Docker搭建Clickhouse集群
Docker搭建Clickhouse集群
环境说明
2C 2G 30G
| hostname | IP | 操作系统 | 服务 |
|---|---|---|---|
| localhost | 192.168.88.171 | CentOs 7.8 | clickhouse-server zookeeper kafka |
| localhost | 192.168.88.172 | CentOs 7.8 | clickhouse-server zookeeper kafka |
| localhost | 192.168.88.173 | CentOs 7.8 | clickhouse-server zookeeper kafka |
1.安装Zookeeper
docker pull wurstmeister/zookeeper
docker pull wurstmeister/kafka
# 拉取完毕后查看
docker images
REPOSITORY TAG IMAGE ID CREATED SIZE
wurstmeister/kafka latest 161b1a19ddd6 13 hours ago 618MB
wurstmeister/zookeeper latest 3f43f72cb283 3 years ago 510MB
# 启动
docker run --restart=always \
--name zk01 -d \
-p 2181:2181 -p 2888:2888 -p 3888:3888 \
wurstmeister/zookeeper
# 进入容器
docker exec -it zookeeper bash
pwd
/opt/zookeeper-3.4.13
# 进入conf文件夹，修改zoo.cfg，在最下方添加
vi zoo.cfg
server.1=0.0.0.0:2888:3888
server.2=192.168.88.172:2888:3888
server.3=192.168.88.173:2888:3888
# 另外两台一样添加
docker run --restart=always --name zk02 -d -p 2181:2181 -p 2888:2888 -p 3888:3888 wurstmeister/zookeeper
docker run --restart=always --name zk03 -d -p 2181:2181 -p 2888:2888 -p 3888:3888 wurstmeister/zookeeper
# 第二台
server.1=192.168.88.171:2888:3888
server.2=0.0.0.0:2888:3888
server.3=192.168.88.173:2888:3888
# 第三台
server.1=192.168.88.171:2888:3888
server.2=192.168.88.172:2888:3888
server.3=0.0.0.0:2888:3888
# 请修改本机所在节点的ip为0.0.0.0
# 而我当前节点是server.1，则ip修改为0.0.0.0
# 修改完毕后添加myid文件内的值为1
# 第一台
echo 1 > data/myid
# 第二台
echo 2 > data/myid
# 第三台
echo 3 > data/myid
# 到此我们就配置好了，重新启动zookeeper容器即可。
docker restart zookeeper
# 接下来验证集群
./bin/zkServer.sh status
# 可以看到集群状态
# server.1
Mode: follower
# server.2
Mode: follower
# server.3
Mode: leader
2.搭建kafka
# 运行准备好的镜像
# 1
docker run -it --restart=always \
--name kafka01 -p 9092:9092 -e KAFKA_BROKER_ID=0 \
-e KAFKA_ZOOKEEPER_CONNECT=192.168.88.171:2181,192.168.88.172:2181,192.168.88.173:2181 \
-e KAFKA_ADVERTISED_LISTENERS=PLAINTEXT://192.168.88.171:9092 \
-e KAFKA_LISTENERS=PLAINTEXT://0.0.0.0:9092 \
-d wurstmeister/kafka:latest
# 2
docker run -it --restart=always \
--name kafka02 -p 9092:9092 -e KAFKA_BROKER_ID=1 \
-e KAFKA_ZOOKEEPER_CONNECT=192.168.88.171:2181,192.168.88.172:2181,192.168.88.173:2181 \
-e KAFKA_ADVERTISED_LISTENERS=PLAINTEXT://192.168.88.172:9092 \
-e KAFKA_LISTENERS=PLAINTEXT://0.0.0.0:9092 \
-d wurstmeister/kafka:latest
# 3
docker run -it --restart=always \
--name kafka03 -p 9092:9092 -e KAFKA_BROKER_ID=2 \
-e KAFKA_ZOOKEEPER_CONNECT=192.168.88.171:2181,192.168.88.172:2181,192.168.88.173:2181 \
-e KAFKA_ADVERTISED_LISTENERS=PLAINTEXT://192.168.88.173:9092 \
-e KAFKA_LISTENERS=PLAINTEXT://0.0.0.0:9092 \
-d wurstmeister/kafka:latest
# 查看zookeeper
docker exec -it zk01 bash
./bin/zkCli.sh
ls /brokers/ids
[2, 1, 0]
# 创建topic
# 进入容器
docker exec -it kafka01 bash
cd /opt/kafka/
./bin/kafka-topics.sh --create --zookeeper 192.168.88.171:2181 --topic test --partitions 1 --replication-factor 1
Created topic test.
