连接Oracle与Hadoop(1) 使用OLH加载HDFS文件到Oracle
OLH是Oracle Loader for Hadoop的缩写，Oracle的大数据连接器（BDC）的一个组件，可将多种数据格式从HDFS上加载到Oracle数据库库中。
本文在同一台服务器上模拟oracle数据库与hadoop集群，实验目标：使用OLH从Hadoop端的HDFS加载数据到Oracle表中。
Oracle端：
| 服务器 |
系统用户 |
安装软件 |
软件安装路径 |
| Server1 |
oracle |
Oracle Database 12.1.0.2 |
/u01/app/oracle/product/12.1.0/dbhome_1 |
Hadoop集群端：
| 服务器 |
系统用户 |
安装软件 |
软件安装路径 |
| Server1 |
hadoop |
Hadoop 2.6.2 |
/home/hadoop/hadoop-2.6.2 |
| Hive 1.1.1 |
/home/hadoop/hive-1.1.1 |
||
| Hbase 1.1.2 |
/home/hadoop/hbase-1.1.2 |
||
| jdk1.8.0_65 |
/home/hadoop/jdk1.8.0_65 |
||
| OLH 3.5.0 |
/home/hadoop/oraloader-3.5.0-h2 |
- 部署Hadoop/Hive/Hbase/OLH软件
将Hadoop/Hive/Hbase/OLH软件解压到相应目录
-
[hadoop@server1 ~]$ tree -L 1
-
├── hadoop-2.6.2
-
├── hbase-1.1.2
-
├── hive-1.1.1
-
├── jdk1.8.0_65
-
├── oraloader-3.5.0-h2
- 配置Hadoop/Hive/Hbase/OLH环境变量
-
export JAVA_HOME=/home/hadoop/jdk1.8.0_65
-
-
export HADOOP_USER_NAME=hadoop
-
export HADOOP_YARN_USER=hadoop
-
export HADOOP_HOME=/home/hadoop/hadoop-2.6.2
-
export HADOOP_CONF_DIR=${HADOOP_HOME}/etc/hadoop
-
export HADOOP_LOG_DIR=${HADOOP_HOME}/logs
-
export HADOOP_LIBEXEC_DIR=${HADOOP_HOME}/libexec
-
export HADOOP_COMMON_HOME=${HADOOP_HOME}
-
export HADOOP_HDFS_HOME=${HADOOP_HOME}
-
export HADOOP_MAPRED_HOME=${HADOOP_HOME}
-
export HADOOP_YARN_HOME=${HADOOP_HOME}
-
export HDFS_CONF_DIR=${HADOOP_HOME}/etc/hadoop
-
export YARN_CONF_DIR=${HADOOP_HOME}/etc/hadoop
-
-
export HIVE_HOME=/home/hadoop/hive-1.1.1
-
export HIVE_CONF_DIR=${HIVE_HOME}/conf
-
-
export HBASE_HOME=/home/hadoop/hbase-1.1.2
-
export HBASE_CONF_DIR=/home/hadoop/hbase-1.1.2/conf
-
-
export OLH_HOME=/home/hadoop/oraloader-3.5.0-h2
-
-
export HADOOP_CLASSPATH=/usr/share/java/mysql-connector-java.jar
-
export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$HIVE_HOME/lib/*:$HIVE_CONF_DIR:$HBASE_HOME/lib/*:$HBASE_CONF_DIR
-
export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$OLH_HOME/jlib/*
-
-
export PATH=$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HIVE_HOME/bin:$HBASE_HOME/bin:$PATH
- 配置Hadoop/Hive/Hbase软件
core-site.xml
-
<configuration>
-
<property>
-
<name>fs.defaultFS</name>
-
<value>hdfs://server1:8020</value>
-
</property>
-
<property>
-
<name>fs.checkpoint.period</name>
-
<value>3600</value>
-
</property>
-
<property>
-
<name>fs.checkpoint.size</name>
-
<value>67108864</value>
-
</property>
-
<property>
-
<name>hadoop.proxyuser.hadoop.groups</name>
-
<value>*</value>
-
</property>
-
<property>
-
<name>hadoop.proxyuser.hadoop.hosts</name>
-
<value>*</value>
-
</property>
-
</configuration>
hdfs-site.xml
-
<configuration>
-
<property>
-
<name>hadoop.tmp.dir</name>
-
<value>file:///home/hadoop</value>
-
</property>
-
<property>
-
<name>dfs.namenode.name.dir</name>
-
<value>file:///home/hadoop/dfs/nn</value>
-
</property>
-
<property>
-
<name>dfs.datanode.data.dir</name>
-
<value>file:///home/hadoop/dfs/dn</value>
