hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Ted Yu <yuzhih...@gmail.com>
Subject Re: Using Mahout 1.0-SNAPSHOT with yarn cluster
Date Fri, 09 Jan 2015 15:17:28 GMT
In your driver, you can call:

    job.setJarByClass(theclass.class);

where theclass can be one of the classes in mahout jar.

FYI

On Fri, Jan 9, 2015 at 1:30 AM, mw <mw@plista.com> wrote:

>  Hello,
>
> i am working on a web application that should execute lda on a external
> yarn cluster.
>
> I am uploading all the relevant sequence files onto the yarn cluter.
> This is how it try to remotely execute lda on the cluster.
>
>         try {
>             ugi.doAs(new PrivilegedExceptionAction<Void>() {
>                 public Void run() throws Exception {
>                     Configuration hdoopConf = new Configuration();
>                     hdoopConf.set("fs.defaultFS",
> "hdfs://xxx.xxx.xxx.xxx:9000/user/xx");
>                     hdoopConf.set("yarn.resourcemanager.hostname",
> "xxx.xxx.xxx.xxx");
>                     hdoopConf.set("mapreduce.framework.name", "yarn");
>                     hdoopConf.set("mapred.framework.name", "yarn");
>                     hdoopConf.set("mapred.job.tracker",
> "xxx.xxx.xxx.xxx");
>                     hdoopConf.set("dfs.permissions.enabled", "false");
>                     hdoopConf.set("hadoop.job.ugi", "xx");
> hdoopConf.set("mapreduce.jobhistory.address","xxx.xxx.xxx.xxx:10020" );
>                     CVB0Driver driver = new CVB0Driver();
>                     try {
>                         driver.run(hdoopConf,
> sparseVectorIn.suffix("/matrix"),
>                                 topicsOut, k, numTerms,
> doc_topic_smoothening, term_topic_smoothening,
>                                 maxIter, iteration_block_size,
> convergenceDelta,
> sparseVectorIn.suffix("/dictionary.file-0"), topicsOut.suffix("
> */DocumentTopics/*"), sparseVectorIn,
>                                 seed, testFraction, numTrainThreads,
> numUpdateThreads, maxItersPerDoc,
>                                 numReduceTasks, backfillPerplexity);
>                     } catch (ClassNotFoundException e) {
>                         e.printStackTrace();
>                     } catch (InterruptedException e) {
>                         e.printStackTrace();
>                     }
>                     return null;
>                 }
>             });
>         } catch (InterruptedException e) {
>             e.printStackTrace();
>         }
>
> I am getting the following error message:
>
> Error: java.lang.ClassNotFoundException: org.apache.mahout.math.Vector
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:372)
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at java.net.URLClassLoader.findClass(URLClassLoader.java:360)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>     at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>     at java.lang.Class.forName0(Native Method)
>     at java.lang.Class.forName(Class.java:344)
>     at
> org.apache.hadoop.conf.Configuration.getClassByNameOrNull(Configuration.java:1844)
>     at
> org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:1809)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1903)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1929)
>     at
> org.apache.hadoop.mapred.JobConf.getMapOutputValueClass(JobConf.java:837)
>     at
> org.apache.hadoop.mapred.MapTask$MapOutputBuffer.init(MapTask.java:983)
>     at
> org.apache.hadoop.mapred.MapTask.createSortingCollector(MapTask.java:391)
>     at org.apache.hadoop.mapred.MapTask.access$100(MapTask.java:80)
>     at
> org.apache.hadoop.mapred.MapTask$NewOutputCollector.<init>(MapTask.java:675)
>     at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:747)
>     at org.apache.hadoop.mapred.MapTask.run(MapTask.java:340)
>     at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:168)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at javax.security.auth.Subject.doAs(Subject.java:422)
>     at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1614)
>     at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:163)
>
> Error: java.lang.ClassNotFoundException: org.apache.mahout.math.Vector
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:372)
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at java.net.URLClassLoader.findClass(URLClassLoader.java:360)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>     at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>     at java.lang.Class.forName0(Native Method)
>     at java.lang.Class.forName(Class.java:344)
>     at
> org.apache.hadoop.conf.Configuration.getClassByNameOrNull(Configuration.java:1844)
>     at
