From e54d42b66a4a2120319ebfadcfbd57dd0c0f7a3a Mon Sep 17 00:00:00 2001 From: Zhou Sun Date: Tue, 7 Jan 2025 13:46:51 -0800 Subject: [PATCH 1/2] add pg_mooncake --- pg_mooncake/benchmark.sh | 22 ++++++ pg_mooncake/create.sql | 112 +++++++++++++++++++++++++++ pg_mooncake/queries.sql | 43 ++++++++++ pg_mooncake/results/c6a.4xlarge.json | 58 ++++++++++++++ pg_mooncake/run.sh | 12 +++ 5 files changed, 247 insertions(+) create mode 100755 pg_mooncake/benchmark.sh create mode 100644 pg_mooncake/create.sql create mode 100644 pg_mooncake/queries.sql create mode 100644 pg_mooncake/results/c6a.4xlarge.json create mode 100755 pg_mooncake/run.sh diff --git a/pg_mooncake/benchmark.sh b/pg_mooncake/benchmark.sh new file mode 100755 index 0000000000..91cbc75b42 --- /dev/null +++ b/pg_mooncake/benchmark.sh @@ -0,0 +1,22 @@ +#!/bin/bash + + +sudo apt-get update +sudo apt-get install -y docker.io +sudo apt-get install -y postgresql-client + +wget --no-verbose --continue https://datasets.clickhouse.com/hits_compatible/athena/hits.parquet +sudo docker run -d --name pg_mooncake -p 5432:5432 -e POSTGRES_HOST_AUTH_METHOD=trust - -v ./hits.parquet:/tmp/hits.parquet mooncakelabs/pg_mooncake + +sleep 5 +psql postgres://postgres:pg_mooncake@localhost:5432/postgres -f create.sql + +# COPY 99997497 +# Time: 576219.151 ms (09:36.219) + +./run.sh 2>&1 | tee log.txt + +sudo docker exec -it pg_mooncake du -bcs /var/lib/postgresql/data + +cat log.txt | grep -oP 'Time: \d+\.\d+ ms' | sed -r -e 's/Time: ([0-9]+\.[0-9]+) ms/\1/' | + awk '{ if (i % 3 == 0) { printf "[" }; printf $1 / 1000; if (i % 3 != 2) { printf "," } else { print "]," }; ++i; }' \ No newline at end of file diff --git a/pg_mooncake/create.sql b/pg_mooncake/create.sql new file mode 100644 index 0000000000..863ce3cf02 --- /dev/null +++ b/pg_mooncake/create.sql @@ -0,0 +1,112 @@ +CREATE TABLE hits +( + WatchID BIGINT NOT NULL, + JavaEnable SMALLINT NOT NULL, + Title TEXT NOT NULL, + GoodEvent SMALLINT NOT NULL, + EventTime TIMESTAMP NOT NULL, + EventDate Date NOT NULL, + CounterID INTEGER NOT NULL, + ClientIP INTEGER NOT NULL, + RegionID INTEGER NOT NULL, + UserID BIGINT NOT NULL, + CounterClass SMALLINT NOT NULL, + OS SMALLINT NOT NULL, + UserAgent SMALLINT NOT NULL, + URL TEXT NOT NULL, + Referer TEXT NOT NULL, + IsRefresh SMALLINT NOT NULL, + RefererCategoryID SMALLINT NOT NULL, + RefererRegionID INTEGER NOT NULL, + URLCategoryID SMALLINT NOT NULL, + URLRegionID INTEGER NOT NULL, + ResolutionWidth SMALLINT NOT NULL, + ResolutionHeight SMALLINT NOT NULL, + ResolutionDepth SMALLINT NOT NULL, + FlashMajor SMALLINT NOT NULL, + FlashMinor SMALLINT NOT NULL, + FlashMinor2 TEXT NOT NULL, + NetMajor SMALLINT NOT NULL, + NetMinor SMALLINT NOT NULL, + UserAgentMajor SMALLINT NOT NULL, + UserAgentMinor VARCHAR(255) NOT NULL, + CookieEnable SMALLINT NOT NULL, + JavascriptEnable SMALLINT NOT NULL, + IsMobile SMALLINT NOT NULL, + MobilePhone SMALLINT NOT NULL, + MobilePhoneModel TEXT NOT NULL, + Params TEXT NOT