clickhouse-20版本安装部署

**1,安装包系在路径:

https://mirrors.aliyun.com/clickhouse/tgz/stable/\*\*

2,环境准备

1.配置主机名

hostnamectl set-hostname ${hostname}

2.配置hosts

ip hostname

3.关闭防火墙

vim /etc/selinux/config 改为 SELINUX=disabled

ps:

1)关闭systemctl stop firewalld

2)查看防火墙端口是否开发

lsof -i:80 or netstat -apnt |grep 80

重启防火墙:systemctl restart firewalld.service

查看所有开放端口:firewall-cmd --list-ports

查看防火墙状态:firewall-cmd --state

开启防火墙:systemctl start firewalld.service

设置防火墙开机自启动:systemctl enable firewalld.service

重启防火墙:systemctl restart firewalld.service

3,clickhouse 前期准备

1.创建用户

useradd clickhouse

passwd clickhouse

2.clickhouse用户授权

visudo

添加 clickhouse ALL=(ALL) ALL

4.jdk 安装

5.zk 安装

三:安装clickhouse

1.安装

sudo rpm -ivh clickhouse-*.rpm
2. 修改config.xml 文件

yaml 复制代码
<?xml version="1.0"?>
<yandex>
    <!--根据实际替换-->    
    <listen_host>::1</listen_host>
   <listen_host>0.0.0.0</listen_host>
    <include_from>/etc/clickhouse-server/metrika.xml</include_from>
    <remote_url_allow_hosts></remote_url_allow_hosts>
    <logger>
        <level>trace</level>
        <log>/var/log/clickhouse-server/clickhouse-server.log</log>
        <errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
        <size>1000M</size>
        <count>10</count>
    </logger>
    <!--根据实际替换-->
    <http_port>8123</http_port>
    <tcp_port>9000</tcp_port>
    <openSSL>
        <server>
            <certificateFile>/etc/clickhouse-server/server.crt</certificateFile>
            <privateKeyFile>/etc/clickhouse-server/server.key</privateKeyFile>
            <dhParamsFile>/etc/clickhouse-server/dhparam.pem</dhParamsFile>
            <verificationMode>none</verificationMode>
            <loadDefaultCAFile>true</loadDefaultCAFile>
            <cacheSessions>true</cacheSessions>
            <disableProtocols>sslv2,sslv3</disableProtocols>
            <preferServerCiphers>true</preferServerCiphers>
        </server>
        <client>
            <loadDefaultCAFile>true</loadDefaultCAFile>
            <cacheSessions>true</cacheSessions>
            <disableProtocols>sslv2,sslv3</disableProtocols>
            <preferServerCiphers>true</preferServerCiphers>
            <invalidCertificateHandler>
                <name>RejectCertificateHandler</name>
            </invalidCertificateHandler>
        </client>
    </openSSL>
    <interserver_http_port>9009</interserver_http_port>
    <max_connections>4096</max_connections>
    <keep_alive_timeout>600</keep_alive_timeout>
    <max_concurrent_queries>150</max_concurrent_queries>
    <uncompressed_cache_size>8589934592</uncompressed_cache_size>
    <mark_cache_size>5368709120</mark_cache_size>
    <path>/var/lib/clickhouse/</path>
    <tmp_path>/var/lib/clickhouse/tmp/</tmp_path>
    <user_files_path>/var/lib/clickhouse/user_files/</user_files_path>
    <users_config>users.xml</users_config>
    <default_profile>default</default_profile>
    <default_database>default</default_database>
    <default_replica_path>/clickhouse/tables/{shard}/{database}/{table}</default_replica_path>
    <default_replica_name>{replica}</default_replica_name>
    <mlock_executable>false</mlock_executable>
    <remote_servers incl="clickhouse_remote_servers" ></remote_servers>
    <zookeeper incl="zookeeper-servers" optional="true" />
    <macros incl="macros" optional="true" />
    <builtin_dictionaries_reload_interval>3600</builtin_dictionaries_reload_interval>
    <max_session_timeout>3600</max_session_timeout>
    <default_session_timeout>60</default_session_timeout>
    <format_schema_path>/var/lib/clickhouse/format_schemas/</format_schema_path>
    <query_log>
        <database>system</database>
        <table>query_log</table>
        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </query_log>
    <trace_log>
        <database>system</database>
        <table>trace_log</table>
        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </trace_log>
    <query_thread_log>
        <database>system</database>
        <table>query_thread_log</table>
        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </query_thread_log>
    <dictionaries_config>*_dictionary.xml</dictionaries_config>
    <compression incl="clickhouse_compression"></compression>
    <distributed_ddl>
        <path>/clickhouse/task_queue/ddl</path>
    </distributed_ddl>
    <graphite_rollup_example>
        <pattern>
            <regexp>click_cost</regexp>
            <function>any</function>
            <retention>
                <age>0</age>
                <precision>3600</precision>
            </retention>
            <retention>
                <age>86400</age>
                <precision>60</precision>
            </retention>
        </pattern>
        <default>
            <function>max</function>
            <retention>
                <age>0</age>
                <precision>60</precision>
            </retention>
            <retention>
                <age>3600</age>
                <precision>300</precision>
            </retention>
            <retention>
                <age>86400</age>
                <precision>3600</precision>
            </retention>
        </default>
    </graphite_rollup_example>
</yandex>

