mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-09-20 08:40:50 +00:00
benchmark: added clickhouse log files for new data[#CONV-8419]
This commit is contained in:
Pavel Kartavyy
parent
18b36efc4a
commit
b0fadc6216
@ -1,7 +1,7 @@
|
||||
#!/bin/bash
|
||||
|
||||
ck="clickhouse-client "
|
||||
test_table="hits_mt_test_10m"
|
||||
test_table="hits_100m"
|
||||
claster="self"
|
||||
|
||||
start_date="'2013-07-01'"
|
||||
@ -65,7 +65,7 @@ init_queries=(
|
||||
#"CREATE TABLE $test_table ( WatchID UInt64, JavaEnable UInt8, Title String, GoodEvent Int16, EventTime DateTime, EventDate Date, CounterID UInt32, ClientIP UInt32, RegionID UInt32, UserID UInt64, CounterClass Int8, OS UInt8, UserAgent UInt8, URL String, Referer String, Refresh UInt8, RefererCategoryID UInt16, RefererRegionID UInt32, URLCategoryID UInt16, URLRegionID 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, OriginalURL String, HID UInt32, IsOldCounter UInt8, IsEvent UInt8, IsParameter UInt8, DontCountHits UInt8, WithHash UInt8, HitColor FixedString(1), LocalEventTime DateTime, Age UInt8, Sex UInt8, Income UInt8, Interests UInt16, Robotness UInt8, RemoteIP UInt32, WindowName Int32, OpenerName Int32, HistoryLength Int16, BrowserLanguage FixedString(2), BrowserCountry FixedString(2), SocialNetwork String, SocialAction String, HTTPError UInt16, SendTiming UInt32, DNSTiming UInt32, ConnectTiming UInt32, ResponseStartTiming UInt32, ResponseEndTiming UInt32, FetchTiming UInt32, SocialSourceNetworkID UInt8, SocialSourcePage String, ParamPrice Int64, ParamOrderID String, ParamCurrency FixedString(3), ParamCurrencyID UInt16, 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 ) ENGINE = MergeTree(EventDate, intHash32(UserID), tuple(CounterID, EventDate, intHash32(UserID), EventTime), 8192);"
|
||||
|
||||
#modified table without uint
|
||||
"CREATE TABLE $test_table ( WatchID Int64, JavaEnable UInt8, Title String, GoodEvent Int16, EventTime DateTime, EventDate Date, CounterID UInt32, ClientIP UInt32, RegionID UInt32, UserID Int64, CounterClass Int8, OS UInt8, UserAgent UInt8, URL String, Referer String, Refresh UInt8, RefererCategoryID UInt16, RefererRegionID UInt32, URLCategoryID UInt16, URLRegionID 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 Int64, OriginalURL String, HID UInt32, IsOldCounter UInt8, IsEvent UInt8, IsParameter UInt8, DontCountHits UInt8, WithHash UInt8, HitColor FixedString(1), LocalEventTime DateTime, Age UInt8, Sex UInt8, Income UInt8, Interests UInt16, Robotness UInt8, RemoteIP UInt32, WindowName Int32, OpenerName Int32, HistoryLength Int16, BrowserLanguage FixedString(2), BrowserCountry FixedString(2), SocialNetwork String, SocialAction String, HTTPError UInt16, SendTiming UInt32, DNSTiming UInt32, ConnectTiming UInt32, ResponseStartTiming UInt32, ResponseEndTiming UInt32, FetchTiming UInt32, SocialSourceNetworkID UInt8, SocialSourcePage String, ParamPrice Int64, ParamOrderID String, ParamCurrency FixedString(3), ParamCurrencyID UInt16, OpenstatServiceName String, OpenstatCampaignID String, OpenstatAdID String, OpenstatSourceID String, UTMSource String, UTMMedium String, UTMCampaign String, UTMContent String, UTMTerm String, FromTag String, HasGCLID UInt8, RefererHash Int64, URLHash Int64, CLID UInt32 ) ENGINE = MergeTree(EventDate, intHash32(UserID), tuple(CounterID, EventDate, intHash32(UserID), EventTime), 8192);"
