diff options
Diffstat (limited to 'full_hosts')
| -rw-r--r-- | full_hosts | 118 |
1 files changed, 118 insertions, 0 deletions
diff --git a/full_hosts b/full_hosts new file mode 100644 index 0000000..8393e20 --- /dev/null +++ b/full_hosts @@ -0,0 +1,118 @@ +#============================================================================== +# Basic Components +# +# Orchestration & Coordinator & Configuration & Cold Storage +#============================================================================== + +#Configure Mariadb deployed nodes,Use master-master replication mode,maximum 2 servers. +[mariadb] + + +#Apache Zookeeper is a centralized service for maintaining configuration information, naming, providing distributed synchronization, and providing group services. +#At least 3 servers,And it is strongly recommended that you have an odd number of servers. +[zookeeper] + + +#Alibaba Nacos an easy-to-use dynamic service discovery, configuration and service management platform +#At least 3 servers,Multi-node HA mode. +[nacos] + + +#Apache Hadoop HDFS(Hadoop Distributed File System) +#At least 3 servers,An HDFS cluster consists of two Namenodes and a certain number of Datanodes node. +[hdfs] + + +#============================================================================== +# BigData Processing Components +# +# Big data is a term that refers to the massive volume, variety, and velocity of data that is generated from various sources and needs to be stored, processed, and analyzed efficiently. +# The Big Data processing component is used to provide a platform for fast and efficient processing +#============================================================================== + +#Apache Kafka is a distributed event streaming platform,used for high-performance data pipelines, streaming analytics. +#At least 3 servers,By default install CMAK(Management tool) on the first server. +[kafka] + + +#Apache Hadoop Yarn,Includes the Flink runtime environment. +#Yarn is the resource management and job scheduling technology in the open source Hadoop distributed processing framework. +#At least 3 servers,A Yarn cluster consists of two ResourceManager (RM) and a certain number of NodeManager(NM) node. +[yarn] + + +#Groot Stream is a real-time data stream processing platform. +[grootstream] + +#============================================================================== +# BigData Processing Components +# +# Big data is a term that refers to the massive volume, variety, and velocity of data that is generated from various sources and needs to be stored, processed, and analyzed efficiently. +# The Big Data processing component is used to provide a platform for fast and efficient processing +#============================================================================== + +#Apache HBase is the hosting of very large tables -- billions of rows X millions of columns -- atop clusters of commodity hardware +#At least 3 servers,A HBase cluster consists of three HMaster and a certain number of HRegionServer node. +[hbase] + + +#Apache Druid is a high performance, real-time analytics database that delivers sub-second queries on streaming and batch data at scale and under load. +#At least 3 servers,A Druid cluster consists of two master/query and a certain number of worker node. +[druid] + + +#Yandex ClickHouse is the fastest and most resource efficient open-source database for real-time apps and analytics. +#At least 3 servers,A Clickhouse cluster consists of two query and a certain number of data node. +[clickhouse] + + +#ArangoDB is a scalable graph database system to drive value from connected data, faster. +#Only support single server deployment +[arangodb] + +#Redis is an open source (BSD licensed), in-memory data structure store, used as a database, cache, and message broker. +#Supports single-node and master-slave modes +[redis] + +#Apache Ignite is a leading distributed database management system for high-performance computing with in-memory speed +#Supports single-node and cluster modes +[ignite] + +#============================================================================== +# OLAP Self-research service +# +#============================================================================== +#Default load balancer include keepalived/Galaxy-gateway-nginx +[loadbalancer] + + +#Chproxy is an HTTP proxy and load balancer for ClickHouse +[chproxy] + + +#Galaxy-hos-service is a distributed object storage service. +#Include components:Keepalived/Nginx/galaxy-hos-service +#At least 2 servers,keepalived and nginx services are deployed on the first two nodes by default. +[galaxy_hos_service] + + +#The query gateway,Provides a unified query entry +[galaxy_qgw_service] + + +#A lightweight distributed task scheduling framework. +#Include components: Galaxy-job-admin/Galaxy-job-executor +[galaxy_job_service] + +# +[saved_query_scheduler] + + +#============================================================================== +# Monitoring module +# +#============================================================================== + +#Receive metrics pushed by the program. Pushgateway then exposed these metrics to Prometheus. +[pushgateway] + |