2.修改users.xml

yaml 复制代码
<?xml version="1.0"?>
<yandex>
    <!-- Profiles of settings. -->
    <profiles>
        <!-- Default settings. -->
        <default>
            <!-- Maximum memory usage for processing single query, in bytes. -->
            <max_memory_usage>10000000000</max_memory_usage>

            <!-- Use cache of uncompressed blocks of data. Meaningful only for processing many of very short queries. -->
            <use_uncompressed_cache>0</use_uncompressed_cache>
             <skip_unavailable_shards>1</skip_unavailable_shards>  <!-- 1=true,0=false -->
            <!-- How to choose between replicas during distributed query processing.
                 random - choose random replica from set of replicas with minimum number of errors
                 nearest_hostname - from set of replicas with minimum number of errors, choose replica
                  with minimum number of different symbols between replica's hostname and local hostname
                  (Hamming distance).
                 in_order - first live replica is chosen in specified order.
                 first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
            -->
            <load_balancing>random</load_balancing>
        </default>

        <!-- Profile that allows only read queries. -->
        <readonly>
            <readonly>1</readonly>
        </readonly>
     
    </profiles>

    <!-- Users and ACL. -->
    <users>
        <!-- If user name was not specified, 'default' user is used. -->
        <default>
            <!-- Password could be specified in plaintext or in SHA256 (in hex format).

                 If you want to specify password in plaintext (not recommended), place it in 'password' element.
                 Example: <password>qwerty</password>.
                 Password could be empty.

                 If you want to specify SHA256, place it in 'password_sha256_hex' element.
                 Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
                 Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).

                 If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
                 Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>

                 If you want to specify a previously defined LDAP server (see 'ldap_servers' in main config) for authentication, place its name in 'server' element inside 'ldap' element.
                 Example: <ldap><server>my_ldap_server</server></ldap>

                 How to generate decent password:
                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
                 In first line will be password and in second - corresponding SHA256.

                 How to generate double SHA1:
                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha1sum | tr -d '-' | xxd -r -p | sha1sum | tr -d '-'
                 In first line will be password and in second - corresponding double SHA1.
            -->
            <password></password>

            <!-- List of networks with open access.

                 To open access from everywhere, specify:
                    <ip>::/0</ip>

                 To open access only from localhost, specify:
                    <ip>::1</ip>
                    <ip>127.0.0.1</ip>

                 Each element of list has one of the following forms:
                 <ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
                     2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
                 <host> Hostname. Example: server01.yandex.ru.
                     To check access, DNS query is performed, and all received addresses compared to peer address.
                 <host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.yandex\.ru$
                     To check access, DNS PTR query is performed for peer address and then regexp is applied.
                     Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
                     Strongly recommended that regexp is ends with $
                 All results of DNS requests are cached till server restart.
            -->
            <networks incl="networks" replace="replace">
                <ip>::/0</ip>
            </networks>

            <!-- Settings profile for user. -->
            <profile>default</profile>

            <!-- Quota for user. -->
            <quota>default</quota>

            <!-- User can create other users and grant rights to them. -->
            <!-- <access_management>1</access_management> -->
        </default>
    </users>

