You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jv...@apache.org on 2010/10/12 01:41:25 UTC
svn commit: r1021549 - in /hadoop/hive/trunk: ./
common/src/java/org/apache/hadoop/hive/conf/ contrib/ hbase-handler/ ql/
ql/src/java/org/apache/hadoop/hive/ql/ shims/
shims/src/0.17/java/org/apache/hadoop/hive/shims/
shims/src/0.18/java/org/apache/had...
Author: jvs
Date: Mon Oct 11 23:41:24 2010
New Revision: 1021549
URL: http://svn.apache.org/viewvc?rev=1021549&view=rev
Log:
HIVE-1264. Make Hive work with Hadoop security
(Todd Lipcon via jvs)
Added:
hadoop/hive/trunk/shims/src/0.20S/
hadoop/hive/trunk/shims/src/0.20S/java/
hadoop/hive/trunk/shims/src/0.20S/java/org/
hadoop/hive/trunk/shims/src/0.20S/java/org/apache/
hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/
hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/
hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/
hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Hadoop20SShims.java
hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Jetty20SShims.java
Modified:
hadoop/hive/trunk/CHANGES.txt
hadoop/hive/trunk/build-common.xml
hadoop/hive/trunk/build.properties
hadoop/hive/trunk/build.xml
hadoop/hive/trunk/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
hadoop/hive/trunk/contrib/build.xml
hadoop/hive/trunk/hbase-handler/build.xml
hadoop/hive/trunk/ql/build.xml
hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/Driver.java
hadoop/hive/trunk/shims/build.xml
hadoop/hive/trunk/shims/ivy.xml
hadoop/hive/trunk/shims/src/0.17/java/org/apache/hadoop/hive/shims/Hadoop17Shims.java
hadoop/hive/trunk/shims/src/0.18/java/org/apache/hadoop/hive/shims/Hadoop18Shims.java
hadoop/hive/trunk/shims/src/0.19/java/org/apache/hadoop/hive/shims/Hadoop19Shims.java
hadoop/hive/trunk/shims/src/0.20/java/org/apache/hadoop/hive/shims/Hadoop20Shims.java
hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/HadoopShims.java
hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/ShimLoader.java
Modified: hadoop/hive/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/CHANGES.txt?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/CHANGES.txt (original)
+++ hadoop/hive/trunk/CHANGES.txt Mon Oct 11 23:41:24 2010
@@ -181,6 +181,9 @@ Trunk - Unreleased
HIVE-1697. Migration scripts should increase size of PARAM_VALUE in
PARTITION_PARAMS (Paul Yang via namit)
+ HIVE-1264. Make Hive work with Hadoop security
+ (Todd Lipcon via jvs)
+
OPTIMIZATIONS
BUG FIXES
Modified: hadoop/hive/trunk/build-common.xml
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/build-common.xml?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/build-common.xml (original)
+++ hadoop/hive/trunk/build-common.xml Mon Oct 11 23:41:24 2010
@@ -218,8 +218,10 @@
<!-- the normal classpath -->
<path id="common-classpath">
- <pathelement location="${hadoop.jar}"/>
- <pathelement location="${hadoop.tools.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.tools.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.tools.jar}"/>
<pathelement location="${build.dir.hive}/classes"/>
<fileset dir="${build.dir.hive}" includes="*/*.jar"/>
<fileset dir="${hive.root}/lib" includes="*.jar"/>
Modified: hadoop/hive/trunk/build.properties
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/build.properties?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/build.properties (original)
+++ hadoop/hive/trunk/build.properties Mon Oct 11 23:41:24 2010
@@ -20,9 +20,15 @@ build.dir.hadoop=${build.dir.hive}/hadoo
hadoop.version.ant-internal=${hadoop.version}
hadoop.root.default=${build.dir.hadoop}/hadoop-${hadoop.version.ant-internal}
hadoop.root=${hadoop.root.default}
-hadoop.jar=${hadoop.root}/hadoop-${hadoop.version.ant-internal}-core.jar
-hadoop.tools.jar=${hadoop.root}/hadoop-${hadoop.version.ant-internal}-tools.jar
-hadoop.test.jar=${hadoop.root}/hadoop-${hadoop.version.ant-internal}-test.jar
+# Newer versions of Hadoop name the jar as hadoop-{core,test}-VERSION instead of hadoop-VERSION-{core,test}
+# We will add both styles to the classpath and it will pick up whichever is there
+hadoop.oldstyle-name.jar=${hadoop.root}/hadoop-${hadoop.version.ant-internal}-core.jar
+hadoop.oldstyle-name.tools.jar=${hadoop.root}/hadoop-${hadoop.version.ant-internal}-tools.jar
+hadoop.oldstyle-name.test.jar=${hadoop.root}/hadoop-${hadoop.version.ant-internal}-test.jar
+hadoop.newstyle-name.jar=${hadoop.root}/hadoop-core-${hadoop.version.ant-internal}.jar
+hadoop.newstyle-name.test.jar=${hadoop.root}/hadoop-test-${hadoop.version.ant-internal}.jar
+hadoop.newstyle-name.tools.jar=${hadoop.root}/hadoop-tools-${hadoop.version.ant-internal}.jar
+
jetty.test.jar=${hadoop.root}/lib/jetty-5.1.4.jar
servlet.test.jar=${hadoop.root}/lib/servlet-api.jar
jasper.test.jar=${hadoop.root}/lib/jetty-ext/jasper-runtime.jar
@@ -34,3 +40,8 @@ common.jar=${hadoop.root}/lib/commons-ht
# Data nucleus repository - needed for jdo2-api-2.3-ec.jar download
#
datanucleus.repo=http://www.datanucleus.org/downloads/maven2
+
+# URLs pointing to a built tarball of a secure hadoop release
