elasticsearch-hadoop是一个深度集成Hadoop和ElasticSearch的项目，也是ES官方来维护的一个子项目，通过实现Hadoop和ES之间的输入输出，可以在Hadoop里面对ES集群的数据进行读取和写入，充分发挥Map-Reduce并行处理的优势，为Hadoop数据带来实时搜索的可能。
项目网址：http://www.elasticsearch.org/overview/hadoop/
运行环境：
CDH4、ElasticSearch0.90.2
http://www.cloudera.com/content/cloudera-content/cloudera-docs/CDH4/latest/CDH4-Quick-Start/cdh4qs_topic_3_3.html
https://github.com/medcl/elasticsearch-rtf
Hive和ES的互操作：
#安装，HIVE里面添加ElasticSearch-Hadoop的JAR路径
#下载hadoop-es jar包,https://download.elasticsearch.org/hadoop/hadoop-latest.zip
#Hive加载的JAR路径为本地路径
[medcl@node- ~]$ ls
elasticsearch-hadoop-1.3..M1.jar
[medcl@node- ~]$ pwd
/home/medcl
[medcl@node- ~]$ hive -hiveconf hive.aux.jars.path=/home/medcl/elasticsearch-hadoop-1.3..M1.jar
Logging initialized using configuration in file:/etc/hive/conf.dist/hive-log4j.properties
Hive history file=/tmp/medcl/hive_job_log_94db3616-e210-4aab-b07b-6fb159e217ec_1758848920.txt
#ElasticSearch集群名为"elasticsearch",和Hadoop在一个机器上
#Hive里面创建一个Table(user)，并使用Hadoop-ElasticSearch关联一个索引（/index/user）,2个字段，id和name
CREATE EXTERNAL TABLE user (id INT, name STRING,site STRING)
STORED BY 'org.elasticsearch.hadoop.hive.ESStorageHandler'
TBLPROPERTIES('es.resource' = 'index/user/',
'es.index.auto.create' = 'true')
在medcl用下操作：
CREATE EXTERNAL TABLE user (id INT, name STRING)
STORED BY 'org.elasticsearch.hadoop.hive.ESStorageHandler'
TBLPROPERTIES('es.resource' = '/index/user/',
'es.index.auto.create' = 'true');
FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask
hive> CREATE EXTERNAL TABLE user (id INT, name STRING)
> STORED BY 'org.elasticsearch.hadoop.hive.ESStorageHandler'
> TBLPROPERTIES('es.resource' = 'medcl/',
> 'es.index.auto.create' = 'false');
FAILED: Error in metadata: MetaException(message:Got exception: org.apache.hadoop.security.AccessControlException Permission denied: user=medcl, access=WRITE, inode="/user":hdfs:supergroup:drwxr-xr-x
#擦，看下权限
[medcl@node- ~]$ hadoop fs -lsr /
lsr: DEPRECATED: Please use 'ls -R' instead.
drwxrwxrwt - hdfs supergroup -- : /tmp
drwxr-xr-x - hdfs supergroup -- : /user
drwxr-xr-x - medcl supergroup -- : /user/medcl
drwxr-xr-x - medcl supergroup -- : /user/medcl/input
-rw-r--r-- medcl supergroup -- : /user/medcl/input/file1.txt
drwxr-xr-x - medcl supergroup -- : /user/medcl/lib
-rw-r--r-- medcl supergroup -- : /user/medcl/lib/elasticsearch-hadoop-1.3..M1.jar
drwxr-xr-x - hdfs supergroup -- : /var
drwxr-xr-x - hdfs supergroup -- : /var/lib
#原来user目录权限是hdfs，ok，切换hdfs，jar也换个hdfs用户可以访问到的位置，就/tmp吧
[root@node- medcl]# cp elasticsearch-hadoop-1.3..M1.jar /tmp/
[root@node- medcl]# ^C
[root@node- medcl]# sudo -u hdfs hive -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar
Logging initialized using configuration in file:/etc/hive/conf.dist/hive-log4j.properties
Hive history file=/tmp/hdfs/hive_job_log_bdad4d7a-f929-43d7-a56e-e026fdd7e3b4_1219802521.txt
hive> CREATE EXTERNAL TABLE user (id INT, name STRING)
> STORED BY 'org.elasticsearch.hadoop.hive.ESStorageHandler'
> TBLPROPERTIES('es.resource' = '/index/user/',
