To avoid various environmental problems, you can run the script, $KYLIN_HOME/bin/check-env.sh to have a test on your environment, if there are any problems with your environment, the script will print a detailed error message. Kylin runs on a Hadoop cluster and has certain requirements for the version, access rights, and CLASSPATH of each component. tool: the jar file for running utility CLI.tomcat the tomcat web server that run Kylin application.spark: the default spark binary that built with Kylin.sample_cube: files to create the sample cube and its tables.meta_backups: default backup folder when run “bin/metastore.sh backup”.lib: Kylin jar files for external use, like the Hadoop job jar, JDBC driver, HBase coprocessor jar, etc.The function of these xml files can be found in configuration page
Download a binary package for your Hadoop version from the Apache Kylin Download Site.Linux accounts running Kylin must have access to the Hadoop cluster, including the permission to create/write HDFS folders, Hive tables, HBase tables, and submit MapReduce tasks. For better stability, it is recommended to deploy Kylin on a clean Hadoop client node with Hive, HBase, HDFS and other command lines installed and client configuration (such as core-site.xml, hive-site.xml, hbase-site.xml and others) are also reasonably configured and can be automatically synchronized with other nodes. For convenience, you can run Kylin on the master node. Kylin can be launched on any node in a Hadoop cluster. You need to prepare a Hadoop cluster with HDFS, YARN, MapReduce, Hive, HBase, Zookeeper and other services for Kylin to run.
Kylin relies on Hadoop clusters to handle large data sets.
For high-load scenarios, a 24-core CPU, 64 GB RAM or higher is recommended. The minimum configuration of a server running Kylin is 4 core CPU, 16 GB RAM and 100 GB disk. When configuring a sandbox, we recommend that you use the Bridged Adapter model instead of the NAT model. We recommend you to try out Kylin or develop it using the integrated sandbox, such as HDP sandbox, and make sure it has at least 10 GB of memory.