|
||||
"CREATE TABLE $test_table ( WatchID Int64, JavaEnable UInt8, Title String, GoodEvent Int16, EventTime DateTime, EventDate Date, CounterID UInt32, ClientIP UInt32, RegionID UInt32, UserID Int64, CounterClass Int8, OS UInt8, UserAgent UInt8, URL String, Referer String, Refresh UInt8, RefererCategoryID UInt16, RefererRegionID UInt32, URLCategoryID UInt16, URLRegionID 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 Int64, OriginalURL String, HID UInt32, IsOldCounter UInt8, IsEvent UInt8, IsParameter UInt8, DontCountHits UInt8, WithHash UInt8, HitColor FixedString(1), LocalEventTime DateTime, Age UInt8, Sex UInt8, Income UInt8, Interests UInt16, Robotness UInt8, RemoteIP UInt32, WindowName Int32, OpenerName Int32, HistoryLength Int16, BrowserLanguage FixedString(2), BrowserCountry FixedString(2), SocialNetwork String, SocialAction String, HTTPError UInt16, SendTiming UInt32, DNSTiming UInt32, ConnectTiming UInt32, ResponseStartTiming UInt32, ResponseEndTiming UInt32, FetchTiming UInt32, SocialSourceNetworkID UInt8, SocialSourcePage String, ParamPrice Int64, ParamOrderID String, ParamCurrency FixedString(3), ParamCurrencyID UInt16, OpenstatServiceName String, OpenstatCampaignID String, OpenstatAdID String, OpenstatSourceID String, UTMSource String, UTMMedium String, UTMCampaign String, UTMContent String, UTMTerm String, FromTag String, HasGCLID UInt8, RefererHash Int64, URLHash Int64, CLID UInt32, UserIDHash UInt64 ) ENGINE = MergeTree(EventDate, intHash32(UserID), tuple(CounterID, EventDate, intHash32(UserID), EventTime), 8192);"
|
||||
|
||||
)
|
||||
|
||||
|
||||
4
dbms/benchmark/clickhouse/conf.sh
Normal file
4
dbms/benchmark/clickhouse/conf.sh
Normal file
@ -0,0 +1,4 @@
|
||||
CONF_DIR=/home/kartavyy/benchmark/clickhouse
|
||||
expect_file=$CONF_DIR/expect.tcl
|
||||
test_file=$CONF_DIR/queries.sql
|
||||
etc_init_d_service=/etc/init.d/clickhouse-server-metrika-yandex
|
||||
109
dbms/benchmark/clickhouse/queries.sql
Normal file
109
dbms/benchmark/clickhouse/queries.sql
Normal file
@ -0,0 +1,109 @@
|
||||
SELECT count() FROM hits_10m;
|
||||
SELECT count() FROM hits_10m WHERE AdvEngineID != 0;
|
||||
SELECT sum(AdvEngineID), count(), avg(ResolutionWidth) FROM hits_10m ;
|
||||
SELECT sum(UserID) FROM hits_10m ;
|
||||
SELECT uniq(UserID) FROM hits_10m ;
|
||||
SELECT uniq(SearchPhrase) FROM hits_10m ;
|
||||
SELECT min(EventDate), max(EventDate) FROM hits_10m ;
|
||||
|
||||
SELECT AdvEngineID, count() FROM hits_10m WHERE AdvEngineID != 0 GROUP BY AdvEngineID ORDER BY count() DESC;
|
||||
-- мощная фильтрация. После фильтрации почти ничего не остаётся, но делаем ещё агрегацию.;
|
||||
|
||||
SELECT RegionID, uniq(UserID) AS u FROM hits_10m GROUP BY RegionID ORDER BY u DESC LIMIT 10;
|
||||
-- агрегация, среднее количество ключей.;
|
||||
|
||||
SELECT RegionID, sum(AdvEngineID), count() AS c, avg(ResolutionWidth), uniq(UserID) FROM hits_10m GROUP BY RegionID ORDER BY c DESC LIMIT 10;
|
||||
-- агрегация, среднее количество ключей, несколько агрегатных функций.;