-
</property>
-
<property>
-
<name>dfs.namenode.checkpoint.dir</name>
-
<value>file:///home/hadoop/dfs/sn</value>
-
</property>
-
<property>
-
<name>dfs.replication</name>
-
<value>1</value>
-
</property>
-
<property>
-
<name>dfs.permissions.superusergroup</name>
-
<value>supergroup</value>
-
</property>
-
<property>
-
<name>dfs.namenode.http-address</name>
-
<value>server1:50070</value>
-
</property>
-
<property>
-
<name>dfs.namenode.secondary.http-address</name>
-
<value>server1:50090</value>
-
</property>
-
<property>
-
<name>dfs.webhdfs.enabled</name>
-
<value>true</value>
-
</property>
-
</configuration>
yarn-site.xml
-
<configuration>
-
<property>
-
<name>yarn.resourcemanager.scheduler.address</name>
-
<value>server1:8030</value>
-
</property>
-
<property>
-
<name>yarn.resourcemanager.resource-tracker.address</name>
-
<value>server1:8031</value>
-
</property>
-
<property>
-
<name>yarn.resourcemanager.address</name>
-
<value>server1:8032</value>
-
</property>
-
<property>
-
<name>yarn.resourcemanager.admin.address</name>
-
<value>server1:8033</value>
-
</property>
-
<property>
-
<name>yarn.resourcemanager.webapp.address</name>
-
<value>server1:8088</value>
-
</property>
-
<property>
-
<name>yarn.nodemanager.local-dirs</name>
-
<value>file:///home/hadoop/yarn/local</value>
-
</property>
-
<property>
-
<name>yarn.nodemanager.log-dirs</name>
-
<value>file:///home/hadoop/yarn/logs</value>
-
</property>
-
<property>
-
<name>yarn.log-aggregation-enable</name>
-
<value>true</value>
-
</property>
-
<property>
-
<name>yarn.nodemanager.remote-app-log-dir</name>
-
<value>/yarn/apps</value>
-
</property>
-
<property>
-
<name>yarn.app.mapreduce.am.staging-dir</name>
-
<value>/user</value>
-
</property>
-
<property>
-
<name>yarn.nodemanager.aux-services</name>
-
<value>mapreduce_shuffle</value>
-
</property>
-
<property>
-
<name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
-
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
-
</property>
-
<property>
-
<name>yarn.log.server.url</name>
-
<value>http://server1:19888/jobhistory/logs/</value>
-
</property>
-
</configuration>
- 设置OraLoader配置文件
-
<?xml version="1.0" encoding="UTF-8" ?>
-
<configuration>
-
<!-- Input settings -->
-
<property>
-
<name>mapreduce.inputformat.class</name>
-
<value>oracle.hadoop.loader.lib.input.DelimitedTextInputFormat</value>
-
</property>
-
<property>
-
<name>mapred.input.dir</name>
-
<value>/catalog</value>
-
</property>
-
<property>
-
<name>oracle.hadoop.loader.input.fieldTerminator</name>
-
<value>\u002C</value>
-
</property>
-
<property>
-
<name>oracle.hadoop.loader.input.fieldNames</name>
-
<value>CATALOGID,JOURNAL,PUBLISHER,EDITION,TITLE,AUTHOR</value>
-
</property>
-
-
<!-- Output settings -->
-
<property>
-
<name>mapreduce.job.outputformat.class</name>
-
<value>oracle.hadoop.loader.lib.output.JDBCOutputFormat</value>
-
</property>
-
