文章目录
docker-compose搭建
新建文件夹新建四个文件
docker-compose.yml
version: "3"
services:
namenode:
image: bde2020/hadoop-namenode:2.0.0-hadoop3.2.1-java8
container_name: namenode
restart: always
ports:
- 9870:9870
- 9000:9000
volumes:
- hadoop_namenode:/hadoop/dfs/name
environment:
- CLUSTER_NAME=test
env_file:
- ./hadoop.env
datanode:
image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
container_name: datanode
restart: always
volumes:
- hadoop_datanode:/hadoop/dfs/data
environment:
SERVICE_PRECONDITION: "namenode:9870"
env_file:
- ./hadoop.env
depends_on:
- namenode
resourcemanager:
image: bde2020/hadoop-resourcemanager:2.0.0-hadoop3.2.1-java8
container_name: resourcemanager
restart: always
environment:
SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864"
env_file:
- ./hadoop.env
ports:
- 8088:8088
depends_on:
- namenode
- datanode
nodemanager1:
image: bde2020/hadoop-nodemanager:2.0.0-hadoop3.2.1-java8
container_name: nodemanager
restart: always
environment:
SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
env_file:
- ./hadoop.env
depends_on:
- namenode
- datanode
- resourcemanager
historyserver:
image: bde2020/hadoop-historyserver:2.0.0-hadoop3.2.1-java8
container_name: historyserver
restart: always
environment:
SERVICE_PRECONDITION: "namenode:9000 namenode:9870 datanode:9864 resourcemanager:8088"
volumes:
- hadoop_historyserver:/hadoop/yarn/timeline
env_file:
- ./hadoop.env
depends_on:
- namenode
- datanode
- resourcemanager
hbase:
image: bde2020/hbase-standalone:1.0.0-hbase1.2.6
container_name: hbase
volumes:
- hbase_data:/hbase-data
- hbase_zookeeper_data:/zookeeper-data
ports:
- 16000:16000
- 16010:16010
- 16020:16020
- 16030:16030
- 2888:2888
- 3888:3888
- 2181:2181
environment:
SERVICE_PRECONDITION: "namenode:9870 datanode:9864"
env_file:
- ./hbase-standalone.env
depends_on:
- namenode
- datanode
hive-server:
container_name: hive-server
image: bde2020/hive:2.3.2-postgresql-metastore
env_file:
- ./hadoop-hive.env
environment:
HIVE_CORE_CONF_javax_jdo_option_ConnectionURL: "jdbc:postgresql://hive-metastore/metastore"
SERVICE_PRECONDITION: "hive-metastore:9083"
ports:
- "10000:10000"
depends_on:
- hive-metastore
hive-metastore:
container_name: hive-metastore
image: bde2020/hive:2.3.2-postgresql-metastore
env_file:
- ./hadoop-hive.env
command: /opt/hive/bin/hive --service metastore
environment:
SERVICE_PRECONDITION: "namenode:9870 datanode:9864 hive-metastore-postgresql:5432"
ports:
- "9083:9083"
depends_on:
- namenode
- datanode
- hive-metastore-postgresql
hive-metastore-postgresql:
container_name: hive-metastore-postgresql
image: bde2020/hive-metastore-postgresql:2.3.0
presto-coordinator:
container_name: presto-coordinator
image: shawnzhu/prestodb:0.181
ports:
- "8080:8080"
volumes:
hadoop_namenode:
hadoop_datanode:
hadoop_historyserver:
hbase_data:
hbase_zookeeper_data:
hadoop.env
CORE_CONF_fs_defaultFS=hdfs://namenode:9000
CORE_CONF_hadoop_http_staticuser_user=root
CORE_CONF_hadoop_proxyuser_hue_hosts=*
CORE_CONF_hadoop_proxyuser_hue_groups=*
CORE_CONF_io_compression_codecs=org.apache.hadoop.io.compress.SnappyCodec
HDFS_CONF_dfs_webhdfs_enabled=true
HDFS_CONF_dfs_permissions_enabled=false
HDFS_CONF_dfs_namenode_datanode_registration_ip___hostname___check=false
YARN_CONF_yarn_log___aggregation___enable=true
YARN_CONF_yarn_log_server_url=http://historyserver:8188/applicationhistory/logs/
YARN_CONF_yarn_resourcemanager_recovery_enabled=true
YARN_CONF_yarn_resourcemanager_store_class=org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
YARN_CONF_yarn_resourcemanager_scheduler_class=org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler
YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___mb=8192
YARN_CONF_yarn_scheduler_capacity_root_default_maximum___allocation___vcores=4
YARN_CONF_yarn_resourcemanager_fs_state___store_uri=/rmstate