> org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:1809)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1903)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1929)
>     at
> org.apache.hadoop.mapred.JobConf.getMapOutputValueClass(JobConf.java:837)
>     at
> org.apache.hadoop.mapred.MapTask$MapOutputBuffer.init(MapTask.java:983)
>     at
> org.apache.hadoop.mapred.MapTask.createSortingCollector(MapTask.java:391)
>     at org.apache.hadoop.mapred.MapTask.access$100(MapTask.java:80)
>     at
> org.apache.hadoop.mapred.MapTask$NewOutputCollector.<init>(MapTask.java:675)
>     at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:747)
>     at org.apache.hadoop.mapred.MapTask.run(MapTask.java:340)
>     at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:168)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at javax.security.auth.Subject.doAs(Subject.java:422)
>     at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1614)
>     at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:163)
>
> Error: java.lang.ClassNotFoundException: org.apache.mahout.math.Vector
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:372)
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at java.net.URLClassLoader.findClass(URLClassLoader.java:360)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>     at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>     at java.lang.Class.forName0(Native Method)
>     at java.lang.Class.forName(Class.java:344)
>     at
> org.apache.hadoop.conf.Configuration.getClassByNameOrNull(Configuration.java:1844)
>     at
> org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:1809)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1903)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1929)
>     at
> org.apache.hadoop.mapred.JobConf.getMapOutputValueClass(JobConf.java:837)
>     at
> org.apache.hadoop.mapred.MapTask$MapOutputBuffer.init(MapTask.java:983)
>     at
> org.apache.hadoop.mapred.MapTask.createSortingCollector(MapTask.java:391)
>     at org.apache.hadoop.mapred.MapTask.access$100(MapTask.java:80)
>     at
> org.apache.hadoop.mapred.MapTask$NewOutputCollector.<init>(MapTask.java:675)
>     at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:747)
>     at org.apache.hadoop.mapred.MapTask.run(MapTask.java:340)
>     at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:168)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at javax.security.auth.Subject.doAs(Subject.java:422)
>     at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1614)
>     at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:163)
>
> Error: java.lang.ClassNotFoundException: org.apache.mahout.math.Vector
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:372)
>     at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at java.net.URLClassLoader.findClass(URLClassLoader.java:360)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
>     at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
>     at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
>     at java.lang.Class.forName0(Native Method)
>     at java.lang.Class.forName(Class.java:344)
>     at
> org.apache.hadoop.conf.Configuration.getClassByNameOrNull(Configuration.java:1844)
>     at
> org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:1809)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1903)
>     at
> org.apache.hadoop.conf.Configuration.getClass(Configuration.java:1929)
>     at
> org.apache.hadoop.mapred.JobConf.getMapOutputValueClass(JobConf.java:837)
>     at
> org.apache.hadoop.mapred.MapTask$MapOutputBuffer.init(MapTask.java:983)
>     at
> org.apache.hadoop.mapred.MapTask.createSortingCollector(MapTask.java:391)
>     at org.apache.hadoop.mapred.MapTask.access$100(MapTask.java:80)
>     at
> org.apache.hadoop.mapred.MapTask$NewOutputCollector.<init>(MapTask.java:675)
>     at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:747)
>     at org.apache.hadoop.mapred.MapTask.run(MapTask.java:340)
>     at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:168)
>     at java.security.AccessController.doPrivileged(Native Method)
>     at javax.security.auth.Subject.doAs(Subject.java:422)
>     at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1614)
>     at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:163)
>
> java.lang.InterruptedException: Failed to complete iteration 1 stage 1
>     at
> org.apache.mahout.clustering.lda.cvb.CVB0Driver.runIteration(CVB0Driver.java:502)
>     at
> org.apache.mahout.clustering.lda.cvb.CVB0Driver.run(CVB0Driver.java:319)
>     ...
>
> I was told on the user-mahout mailing list that the lda jar mahout sents
> to yarn should contain all relevant classes. Any idea why this error is
> thrown nevertheless?
>
> Best,
> Max
>

Mime
View raw message