+hadoop.security.url=http://mirror.facebook.net/facebook/hive-deps/hadoop/core/hadoop-0.20.3-CDH3-SNAPSHOT/hadoop-0.20.3-CDH3-SNAPSHOT.tar.gz
+hadoop.security.version=0.20.3-CDH3-SNAPSHOT
+
Modified: hadoop/hive/trunk/build.xml
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/build.xml?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/build.xml (original)
+++ hadoop/hive/trunk/build.xml Mon Oct 11 23:41:24 2010
@@ -112,7 +112,8 @@
<!-- the normal classpath -->
<path id="common-classpath">
- <pathelement location="${hadoop.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.jar}"/>
<pathelement location="${build.dir.hive}/classes"/>
<fileset dir="${hive.root}" includes="hive-*.jar"/>
<fileset dir="${hive.root}/lib" includes="*.jar"/>
Modified: hadoop/hive/trunk/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java (original)
+++ hadoop/hive/trunk/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java Mon Oct 11 23:41:24 2010
@@ -591,13 +591,11 @@ public class HiveConf extends Configurat
*/
public String getUser() throws IOException {
try {
- UserGroupInformation ugi = UserGroupInformation.readFrom(this);
- if (ugi == null) {
- ugi = UserGroupInformation.login(this);
- }
+ UserGroupInformation ugi = ShimLoader.getHadoopShims()
+ .getUGIForConf(this);
return ugi.getUserName();
- } catch (LoginException e) {
- throw (IOException) new IOException().initCause(e);
+ } catch (LoginException le) {
+ throw new IOException(le);
}
}
Modified: hadoop/hive/trunk/contrib/build.xml
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/contrib/build.xml?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/contrib/build.xml (original)
+++ hadoop/hive/trunk/contrib/build.xml Mon Oct 11 23:41:24 2010
@@ -36,7 +36,6 @@
<pathelement location="${test.src.data.dir}/conf"/>
<pathelement location="${hive.conf.dir}"/>
<pathelement location="${hive.root}/cli/lib/jline-0.9.94.jar"/>
- <pathelement location="${hadoop.test.jar}"/>
<pathelement location="${jetty.test.jar}"/>
<pathelement location="${servlet.test.jar}"/>
<pathelement location="${jasper.test.jar}"/>
Modified: hadoop/hive/trunk/hbase-handler/build.xml
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/hbase-handler/build.xml?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/hbase-handler/build.xml (original)
+++ hadoop/hive/trunk/hbase-handler/build.xml Mon Oct 11 23:41:24 2010
@@ -37,7 +37,8 @@
<pathelement location="${test.src.data.dir}/conf"/>
<pathelement location="${hive.conf.dir}"/>
<pathelement location="${hive.root}/cli/lib/jline-0.9.94.jar"/>
- <pathelement location="${hadoop.test.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.test.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.test.jar}"/>
<pathelement location="${jetty.test.jar}"/>
<pathelement location="${servlet.test.jar}"/>
<pathelement location="${jasper.test.jar}"/>
Modified: hadoop/hive/trunk/ql/build.xml
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/build.xml?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/build.xml (original)
+++ hadoop/hive/trunk/ql/build.xml Mon Oct 11 23:41:24 2010
@@ -40,7 +40,8 @@
<pathelement location="${test.src.data.dir}/conf"/>
<pathelement location="${hive.conf.dir}"/>
<pathelement location="${hive.root}/cli/lib/jline-0.9.94.jar"/>
- <pathelement location="${hadoop.test.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.test.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.test.jar}"/>
<pathelement location="${jetty.test.jar}"/>
<pathelement location="${servlet.test.jar}"/>
<pathelement location="${jasper.test.jar}"/>
Modified: hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/Driver.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/Driver.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/Driver.java (original)
+++ hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/Driver.java Mon Oct 11 23:41:24 2010
@@ -85,10 +85,10 @@ import org.apache.hadoop.hive.ql.process
import org.apache.hadoop.hive.ql.session.SessionState;
import org.apache.hadoop.hive.ql.session.SessionState.LogHelper;
import org.apache.hadoop.hive.serde2.ByteStream;
+import org.apache.hadoop.hive.shims.ShimLoader;
import org.apache.hadoop.mapred.ClusterStatus;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
-import org.apache.hadoop.security.UnixUserGroupInformation;
import org.apache.hadoop.util.ReflectionUtils;
public class Driver implements CommandProcessor {
@@ -285,21 +285,11 @@ public class Driver implements CommandPr
*/
public Driver(HiveConf conf) {
this.conf = conf;
- try {
- UnixUserGroupInformation.login(conf, true);
- } catch (Exception e) {
- LOG.warn("Ignoring " + e.getMessage());
- }
}
public Driver() {
if (SessionState.get() != null) {
conf = SessionState.get().getConf();
- try {
- UnixUserGroupInformation.login(conf, true);
- } catch (Exception e) {
- LOG.warn("Ignoring " + e.getMessage());
- }
}
}
@@ -739,8 +729,7 @@ public class Driver implements CommandPr
// Get all the pre execution hooks and execute them.