YARN_CONF_yarn_resourcemanager_system___metrics___publisher_enabled=true
YARN_CONF_yarn_resourcemanager_hostname=resourcemanager
YARN_CONF_yarn_resourcemanager_address=resourcemanager:8032
YARN_CONF_yarn_resourcemanager_scheduler_address=resourcemanager:8030
YARN_CONF_yarn_resourcemanager_resource__tracker_address=resourcemanager:8031
YARN_CONF_yarn_timeline___service_enabled=true
YARN_CONF_yarn_timeline___service_generic___application___history_enabled=true
YARN_CONF_yarn_timeline___service_hostname=historyserver
YARN_CONF_mapreduce_map_output_compress=true
YARN_CONF_mapred_map_output_compress_codec=org.apache.hadoop.io.compress.SnappyCodec
YARN_CONF_yarn_nodemanager_resource_memory___mb=16384
YARN_CONF_yarn_nodemanager_resource_cpu___vcores=8
YARN_CONF_yarn_nodemanager_disk___health___checker_max___disk___utilization___per___disk___percentage=98.5
YARN_CONF_yarn_nodemanager_remote___app___log___dir=/app-logs
YARN_CONF_yarn_nodemanager_aux___services=mapreduce_shuffle
MAPRED_CONF_mapreduce_framework_name=yarn
MAPRED_CONF_mapred_child_java_opts=-Xmx4096m
MAPRED_CONF_mapreduce_map_memory_mb=4096
MAPRED_CONF_mapreduce_reduce_memory_mb=8192
MAPRED_CONF_mapreduce_map_java_opts=-Xmx3072m
MAPRED_CONF_mapreduce_reduce_java_opts=-Xmx6144m
MAPRED_CONF_yarn_app_mapreduce_am_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/
MAPRED_CONF_mapreduce_map_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/
MAPRED_CONF_mapreduce_reduce_env=HADOOP_MAPRED_HOME=/opt/hadoop-3.2.1/
hadoop-hive.env
HIVE_SITE_CONF_javax_jdo_option_ConnectionURL=jdbc:postgresql://hive-metastore-postgresql/metastore
HIVE_SITE_CONF_javax_jdo_option_ConnectionDriverName=org.postgresql.Driver
HIVE_SITE_CONF_javax_jdo_option_ConnectionUserName=hive
HIVE_SITE_CONF_javax_jdo_option_ConnectionPassword=hive
HIVE_SITE_CONF_datanucleus_autoCreateSchema=false
HIVE_SITE_CONF_hive_metastore_uris=thrift://hive-metastore:9083
HDFS_CONF_dfs_namenode_datanode_registration_ip___hostname___check=false
CORE_CONF_fs_defaultFS=hdfs://namenode:9000
CORE_CONF_hadoop_http_staticuser_user=root
CORE_CONF_hadoop_proxyuser_hue_hosts=*
CORE_CONF_hadoop_proxyuser_hue_groups=*
HDFS_CONF_dfs_webhdfs_enabled=true
HDFS_CONF_dfs_permissions_enabled=false
YARN_CONF_yarn_log___aggregation___enable=true
YARN_CONF_yarn_resourcemanager_recovery_enabled=true
YARN_CONF_yarn_resourcemanager_store_class=org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore
YARN_CONF_yarn_resourcemanager_fs_state___store_uri=/rmstate
YARN_CONF_yarn_nodemanager_remote___app___log___dir=/app-logs
YARN_CONF_yarn_log_server_url=http://historyserver:8188/applicationhistory/logs/
YARN_CONF_yarn_timeline___service_enabled=true
YARN_CONF_yarn_timeline___service_generic___application___history_enabled=true
YARN_CONF_yarn_resourcemanager_system___metrics___publisher_enabled=true
YARN_CONF_yarn_resourcemanager_hostname=resourcemanager
YARN_CONF_yarn_timeline___service_hostname=historyserver
YARN_CONF_yarn_resourcemanager_address=resourcemanager:8032
YARN_CONF_yarn_resourcemanager_scheduler_address=resourcemanager:8030
YARN_CONF_yarn_resourcemanager_resource__tracker_address=resourcemanager:8031
hbase-standalone.env
HBASE_CONF_hbase_rootdir=hdfs://namenode:9000/hbase
HBASE_CONF_hbase_cluster_distributed=false
HBASE_CONF_hbase_zookeeper_property_dataDir=/zookeeper-data
HBASE_CONF_hbase_zookeeper_quorum=hbase
HBASE_CONF_hbase_master_port=16000
HBASE_CONF_hbase_master_info_port=16010
HBASE_CONF_hbase_regionserver_port=16020
HBASE_CONF_hbase_regionserver_info_port=16030
HBASE_CONF_hbase_zookeeper_peerport=2888
HBASE_CONF_hbase_zookeeper_leaderport=3888
HBASE_CONF_hbase_zookeeper_property_clientPort=2181
源码地址
https://github.com/googalAmbition/docker-big-data
效果预览
hadoop
hive ![在这里插入图片描述](https://img-blog.csdnimg.cn/2228c5e7df89459286e6d79b3246d19f.png)
hbase
资源管理器