Clickhouse安装及使用

# wget -P 
# 下载到指定目录

$ wget https://repo.yandex.ru/clickhouse/rpm/stable/x86_64/clickhouse-client-21.8.4.51-2.noarch.rpm

$ wget https://repo.yandex.ru/clickhouse/rpm/stable/x86_64/clickhouse-common-static-21.8.4.51-2.x86_64.rpm

$ wget https://repo.yandex.ru/clickhouse/rpm/stable/x86_64/clickhouse-common-static-dbg-21.8.4.51-2.x86_64.rpm

$ wget https://repo.yandex.ru/clickhouse/rpm/stable/x86_64/clickhouse-server-21.8.4.51-2.noarch.rpm

$ sudo rpm -ivh {CLICKHOUSE-HOME}/*.rpm

$ sudo rpm -qa|grep clickhouse

$ sudo vim /etc/clickhouse-server/config.xml

# 1.打开listen_host，二选一
# 如果支持IPV6
<listen_host>::</listen_host>
# 如果支持IPV4
<listen_host>0.0.0.0</listen_host>

# 2.修改端口号，9000被python占用
<tcp_port>9099</tcp_port>

  # 默认数据文件路径：<path>/var/lib/clickhouse/</path>
  # 默认日志文件路径：<log>/var/log/clickhouse-server/clickhouse-server.log</log>

$ sudo systemctl start clickhouse-server

$ sudo systemctl status clickhouse-server

$ sudo systemctl stop clickhouse-server

$ sudo clickhouse restart

$ clickhouse-client -m --password {PASSWORD} --port 9099 --user default --host {HOST}

show databases;

use default;

show tables;

# 1. 在/etc/clickhouse-server/config.d 目录下创建一个名为 metrika.xml的配置文件
$ sudo vim /etc/clickhouse-server/config.d/metrika.xml

<?xml version="1.0"?>
<yandex>
 <remote_servers>
  <test_cluster>
   <shard>
    <internal_replication>true</internal_replication>
       <replica>
           <host>{host_01}</host>
           <port>9099</port>
       </replica>
       <replica>
           <host>{host_02}</host>
           <port>9099</port>
       </replica>
   </shard>
  </test_cluster>
 </remote_servers>

 <zookeeper-servers>
     <node index="1">
         <host>{host_01}</host>
         <port>2181</port>
     </node>
     <node index="2">
         <host>{host_02}</host>
         <port>2181</port>
     </node>
     <node index="3">
         <host>{host_03}</host>
         <port>2181</port>
     </node>
 </zookeeper-servers>

 <macros>
  <shard>01</shard>
  <replica>rep_1_1</replica>
 </macros>
</yandex>

$ sudo vim /etc/clickhouse-server/config.xml

<zookeeper incl="zookeeper-servers" optional="true" /> 
<include_from>/etc/clickhouse-server/config.d/metrika.xml</include_from>

$ sudo scp /etc/clickhouse-server/config.d/metrika.xml remote_user@remote_host:/etc/clickhouse-server/config.d/metrika.xml

$ sudo scp /etc/clickhouse-server/config.xml remote_user@remote_host:/etc/clickhouse-server/config.xml

$ sudo vim /etc/clickhouse-server/config.d/metrika.xml

 <macros>
  <shard>01</shard>
  <replica>rep_1_2</replica>
 </macros>

$ sudo clickhouse restart

create table test_local on cluster test_cluster (
    id UInt32,
    sku_id String,
    total_amount Decimal(16,2),
    create_time  Datetime
) engine=ReplicatedMergeTree(‘/clickhouse/tables/{shard}/test_local‘,‘{replica}‘)    
partition by toYYYYMMDD(create_time)    
primary key (id)    
order by (id,sku_id);

create table test_local_all on cluster test_cluster (
    id UInt32, 
    sku_id String,
    total_amount Decimal(16,2),
    create_time  Datetime 
) engine = Distributed(test_cluster,default,test_local,hiveHash(sku_id)); 

show tables;

# 主机1和主机2上都有test_local表和test_local_all表，则证明建表成功

insert into test_local_all values (207,‘sku_006‘,700.00,‘2020-06-02 12:00:00‘);

select * from test_local;

select * from test_local_all;

# 如果主机1和主机2上的test_local和test_local_all共4个表查询结果相同，则证明数据写入成功

# 可以直接向本地表test_local写入数据，来验证4个表数据是否一致。

$ tail -n 100 /var/log/clickhouse-server/clickhouse-server.err.log