# 到另外两台查看新创建的test
# 查看topics
# 192.168.88.172
./bin/kafka-topics.sh --list --zookeeper 192.168.88.172:2181
test
# 192.168.88.173
./bin/kafka-topics.sh --list --zookeeper 192.168.88.173:2181
test
test
# 写（CTRL+D结束写内容）
# 192.168.88.171
./bin/kafka-console-producer.sh --broker-list 192.168.88.171:9092 --topic test
>hello
# 读（CTRL+C结束读内容）
# 192.168.88.173
./bin/kafka-console-consumer.sh --bootstrap-server 192.168.88.173:9092 --topic test --from-beginning
hello
3.Clickhouse集群环境搭建
3.1 修改clickhouse配置文件
创建本地持久化数据目录
# 三台主机依次创建，目录可定义
mkdir /data/clickhouse
# 获取clickhouse-server的配置
# 找一台先启动clickhouse
docker run -d --name clickhouse-server --ulimit nofile=262144:262144 -v /data/clickhouse/:/var/lib/clickhouse yandex/clickhouse-server:latest
# 拷贝容器内容的配置到/data/clickhouse/目录下
docker cp clickhouse-server:/etc/clickhouse-server/ /data/clickhouse/
需要修改的配置为：
- config.xml
- users.xml 如果有需要也可以配置user.xml，不需要配置账户不用此配置
vim /data/clickhouse/clickhouse-server/config.xml
# 打开listen_host
<listen_host>0.0.0.0</listen_host> # 限制来源主机的请求，如果要服务器回答所有请求，请指定“::”
# 修改集群配置remote_servers标签
<remote_servers>
<!-- Test only shard config for testing distributed storage -->
<chainmaker_clusters>
<shard>
<!-- Optional. Whether to write data to just one of the replicas. Default: false (write data to all replicas). -->
<!-- <internal_replication>false</internal_replication> -->
<!-- Optional. Shard weight when writing data. Default: 1. -->
<!-- <weight>1</weight> -->
<replica>
<host>192.168.88.171</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>192.168.88.172</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>192.168.88.173</host>
<port>9000</port>
</replica>
</shard>
</chainmaker_clusters>
</remote_servers>
chainmaker_clusters集群标识，可以自行规定，在创建分布式表（引擎为Distributed）时需要用到
# 修改zookeeper集群配置
<zookeeper>
<node>
<host>192.168.88.171</host>
<port>2181</port>
</node>
<node>
<host>192.168.88.172</host>
<port>2181</port>
</node>
<node>
<host>192.168.88.173</host>
<port>2181</port>
</node>
</zookeeper>
# 倒数第二行添加时区
<timezone>Asia/Shanghai</timezone>
# 如果需要添加密码就需要修改users.xml
# 找到此标签添加
<password>密码</password>
3.2 启动Clickhouse
# clickhouse-server01
docker run --restart always -d \
--name clickhouse-server01 \
--ulimit nofile=262144:262144 \
-v /data/clickhouse/data/:/var/lib/clickhouse/ \
-v /data/clickhouse/clickhouse-server/:/etc/clickhouse-server/ \
-v /data/clickhouse/logs/:/var/log/clickhouse-server/ \
-p 9000:9000 -p 8123:8123 -p 9009:9009 \
yandex/clickhouse-server:latest
# clickhouse-server02
docker run --restart always -d \
--name clickhouse-server02 \
--ulimit nofile=262144:262144 \
-v /data/clickhouse/data/:/var/lib/clickhouse/ \
-v /data/clickhouse/clickhouse-server/:/etc/clickhouse-server/ \
-v /data/clickhouse/logs/:/var/log/clickhouse-server/ \
-p 9000:9000 -p 8123:8123 -p 9009:9009 \
yandex/clickhouse-server:latest
# clickhouse-server03
docker run --restart always -d \
--name clickhouse-server03 \
--ulimit nofile=262144:262144 \
-v /data/clickhouse/data/:/var/lib/clickhouse/ \
-v /data/clickhouse/clickhouse-server/:/etc/clickhouse-server/ \
-v /data/clickhouse/logs/:/var/log/clickhouse-server/ \
-p 9000:9000 -p 8123:8123 -p 9009:9009 \
yandex/clickhouse-server:latest
3.3 测试集群可用性
# 进入clickhouse-server01创建库表
docker exec -it clickhouse-server01 bash
clickhouse-client
# 使用密码登录
# clickhouse-client -h 192.168.88.171 --port 9000 --password 密码
# 默认密码为default
# 查看ClickHouse的集群信息
select * from system.clusters;
SELECT *
FROM system.clusters
Query id: cdd6249a-1ba4-46c6-98bc-0041f55464c0
┌─cluster─────────────┬─shard_num─┬─shard_weight─┬─replica_num─┬─host_name──────┬─host_address───┬─port─┬─is_local─┬─user────┬─default_database─┬─errors_count─┬─slowdowns_count─┬─estimated_recovery_time─┐
│ chainmaker_clusters │ 1 │ 1 │ 1 │ 192.168.88.171 │ 192.168.88.171 │ 9000 │ 0 │ default │ │ 0 │ 0 │ 0 │
│ chainmaker_clusters │ 2 │ 1 │ 1 │ 192.168.88.172 │ 192.168.88.172 │ 9000 │ 0 │ default │ │ 0 │ 0 │ 0 │
│ chainmaker_clusters │ 3 │ 1 │ 1 │ 192.168.88.173 │ 192.168.88.173 │ 9000 │ 0 │ default │ │ 0 │ 0 │ 0 │
└─────────────────────┴───────────┴──────────────┴─────────────┴────────────────┴────────────────┴──────┴──────────┴─────────┴──────────────────┴──────────────┴─────────────────┴─────────────────────────┘
3 rows in set. Elapsed: 0.007 sec.
# 创建库表，三台主机一起创建
create database chainmaker_test;
use chainmaker_test;
CREATE TABLE logs (cur Date, size Int32, message String) ENGINE = MergeTree(cur, message, 8192);
CREATE TABLE logs_dist AS logs ENGINE = Distributed(chainmaker_clusters,chainmaker_test,logs,rand());
# 下列命令在Clickhouse的一个主机上执行即可；
insert into logs_dist values(now(), 1, '1');
# 在任何一个Clickhouse的主机上查询数据一致即表示集群 状态正常
select * from logs_dist;
SELECT *
FROM logs_dist
Query id: ba5ef109-f038-4edd-84ef-efbfe3699d9e
┌────────cur─┬─size─┬─message─┐
│ 2022-02-28 │ 1 │ 1 │
└────────────┴──────┴─────────┘
1 rows in set. Elapsed: 0.027 sec.