|
||||
|
||||
SELECT MobilePhoneModel, uniq(UserID) AS u FROM hits_10m WHERE MobilePhoneModel != '' GROUP BY MobilePhoneModel ORDER BY u DESC LIMIT 10;
|
||||
-- мощная фильтрация по строкам, затем агрегация по строкам.;
|
||||
|
||||
SELECT MobilePhone, MobilePhoneModel, uniq(UserID) AS u FROM hits_10m WHERE MobilePhoneModel != '' GROUP BY MobilePhone, MobilePhoneModel ORDER BY u DESC LIMIT 10;
|
||||
-- мощная фильтрация по строкам, затем агрегация по паре из числа и строки.;
|
||||
|
||||
SELECT SearchPhrase, count() AS c FROM hits_10m WHERE SearchPhrase != '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
|
||||
-- средняя фильтрация по строкам, затем агрегация по строкам, большое количество ключей.;
|
||||
|
||||
SELECT SearchPhrase, uniq(UserID) AS u FROM hits_10m WHERE SearchPhrase != '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
|
||||
-- агрегация чуть сложнее.;
|
||||
|
||||
SELECT SearchEngineID, SearchPhrase, count() AS c FROM hits_10m WHERE SearchPhrase != '' GROUP BY SearchEngineID, SearchPhrase ORDER BY c DESC LIMIT 10;
|
||||
-- агрегация по числу и строке, большое количество ключей.;
|
||||
|
||||
SELECT UserID, count() FROM hits_10m GROUP BY UserID ORDER BY count() DESC LIMIT 10;
|
||||
-- агрегация по очень большому количеству ключей, может не хватить оперативки.;
|
||||
|
||||
SELECT UserID, SearchPhrase, count() FROM hits_10m GROUP BY UserID, SearchPhrase ORDER BY count() DESC LIMIT 10;
|
||||
-- ещё более сложная агрегация.;
|
||||
|
||||
SELECT UserID, SearchPhrase, count() FROM hits_10m GROUP BY UserID, SearchPhrase LIMIT 10;
|
||||
-- то же самое, но без сортировки.;
|
||||
|
||||
SELECT UserID, toMinute(EventTime) AS m, SearchPhrase, count() FROM hits_10m GROUP BY UserID, m, SearchPhrase ORDER BY count() DESC LIMIT 10;
|
||||
-- ещё более сложная агрегация, не стоит выполнять на больших таблицах.;
|
||||
|
||||
SELECT UserID FROM hits_10m WHERE UserID = 12345678901234567890;
|
||||
-- мощная фильтрация по столбцу типа UInt64.;
|
||||
|
||||
SELECT count() FROM hits_10m WHERE URL LIKE '%metrika%';
|
||||
-- фильтрация по поиску подстроки в строке.;
|
||||
|
||||
SELECT SearchPhrase, any(URL), count() AS c FROM hits_10m WHERE URL LIKE '%metrika%' AND SearchPhrase != '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
|
||||
-- вынимаем большие столбцы, фильтрация по строке.;
|
||||
|
||||
SELECT SearchPhrase, any(URL), any(Title), count() AS c, uniq(UserID) FROM hits_10m WHERE Title LIKE '%Яндекс%' AND URL NOT LIKE '%.yandex.%' AND SearchPhrase != '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
|
||||
-- чуть больше столбцы.;
|
||||
|
||||
SELECT * FROM hits_10m WHERE URL LIKE '%metrika%' ORDER BY EventTime LIMIT 10;
|
||||
-- плохой запрос - вынимаем все столбцы.;
|
||||
|
||||
SELECT SearchPhrase FROM hits_10m WHERE SearchPhrase != '' ORDER BY EventTime LIMIT 10;
|
||||
-- большая сортировка.;
|
||||
|
||||
SELECT SearchPhrase FROM hits_10m WHERE SearchPhrase != '' ORDER BY SearchPhrase LIMIT 10;
|
||||
-- большая сортировка по строкам.;
|
||||
|
||||
SELECT SearchPhrase FROM hits_10m WHERE SearchPhrase != '' ORDER BY EventTime, SearchPhrase LIMIT 10;