> 'es.index.auto.create' = 'false');
-- ::29.560 GMT Thread[main,,main] java.io.FileNotFoundException: derby.log (Permission denied)
----------------------------------------------------------------
-- ::29.877 GMT:
Booting Derby version The Apache Software Foundation - Apache Derby - 10.4.2.0 - (): instance a816c00e--fc62-4b5c-000000cec758
on database directory /var/lib/hive/metastore/metastore_db in READ ONLY mode Database Class Loader started - derby.database.classpath=''
FAILED: Error in metadata: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.metastore.HiveMetaStoreClient
FAILED: Execution Error, return code from org.apache.hadoop.hive.ql.exec.DDLTask #ok，干掉lock
[root@node- ~]# ls /var/lib/hive/metastore/metastore_db
dbex.lck db.lck log seg0 service.properties tmp
[root@node- ~]# rm /var/lib/hive/metastore/metastore_db/dbex.lck
rm: remove regular file `/var/lib/hive/metastore/metastore_db/dbex.lck'? y
[root@node- ~]# rm /var/lib/hive/metastore/metastore_db/db.lck
rm: remove regular file `/var/lib/hive/metastore/metastore_db/db.lck'? y
#另外忘记关另外一个hive实例了，难怪呢。
[root@node- tmp]# ps -aux|grep hive
Warning: bad syntax, perhaps a bogus '-'? See /usr/share/doc/procps-3.2./FAQ
root 0.0 0.1 pts/ S+ : : sudo -u hdfs hive -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar
hdfs 1.8 5.7 pts/ Sl+ : : /usr/lib/jvm/java-openjdk/bin/java -Xmx256m -Dhadoop.log.dir=/usr/lib/hadoop/logs -Dhadoop.log.file=hadoop.log -Dhadoop.home.dir=/usr/lib/hadoop -Dhadoop.id.str= -Dhadoop.root.logger=INFO,console -Djava.library.path=/usr/lib/hadoop/lib/native -Dhadoop.policy.file=hadoop-policy.xml -Djava.net.preferIPv4Stack=true -Dhadoop.security.logger=INFO,NullAppender org.apache.hadoop.util.RunJar /usr/lib/hive/lib/hive-cli-0.10.-cdh4.5.0.jar org.apache.hadoop.hive.cli.CliDriver -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar
#权限问题
[root@node- tmp]# ll /var/lib/hive/metastore/metastore_db/
total
drwxrwxr-x medcl medcl Dec : log
drwxrwxr-x medcl medcl Dec : seg0
-rw-rw-r-- medcl medcl Dec : service.properties
drwxrwxr-x medcl medcl Dec : tmp
[root@node- tmp]# sudo -u hdfs hive -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar^C
[root@node- tmp]# chmod /var/lib/hive/metastore/metastore_db/ -R
[root@node- tmp]# sudo -u hdfs hive -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar
Logging initialized using configuration in file:/etc/hive/conf.dist/hive-log4j.properties
Hive history file=/tmp/hdfs/hive_job_log_d5749cb0-fde0-4da2--c85cf4673885_252074310.txt
hive> show tables;
OK
Time taken: 6.934 seconds
hive> CREATE EXTERNAL TABLE user (id INT, name STRING)
> STORED BY 'org.elasticsearch.hadoop.hive.ESStorageHandler'
> TBLPROPERTIES('es.resource' = '/index/user/',
> 'es.index.auto.create' = 'true');
OK
Time taken: 1.115 seconds #ok，创建成功了
hive> show tables;
OK
user
Time taken: 0.15 seconds
hive> #权限问题是Hive默认仓库路径造成的，生疏了
[root@node- tmp]# sudo su hdfs
bash-4.1$ hadoop fs -lsr /
lsr: DEPRECATED: Please use 'ls -R' instead.
