第一章 ClickHouse单节点安装部署

目录

一、说明及准备

二、安装部署

2.1 环境准备

2.2 安装部署

2.2.1 解压安装

2.2.2 目录文件介绍

2.2.3 安装配置

2.2.4 服务启动关闭

2.3 测试

2.3.1 数据库查看

2.3.2 示例数据测试

---

一、说明及准备

操作系统	CentOS Linux release 7.9.2009
ClickHouse	22.3.2.2
用户	root
安装目录	/chbase
主机名	centos01

1、检查当前CPU是否支持SSE 4.2的命令

grep -q sse4_2 /proc/cpuinfo && echo "SSE 4.2 supported" || echo "SSE 4.2 not supported"

 官方预构建的二进制文件针对x86_64进行编译，并使用SSE 4.2指令集，如果不支持SSE指令集，则需要通过源码编译特定版本进行安装。

2、创建安装目录

mkdir /chbase

3、安装方式 - From Tgz Archives

官方链接：https://clickhouse.com/docs/en/getting-started/install

 下载tgz包

clickhouse-client-22.3.2.2.tgz

clickhouse-common-static-22.3.2.2.tgz

clickhouse-common-static-dbg-22.3.2.2.tgz

clickhouse-server-22.3.2.2.tgz

二、安装部署

2.1 环境准备

1、设置FQDN

# 设置服务器FQDN（全称域名）

hostnamectl --static set-hostname centos01.clh.com

# 查看设置结果

hostname -f

# 修改hosts

vim /etc/hosts

192.168.178.61    centos01.clh.com centos01

 2、上传4个安装包到/chbase/setup目录下

2.2 安装部署

2.2.1 解压安装

1、安装clickhouse-common-static-22.3.2.2.tgz

# 解压

tar -zxf clickhouse-common-static-22.3.2.2.tgz

#安装

cd clickhouse-common-static-22.3.2.2/install/

./doinst.sh

2、安装clickhouse-common-static-dbg-22.3.2.2.tgz 

# 解压

tar -zxvf clickhouse-common-static-dbg-22.3.2.2.tgz

# 安装

cd clickhouse-common-static-dbg-22.3.2.2/install/

./doinst.sh

 3、安装clickhouse-server-22.3.2.2.tgz

# 解压

tar -zxvf clickhouse-server-22.3.2.2.tgz

# 安装

cd clickhouse-server-22.3.2.2/install/

./doinst.sh

4、安装

# 解压

tar -zxvf clickhouse-client-22.3.2.2.tgz

# 安装

cd clickhouse-client-22.3.2.2/install/

./doinst.sh

5、目录 授权

chown -R clickhouse:clickhouse /chbase/

2.2.2 目录文件介绍

服务配置目录	/etc/clickhouse-server
默认数据存储目录	/var/lib/clickhouse
默认日志存储目录	/var/log/clickhouse-server
可执行文件目录	/usr/bin
文件句柄数配置	/etc/security/limits.d/clickhouse.conf
定时任务配置	/etc/cron.d/clickhouse-server

2.2.3 安装配置

vim /etc/clickhouse-server/config.xml

# 修改数据保存目录

<path>/chbase/data/</path>

# 修改临时文件保存目录

<tmp_path>/chbase/data/tmp/</tmp_path>

# 用户文件目录

<user_files_path>/chbase/data/user_files/</user_files_path>

2.2.4 服务启动关闭

# 服务启动

systemctl start clickhouse-server

# 查看状态

systemctl status clickhouse-server

# 服务关闭

systemctl stop clickhouse-server

2.3 测试

2.3.1 数据库查看

clickhouse-client --password 123456

clickhouse-client -h centos01 --password 123456

# 进入clickhouse-client命令行执行，查看数据库

show databases;