for (PreExecute peh : getPreExecHooks()) {
peh.run(SessionState.get(), plan.getInputs(), plan.getOutputs(),
- UnixUserGroupInformation.readFromConf(conf,
- UnixUserGroupInformation.UGI_PROPERTY_NAME));
+ ShimLoader.getHadoopShims().getUGIForConf(conf));
}
int jobs = Utilities.getMRTasks(plan.getRootTasks()).size();
@@ -822,8 +811,7 @@ public class Driver implements CommandPr
for (PostExecute peh : getPostExecHooks()) {
peh.run(SessionState.get(), plan.getInputs(), plan.getOutputs(),
(SessionState.get() != null ? SessionState.get().getLineageState().getLineageInfo() : null),
- UnixUserGroupInformation.readFromConf(conf,
- UnixUserGroupInformation.UGI_PROPERTY_NAME));
+ ShimLoader.getHadoopShims().getUGIForConf(conf));
}
if (SessionState.get() != null) {
Modified: hadoop/hive/trunk/shims/build.xml
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/build.xml?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/build.xml (original)
+++ hadoop/hive/trunk/shims/build.xml Mon Oct 11 23:41:24 2010
@@ -26,9 +26,12 @@ to call at top-level: ant deploy-contrib
<import file="../build-common.xml"/>
<path id="classpath">
- <pathelement location="${hadoop.jar}"/>
- <pathelement location="${hadoop.tools.jar}"/>
- <pathelement location="${hadoop.test.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.tools.jar}"/>
+ <pathelement location="${hadoop.oldstyle-name.test.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.test.jar}"/>
+ <pathelement location="${hadoop.newstyle-name.tools.jar}"/>
<fileset dir="${hadoop.root}/lib">
<include name="**/*.jar" />
<exclude name="**/excluded/" />
@@ -66,6 +69,10 @@ to call at top-level: ant deploy-contrib
<antcall target="build_shims" inheritRefs="false" inheritAll="false">
<param name="hadoop.version.ant-internal" value="0.20.0" />
</antcall>
+ <antcall target="build_shims" inheritRefs="false" inheritAll="false">
+ <param name="hadoop.version.ant-internal" value="${hadoop.security.version}" />
+ <param name="hadoop.version.ant-internal.prefix" value="0.20S" />
+ </antcall>
<getversionpref property="hadoop.version.ant-internal.prefix" input="${hadoop.version}" />
<javac
encoding="${build.encoding}"
Modified: hadoop/hive/trunk/shims/ivy.xml
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/ivy.xml?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/ivy.xml (original)
+++ hadoop/hive/trunk/shims/ivy.xml Mon Oct 11 23:41:24 2010
@@ -13,6 +13,10 @@
<dependency org="hadoop" name="core" rev="0.20.0">
<artifact name="hadoop" type="source" ext="tar.gz"/>
</dependency>
+ <dependency org="hadoop" name="core" rev="${hadoop.security.version}">
+ <artifact name="hadoop" type="source" ext="tar.gz"
+ url="${hadoop.security.url}" />
+ </dependency>
<conflict manager="all" />
</dependencies>
</ivy-module>
Modified: hadoop/hive/trunk/shims/src/0.17/java/org/apache/hadoop/hive/shims/Hadoop17Shims.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/0.17/java/org/apache/hadoop/hive/shims/Hadoop17Shims.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/src/0.17/java/org/apache/hadoop/hive/shims/Hadoop17Shims.java (original)
+++ hadoop/hive/trunk/shims/src/0.17/java/org/apache/hadoop/hive/shims/Hadoop17Shims.java Mon Oct 11 23:41:24 2010
@@ -29,6 +29,9 @@ import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.RunningJob;
import org.apache.hadoop.mapred.TaskCompletionEvent;
import org.apache.hadoop.mapred.lib.NullOutputFormat;
+import org.apache.hadoop.security.UserGroupInformation;
+import org.apache.hadoop.security.UnixUserGroupInformation;
+import javax.security.auth.login.LoginException;
import java.io.IOException;
@@ -134,4 +137,13 @@ public class Hadoop17Shims implements Ha
throw new RuntimeException("Not implemented in this Hadoop version");
}
+ @Override
+ public UserGroupInformation getUGIForConf(Configuration conf) throws LoginException {
+ UserGroupInformation ugi =
+ UnixUserGroupInformation.readFromConf(conf, UnixUserGroupInformation.UGI_PROPERTY_NAME);
