jobConf, outputDir);

        // I want the mappers to know the max and min value
        // so they can normalize the data.
        // I will add them as properties in the configuration,
        // by serializing them with avro.
        String minmax = HouseAvroUtil.toBase64String(Arrays.asList(minimumHouse,
                maximumHouse));
        jobConf.set("minmax", minmax);

        Job job = Job.getInstance(jobConf);
        Scan scan = new Scan();
        scan.addFamily(Bytes.toBytes("data"));
        TableMapReduceUtil.initTableMapperJob("homes", scan,
                HouseVectorizingMapper.class, LongWritable.class,
                VectorWritable.class, job);
        job.setOutputFormatClass(SequenceFileOutputFormat.class);
        job.setOutputKeyClass(LongWritable.class);
        job.setOutputValueClass(VectorWritable.class);
        job.setMapOutputKeyClass(LongWritable.class);
        job.setMapOutputValueClass(VectorWritable.class);

        SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK);
        SequenceFileOutputFormat.setOutputCompressorClass(job, SnappyCodec.class);
        SequenceFileOutputFormat.setOutputPath(job, outputDir);
        job.getConfiguration().setClass("mapreduce.map.output.compress.codec", 
                SnappyCodec.class, 
                CompressionCodec.class);

        job.waitForCompletion(true);
    }

当我运行它时,我得到:

java.lang.Exception: java.lang.UnsatisfiedLinkError: org.apache.hadoop.util.NativeCodeLoader.buildSupportsSnappy()Z
    at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:401)
Caused by: java.lang.UnsatisfiedLinkError: org.apache.hadoop.util.NativeCodeLoader.buildSupportsSnappy()Z
    at org.apache.hadoop.util.NativeCodeLoader.buildSupportsSnappy(Native Method)
    at org.apache.hadoop.io.compress.SnappyCodec.checkNativeCodeLoaded(SnappyCodec.java:62)
    at org.apache.hadoop.io.compress.SnappyCodec.getCompressorType(SnappyCodec.java:127)
    at org.apache.hadoop.io.compress.CodecPool.getCompressor(CodecPool.java:104)
    at org.apache.hadoop.io.compress.CodecPool.getCompressor(CodecPool.java:118)
    at org.apache.hadoop.io.SequenceFile$Writer.init(SequenceFile.java:1169)
    at org.apache.hadoop.io.SequenceFile$Writer.<init>(SequenceFile.java:1080)
    at org.apache.hadoop.io.SequenceFile$BlockCompressWriter.<init>(SequenceFile.java:1400)
    at org.apache.hadoop.io.SequenceFile.createWriter(SequenceFile.java:274)
    at org.apache.hadoop.io.SequenceFile.createWriter(SequenceFile.java:527)
    at org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat.getSequenceWriter(SequenceFileOutputFormat.java:64)
    at org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat.getRecordWriter(SequenceFileOutputFormat.java:75)
    at org.apache.hadoop.mapred.MapTask$NewDirectOutputCollector.<init>(MapTask.java:617)
    at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:737)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:338)
    at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:233)
    at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
    at java.util.concurrent.FutureTask.run(FutureTask.java:262)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:744)

如果我注解掉这些行,那么我的测试通过了:

SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK);
        SequenceFileOutputFormat.setOutputCompressorClass(job, SnappyCodec.class);
        job.getConfiguration().setClass("mapreduce.map.output.compress.coded", 
                SnappyCodec.class, 
                CompressionCodec.class);

但是,我确实希望在序列文件中使用snappy压缩。有人能解释一下我做错了什么吗?

nafvub8i

nafvub8i1#

我需要所有的文件,不仅仅是*.so文件。理想情况下,您还可以将文件夹包含到路径中,而不是从那里复制libs。在此之后,您需要重新启动mapreduce服务,以便获取并使用新库。
尼科

mlmc2os5

mlmc2os52#

从cloudera社区中找到以下信息
确保ld\u library\u path和java\u library\u path包含包含libsnappy.so**文件的本机目录路径。
确保已在spark环境(spark env.sh)中导出ld_library_path和java_library path。
例如,我使用hortonworks hdp,在spark-env.sh中有以下配置

export JAVA_LIBRARY_PATH=$JAVA_LIBRARY_PATH:/usr/hdp/2.2.0.0-2041/hadoop/lib/native
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/hdp/2.2.0.0-2041/hadoop/lib/native
export SPARK_YARN_USER_ENV="JAVA_LIBRARY_PATH=$JAVA_LIBRARY_PATH,LD_LIBRARY_PATH=$LD_LIBRARY_PATH"
lbsnaicq

lbsnaicq3#

检查core-site.xml和mapred-site.xml它们应该包含正确的属性和带有库的文件夹路径
core-site.xml文件

<property>
  <name>io.compression.codecs</name>
<value>org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.SnappyCodec</value>
</property>

mapred-site.xml文件

<property>
      <name>mapreduce.map.output.compress</name>
      <value>true</value>
    </property>

    <property>
     <name>mapred.map.output.compress.codec</name>  
     <value>org.apache.hadoop.io.compress.SnappyCodec</value>
    </property>

    <property>
      <name>mapreduce.admin.user.env</name>
      <value>LD_LIBRARY_PATH=/usr/hdp/2.2.0.0-1084/hadoop/lib/native</value>
    </property>

ld\u library\u path-必须包含libsnappy.so的路径。

wmomyfyw

wmomyfyw4#

我的问题是我的jre没有包含适当的本机库。这可能是因为我将jdk从cloudera的预构建vm切换到了jdk1.7。snappy.so文件位于hadoop/lib/native目录中,jre需要它们。将它们添加到类路径似乎并没有解决我的问题。我是这样决定的:

$ cd /usr/lib/hadoop/lib/native
$ sudo cp *.so /usr/java/latest/jre/lib/amd64/

然后我就可以使用snappycodec类了。但你的道路可能不同。
这似乎让我想到了下一个问题:
原因:java.lang.runtimeexception:本机snappy库不可用:尚未加载snappycompressor。
还在努力解决这个问题。

svgewumm

svgewumm5#

在我的例子中,您可以检查配置单元conf文件:mapred-site.xml,并检查键:mapreduce.admin.user.env的值,
我在一个新的datanode中测试了它,在没有本机依赖项的机器上收到unlinked buildsnapy错误(libsnapy.so等)

z6psavjg

z6psavjg6#

从windows\system32中删除hadoop.dll(我手动复制了它)并设置hadoop\u home=\hadoop-2.6.4之后,它就可以工作了!!!

相关问题