<property>
-
<name>mapreduce.output.fileoutputformat.outputdir</name>
-
<value>oraloadout</value>
-
</property>
-
-
<!-- Table information -->
-
<property>
-
<name>oracle.hadoop.loader.loaderMap.targetTable</name>
-
<value>catalog</value>
-
</property>
-
-
<!-- Connection information -->
-
<property>
-
<name>oracle.hadoop.loader.connection.url</name>
-
<value>jdbc:oracle:thin:@${HOST}:${TCPPORT}/${SERVICE_NAME}</value>
-
</property>
-
<property>
-
<name>TCPPORT</name>
-
<value>1521</value>
-
</property>
-
<property>
-
<name>HOST</name>
-
<value>192.168.56.101</value>
-
</property>
-
<property>
-
<name>SERVICE_NAME</name>
-
<value>orcl</value>
-
</property>
-
<property>
-
<name>oracle.hadoop.loader.connection.user</name>
-
<value>baron</value>
-
</property>
-
<property>
-
<name>oracle.hadoop.loader.connection.password</name>
-
<value>baron</value>
-
</property>
- 生成测试数据
-
$cat catalog.txt
-
1,Oracle Magazine,Oracle Publishing,Nov-Dec 2004,Database Resource Manager,Kimberly Floss
-
2,Oracle Magazine,Oracle Publishing,Nov-Dec 2004,From ADF UIX to JSF,Jonas Jacobi
-
3,Oracle Magazine,Oracle Publishing,March-April 2005,Starting with Oracle ADF,Steve Muench
-
-
$ hdfs dfs -mkdir /catalog
-
$ hdfs dfs -put catalog.txt /catalog/catalog.txt
- 使用OraLoader加载HDFS文件到Oracle数据库
-
hadoop jar $OLH_HOME/jlib/oraloader.jar oracle.hadoop.loader.OraLoader -conf OraLoadJobConf.xml -libjars $OLH_HOME/jlib/oraloader.jar
输出结果如下：
-
Oracle Loader for Hadoop Release 3.4.0 - Production
-
Copyright (c) 2011, 2015, Oracle and/or its affiliates. All rights reserved.
-
15/12/07 08:35:52 INFO loader.OraLoader: Oracle Loader for Hadoop Release 3.4.0 - Production
-
Copyright (c) 2011, 2015, Oracle and/or its affiliates. All rights reserved.
-
15/12/07 08:35:52 INFO loader.OraLoader: Built-Against: hadoop-2.2.0 hive-0.13.0 avro-1.7.3 jackson-1.8.8
-
15/12/07 08:35:52 INFO Configuration.deprecation: mapreduce.outputformat.class is deprecated. Instead, use mapreduce.job.outputformat.class
-
15/12/07 08:35:52 INFO Configuration.deprecation: mapred.output.dir is deprecated. Instead, use mapreduce.output.fileoutputformat.outputdir
-
15/12/07 08:36:27 INFO Configuration.deprecation: mapred.submit.replication is deprecated. Instead, use mapreduce.client.submit.file.replication
-
15/12/07 08:36:29 INFO loader.OraLoader: oracle.hadoop.loader.loadByPartition is disabled because table: CATALOG is not partitioned
-
15/12/07 08:36:29 INFO output.DBOutputFormat: Setting reduce tasks speculative execution to false for : oracle.hadoop.loader.lib.output.JDBCOutputFormat
-
15/12/07 08:36:29 INFO Configuration.deprecation: mapred.reduce.tasks.speculative.execution is deprecated. Instead, use mapreduce.reduce.speculative
-
15/12/07 08:36:32 WARN loader.OraLoader: Sampler is disabled because the number of reduce tasks is less than two. Job will continue without sampled information.