+ if(ugi == null) {
+ ugi = UserGroupInformation.login(conf);
+ }
+ return ugi;
+ }
}
Modified: hadoop/hive/trunk/shims/src/0.18/java/org/apache/hadoop/hive/shims/Hadoop18Shims.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/0.18/java/org/apache/hadoop/hive/shims/Hadoop18Shims.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/src/0.18/java/org/apache/hadoop/hive/shims/Hadoop18Shims.java (original)
+++ hadoop/hive/trunk/shims/src/0.18/java/org/apache/hadoop/hive/shims/Hadoop18Shims.java Mon Oct 11 23:41:24 2010
@@ -31,6 +31,9 @@ import org.apache.hadoop.mapred.TaskID;
import org.apache.hadoop.mapred.TaskAttemptID;
import org.apache.hadoop.mapred.TaskCompletionEvent;
import org.apache.hadoop.mapred.lib.NullOutputFormat;
+import org.apache.hadoop.security.UserGroupInformation;
+import org.apache.hadoop.security.UnixUserGroupInformation;
+import javax.security.auth.login.LoginException;
import java.io.IOException;
@@ -137,4 +140,14 @@ public class Hadoop18Shims implements Ha
public void setNullOutputFormat(JobConf conf) {
conf.setOutputFormat(NullOutputFormat.class);
}
+
+ @Override
+ public UserGroupInformation getUGIForConf(Configuration conf) throws LoginException {
+ UserGroupInformation ugi =
+ UnixUserGroupInformation.readFromConf(conf, UnixUserGroupInformation.UGI_PROPERTY_NAME);
+ if(ugi == null) {
+ ugi = UserGroupInformation.login(conf);
+ }
+ return ugi;
+ }
}
Modified: hadoop/hive/trunk/shims/src/0.19/java/org/apache/hadoop/hive/shims/Hadoop19Shims.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/0.19/java/org/apache/hadoop/hive/shims/Hadoop19Shims.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/src/0.19/java/org/apache/hadoop/hive/shims/Hadoop19Shims.java (original)
+++ hadoop/hive/trunk/shims/src/0.19/java/org/apache/hadoop/hive/shims/Hadoop19Shims.java Mon Oct 11 23:41:24 2010
@@ -37,6 +37,9 @@ import org.apache.hadoop.mapred.OutputCo
import org.apache.hadoop.mapred.TaskAttemptContext;
import org.apache.hadoop.mapred.JobContext;
import org.apache.hadoop.mapred.lib.NullOutputFormat;
+import org.apache.hadoop.security.UserGroupInformation;
+import org.apache.hadoop.security.UnixUserGroupInformation;
+import javax.security.auth.login.LoginException;
import java.io.IOException;
import java.lang.reflect.Constructor;
@@ -512,4 +515,15 @@ public class Hadoop19Shims implements Ha
// but can be backported. So we disable setup/cleanup in all versions >= 0.19
conf.setBoolean("mapred.committer.job.setup.cleanup.needed", false);
}
+
+
+ @Override
+ public UserGroupInformation getUGIForConf(Configuration conf) throws LoginException {
+ UserGroupInformation ugi =
+ UnixUserGroupInformation.readFromConf(conf, UnixUserGroupInformation.UGI_PROPERTY_NAME);
+ if(ugi == null) {
+ ugi = UserGroupInformation.login(conf);
+ }
+ return ugi;
+ }
}
Modified: hadoop/hive/trunk/shims/src/0.20/java/org/apache/hadoop/hive/shims/Hadoop20Shims.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/0.20/java/org/apache/hadoop/hive/shims/Hadoop20Shims.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/src/0.20/java/org/apache/hadoop/hive/shims/Hadoop20Shims.java (original)
+++ hadoop/hive/trunk/shims/src/0.20/java/org/apache/hadoop/hive/shims/Hadoop20Shims.java Mon Oct 11 23:41:24 2010
@@ -23,6 +23,7 @@ import java.io.IOException;
import java.lang.reflect.Constructor;
import java.util.ArrayList;
import java.util.List;
+import javax.security.auth.login.LoginException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
@@ -48,6 +49,8 @@ import org.apache.hadoop.mapred.TaskID;
import org.apache.hadoop.mapred.lib.CombineFileInputFormat;
import org.apache.hadoop.mapred.lib.CombineFileSplit;
import org.apache.hadoop.mapred.lib.NullOutputFormat;
+import org.apache.hadoop.security.UserGroupInformation;
+import org.apache.hadoop.security.UnixUserGroupInformation;
import org.apache.hadoop.tools.HadoopArchives;
import org.apache.hadoop.util.ToolRunner;
@@ -436,4 +439,14 @@ public class Hadoop20Shims implements Ha