2.3.2 示例数据测试

1、测试数据下载

下载链接：Anonymized Web Analytics Data | ClickHouse Docs

点击数据：https://datasets.clickhouse.com/hits/tsv/hits_v1.tsv.xz

访问数据：https://datasets.clickhouse.com/visits/tsv/visits_v1.tsv.xz

上传数据到/chbase/setup

2、创建库表

# 进入clickhouse-client命令行执行
clickhouse-client --password 123456

# 创建数据库

CREATE DATABASE IF NOT EXISTS datasets;

# 创建表hits_v1

CREATE TABLE datasets.hits_v1 ( WatchID UInt64,  JavaEnable UInt8,  Title String,  GoodEvent Int16,  EventTime DateTime,  EventDate Date,  CounterID UInt32,  ClientIP UInt32,  ClientIP6 FixedString(16),  RegionID UInt32,  UserID UInt64,  CounterClass Int8,  OS UInt8,  UserAgent UInt8,  URL String,  Referer String,  URLDomain String,  RefererDomain String,  Refresh UInt8,  IsRobot UInt8,  RefererCategories Array(UInt16),  URLCategories Array(UInt16), URLRegions Array(UInt32),  RefererRegions Array(UInt32),  ResolutionWidth UInt16,  ResolutionHeight UInt16,  ResolutionDepth UInt8,  FlashMajor UInt8, FlashMinor UInt8,  FlashMinor2 String,  NetMajor UInt8,  NetMinor UInt8, UserAgentMajor UInt16,  UserAgentMinor FixedString(2),  CookieEnable UInt8, JavascriptEnable UInt8,  IsMobile UInt8,  MobilePhone UInt8,  MobilePhoneModel String,  Params String,  IPNetworkID UInt32,  TraficSourceID Int8, SearchEngineID UInt16,  SearchPhrase String,  AdvEngineID UInt8,  IsArtifical UInt8,  WindowClientWidth UInt16,  WindowClientHeight UInt16,  ClientTimeZone Int16,  ClientEventTime DateTime,  SilverlightVersion1 UInt8, SilverlightVersion2 UInt8,  SilverlightVersion3 UInt32,  SilverlightVersion4 UInt16,  PageCharset String,  CodeVersion UInt32,  IsLink UInt8,  IsDownload UInt8,  IsNotBounce UInt8,  FUniqID UInt64,  HID UInt32,  IsOldCounter UInt8, IsEvent UInt8,  IsParameter UInt8,  DontCountHits UInt8,  WithHash UInt8, HitColor FixedString(1),  UTCEventTime DateTime,  Age UInt8,  Sex UInt8,  Income UInt8,  Interests UInt16,  Robotness UInt8,  GeneralInterests Array(UInt16), RemoteIP UInt32,  RemoteIP6 FixedString(16),  WindowName Int32,  OpenerName Int32,  HistoryLength Int16,  BrowserLanguage FixedString(2),  BrowserCountry FixedString(2),  SocialNetwork String,  SocialAction String,  HTTPError UInt16, SendTiming Int32,  DNSTiming Int32,  ConnectTiming Int32,  ResponseStartTiming Int32,  ResponseEndTiming Int32,  FetchTiming Int32,  RedirectTiming Int32, DOMInteractiveTiming Int32,  DOMContentLoadedTiming Int32,  DOMCompleteTiming Int32,  LoadEventStartTiming Int32,  LoadEventEndTiming Int32, NSToDOMContentLoadedTiming Int32,  FirstPaintTiming Int32,  RedirectCount Int8, SocialSourceNetworkID UInt8,  SocialSourcePage String,  ParamPrice Int64, ParamOrderID String,  ParamCurrency FixedString(3),  ParamCurrencyID UInt16, GoalsReached Array(UInt32),  OpenstatServiceName String,  OpenstatCampaignID String,  OpenstatAdID String,  OpenstatSourceID String,  UTMSource String, UTMMedium String,  UTMCampaign String,  UTMContent String,  UTMTerm String, FromTag String,  HasGCLID UInt8,  RefererHash UInt64,  URLHash UInt64,  CLID UInt32,  YCLID UInt64,  ShareService String,  ShareURL String,  ShareTitle String,  ParsedParams Nested(Key1 String,  Key2 String, Key3 String, Key4 String, Key5 String,  ValueDouble Float64),  IslandID FixedString(16),  RequestNum UInt32,  RequestTry UInt8) ENGINE = MergeTree() PARTITION BY toYYYYMM(EventDate) ORDER BY (CounterID, EventDate, intHash32(UserID)) SAMPLE BY intHash32(UserID) SETTINGS index_granularity = 8192;



