thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-10 01:25:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Incorporated feedback

Browse Source
This commit is contained in:
rfraposa 2022-03-12 10:04:51 -06:00
parent 5a4466cec7
commit ecbdfdea08
8 changed files with 36 additions and 79 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/en/development/developer-instruction.md
View File

@ -259,7 +259,7 @@ Developing ClickHouse often requires loading realistic datasets. It is particula
CREATE TABLE test.hits ( 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.Key1` Array(String), `ParsedParams.Key2` Array(String), `ParsedParams.Key3` Array(String), `ParsedParams.Key4` Array(String), `ParsedParams.Key5` Array(String), `ParsedParams.ValueDouble` Array(Float64), IslandID FixedString(16), RequestNum UInt32, RequestTry UInt8) ENGINE = MergeTree PARTITION BY toYYYYMM(EventDate) SAMPLE BY intHash32(UserID) ORDER BY (CounterID, EventDate, intHash32(UserID), EventTime);
CREATE TABLE test.visits ( 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), IsClickHouse 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.ID` Array(UInt32), `Goals.Serial` Array(UInt32), `Goals.EventTime` Array(DateTime), `Goals.Price` Array(Int64), `Goals.OrderID` Array(String), `Goals.CurrencyID` Array(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.ID` Array(Int8), `TraficSource.SearchEngineID` Array(UInt16), `TraficSource.AdvEngineID` Array(UInt8), `TraficSource.PlaceID` Array(UInt16), `TraficSource.SocialSourceNetworkID` Array(UInt8), `TraficSource.Domain` Array(String), `TraficSource.SearchPhrase` Array(String), `TraficSource.SocialSourcePage` Array(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.Key1` Array(String), `ParsedParams.Key2` Array(String), `ParsedParams.Key3` Array(String), `ParsedParams.Key4` Array(String), `ParsedParams.Key5` Array(String), `ParsedParams.ValueDouble` Array(Float64), `Market.Type` Array(UInt8), `Market.GoalID` Array(UInt32), `Market.OrderID` Array(String), `Market.OrderPrice` Array(Int64), `Market.PP` Array(UInt32), `Market.DirectPlaceID` Array(UInt32), `Market.DirectOrderID` Array(UInt32), `Market.DirectBannerID` Array(UInt32), `Market.GoodID` Array(String), `Market.GoodName` Array(String), `Market.GoodQuantity` Array(Int32), `Market.GoodPrice` Array(Int64), IslandID FixedString(16)) ENGINE = CollapsingMergeTree(Sign) PARTITION BY toYYYYMM(StartDate) SAMPLE BY intHash32(UserID) ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID);
CREATE TABLE test.visits ( 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.ID` Array(UInt32), `Goals.Serial` Array(UInt32), `Goals.EventTime` Array(DateTime), `Goals.Price` Array(Int64), `Goals.OrderID` Array(String), `Goals.CurrencyID` Array(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.ID` Array(Int8), `TraficSource.SearchEngineID` Array(UInt16), `TraficSource.AdvEngineID` Array(UInt8), `TraficSource.PlaceID` Array(UInt16), `TraficSource.SocialSourceNetworkID` Array(UInt8), `TraficSource.Domain` Array(String), `TraficSource.SearchPhrase` Array(String), `TraficSource.SocialSourcePage` Array(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.Key1` Array(String), `ParsedParams.Key2` Array(String), `ParsedParams.Key3` Array(String), `ParsedParams.Key4` Array(String), `ParsedParams.Key5` Array(String), `ParsedParams.ValueDouble` Array(Float64), `Market.Type` Array(UInt8), `Market.GoalID` Array(UInt32), `Market.OrderID` Array(String), `Market.OrderPrice` Array(Int64), `Market.PP` Array(UInt32), `Market.DirectPlaceID` Array(UInt32), `Market.DirectOrderID` Array(UInt32), `Market.DirectBannerID` Array(UInt32), `Market.GoodID` Array(String), `Market.GoodName` Array(String), `Market.GoodQuantity` Array(Int32), `Market.GoodPrice` Array(Int64), IslandID FixedString(16)) ENGINE = CollapsingMergeTree(Sign) PARTITION BY toYYYYMM(StartDate) SAMPLE BY intHash32(UserID) ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID);
clickhouse-client --max_insert_block_size 100000 --query "INSERT INTO test.hits FORMAT TSV" < hits_v1.tsv
clickhouse-client --max_insert_block_size 100000 --query "INSERT INTO test.visits FORMAT TSV" < visits_v1.tsv