drwxrwxrwt - hdfs supergroup -- : /tmp
drwxr-xr-x - hdfs supergroup -- : /user
drwxr-xr-x - hdfs supergroup -- : /user/hive
drwxr-xr-x - hdfs supergroup -- : /user/hive/warehouse
drwxr-xr-x - hdfs supergroup -- : /user/hive/warehouse/user #好了，开始往HIVE里面倒数据了，先来几行数据
[root@node- tmp]# cat files1.txt
,medcl
,lcdem
,tom
,jack #传上去
[root@node- tmp]# sudo su hdfs
bash-4.1$ hadoop fs -put files1.txt /tmp/
bash-4.1$ hadoop fs -ls /tmp/
Found items
-rw-r--r-- hdfs supergroup -- : /tmp/files1.txt #加载到Hive里面
hive -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar
#LOAD DATA LOCAL INPATH '/tmp/files1.txt' OVERWRITE INTO TABLE user_source;
#CREATE EXTERNAL TABLE user_source (id INT, name STRING); #不是原始Hive表，还不能直接LOAD
bash-4.1$ hive -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar
Logging initialized using configuration in file:/etc/hive/conf.dist/hive-log4j.properties
Hive history file=/tmp/hdfs/hive_job_log_a9516f87-6e2d-44db-9d38-18eed77d9dec_1583221137.txt
hive> LOAD DATA LOCAL INPATH '/tmp/files1.txt' OVERWRITE INTO TABLE user;
FAILED: SemanticException [Error ]: A non-native table cannot be used as target for LOAD
hive> CREATE EXTERNAL TABLE user_source (id INT, name STRING);
OK
Time taken: 1.104 seconds
hive> LOAD DATA LOCAL INPATH '/tmp/files1.txt' OVERWRITE INTO TABLE user_source;
Copying data from file:/tmp/files1.txt
Copying file: file:/tmp/files1.txt
Loading data to table default.user_source
Table default.user_source stats: [num_partitions: , num_files: , num_rows: , total_size: , raw_data_size: ]
OK
Time taken: 0.911 seconds
hive> show tables;
OK
user
user_source
Time taken: 0.226 seconds #下面这个错误是因为es-hadoop的jar文件没有传到HDFS上面，看来本地和HDFS都要上传，并且路径要一致
hive> select id,name from user_source;
Total MapReduce jobs =
Launching Job out of
Number of reduce tasks is set to since there's no reduce operator
java.io.FileNotFoundException: File does not exist: /tmp/elasticsearch-hadoop-1.3..M1.jar
at org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:)
at org.apache.hadoop.filecache.DistributedCache.getFileStatus(DistributedCache.java:)
at org.apache.hadoop.filecache.TrackerDistributedCacheManager.determineTimestamps(TrackerDistributedCacheManager.java:)
at org.apache.hadoop.filecache.TrackerDistributedCacheManager.determineTimestampsAndCacheVisibilities(TrackerDistributedCacheManager.java:)
at org.apache.hadoop.mapred.JobClient.copyAndConfigureFiles(JobClient.java:)
at org.apache.hadoop.mapred.JobClient.copyAndConfigureFiles(JobClient.java:)
at org.apache.hadoop.mapred.JobClient.access$(JobClient.java:)
at org.apache.hadoop.mapred.JobClient$.run(JobClient.java:)
at org.apache.hadoop.mapred.JobClient$.run(JobClient.java:)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:)
at org.apache.hadoop.mapred.JobClient.submitJobInternal(JobClient.java:)
at org.apache.hadoop.mapred.JobClient.submitJob(JobClient.java:)
at org.apache.hadoop.hive.ql.exec.ExecDriver.execute(ExecDriver.java:)
at org.apache.hadoop.hive.ql.exec.MapRedTask.execute(MapRedTask.java:)
at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:)
at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:)
at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:)
at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:)
at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:)
at java.lang.reflect.Method.invoke(Method.java:)
at org.apache.hadoop.util.RunJar.main(RunJar.java:)
Job Submission failed with exception 'java.io.FileNotFoundException(File does not exist: /tmp/elasticsearch-hadoop-1.3.0.M1.jar)'
FAILED: Execution Error, return code from org.apache.hadoop.hive.ql.exec.MapRedTask #ok，再看看
bash-4.1$ hadoop fs -put elasticsearch-hadoop-1.3..M1.jar /tmp/
bash-4.1$ hive -hiveconf hive.aux.jars.path=/tmp/elasticsearch-hadoop-1.3..M1.jar
Logging initialized using configuration in file:/etc/hive/conf.dist/hive-log4j.properties
Hive history file=/tmp/hdfs/hive_job_log_28ea1fbc-dc3b-4e62-9f47-1a88eed30069_1310993479.txt
hive> select id,name from user_source;