# create visits table

CREATE TABLE datasets.visits_v1 ( CounterID UInt32,  StartDate Date,  Sign Int8,  IsNew UInt8,  VisitID UInt64,  UserID UInt64,  StartTime DateTime,  Duration UInt32,  UTCStartTime DateTime,  PageViews Int32,  Hits Int32,  IsBounce UInt8,  Referer String,  StartURL String,  RefererDomain String,  StartURLDomain String,  EndURL String,  LinkURL String,  IsDownload UInt8,  TraficSourceID Int8,  SearchEngineID UInt16,  SearchPhrase String,  AdvEngineID UInt8,  PlaceID Int32,  RefererCategories Array(UInt16),  URLCategories Array(UInt16),  URLRegions Array(UInt32),  RefererRegions Array(UInt32),  IsYandex UInt8,  GoalReachesDepth Int32,  GoalReachesURL Int32,  GoalReachesAny Int32,  SocialSourceNetworkID UInt8,  SocialSourcePage String,  MobilePhoneModel String,  ClientEventTime DateTime,  RegionID UInt32,  ClientIP UInt32,  ClientIP6 FixedString(16),  RemoteIP UInt32,  RemoteIP6 FixedString(16),  IPNetworkID UInt32,  SilverlightVersion3 UInt32,  CodeVersion UInt32,  ResolutionWidth UInt16,  ResolutionHeight UInt16,  UserAgentMajor UInt16,  UserAgentMinor UInt16,  WindowClientWidth UInt16,  WindowClientHeight UInt16,  SilverlightVersion2 UInt8,  SilverlightVersion4 UInt16,  FlashVersion3 UInt16,  FlashVersion4 UInt16,  ClientTimeZone Int16,  OS UInt8,  UserAgent UInt8,  ResolutionDepth UInt8,  FlashMajor UInt8,  FlashMinor UInt8,  NetMajor UInt8,  NetMinor UInt8,  MobilePhone UInt8,  SilverlightVersion1 UInt8,  Age UInt8,  Sex UInt8,  Income UInt8,  JavaEnable UInt8,  CookieEnable UInt8,  JavascriptEnable UInt8,  IsMobile UInt8,  BrowserLanguage UInt16,  BrowserCountry UInt16,  Interests UInt16,  Robotness UInt8,  GeneralInterests Array(UInt16),  Params Array(String),  Goals Nested(ID UInt32, Serial UInt32, EventTime DateTime,  Price Int64,  OrderID String, CurrencyID UInt32),  WatchIDs Array(UInt64),  ParamSumPrice Int64,  ParamCurrency FixedString(3),  ParamCurrencyID UInt16,  ClickLogID UInt64,  ClickEventID Int32,  ClickGoodEvent Int32,  ClickEventTime DateTime,  ClickPriorityID Int32,  ClickPhraseID Int32,  ClickPageID Int32,  ClickPlaceID Int32,  ClickTypeID Int32,  ClickResourceID Int32,  ClickCost UInt32,  ClickClientIP UInt32,  ClickDomainID UInt32,  ClickURL String,  ClickAttempt UInt8,  ClickOrderID UInt32,  ClickBannerID UInt32,  ClickMarketCategoryID UInt32,  ClickMarketPP UInt32,  ClickMarketCategoryName String,  ClickMarketPPName String,  ClickAWAPSCampaignName String,  ClickPageName String,  ClickTargetType UInt16,  ClickTargetPhraseID UInt64,  ClickContextType UInt8,  ClickSelectType Int8,  ClickOptions String,  ClickGroupBannerID Int32,  OpenstatServiceName String,  OpenstatCampaignID String,  OpenstatAdID String,  OpenstatSourceID String,  UTMSource String,  UTMMedium String,  UTMCampaign String,  UTMContent String,  UTMTerm String,  FromTag String,  HasGCLID UInt8,  FirstVisit DateTime,  PredLastVisit Date,  LastVisit Date,  TotalVisits UInt32,  TraficSource    Nested(ID Int8,  SearchEngineID UInt16, AdvEngineID UInt8, PlaceID UInt16, SocialSourceNetworkID UInt8, Domain String, SearchPhrase String, SocialSourcePage String),  Attendance FixedString(16),  CLID UInt32,  YCLID UInt64,  NormalizedRefererHash UInt64,  SearchPhraseHash UInt64,  RefererDomainHash UInt64,  NormalizedStartURLHash UInt64,  StartURLDomainHash UInt64,  NormalizedEndURLHash UInt64,  TopLevelDomain UInt64,  URLScheme UInt64,  OpenstatServiceNameHash UInt64,  OpenstatCampaignIDHash UInt64,  OpenstatAdIDHash UInt64,  OpenstatSourceIDHash UInt64,  UTMSourceHash UInt64,  UTMMediumHash UInt64,  UTMCampaignHash UInt64,  UTMContentHash UInt64,  UTMTermHash UInt64,  FromHash UInt64,  WebVisorEnabled UInt8,  WebVisorActivity UInt32,  ParsedParams    Nested(Key1 String,  Key2 String,  Key3 String,  Key4 String, Key5 String, ValueDouble    Float64),  Market Nested(Type UInt8, GoalID UInt32, OrderID String,  OrderPrice Int64,  PP UInt32,  DirectPlaceID UInt32,  DirectOrderID  UInt32,  DirectBannerID UInt32,  GoodID String, GoodName String, GoodQuantity Int32,  GoodPrice Int64),  IslandID FixedString(16)) ENGINE = CollapsingMergeTree(Sign) PARTITION BY toYYYYMM(StartDate) ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID) SAMPLE BY intHash32(UserID) SETTINGS index_granularity = 8192;

