跟着官网学clickhouse
一、简介
Clickhouse是Yandex在2016年6月15日开源的一个分布式列式的实时olap数据仓库,支持索引,并行化运行,大单表查询性能极佳;多个大厂包括阿里、腾讯、美团都在使用clickhouse。
二、安装
版本:
操作系统:
CentOS Linux release 7.6.1810 (Core)
Clickhouse:
最新稳定版
1 安装仓库和包管理工具yum-utils
sudo yum install -y yum-utils
2 导入clickhouse秘钥
sudo rpm --import https://repo.clickhouse.tech/CLICKHOUSE-KEY.GPG
3 添加clickhouse仓库
sudo yum-config-manager --add-repo https://repo.clickhouse.tech/rpm/clickhouse.repo
4 安装clickhouse服务端和客户端
sudo yum install -y clickhouse-server clickhouse-client
5 启动clickhouse服务端
注意:官方命令无法启动
sudo /etc/init.d/clickhouse-server start
启动命令修改为如下可以正常启动
systemctl start clickhouse-server.service
6 以交互式命令行模式启动clickhouse客户端
clickhouse-client
7 helloworld
select 1;
三、示例运行
1 创建数据库
CREATE DATABASE IF NOT EXISTS tutorial;
show databases;
use tutorial;
2 创建测试表
2.1 退出当前客户端,以多行模式重新启动客户端
客户端默认以单行模式启动,创建表需要执行多行sql,所以这里需要先退出客户端,再以多行模式启动客户端
exit
clickhouse-client -m
use tutorial;
2.2 执行2个建表sql
CREATE TABLE tutorial.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);
CREATE TABLE tutorial.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);
2.3 查看创建的表
这里如果查询不到表可以检查一下数据库名是不是之前创建的数据库名
show tables;
exit;
退出客户端
3 下载测试数据
curl https://datasets.clickhouse.tech/hits/tsv/hits_v1.tsv.xz | unxz --threads=`nproc` > hits_v1.tsv
curl https://datasets.clickhouse.tech/visits/tsv/visits_v1.tsv.xz | unxz --threads=`nproc` > visits_v1.tsv
我这里大概10分钟下载完毕
4 导入数据到上面创建的表
clickhouse-client --query "INSERT INTO tutorial.hits_v1 FORMAT TSV" --max_insert_block_size=100000 < hits_v1.tsv
clickhouse-client --query "INSERT INTO tutorial.visits_v1 FORMAT TSV" --max_insert_block_size=100000 < visits_v1.tsv
5 优化存储(可选)
导入完成后有一个可选操作是优化存储
clickhouse-client --query "OPTIMIZE TABLE tutorial.hits_v1 FINAL"
clickhouse-client --query "OPTIMIZE TABLE tutorial.visits_v1 FINAL"
6 查询数量
clickhouse-client --query "SELECT COUNT(*) FROM tutorial.hits_v1"
clickhouse-client --query "SELECT COUNT(*) FROM tutorial.visits_v1"
7 执行示例查询
多行交互式启动客户端
clickhouse-client -m
执行sql
SELECT
StartURL AS URL,
AVG(Duration) AS AvgDuration
FROM tutorial.visits_v1
WHERE StartDate BETWEEN '2014-03-23' AND '2014-03-30'
GROUP BY URL
ORDER BY AvgDuration DESC
LIMIT 10;
执行第二个示例sql
SELECT
sum(Sign) AS visits,
sumIf(Sign, has(Goals.ID, 1105530)) AS goal_visits,
(100. * goal_visits) / visits AS goal_percent
FROM tutorial.visits_v1
WHERE (CounterID = 912887) AND (toYYYYMM(StartDate) = 201403) AND (domain(StartURL) = 'yandex.ru');
虽然数据量不大,不过仍旧可以看到性能非常出色