// but can be backported. So we disable setup/cleanup in all versions >= 0.19
conf.setBoolean("mapred.committer.job.setup.cleanup.needed", false);
}
+
+ @Override
+ public UserGroupInformation getUGIForConf(Configuration conf) throws LoginException {
+ UserGroupInformation ugi =
+ UnixUserGroupInformation.readFromConf(conf, UnixUserGroupInformation.UGI_PROPERTY_NAME);
+ if(ugi == null) {
+ ugi = UserGroupInformation.login(conf);
+ }
+ return ugi;
+ }
}
Added: hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Hadoop20SShims.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Hadoop20SShims.java?rev=1021549&view=auto
==============================================================================
--- hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Hadoop20SShims.java (added)
+++ hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Hadoop20SShims.java Mon Oct 11 23:41:24 2010
@@ -0,0 +1,446 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hive.shims;
+
+import java.io.DataInput;
+import java.io.DataOutput;
+import java.io.IOException;
+import java.lang.reflect.Constructor;
+import java.util.ArrayList;
+import java.util.List;
+import javax.security.auth.login.LoginException;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.PathFilter;
+import org.apache.hadoop.hdfs.MiniDFSCluster;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.WritableComparable;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.InputFormat;
+import org.apache.hadoop.mapred.InputSplit;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.JobContext;
+import org.apache.hadoop.mapred.JobStatus;
+import org.apache.hadoop.mapred.OutputCommitter;
+import org.apache.hadoop.mapred.RecordReader;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.RunningJob;
+import org.apache.hadoop.mapred.TaskAttemptContext;
+import org.apache.hadoop.mapred.TaskCompletionEvent;
+import org.apache.hadoop.mapred.TaskID;
+import org.apache.hadoop.mapred.lib.CombineFileInputFormat;
+import org.apache.hadoop.mapred.lib.CombineFileSplit;
+import org.apache.hadoop.mapred.lib.NullOutputFormat;
+import org.apache.hadoop.security.UserGroupInformation;
+import org.apache.hadoop.tools.HadoopArchives;
+import org.apache.hadoop.util.ToolRunner;
+
+/**
+ * Implemention of shims against Hadoop 0.20.0.
+ */
+public class Hadoop20SShims implements HadoopShims {
+ public boolean usesJobShell() {
+ return false;
+ }
+
+ public boolean fileSystemDeleteOnExit(FileSystem fs, Path path)
+ throws IOException {
+
+ return fs.deleteOnExit(path);
+ }
+
+ public void inputFormatValidateInput(InputFormat fmt, JobConf conf)
+ throws IOException {
+ // gone in 0.18+
+ }
+
+ public boolean isJobPreparing(RunningJob job) throws IOException {
+ return job.getJobState() == JobStatus.PREP;
+ }
+ /**
+ * Workaround for hadoop-17 - jobclient only looks at commandlineconfig.
+ */
+ public void setTmpFiles(String prop, String files) {
+ // gone in 20+
+ }
+
+ public HadoopShims.MiniDFSShim getMiniDfs(Configuration conf,
+ int numDataNodes,
+ boolean format,
+ String[] racks) throws IOException {
+ return new MiniDFSShim(new MiniDFSCluster(conf, numDataNodes, format, racks));
+ }
+
+ /**
+ * MiniDFSShim.
+ *
+ */
+ public class MiniDFSShim implements HadoopShims.MiniDFSShim {
+ private final MiniDFSCluster cluster;
+
+ public MiniDFSShim(MiniDFSCluster cluster) {
+ this.cluster = cluster;
+ }
+
+ public FileSystem getFileSystem() throws IOException {
+ return cluster.getFileSystem();
+ }
+
+ public void shutdown() {
+ cluster.shutdown();
+ }
+ }
+
+ /**
+ * We define this function here to make the code compatible between
+ * hadoop 0.17 and hadoop 0.20.
+ *
+ * Hive binary that compiled Text.compareTo(Text) with hadoop 0.20 won't
+ * work with hadoop 0.17 because in hadoop 0.20, Text.compareTo(Text) is
+ * implemented in org.apache.hadoop.io.BinaryComparable, and Java compiler
+ * references that class, which is not available in hadoop 0.17.