-
15/12/07 08:36:32 INFO loader.OraLoader: Submitting OraLoader job OraLoader
-
15/12/07 08:36:32 INFO client.RMProxy: Connecting to ResourceManager at server1/192.168.56.101:8032
-
15/12/07 08:36:34 INFO input.FileInputFormat: Total input paths to process : 1
-
15/12/07 08:36:34 INFO mapreduce.JobSubmitter: number of splits:1
-
15/12/07 08:36:35 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1449494864827_0001
-
15/12/07 08:36:36 INFO impl.YarnClientImpl: Submitted application application_1449494864827_0001
-
15/12/07 08:36:37 INFO mapreduce.Job: The url to track the job: http://server1:8088/proxy/application_1449494864827_0001/
-
15/12/07 08:37:05 INFO loader.OraLoader: map 0% reduce 0%
-
15/12/07 08:37:22 INFO loader.OraLoader: map 100% reduce 0%
-
15/12/07 08:37:36 INFO loader.OraLoader: map 100% reduce 67%
-
15/12/07 08:38:05 INFO loader.OraLoader: map 100% reduce 100%
-
15/12/07 08:38:06 INFO loader.OraLoader: Job complete: OraLoader (job_1449494864827_0001)
-
15/12/07 08:38:06 INFO loader.OraLoader: Counters: 49
-
File System Counters
-
FILE: Number of bytes read=395
-
FILE: Number of bytes written=244157
-
FILE: Number of read operations=0
-
FILE: Number of large read operations=0
-
FILE: Number of write operations=0
-
HDFS: Number of bytes read=367
-
HDFS: Number of bytes written=1861
-
HDFS: Number of read operations=7
-
HDFS: Number of large read operations=0
-
HDFS: Number of write operations=5
-
Job Counters
-
Launched map tasks=1
-
Launched reduce tasks=1
-
Data-local map tasks=1
-
Total time spent by all maps in occupied slots (ms)=12516
-
Total time spent by all reduces in occupied slots (ms)=40696
-
Total time spent by all map tasks (ms)=12516
-
Total time spent by all reduce tasks (ms)=40696
-
Total vcore-seconds taken by all map tasks=12516
-
Total vcore-seconds taken by all reduce tasks=40696
-
Total megabyte-seconds taken by all map tasks=12816384
-
Total megabyte-seconds taken by all reduce tasks=41672704
-
Map-Reduce Framework
-
Map input records=3
-
Map output records=3
-
Map output bytes=383
-
Map output materialized bytes=395
-
Input split bytes=104
-
Combine input records=0
-
Combine output records=0
-
Reduce input groups=1
-
Reduce shuffle bytes=395
-
Reduce input records=3
-
Reduce output records=3
-
Spilled Records=6
-
Shuffled Maps =1
-
Failed Shuffles=0
-
Merged Map outputs=1
-
GC time elapsed (ms)=556
-
CPU time spent (ms)=9450
-
Physical memory (bytes) snapshot=444141568
-
Virtual memory (bytes) snapshot=4221542400
-
Total committed heap usage (bytes)=331350016
-
Shuffle Errors
-
BAD_ID=0
-
CONNECTION=0
-
IO_ERROR=0
-
WRONG_LENGTH=0
-
WRONG_MAP=0
-
WRONG_REDUCE=0
-
File Input Format Counters
-
Bytes Read=263
-
File Output Format Counters
-
Bytes Written=1620
- 在Oracle中验证加载结果
-
select * fromcatalog;
CATALOGID JOURNAL PUBLISHER EDITION TITLE AUTHOR
---------- ------------------------- ------------------------- ------------------------- ------------------------------ ---------------------
1 Oracle Magazine Oracle Publishing Nov-Dec 2004 Database Resource Manager Kimberly Floss
2 Oracle Magazine Oracle Publishing Nov-Dec 2004 From ADF UIX to JSF Jonas Jacobi
3 Oracle Magazine Oracle Publishing March-April 2005 Starting with Oracle ADF Steve Muenc