[大数据]Apache Atlas 安装

安装Solr(单节点)

1. 下载地址：https://solr.apache.org/downloads.html

2. 解压后直接启动

   bin/solr start -c -z <zookeeper_host:port>  -p 8983
   

kafka安装

kafka安装连接

安装Maven并配置MAVEN_HOME

（配置maven镜像）

下载Atlas源码文件并编译(独立Hbase、Solr)

1. http://atlas.apache.org/#/Downloads

2. 解压

   tar -zxvf apache-atlas-2.1.0-sources.tar.gz
   

3. 进入Atlas文件夹编译

   # 配置maven jvm
   export MAVEN_OPTS="-Xms2g -Xmx2g"
   # 编译
   mvn clean -DskipTests install
   # 打包
   mvn clean -DskipTests package -Pdist
   

   

4. 将Atlas文件夹cp至自定义文件夹下

   cp -r apache-atlas-sources-2.1.0/distro/target/apache-atlas-2.1.0-bin /usr/local/service/
   

配置Atlas

1. 配置atlas-env

   # 修改为false
   export MANAGE_EMBEDDED_CASSANDRA=false
   
   # 修改为false
   # indicates whether or not a local instance of Elasticsearch should be started for Atlas
   export MANAGE_LOCAL_ELASTICSEARCH=false
   
   # 添加hbase配置目录
   export HBASE_CONF_DIR=/usr/local/service/hbase/conf
   

2. 修改atlas-application.properties

   atlas.graph.storage.backend=hbase
   atlas.graph.storage.hbase.table=atlas
   
   atlas.graph.storage.hostname=namenode:2181
   atlas.graph.storage.hbase.regions-per-server=1
   atlas.graph.storage.lock.wait-time=10000
   
   #Solr
   #Solr cloud mode properties
   atlas.graph.index.search.solr.mode=cloud
   atlas.graph.index.search.solr.zookeeper-url=namenode:2181
   atlas.graph.index.search.solr.zookeeper-connect-timeout=60000
   atlas.graph.index.search.solr.zookeeper-session-timeout=60000
   atlas.graph.index.search.solr.wait-searcher=true
   
   #########  Notification Configs  #########
   atlas.notification.embedded=false
   atlas.kafka.data=${sys:atlas.home}/data/kafka
   atlas.kafka.zookeeper.connect=namenode:2181
   atlas.kafka.bootstrap.servers=namenode:9092
   atlas.kafka.zookeeper.session.timeout.ms=400
   atlas.kafka.zookeeper.connection.timeout.ms=200
   atlas.kafka.zookeeper.sync.time.ms=20
   atlas.kafka.auto.commit.interval.ms=1000
   atlas.kafka.hook.group.id=atlas
   
   atlas.kafka.enable.auto.commit=false
   atlas.kafka.auto.offset.reset=earliest
   atlas.kafka.session.timeout.ms=30000
   atlas.kafka.offsets.topic.replication.factor=1
   atlas.kafka.poll.timeout.ms=1000
   
   atlas.notification.create.topics=true
   atlas.notification.replicas=1
   atlas.notification.topics=ATLAS_HOOK,ATLAS_ENTITIES
   atlas.notification.log.failed.messages=true
   atlas.notification.consumer.retry.interval=500
   atlas.notification.hook.retry.interval=1000
   
   #########  Entity Audit Configs  #########
   atlas.audit.hbase.tablename=apache_atlas_entity_audit
   atlas.audit.zookeeper.session.timeout.ms=5000
   atlas.audit.hbase.zookeeper.quorum=namenode:2181
   

3. 启动

   bin/atlas_start.py
   

配置Hive Hook

1. 修改hive-env

   export HIVE_AUX_JARS_PATH=/usr/local/service/apache-atlas-2.1.0/hook/hive
   

2. 修改hive-site.xml

   <property>
       <name>hive.exec.post.hooks</name>
       <value>org.apache.atlas.hive.hook.HiveHook</value>
   </property>
   

3. 修改Atlas的 atlas-application.properties

   # 新增
   ######## Hive Hook ########
   atlas.hook.hive.synchronous=true
   atlas.hook.hive.numRetries=3
   atlas.hook.hive.queueSize=10000
   atlas.cluster.name=atlas
   atlas.rest.address=http://namenode:21000
   

4. 将Atlas的 atlas-application.properties文件分发至所有节点HIVE_HOME/conf

5. 重启Hive、Atlas（有Hue重启Hue）

6. 在atlas目录下执行倒入命令

   bin/import-hive.sh