|
||||
-- большая сортировка по кортежу.;
|
||||
|
||||
SELECT CounterID, avg(length(URL)) AS l, count() AS c FROM hits_10m WHERE URL != '' GROUP BY CounterID HAVING c > 100000 ORDER BY l DESC LIMIT 25;
|
||||
-- считаем средние длины URL для крупных счётчиков.;
|
||||
|
||||
SELECT domainWithoutWWW(Referer) AS key, avg(length(Referer)) AS l, count() AS c, any(Referer) FROM hits_10m WHERE Referer != '' GROUP BY key HAVING c > 100000 ORDER BY l DESC LIMIT 25;
|
||||
-- то же самое, но с разбивкой по доменам.;
|
||||
|
||||
SELECT sum(ResolutionWidth), sum(ResolutionWidth + 1), sum(ResolutionWidth + 2), sum(ResolutionWidth + 3), sum(ResolutionWidth + 4), sum(ResolutionWidth + 5), sum(ResolutionWidth + 6), sum(ResolutionWidth + 7), sum(ResolutionWidth + 8), sum(ResolutionWidth + 9), sum(ResolutionWidth + 10), sum(ResolutionWidth + 11), sum(ResolutionWidth + 12), sum(ResolutionWidth + 13), sum(ResolutionWidth + 14), sum(ResolutionWidth + 15), sum(ResolutionWidth + 16), sum(ResolutionWidth + 17), sum(ResolutionWidth + 18), sum(ResolutionWidth + 19), sum(ResolutionWidth + 20), sum(ResolutionWidth + 21), sum(ResolutionWidth + 22), sum(ResolutionWidth + 23), sum(ResolutionWidth + 24), sum(ResolutionWidth + 25), sum(ResolutionWidth + 26), sum(ResolutionWidth + 27), sum(ResolutionWidth + 28), sum(ResolutionWidth + 29), sum(ResolutionWidth + 30), sum(ResolutionWidth + 31), sum(ResolutionWidth + 32), sum(ResolutionWidth + 33), sum(ResolutionWidth + 34), sum(ResolutionWidth + 35), sum(ResolutionWidth + 36), sum(ResolutionWidth + 37), sum(ResolutionWidth + 38), sum(ResolutionWidth + 39), sum(ResolutionWidth + 40), sum(ResolutionWidth + 41), sum(ResolutionWidth + 42), sum(ResolutionWidth + 43), sum(ResolutionWidth + 44), sum(ResolutionWidth + 45), sum(ResolutionWidth + 46), sum(ResolutionWidth + 47), sum(ResolutionWidth + 48), sum(ResolutionWidth + 49), sum(ResolutionWidth + 50), sum(ResolutionWidth + 51), sum(ResolutionWidth + 52), sum(ResolutionWidth + 53), sum(ResolutionWidth + 54), sum(ResolutionWidth + 55), sum(ResolutionWidth + 56), sum(ResolutionWidth + 57), sum(ResolutionWidth + 58), sum(ResolutionWidth + 59), sum(ResolutionWidth + 60), sum(ResolutionWidth + 61), sum(ResolutionWidth + 62), sum(ResolutionWidth + 63), sum(ResolutionWidth + 64), sum(ResolutionWidth + 65), sum(ResolutionWidth + 66), sum(ResolutionWidth + 67), sum(ResolutionWidth + 68), sum(ResolutionWidth + 69), sum(ResolutionWidth + 70), sum(ResolutionWidth + 71), sum(ResolutionWidth + 72), sum(ResolutionWidth + 73), sum(ResolutionWidth + 74), sum(ResolutionWidth + 75), sum(ResolutionWidth + 76), sum(ResolutionWidth + 77), sum(ResolutionWidth + 78), sum(ResolutionWidth + 79), sum(ResolutionWidth + 80), sum(ResolutionWidth + 81), sum(ResolutionWidth + 82), sum(ResolutionWidth + 83), sum(ResolutionWidth + 84), sum(ResolutionWidth + 85), sum(ResolutionWidth + 86), sum(ResolutionWidth + 87), sum(ResolutionWidth + 88), sum(ResolutionWidth + 89) FROM hits_10m ;
|
||||
-- много тупых агрегатных функций.;
|
||||
|
||||
SELECT SearchEngineID, ClientIP, count() AS c, sum(Refresh), avg(ResolutionWidth) FROM hits_10m WHERE SearchPhrase != '' GROUP BY SearchEngineID, ClientIP ORDER BY c DESC LIMIT 10;
