Details
-
Bug
-
Status: Open
-
Major
-
Resolution: Unresolved
-
0.12.0
-
None
-
None
Description
Jars referenced in ADD JAR statements are not made available on the immediate classpath. That means they're useless for scripts which need to initialize external output formats for job submission (ie, hbase storage handler). Is this expected behavior?
For example, the table 'pagecounts_hbase' is an hbase table defined using the HBaseStorageHandler
$ cat foo.hql
ADD FILE /etc/hbase/conf/hbase-site.xml;
ADD JAR /usr/lib/hbase/lib/hbase-common-0.96.0.2.0.6.0-68-hadoop2.jar;
ADD JAR /usr/lib/hbase/lib/hbase-server-0.96.0.2.0.6.0-68-hadoop2.jar;
ADD JAR /usr/lib/hbase/lib/hbase-client-0.96.0.2.0.6.0-68-hadoop2.jar;
ADD JAR /usr/lib/hbase/lib/hbase-protocol-0.96.0.2.0.6.0-68-hadoop2.jar;
FROM pgc INSERT INTO TABLE pagecounts_hbase SELECT pgc.* WHERE rowkey LIKE 'en/q%' LIMIT 10;
$ hive -f foo.hql
...
Added resource: /etc/hbase/conf/hbase-site.xml
Added /usr/lib/hbase/lib/hbase-common-0.96.0.2.0.6.0-68-hadoop2.jar to class path
Added resource: /usr/lib/hbase/lib/hbase-common-0.96.0.2.0.6.0-68-hadoop2.jar
...
Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/hadoop/hbase/mapreduce/TableInputFormatBase [29/1858]
at java.lang.ClassLoader.defineClass1(Native Method)
at java.lang.ClassLoader.defineClass(ClassLoader.java:791)
at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
at java.net.URLClassLoader.defineClass(URLClassLoader.java:449)
at java.net.URLClassLoader.access$100(URLClassLoader.java:71)
at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:423)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:410)
at java.lang.ClassLoader.loadClass(ClassLoader.java:410)
at java.lang.ClassLoader.loadClass(ClassLoader.java:410)
at java.lang.ClassLoader.loadClass(ClassLoader.java:410)
at java.lang.ClassLoader.loadClass(ClassLoader.java:410)
at java.lang.ClassLoader.loadClass(ClassLoader.java:410)
at java.lang.ClassLoader.loadClass(ClassLoader.java:356)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:266)
at org.apache.hadoop.hive.ql.metadata.Table.getInputFormatClass(Table.java:305)
at org.apache.hadoop.hive.ql.metadata.Table.<init>(Table.java:98)
at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:989)
at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:892)
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer$tableSpec.<init>(BaseSemanticAnalyzer.java:730)
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer$tableSpec.<init>(BaseSemanticAnalyzer.java:707)
at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.getMetaData(SemanticAnalyzer.java:1196)
at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.getMetaData(SemanticAnalyzer.java:1053)
at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:8342)
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:284)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:441)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:342)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:977)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:888)
at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:259)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:216)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:413)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:348)
at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:446)
at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:456)
at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:737)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:675)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:614)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:601)
at org.apache.hadoop.util.RunJar.main(RunJar.java:212)
Caused by: java.lang.ClassNotFoundException: org.apache.hadoop.hbase.mapreduce.TableInputFormatBase
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:423)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:356)
... 48 more
The ADDed jar hbase-server.jar contains the missing class:
$ unzip -l /usr/lib/hbase/lib/hbase-server-0.96.0.2.0.6.0-68-hadoop2.jar | grep TableInputFormatBase
5363 10-09-2013 19:45 org/apache/hadoop/hbase/mapred/TableInputFormatBase.class
7460 10-09-2013 19:45 org/apache/hadoop/hbase/mapreduce/MultiTableInputFormatBase.class
8803 10-09-2013 19:45 org/apache/hadoop/hbase/mapreduce/TableInputFormatBase.class