CDH6.3.0集成atlas

1、下载atlas2.0源码

https://www.apache.org/dyn/closer.cgi/atlas/2.0.0/apache-atlas-2.0.0-sources.tar.gz

2、使用idea打开源码，修改源码中pom文件依赖，将Hadoop、hbase、kafka、zookeeper版本改成与CDH中版本一致

 

查看版本

 

 修改atlas-application.properties配置文件（在distrosrcconf中）

#hbase

#atlas.graph.storage.backend=${graph.storage.backend}
atlas.graph.storage.backend=hbase
atlas.graph.storage.hostname=node0:2181,node1:2181,node2:2181,node3:2181
atlas.graph.storage.hbase.table=apache_atlas_janus

#Solr
#Solr cloud mode properties
atlas.graph.index.search.solr.mode=cloud
atlas.graph.index.search.solr.wait-searcher=true
# ZK quorum setup for solr as comma separated value. Example: 10.1.6.4:2181,10.1.6.5:2181
atlas.graph.index.search.solr.zookeeper-url=node0:2181,node1:2181,node2:2181,node3:2181
# SolrCloud Zookeeper Connection Timeout. Default value is 60000 ms
atlas.graph.index.search.solr.zookeeper-connect-timeout=60000
# SolrCloud Zookeeper Session Timeout. Default value is 60000 ms
atlas.graph.index.search.solr.zookeeper-session-timeout=60000

 # Default limit used when limit is not specified in API
atlas.search.defaultlimit=100
# Maximum limit allowed in API. Limits maximum results that can be fetched to make sure the atlas server doesn't run out of memory
atlas.search.maxlimit=10000

#Solr http mode properties
#atlas.graph.index.search.solr.mode=http
#atlas.graph.index.search.solr.http-urls=http://xxxxx:8983/solr

#########  Notification Configs  #########
atlas.notification.embedded=false
atlas.kafka.data=${sys:atlas.home}/data/kafka
atlas.kafka.zookeeper.connect=node0:2181,node1:2181,node2:2181,node3:2181
atlas.kafka.bootstrap.servers=node0:2181,node1:2181,node2:2181,node3:2181
atlas.kafka.zookeeper.session.timeout.ms=60000
atlas.kafka.zookeeper.connection.timeout.ms=30000
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=true
atlas.kafka.auto.offset.reset=earliest
atlas.kafka.session.timeout.ms=30000

 4、修改atlas-env.sh（在distrosrcconf中）

#集成添加hbase配置->下面的目录为atlas下的hbase配置目录，需要后面加入集群hbase配置
export HBASE_CONF_DIR=/usr/local/src/atlas/apache-atlas-2.0.0/conf/hbase/conf
#export MANAGE_LOCAL_HBASE=false  (false外置的zk和hbase)
#export MANAGE_LOCAL_SOLR=false  （false外置的solr）
    
#修改内存指标（根据线上机器配置）
export ATLAS_SERVER_OPTS="-server -XX:SoftRefLRUPolicyMSPerMB=0
-XX:+CMSClassUnloadingEnabled -XX:+UseConcMarkSweepGC
-XX:+CMSParallelRemarkEnabled -XX:+PrintTenuringDistribution
-XX:+HeapDumpOnOutOfMemoryError
-XX:HeapDumpPath=dumps/atlas_server.hprof
-Xloggc:logs/gc-worker.log -verbose:gc
-XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=10
-XX:GCLogFileSize=1m -XX:+PrintGCDetails -XX:+PrintHeapAtGC
-XX:+PrintGCTimeStamps"

#优化 JDK1.8(以下需要16G内存)
export ATLAS_SERVER_HEAP="-Xms15360m -Xmx15360m
-XX:MaxNewSize=5120m -XX:MetaspaceSize=100M
-XX:MaxMetaspaceSize=512m"

 5、修改atlas-log4j.xml（位置同上）

#去掉如下代码的注释(开启如下代码)
    <appender name="perf_appender" class="org.apache.log4j.DailyRollingFileAppender">
        <param name="file" value="${atlas.log.dir}/atlas_perf.log" />
        <param name="datePattern" value="'.'yyyy-MM-dd" />
        <param name="append" value="true" />
        <layout class="org.apache.log4j.PatternLayout">
            <param name="ConversionPattern" value="%d|%t|%m%n" />
        </layout>
    </appender>

    <logger name="org.apache.atlas.perf" additivity="false">
        <level value="debug" />
        <appender-ref ref="perf_appender" />
    </logger>

 6、编译打包

mvn clean -DskipTests install
mvn clean -DskipTests package -Pdist

参考博客：

CDH集成atlas
https://blog.csdn.net/tom_fans/article/details/85506662

https://blog.csdn.net/fairynini/article/details/106134361?utm_medium=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.add_param_isCf&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.add_param_isCf

end