43
docs/en/development/tests.md
View File

@ -133,43 +133,6 @@ If the system clickhouse-server is already running and you do not want to stop i
`clickhouse` binary has almost no dependencies and works across wide range of Linux distributions. To quick and dirty test your changes on a server, you can simply `scp` your fresh built `clickhouse` binary to your server and then run it as in examples above.
## Testing Environment {#testing-environment}
Before publishing release as stable we deploy it on testing environment. Testing environment is a cluster that process 1/39 part of ClickHouse web analytics data. ClickHouse is upgraded without downtime on top of existing data. We look at first that data is processed successfully without lagging from realtime, the replication continue to work and there is no issues visible to the ClickHouse team. First check can be done in the following way:
``` sql
SELECT hostName() AS h, any(version()), any(uptime()), max(UTCEventTime), count() FROM remote('example01-01-{1..3}t', merge, hits) WHERE EventDate >= today() - 2 GROUP BY h ORDER BY h;
```
## Load Testing {#load-testing}
After deploying to testing environment we run load testing with queries from production cluster. This is done manually.
Make sure you have enabled `query_log` on your production cluster.
Collect query log for a day or more:
``` bash
$ clickhouse-client --query="SELECT DISTINCT query FROM system.query_log WHERE event_date = today() AND query LIKE '%ym:%' AND query NOT LIKE '%system.query_log%' AND type = 2 AND is_initial_query" > queries.tsv
```
This is a way complicated example. `type = 2` will filter queries that are executed successfully. `query LIKE '%ym:%'` is to select relevant queries from the web analytics data. `is_initial_query` is to select only queries that are initiated by client, not by ClickHouse itself (as parts of distributed query processing).
`scp` this log to your testing cluster and run it as following:
``` bash
$ clickhouse benchmark --concurrency 16 < queries.tsv
```
(probably you also want to specify a `--user`)
Then leave it for a night or weekend and go take a rest.
You should check that `clickhouse-server` does not crash, memory footprint is bounded and performance not degrading over time.
Precise query execution timings are not recorded and not compared due to high variability of queries and environment.
## Build Tests {#build-tests}
Build tests allow to check that build is not broken on various alternative configurations and on some foreign systems. These tests are automated as well.
@ -309,12 +272,6 @@ Alternatively you can try `uncrustify` tool to reformat your code. Configuration
We also use `codespell` to find typos in code. It is automated as well.
## Metrica B2B Tests {#metrica-b2b-tests}
Each ClickHouse release is tested with AppMetrica engines. Testing and stable versions of ClickHouse are deployed on VMs and run with a small copy of Metrica engine that is processing fixed sample of input data. Then results of two instances of Metrica engine are compared together.
These tests are automated by separate team. Due to high number of moving parts, tests are fail most of the time by completely unrelated reasons, that are very difficult to figure out. Most likely these tests have negative value for us. Nevertheless these tests was proved to be useful in about one or two times out of hundreds.
## Test Coverage {#test-coverage}
We also track test coverage but only for functional tests and only for clickhouse-server. It is performed on daily basis.