+ */
+ public int compareText(Text a, Text b) {
+ return a.compareTo(b);
+ }
+
+ @Override
+ public long getAccessTime(FileStatus file) {
+ return file.getAccessTime();
+ }
+
+ public HadoopShims.CombineFileInputFormatShim getCombineFileInputFormat() {
+ return new CombineFileInputFormatShim() {
+ @Override
+ public RecordReader getRecordReader(InputSplit split,
+ JobConf job, Reporter reporter) throws IOException {
+ throw new IOException("CombineFileInputFormat.getRecordReader not needed.");
+ }
+ };
+ }
+
+ public static class InputSplitShim extends CombineFileSplit implements HadoopShims.InputSplitShim {
+ public InputSplitShim() {
+ super();
+ }
+
+ public InputSplitShim(CombineFileSplit old) throws IOException {
+ super(old);
+ }
+ }
+
+ public static class CombineHiveKey implements WritableComparable {
+ Object key;
+
+ public CombineHiveKey(Object key) {
+ this.key = key;
+ }
+
+ public Object getKey() {
+ return key;
+ }
+
+ public void setKey(Object key) {
+ this.key = key;
+ }
+
+ public void write(DataOutput out) throws IOException {
+ throw new IOException("Method not supported");
+ }
+
+ public void readFields(DataInput in) throws IOException {
+ throw new IOException("Method not supported");
+ }
+
+ public int compareTo(Object w) {
+ assert false;
+ return 0;
+ }
+ }
+
+ /* This class should be replaced with org.apache.hadoop.mapred.lib.CombineFileRecordReader class, once
+ * https://issues.apache.org/jira/browse/MAPREDUCE-955 is fixed. This code should be removed - it is a copy
+ * of org.apache.hadoop.mapred.lib.CombineFileRecordReader
+ */
+ public static class CombineFileRecordReader<K, V> implements RecordReader<K, V> {
+
+ static final Class[] constructorSignature = new Class[] {
+ InputSplit.class,
+ Configuration.class,
+ Reporter.class,
+ Integer.class
+ };
+
+ protected CombineFileSplit split;
+ protected JobConf jc;
+ protected Reporter reporter;
+ protected Class<RecordReader<K, V>> rrClass;
+ protected Constructor<RecordReader<K, V>> rrConstructor;
+ protected FileSystem fs;
+
+ protected int idx;
+ protected long progress;
+ protected RecordReader<K, V> curReader;
+
+ public boolean next(K key, V value) throws IOException {
+
+ while ((curReader == null) || !curReader.next((K)((CombineHiveKey)key).getKey(), value)) {
+ if (!initNextRecordReader(key)) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ public K createKey() {
+ K newKey = curReader.createKey();
+ return (K)(new CombineHiveKey(newKey));
+ }
+
+ public V createValue() {
+ return curReader.createValue();
+ }
+
+ /**
+ * Return the amount of data processed.
+ */
+ public long getPos() throws IOException {
+ return progress;
+ }
+
+ public void close() throws IOException {
+ if (curReader != null) {
+ curReader.close();
+ curReader = null;
+ }
+ }
+
+ /**
+ * Return progress based on the amount of data processed so far.
+ */
+ public float getProgress() throws IOException {
+ return Math.min(1.0f, progress / (float) (split.getLength()));
+ }
+
+ /**
+ * A generic RecordReader that can hand out different recordReaders
+ * for each chunk in the CombineFileSplit.
+ */
+ public CombineFileRecordReader(JobConf job, CombineFileSplit split,
+ Reporter reporter,
+ Class<RecordReader<K, V>> rrClass)
+ throws IOException {
+ this.split = split;
+ this.jc = job;
+ this.rrClass = rrClass;
+ this.reporter = reporter;
+ this.idx = 0;
+ this.curReader = null;
+ this.progress = 0;
+
+ try {
+ rrConstructor = rrClass.getDeclaredConstructor(constructorSignature);
+ rrConstructor.setAccessible(true);
+ } catch (Exception e) {
+ throw new RuntimeException(rrClass.getName() +
+ " does not have valid constructor", e);
+ }
+ initNextRecordReader(null);
+ }
+
+ /**
+ * Get the record reader for the next chunk in this CombineFileSplit.
+ */
+ protected boolean initNextRecordReader(K key) throws IOException {
+
+ if (curReader != null) {
+ curReader.close();
+ curReader = null;
+ if (idx > 0) {
+ progress += split.getLength(idx - 1); // done processing so far
+ }
+ }
+
+ // if all chunks have been processed, nothing more to do.
+ if (idx == split.getNumPaths()) {
+ return false;
+ }
+
+ // get a record reader for the idx-th chunk
+ try {
+ curReader = rrConstructor.newInstance(new Object[]
+ {split, jc, reporter, Integer.valueOf(idx)});
+
+ // change the key if need be
+ if (key != null) {
+ K newKey = curReader.createKey();
+ ((CombineHiveKey)key).setKey(newKey);
+ }
+
+ // setup some helper config variables.