Total MapReduce jobs =
Launching Job out of
Number of reduce tasks is set to since there's no reduce operator
Starting Job = job_201312162220_0004, Tracking URL = http://localhost:50030/jobdetails.jsp?jobid=job_201312162220_0004
Kill Command = /usr/lib/hadoop/bin/hadoop job -kill job_201312162220_0004
Hadoop job information for Stage-: number of mappers: ; number of reducers:
-- ::, Stage- map = %, reduce = %
-- ::, Stage- map = %, reduce = %, Cumulative CPU 0.88 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 0.88 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 0.88 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 0.88 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 0.88 sec
MapReduce Total cumulative CPU time: msec
Ended Job = job_201312162220_0004
MapReduce Jobs Launched:
Job : Map: Cumulative CPU: 0.88 sec HDFS Read: HDFS Write: SUCCESS
Total MapReduce CPU Time Spent: msec
OK
NULL NULL
NULL NULL
NULL NULL
NULL NULL
Time taken: 25.999 seconds #慢，数据怎么是空的，建成外表了(EXTERNAL)，没有设置默认的分隔符,好纠结
hive> drop table user_source;
OK
Time taken: 0.649 seconds
hive> CREATE TABLE user_source (id INT, name STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';
OK
Time taken: 0.109 seconds
hive> LOAD DATA LOCAL INPATH '/tmp/files1.txt' INTO TABLE user_source;
Copying data from file:/tmp/files1.txt
Copying file: file:/tmp/files1.txt
Loading data to table default.user_source
Table default.user_source stats: [num_partitions: , num_files: , num_rows: , total_size: , raw_data_size: ]
OK
Time taken: 0.348 seconds
hive> select * from user_source;
OK
medcl
lcdem
tom
jack
Time taken: 0.155 seconds #源表现在有了，导入到ES所在的表里面去 hive> INSERT OVERWRITE TABLE user
> SELECT s.id, s.name FROM user_source s;
Total MapReduce jobs =
Launching Job out of
Number of reduce tasks is set to since there's no reduce operator
Starting Job = job_201312162220_0005, Tracking URL = http://localhost:50030/jobdetails.jsp?jobid=job_201312162220_0005
Kill Command = /usr/lib/hadoop/bin/hadoop job -kill job_201312162220_0005
Hadoop job information for Stage-: number of mappers: ; number of reducers:
-- ::, Stage- map = %, reduce = %
-- ::, Stage- map = %, reduce = %, Cumulative CPU 1.16 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 1.16 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 1.16 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 1.16 sec
-- ::, Stage- map = %, reduce = %, Cumulative CPU 1.16 sec
MapReduce Total cumulative CPU time: seconds msec
Ended Job = job_201312162220_0005
Rows loaded to user
MapReduce Jobs Launched:
Job : Map: Cumulative CPU: 1.16 sec HDFS Read: HDFS Write: SUCCESS
Total MapReduce CPU Time Spent: seconds msec
OK
Time taken: 21.849 seconds
hive> select * from user;
OK
Failed with exception java.io.IOException:java.lang.IllegalStateException: [GET] on [/index/user/&search_type=scan&scroll=10m&size=&preference=_shards:;_only_node:MP7Zl3owTRm8O2V6cWvOSg] failed; server[http://10.0.2.15:9200] returned [{"_index":"index","_type":"user","_id":"&search_type=scan&scroll=10m&size=50&preference=_shards:4;_only_node:MP7Zl3owTRm8O2V6cWvOSg","exists":false}]
Time taken: 0.387 seconds #可以看出来hadoop-elasticsearch翻译出来的查询语句好像有问题！不过elasticsearch里面已经有数据了，反正暂时不需要用hive来执行查询，先官方发个issue吧。 #ES查询结果
bash-4.1$ curl localhost:/index/user/_search?q=*&pretty=true
[]
bash-4.1$ {"took":,"timed_out":false,"_shards":{"total":,"successful":,"failed":},"hits":{"total":,"max_score":1.0,"hits":[{"_index":"index","_type":"user","_id":"3x4bEcriRvS6AHkX2Sb7UA","_score":1.0, "_source" : {"id":,"name":"lcdem"}},{"_index":"index","_type":"user","_id":"_3rGVWhaTSCixYxRzBUSLQ","_score":1.0, "_source" : {"id":,"name":"jack"}},{"_index":"index","_type":"user","_id":"T-Q_icjgR8ehsH3IV-twWw","_score":1.0, "_source" : {"id":,"name":"medcl"}},{"_index":"index","_type":"user","_id":"Vdz0sryBT5u0e9hfoMY8Tg","_score":1.0, "_source" : {"id":,"name":"tom"}}]}}
#接下来试试大量数据bulk导入的性能，是不是真的做到data locality。
elasticsearch-hadoop下载地址：https://github.com/elastic/elasticsearch-hadoop