24
docs/en/engines/table-engines/integrations/s3.md
View File

@ -26,7 +26,7 @@ CREATE TABLE s3_engine_table (name String, value UInt32)
``` sql
CREATE TABLE s3_engine_table (name String, value UInt32)
ENGINE=S3('https://hostname/my-test-bucket-768/test-data.csv.gz', 'CSV', 'gzip')
ENGINE=S3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/test-data.csv.gz', 'CSV', 'gzip')
SETTINGS input_format_with_names_use_header = 0;
INSERT INTO s3_engine_table VALUES ('one', 1), ('two', 2), ('three', 3);
@ -75,19 +75,19 @@ Create table with files named `file-000.csv`, `file-001.csv`, … , `file-999.cs
``` sql
CREATE TABLE big_table (name String, value UInt32)
ENGINE = S3('https://hostname/my-bucket/my_folder/file-{000..999}.csv', 'CSV');
ENGINE = S3('https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/my_folder/file-{000..999}.csv', 'CSV');
```
**Example with wildcards 2**
Suppose we have several files in CSV format with the following URIs on S3:
- 'https://hostname/my-bucket/some_folder/some_file_1.csv'
- 'https://hostname/my-bucket/some_folder/some_file_2.csv'
- 'https://hostname/my-bucket/some_folder/some_file_3.csv'
- 'https://hostname/my-bucket/another_folder/some_file_1.csv'
- 'https://hostname/my-bucket/another_folder/some_file_2.csv'
- 'https://hostname/my-bucket/another_folder/some_file_3.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/some_folder/some_file_1.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/some_folder/some_file_2.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/some_folder/some_file_3.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/another_folder/some_file_1.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/another_folder/some_file_2.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/another_folder/some_file_3.csv'
There are several ways to make a table consisting of all six files:
@ -96,21 +96,21 @@ There are several ways to make a table consisting of all six files:
``` sql
CREATE TABLE table_with_range (name String, value UInt32)
ENGINE = S3('https://hostname/my-bucket/{some,another}_folder/some_file_{1..3}', 'CSV');
ENGINE = S3('https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/{some,another}_folder/some_file_{1..3}', 'CSV');
```
2. Take all files with `some_file_` prefix (there should be no extra files with such prefix in both folders):
``` sql
CREATE TABLE table_with_question_mark (name String, value UInt32)
ENGINE = S3('https://hostname/my-bucket/{some,another}_folder/some_file_?', 'CSV');
ENGINE = S3('https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/{some,another}_folder/some_file_?', 'CSV');
```
3. Take all the files in both folders (all files should satisfy format and schema described in query):
``` sql
CREATE TABLE table_with_asterisk (name String, value UInt32)
ENGINE = S3('https://hostname/my-bucket/{some,another}_folder/*', 'CSV');
ENGINE = S3('https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/{some,another}_folder/*', 'CSV');
```
## S3-related Settings {#settings}
@ -142,7 +142,7 @@ The following settings can be specified in configuration file for given endpoint
``` xml
<s3>
<endpoint-name>
<endpoint>https://hostname/my-test-bucket-768/</endpoint>
<endpoint>https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/</endpoint>
<!-- <access_key_id>ACCESS_KEY_ID</access_key_id> -->
<!-- <secret_access_key>SECRET_ACCESS_KEY</secret_access_key> -->
<!-- <region>us-west-1</region> -->

4
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -802,7 +802,7 @@ Configuration markup:
<disks>
<s3>
<type>s3</type>
<endpoint>https://hostname/my-bucket/root-path/</endpoint>
<endpoint>https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/root-path/</endpoint>
<access_key_id>your_access_key_id</access_key_id>
<secret_access_key>your_secret_access_key</secret_access_key>
<region></region>
@ -856,7 +856,7 @@ S3 disk can be configured as `main` or `cold` storage:
<disks>
<s3>
<type>s3</type>
<endpoint>https://hostname/my-bucket/root-path/</endpoint>
<endpoint>https://clickhouse-public-datasets.s3.amazonaws.com/my-bucket/root-path/</endpoint>
<access_key_id>your_access_key_id</access_key_id>
<secret_access_key>your_secret_access_key</secret_access_key>
</s3>

2
docs/en/getting-started/example-datasets/metrica.md
View File

@ -63,7 +63,7 @@ md5sum visits_v1.tsv
# Checksum should be equal to: 6dafe1a0f24e59e3fc2d0fed85601de6
# now create table
clickhouse-client --query "CREATE DATABASE IF NOT EXISTS datasets"
clickhouse-client --query "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), IsClickHouse 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"
clickhouse-client --query "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"
# import data
cat visits_v1.tsv | clickhouse-client --query "INSERT INTO datasets.visits_v1 FORMAT TSV" --max_insert_block_size=100000
# optionally you can optimize table