3、导入数据

# hits数据

cat /chbase/setup/hits_v1.tsv | clickhouse-client --password 123456 --query "INSERT INTO datasets.hits_v1 FORMAT TSV" --max_insert_block_size=100000

# 查看数据条数

clickhouse-client --query "SELECT COUNT(*) FROM datasets.hits_v1" --password 123456

# visits数据

cat visits_v1.tsv | clickhouse-client --query "INSERT INTO datasets.visits_v1 FORMAT TSV" --max_insert_block_size=100000

4、查询测试

# 查看数据条数

clickhouse-client --query "SELECT COUNT(*) FROM datasets.visits_v1" --password 123456

# 优化

clickhouse-client --query "OPTIMIZE TABLE datasets.hits_v1" --password 123456

clickhouse-client --query "OPTIMIZE TABLE datasets.visits_v1" --password 123456

# join 查询
clickhouse-client --query "SELECT
    EventDate,
    hits,
    visits
FROM
(
    SELECT
        EventDate,
        count() AS hits
    FROM datasets.hits_v1
    GROUP BY EventDate
) ANY LEFT JOIN
(
    SELECT
        StartDate AS EventDate,
        sum(Sign) AS visits
    FROM datasets.visits_v1
    GROUP BY EventDate
) USING EventDate
ORDER BY hits DESC
LIMIT 10
SETTINGS joined_subquery_requires_alias = 0
FORMAT PrettyCompact"

# 查询页面平均启动时间

SELECT StartURL AS URL, AVG(Duration) AS AVG_DURATION FROM visits_v1 GROUP BY URL ORDER BY AVG_DURATION DESC LIMIT 10;