    <!-- Quotas. -->
    <quotas>
        <!-- Name of quota. -->
        <default>
            <!-- Limits for time interval. You could specify many intervals with different limits. -->
            <interval>
                <!-- Length of interval. -->
                <duration>3600</duration>

                <!-- No limits. Just calculate resource usage for time interval. -->
                <queries>0</queries>
                <errors>0</errors>
                <result_rows>0</result_rows>
                <read_rows>0</read_rows>
                <execution_time>0</execution_time>
            </interval>
        </default>
    </quotas>
</yandex>

这里重点添加了<skip_unavailable_shards>1</skip_unavailable_shards>
3.配置metrika.xml 文件

yaml 复制代码
<?xml version="1.0"?>
<yandex>
    <!-- 集群配置(正确) -->
    <clickhouse_remote_servers>
        <shards_0replicas>  <!-- 集群名称需与 SQL 中 ON CLUSTER 一致 -->
            <!-- 分片1 -->
            <shard>
                <replica>  <!-- 20.x 必须用 <replica> 包裹节点 -->
                    <host>bigdata57</host>  <!-- 节点 IP -->
                    <port>9000</port>  <!-- TCP 端口(正确) -->
                </replica>
            </shard>
            <!-- 分片2 -->
            <shard>
                <replica>
                    <host>bigdata93</host>
                    <port>9000</port>
                </replica>
            </shard>
        </shards_0replicas>
    </clickhouse_remote_servers>

    <!-- ZooKeeper 配置(修正标签:<host> → <node>) -->
    <zookeeper-servers>
        <node index="1">  <!-- 正确标签:<node> -->
            <host>bigdata57</host>  <!-- 节点主机名(内层 <host> 正确) -->
            <port>2181</port>  <!-- ZooKeeper 端口(正确) -->
        </node>
        <node index="2">
            <host>bigdata93</host>
            <port>2181</port>
        </node>
        <node index="3">
            <host>bigdata70</host>
            <port>2181</port>
        </node>
    </zookeeper-servers>

    <!-- 网络配置(正确) -->
    <networks>
        <ip>::/0</ip>  <!-- 允许所有 IP 访问 -->
    </networks>

    <!-- 压缩配置(正确) -->
    <clickhouse_compression>
        <case>
            <min_part_size>10000000000</min_part_size>
            <min_part_size_ratio>0.01</min_part_size_ratio>
            <method>lz4</method>
        </case>
    </clickhouse_compression>
</yandex>

注意格式一定要按照图中的来,新版本和这个版本区别很大

启动

service clickhouse-server start

验证

相关推荐
广州灵眸科技有限公司14 小时前
xfce桌面触摸校准:基于灵眸科技EASY-EAl-Orin-Nano
数据库·windows·科技
Cloud云卷云舒16 小时前
云卷云舒:从Oracle/MySQL迁移到HaishanDB:迁移评估工具核心技术拆解
mysql·oracle·ai-native·haishandb·信创数据库替换
憧憬成为web高手16 小时前
皮卡丘靶场速通--sql 2
数据库·sql·mybatis
段一凡-华北理工大学16 小时前
向量数据库实战:选型、调优与落地~系列文章12:文本分块策略实战:chunk_size 怎么选?重叠多少?
开发语言·数据库·后端·oracle·rust·工业智能体·高炉智能化
oradh18 小时前
Oracle XTTS实现跨版本迁移和升级(Oracle 11g单库升级至19C RAC集群)
数据库·oracle·11g升级19c·xtts跨版本迁移和升级
用户713335851562419 小时前
MySQL - 事务、redo/undo 日志与 MVCC
mysql
z1234567898619 小时前
2026最新两款AI编程工具深度对比实测
java·数据库·ai编程
程序猿DD19 小时前
一个 API Key,统一调用大模型、生图和联网搜索
数据库·网关
java_logo20 小时前
Docker Compose 部署 ClickHouse:快速搭建高性能列式数据库
数据库·clickhouse·docker·列式数据库·轩辕镜像·高性能数据库·clickhouse部署教程
用户713335851562420 小时前
MySQL - InnoDB 的 Buffer Pool
mysql