+ jc.set("map.input.file", split.getPath(idx).toString());
+ jc.setLong("map.input.start", split.getOffset(idx));
+ jc.setLong("map.input.length", split.getLength(idx));
+ } catch (Exception e) {
+ throw new RuntimeException(e);
+ }
+ idx++;
+ return true;
+ }
+ }
+
+ public abstract static class CombineFileInputFormatShim<K, V> extends
+ CombineFileInputFormat<K, V>
+ implements HadoopShims.CombineFileInputFormatShim<K, V> {
+
+ public Path[] getInputPathsShim(JobConf conf) {
+ try {
+ return FileInputFormat.getInputPaths(conf);
+ } catch (Exception e) {
+ throw new RuntimeException(e);
+ }
+ }
+
+ @Override
+ public void createPool(JobConf conf, PathFilter... filters) {
+ super.createPool(conf, filters);
+ }
+
+ @Override
+ public InputSplitShim[] getSplits(JobConf job, int numSplits) throws IOException {
+ long minSize = job.getLong("mapred.min.split.size", 0);
+
+ // For backward compatibility, let the above parameter be used
+ if (job.getLong("mapred.min.split.size.per.node", 0) == 0) {
+ super.setMinSplitSizeNode(minSize);
+ }
+
+ if (job.getLong("mapred.min.split.size.per.rack", 0) == 0) {
+ super.setMinSplitSizeRack(minSize);
+ }
+
+ if (job.getLong("mapred.max.split.size", 0) == 0) {
+ super.setMaxSplitSize(minSize);
+ }
+
+ CombineFileSplit[] splits = (CombineFileSplit[]) super.getSplits(job, numSplits);
+
+ InputSplitShim[] isplits = new InputSplitShim[splits.length];
+ for (int pos = 0; pos < splits.length; pos++) {
+ isplits[pos] = new InputSplitShim(splits[pos]);
+ }
+
+ return isplits;
+ }
+
+ public InputSplitShim getInputSplitShim() throws IOException {
+ return new InputSplitShim();
+ }
+
+ public RecordReader getRecordReader(JobConf job, HadoopShims.InputSplitShim split,
+ Reporter reporter,
+ Class<RecordReader<K, V>> rrClass)
+ throws IOException {
+ CombineFileSplit cfSplit = (CombineFileSplit) split;
+ return new CombineFileRecordReader(job, cfSplit, reporter, rrClass);
+ }
+
+ }
+
+ public String getInputFormatClassName() {
+ return "org.apache.hadoop.hive.ql.io.CombineHiveInputFormat";
+ }
+
+ String[] ret = new String[2];
+
+ @Override
+ public String[] getTaskJobIDs(TaskCompletionEvent t) {
+ TaskID tid = t.getTaskAttemptId().getTaskID();
+ ret[0] = tid.toString();
+ ret[1] = tid.getJobID().toString();
+ return ret;
+ }
+
+ public void setFloatConf(Configuration conf, String varName, float val) {
+ conf.setFloat(varName, val);
+ }
+
+ @Override
+ public int createHadoopArchive(Configuration conf, Path sourceDir, Path destDir,
+ String archiveName) throws Exception {
+
+ HadoopArchives har = new HadoopArchives(conf);
+ List<String> args = new ArrayList<String>();
+
+ if (conf.get("hive.archive.har.parentdir.settable") == null) {
+ throw new RuntimeException("hive.archive.har.parentdir.settable is not set");
+ }
+ boolean parentSettable =
+ conf.getBoolean("hive.archive.har.parentdir.settable", false);
+
+ if (parentSettable) {
+ args.add("-archiveName");
+ args.add(archiveName);
+ args.add("-p");
+ args.add(sourceDir.toString());
+ args.add(destDir.toString());
+ } else {
+ args.add("-archiveName");
+ args.add(archiveName);
+ args.add(sourceDir.toString());
+ args.add(destDir.toString());
+ }
+
+ return ToolRunner.run(har, args.toArray(new String[0]));
+ }
+
+ public static class NullOutputCommitter extends OutputCommitter {
+ @Override
+ public void setupJob(JobContext jobContext) { }
+ @Override
+ public void cleanupJob(JobContext jobContext) { }
+
+ @Override
+ public void setupTask(TaskAttemptContext taskContext) { }
+ @Override
+ public boolean needsTaskCommit(TaskAttemptContext taskContext) {
+ return false;
+ }
+ @Override
+ public void commitTask(TaskAttemptContext taskContext) { }
+ @Override
+ public void abortTask(TaskAttemptContext taskContext) { }
+ }
+
+ public void setNullOutputFormat(JobConf conf) {
+ conf.setOutputFormat(NullOutputFormat.class);
+ conf.setOutputCommitter(Hadoop20Shims.NullOutputCommitter.class);
+
+ // option to bypass job setup and cleanup was introduced in hadoop-21 (MAPREDUCE-463)
+ // but can be backported. So we disable setup/cleanup in all versions >= 0.19
+ conf.setBoolean("mapred.committer.job.setup.cleanup.needed", false);
+ }
+
+ @Override
+ public UserGroupInformation getUGIForConf(Configuration conf) throws IOException {
+ return UserGroupInformation.getCurrentUser();
+ }
+}
Added: hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Jetty20SShims.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Jetty20SShims.java?rev=1021549&view=auto