4
docs/en/getting-started/tutorial.md
View File

@ -287,7 +287,7 @@ CREATE TABLE tutorial.visits_v1
`URLCategories` Array(UInt16),
`URLRegions` Array(UInt32),
`RefererRegions` Array(UInt32),
`IsClickHouse` UInt8,
`IsYandex` UInt8,
`GoalReachesDepth` Int32,
`GoalReachesURL` Int32,
`GoalReachesAny` Int32,
@ -512,7 +512,7 @@ SELECT
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) = 'http://public_search')
WHERE (CounterID = 912887) AND (toYYYYMM(StartDate) = 201403) AND (domain(StartURL) = 'yandex.ru')
```
## Cluster Deployment {#cluster-deployment}

32
docs/en/sql-reference/table-functions/s3.md
View File

@ -26,11 +26,11 @@ A table with the specified structure for reading or writing data in the specifie
**Examples**
Selecting the first two rows from the table from S3 file `https://hostname/my-test-bucket-768/data.csv`:
Selecting the first two rows from the table from S3 file `https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/data.csv`:
``` sql
SELECT *
FROM s3('https://hostname/my-test-bucket-768/data.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32')
FROM s3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/data.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32')
LIMIT 2;
```
@ -45,7 +45,7 @@ The similar but from file with `gzip` compression:
``` sql
SELECT *
FROM s3('https://hostname/my-test-bucket-768/data.csv.gz', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32', 'gzip')
FROM s3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/data.csv.gz', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32', 'gzip')
LIMIT 2;
```
@ -60,20 +60,20 @@ LIMIT 2;
Suppose that we have several files with following URIs on S3:
- 'https://hostname/my-test-bucket-768/some_prefix/some_file_1.csv'
- 'https://hostname/my-test-bucket-768/some_prefix/some_file_2.csv'
- 'https://hostname/my-test-bucket-768/some_prefix/some_file_3.csv'
- 'https://hostname/my-test-bucket-768/some_prefix/some_file_4.csv'
- 'https://hostname/my-test-bucket-768/another_prefix/some_file_1.csv'
- 'https://hostname/my-test-bucket-768/another_prefix/some_file_2.csv'
- 'https://hostname/my-test-bucket-768/another_prefix/some_file_3.csv'
- 'https://hostname/my-test-bucket-768/another_prefix/some_file_4.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/some_prefix/some_file_1.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/some_prefix/some_file_2.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/some_prefix/some_file_3.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/some_prefix/some_file_4.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/another_prefix/some_file_1.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/another_prefix/some_file_2.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/another_prefix/some_file_3.csv'
- 'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/another_prefix/some_file_4.csv'
Count the amount of rows in files ending with numbers from 1 to 3:
``` sql
SELECT count(*)
FROM s3('https://hostname/my-test-bucket-768/{some,another}_prefix/some_file_{1..3}.csv', 'CSV', 'name String, value UInt32')
FROM s3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/{some,another}_prefix/some_file_{1..3}.csv', 'CSV', 'name String, value UInt32')
```
``` text
@ -86,7 +86,7 @@ Count the total amount of rows in all files in these two directories:
``` sql
SELECT count(*)
FROM s3('https://hostname/my-test-bucket-768/{some,another}_prefix/*', 'CSV', 'name String, value UInt32')
FROM s3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/{some,another}_prefix/*', 'CSV', 'name String, value UInt32')
```
``` text
@ -102,7 +102,7 @@ Count the total amount of rows in files named `file-000.csv`, `file-001.csv`,
``` sql
SELECT count(*)
FROM s3('https://hostname/my-test-bucket-768/big_prefix/file-{000..999}.csv', 'CSV', 'name String, value UInt32');
FROM s3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/big_prefix/file-{000..999}.csv', 'CSV', 'name String, value UInt32');
```
``` text
@ -114,14 +114,14 @@ FROM s3('https://hostname/my-test-bucket-768/big_prefix/file-{000..999}.csv', 'C
Insert data into file `test-data.csv.gz`:
``` sql
INSERT INTO FUNCTION s3('https://hostname/my-test-bucket-768/test-data.csv.gz', 'CSV', 'name String, value UInt32', 'gzip')
INSERT INTO FUNCTION s3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/test-data.csv.gz', 'CSV', 'name String, value UInt32', 'gzip')
VALUES ('test-data', 1), ('test-data-2', 2);
```
Insert data into file `test-data.csv.gz` from existing table:
``` sql
INSERT INTO FUNCTION s3('https://hostname/my-test-bucket-768/test-data.csv.gz', 'CSV', 'name String, value UInt32', 'gzip')
INSERT INTO FUNCTION s3('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/test-data.csv.gz', 'CSV', 'name String, value UInt32', 'gzip')
SELECT name, value FROM existing_table;
```

4
docs/ja/getting-started/tutorial.md
View File

@ -295,7 +295,7 @@ CREATE TABLE tutorial.visits_v1
`URLCategories` Array(UInt16),
`URLRegions` Array(UInt32),
`RefererRegions` Array(UInt32),
`IsClickHouse` UInt8,
`IsYandex` UInt8,
`GoalReachesDepth` Int32,
`GoalReachesURL` Int32,
`GoalReachesAny` Int32,
@ -523,7 +523,7 @@ SELECT
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) = 'http://public_search')
WHERE (CounterID = 912887) AND (toYYYYMM(StartDate) = 201403) AND (domain(StartURL) = 'yandex.ru')
```
## クラスタのデプロイ {#cluster-deployment}