|
||||
-- сложная агрегация, для больших таблиц может не хватить оперативки.;
|
||||
|
||||
SELECT WatchID, ClientIP, count() AS c, sum(Refresh), avg(ResolutionWidth) FROM hits_10m WHERE SearchPhrase != '' GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
|
||||
-- агрегация по двум полям, которая ничего не агрегирует. Для больших таблиц выполнить не получится.;
|
||||
|
||||
SELECT WatchID, ClientIP, count() AS c, sum(Refresh), avg(ResolutionWidth) FROM hits_10m GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
|
||||
-- то же самое, но ещё и без фильтрации.;
|
||||
|
||||
SELECT URL, count() AS c FROM hits_10m GROUP BY URL ORDER BY c DESC LIMIT 10;
|
||||
-- агрегация по URL.;
|
||||
|
||||
SELECT 1, URL, count() AS c FROM hits_10m GROUP BY 1, URL ORDER BY c DESC LIMIT 10;
|
||||
-- агрегация по URL и числу.;
|
||||
|
||||
SELECT ClientIP AS x, x - 1, x - 2, x - 3, count() AS c FROM hits_10m GROUP BY x, x - 1, x - 2, x - 3 ORDER BY c DESC LIMIT 10;
|
||||
|
||||
SELECT URL, count() AS PageViews FROM hits_10m WHERE CounterID = 34 AND EventDate >= toDate('2013-07-01') AND EventDate <= toDate('2013-07-31') AND NOT DontCountHits AND NOT Refresh AND notEmpty(URL) GROUP BY URL ORDER BY PageViews DESC LIMIT 10;
|
||||
|
||||
|
||||
SELECT Title, count() AS PageViews FROM hits_10m WHERE CounterID = 34 AND EventDate >= toDate('2013-07-01') AND EventDate <= toDate('2013-07-31') AND NOT DontCountHits AND NOT Refresh AND notEmpty(Title) GROUP BY Title ORDER BY PageViews DESC LIMIT 10;
|
||||
|
||||
SELECT URL, count() AS PageViews FROM hits_10m WHERE CounterID = 34 AND EventDate >= toDate('2013-07-01') AND EventDate <= toDate('2013-07-31') AND NOT Refresh AND IsLink AND NOT IsDownload GROUP BY URL ORDER BY PageViews DESC LIMIT 1000;
|
||||
|
||||
SELECT TraficSourceID, SearchEngineID, AdvEngineID, ((SearchEngineID = 0 AND AdvEngineID = 0) ? Referer : '') AS Src, URL AS Dst, count() AS PageViews FROM hits_10m WHERE CounterID = 34 AND EventDate >= toDate('2013-07-01') AND EventDate <= toDate('2013-07-31') AND NOT Refresh GROUP BY TraficSourceID, SearchEngineID, AdvEngineID, Src, Dst ORDER BY PageViews DESC LIMIT 1000;
|
||||
|
||||
SELECT URLHash, EventDate, count() AS PageViews FROM hits_10m WHERE CounterID = 34 AND EventDate >= toDate('2013-07-01') AND EventDate <= toDate('2013-07-31') AND NOT Refresh AND TraficSourceID IN (-1, 6) AND RefererHash = halfMD5('http://example.ru/') GROUP BY URLHash, EventDate ORDER BY PageViews DESC LIMIT 100;
|
||||
|
||||
|
||||
SELECT WindowClientWidth, WindowClientHeight, count() AS PageViews FROM hits_10m WHERE CounterID = 34 AND EventDate >= toDate('2013-07-01') AND EventDate <= toDate('2013-07-31') AND NOT Refresh AND NOT DontCountHits AND URLHash = halfMD5('http://example.ru/') GROUP BY WindowClientWidth, WindowClientHeight ORDER BY PageViews DESC LIMIT 10000;
|
||||
|
||||
SELECT toStartOfMinute(EventTime) AS Minute, count() AS PageViews FROM hits_10m WHERE CounterID = 34 AND EventDate >= toDate('2013-07-01') AND EventDate <= toDate('2013-07-02') AND NOT Refresh AND NOT DontCountHits GROUP BY Minute ORDER BY Minute;
|
||||
Loading…
Reference in New Issue
Block a user