==============================================================================
--- hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Jetty20SShims.java (added)
+++ hadoop/hive/trunk/shims/src/0.20S/java/org/apache/hadoop/hive/shims/Jetty20SShims.java Mon Oct 11 23:41:24 2010
@@ -0,0 +1,53 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hive.shims;
+
+
+import org.mortbay.jetty.bio.SocketConnector;
+import org.mortbay.jetty.handler.RequestLogHandler;
+import org.mortbay.jetty.webapp.WebAppContext;
+
+import java.io.IOException;
+
+public class Jetty20SShims implements JettyShims {
+ public Server startServer(String listen, int port) throws IOException {
+ Server s = new Server();
+ s.setupListenerHostPort(listen, port);
+ return s;
+ }
+
+ private static class Server extends org.mortbay.jetty.Server implements JettyShims.Server {
+ public void addWar(String war, String contextPath) {
+ WebAppContext wac = new WebAppContext();
+ wac.setContextPath(contextPath);
+ wac.setWar(war);
+ RequestLogHandler rlh = new RequestLogHandler();
+ rlh.setHandler(wac);
+ this.addHandler(rlh);
+ }
+
+ public void setupListenerHostPort(String listen, int port)
+ throws IOException {
+
+ SocketConnector connector = new SocketConnector();
+ connector.setPort(port);
+ connector.setHost(listen);
+ this.addConnector(connector);
+ }
+ }
+}
Modified: hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/HadoopShims.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/HadoopShims.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/HadoopShims.java (original)
+++ hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/HadoopShims.java Mon Oct 11 23:41:24 2010
@@ -34,6 +34,11 @@ import org.apache.hadoop.mapred.RecordRe
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.RunningJob;
import org.apache.hadoop.mapred.TaskCompletionEvent;
+import org.apache.hadoop.security.UserGroupInformation;
+import javax.security.auth.login.LoginException;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
/**
* In order to be compatible with multiple versions of Hadoop, all parts
@@ -45,6 +50,8 @@ import org.apache.hadoop.mapred.TaskComp
*/
public interface HadoopShims {
+ static final Log LOG = LogFactory.getLog(HadoopShims.class);
+
/**
* Return true if the current version of Hadoop uses the JobShell for
* command line interpretation.
@@ -144,6 +151,14 @@ public interface HadoopShims {
void setNullOutputFormat(JobConf conf);
/**
+ * Get the UGI that the given job configuration will run as.
+ *
+ * In secure versions of Hadoop, this simply returns the current
+ * access control context's user, ignoring the configuration.
+ */
+ public UserGroupInformation getUGIForConf(Configuration conf) throws LoginException, IOException;
+
+ /**
* InputSplitShim.
*
*/
Modified: hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/ShimLoader.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/ShimLoader.java?rev=1021549&r1=1021548&r2=1021549&view=diff
==============================================================================
--- hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/ShimLoader.java (original)
+++ hadoop/hive/trunk/shims/src/common/java/org/apache/hadoop/hive/shims/ShimLoader.java Mon Oct 11 23:41:24 2010
@@ -41,6 +41,7 @@ public abstract class ShimLoader {
HADOOP_SHIM_CLASSES.put("0.18", "org.apache.hadoop.hive.shims.Hadoop18Shims");
HADOOP_SHIM_CLASSES.put("0.19", "org.apache.hadoop.hive.shims.Hadoop19Shims");
HADOOP_SHIM_CLASSES.put("0.20", "org.apache.hadoop.hive.shims.Hadoop20Shims");
+ HADOOP_SHIM_CLASSES.put("0.20S", "org.apache.hadoop.hive.shims.Hadoop20SShims");
}
/**
@@ -55,6 +56,7 @@ public abstract class ShimLoader {
JETTY_SHIM_CLASSES.put("0.18", "org.apache.hadoop.hive.shims.Jetty18Shims");
JETTY_SHIM_CLASSES.put("0.19", "org.apache.hadoop.hive.shims.Jetty19Shims");
JETTY_SHIM_CLASSES.put("0.20", "org.apache.hadoop.hive.shims.Jetty20Shims");
+ JETTY_SHIM_CLASSES.put("0.20S", "org.apache.hadoop.hive.shims.Jetty20SShims");
}
/**
@@ -105,7 +107,16 @@ public abstract class ShimLoader {
throw new RuntimeException("Illegal Hadoop Version: " + vers +
" (expected A.B.* format)");
}
- return parts[0] + "." + parts[1];
+ String majorVersion = parts[0] + "." + parts[1];
+
+ // If we are running a security release, we won't have UnixUserGroupInformation
+ // (removed by HADOOP-6299 when switching to JAAS for Login)
+ try {
+ Class.forName("org.apache.hadoop.security.UnixUserGroupInformation");
+ } catch (ClassNotFoundException cnf) {
+ majorVersion += "S";
+ }
+ return majorVersion;
}
private ShimLoader() {