NULL, + IPNetworkID INTEGER NOT NULL, + TraficSourceID SMALLINT NOT NULL, + SearchEngineID SMALLINT NOT NULL, + SearchPhrase TEXT NOT NULL, + AdvEngineID SMALLINT NOT NULL, + IsArtifical SMALLINT NOT NULL, + WindowClientWidth SMALLINT NOT NULL, + WindowClientHeight SMALLINT NOT NULL, + ClientTimeZone SMALLINT NOT NULL, + ClientEventTime TIMESTAMP NOT NULL, + SilverlightVersion1 SMALLINT NOT NULL, + SilverlightVersion2 SMALLINT NOT NULL, + SilverlightVersion3 INTEGER NOT NULL, + SilverlightVersion4 SMALLINT NOT NULL, + PageCharset TEXT NOT NULL, + CodeVersion INTEGER NOT NULL, + IsLink SMALLINT NOT NULL, + IsDownload SMALLINT NOT NULL, + IsNotBounce SMALLINT NOT NULL, + FUniqID BIGINT NOT NULL, + OriginalURL TEXT NOT NULL, + HID INTEGER NOT NULL, + IsOldCounter SMALLINT NOT NULL, + IsEvent SMALLINT NOT NULL, + IsParameter SMALLINT NOT NULL, + DontCountHits SMALLINT NOT NULL, + WithHash SMALLINT NOT NULL, + HitColor CHAR NOT NULL, + LocalEventTime TIMESTAMP NOT NULL, + Age SMALLINT NOT NULL, + Sex SMALLINT NOT NULL, + Income SMALLINT NOT NULL, + Interests SMALLINT NOT NULL, + Robotness SMALLINT NOT NULL, + RemoteIP INTEGER NOT NULL, + WindowName INTEGER NOT NULL, + OpenerName INTEGER NOT NULL, + HistoryLength SMALLINT NOT NULL, + BrowserLanguage TEXT NOT NULL, + BrowserCountry TEXT NOT NULL, + SocialNetwork TEXT NOT NULL, + SocialAction TEXT NOT NULL, + HTTPError SMALLINT NOT NULL, + SendTiming INTEGER NOT NULL, + DNSTiming INTEGER NOT NULL, + ConnectTiming INTEGER NOT NULL, + ResponseStartTiming INTEGER NOT NULL, + ResponseEndTiming INTEGER NOT NULL, + FetchTiming INTEGER NOT NULL, + SocialSourceNetworkID SMALLINT NOT NULL, + SocialSourcePage TEXT NOT NULL, + ParamPrice BIGINT NOT NULL, + ParamOrderID TEXT NOT NULL, + ParamCurrency TEXT NOT NULL, + ParamCurrencyID SMALLINT NOT NULL, + OpenstatServiceName TEXT NOT NULL, + OpenstatCampaignID TEXT NOT NULL, + OpenstatAdID TEXT NOT NULL, + OpenstatSourceID TEXT NOT NULL, + UTMSource TEXT NOT NULL, + UTMMedium TEXT NOT NULL, + UTMCampaign TEXT NOT NULL, + UTMContent TEXT NOT NULL, + UTMTerm TEXT NOT NULL, + FromTag TEXT NOT NULL, + HasGCLID SMALLINT NOT NULL, + RefererHash BIGINT NOT NULL, + URLHash BIGINT NOT NULL, + CLID INTEGER NOT NULL +) using columnstore; + + +insert into hits select WatchID, JavaEnable, Title, GoodEvent, 'epoch'::timestamp + (EventTime || 'second')::interval EventTime, 'epoch'::timestamp + (EventDate || 'day')::interval EventDate, CounterID, ClientIP, RegionID, UserID, CounterClass, OS, UserAgent, URL, Referer, IsRefresh, RefererCategoryID, RefererRegionID, URLCategoryID, URLRegionID, ResolutionWidth, ResolutionHeight, ResolutionDepth, FlashMajor, FlashMinor, FlashMinor2, NetMajor, NetMinor, UserAgentMajor, UserAgentMinor, CookieEnable, JavascriptEnable, IsMobile, MobilePhone, MobilePhoneModel, Params, IPNetworkID, TraficSourceID, SearchEngineID, SearchPhrase, AdvEngineID, IsArtifical, WindowClientWidth, WindowClientHeight, ClientTimeZone, 'epoch'::timestamp + (ClientEventTime || 'second')::interval ClientEventTime, SilverlightVersion1, SilverlightVersion2, SilverlightVersion3, SilverlightVersion4, PageCharset, CodeVersion, IsLink, IsDownload, IsNotBounce, FUniqID, OriginalURL, HID, IsOldCounter, IsEvent, IsParameter, DontCountHits, WithHash, HitColor, 'epoch'::timestamp + (LocalEventTime || 'second')::interval LocalEventTime, Age, Sex, Income, Interests, Robotness, RemoteIP, WindowName, OpenerName, HistoryLength, BrowserLanguage, BrowserCountry, SocialNetwork, SocialAction, HTTPError, SendTiming, DNSTiming, ConnectTiming, ResponseStartTiming, ResponseEndTiming, FetchTiming, SocialSourceNetworkID, SocialSourcePage, ParamPrice, ParamOrderID, ParamCurrency, ParamCurrencyID, OpenstatServiceName, OpenstatCampaignID, OpenstatAdID, OpenstatSourceID, UTMSource, UTMMedium, UTMCampaign, UTMContent, UTMTerm, FromTag, HasGCLID, RefererHash, URLHash, CLID +from mooncake.read_parquet('/tmp/hits.parquet') as (WatchID BIGINT, JavaEnable SMALLINT, Title VARCHAR, GoodEvent SMALLINT, EventTime BIGINT, EventDate int, CounterID INTEGER, ClientIP INTEGER, RegionID INTEGER, UserID BIGINT, CounterClass SMALLINT, OS SMALLINT, UserAgent SMALLINT, URL VARCHAR, Referer VARCHAR, IsRefresh SMALLINT, RefererCategoryID SMALLINT, RefererRegionID INTEGER, URLCategoryID SMALLINT, URLRegionID INTEGER, ResolutionWidth SMALLINT, ResolutionHeight SMALLINT, ResolutionDepth SMALLINT, FlashMajor SMALLINT, FlashMinor SMALLINT, FlashMinor2 VARCHAR, NetMajor SMALLINT, NetMinor SMALLINT, UserAgentMajor SMALLINT, UserAgentMinor VARCHAR, CookieEnable SMALLINT, JavascriptEnable SMALLINT, IsMobile SMALLINT, MobilePhone SMALLINT, MobilePhoneModel VARCHAR, Params VARCHAR, IPNetworkID INTEGER, TraficSourceID SMALLINT, SearchEngineID SMALLINT, SearchPhrase VARCHAR, AdvEngineID SMALLINT, IsArtifical SMALLINT, WindowClientWidth SMALLINT, WindowClientHeight SMALLINT, ClientTimeZone SMALLINT, ClientEventTime BIGINT, SilverlightVersion1 SMALLINT, SilverlightVersion2 SMALLINT, SilverlightVersion3 INTEGER, SilverlightVersion4 SMALLINT, PageCharset VARCHAR, CodeVersion INTEGER, IsLink SMALLINT, IsDownload SMALLINT, IsNotBounce SMALLINT, FUniqID BIGINT, OriginalURL VARCHAR, HID INTEGER, IsOldCounter SMALLINT, IsEvent SMALLINT, IsParameter SMALLINT, DontCountHits SMALLINT, WithHash SMALLINT, HitColor VARCHAR, LocalEventTime BIGINT, Age SMALLINT, Sex SMALLINT, Income SMALLINT, Interests SMALLINT, Robotness SMALLINT, RemoteIP INTEGER, WindowName INTEGER, OpenerName INTEGER, HistoryLength SMALLINT, BrowserLanguage VARCHAR, BrowserCountry VARCHAR, SocialNetwork VARCHAR, SocialAction VARCHAR, HTTPError SMALLINT, SendTiming INTEGER, DNSTiming INTEGER, ConnectTiming INTEGER, ResponseStartTiming INTEGER, ResponseEndTiming INTEGER, FetchTiming INTEGER, SocialSourceNetworkID SMALLINT, SocialSourcePage VARCHAR, ParamPrice BIGINT, ParamOrderID VARCHAR, ParamCurrency VARCHAR, ParamCurrencyID SMALLINT, OpenstatServiceName VARCHAR, OpenstatCampaignID VARCHAR, OpenstatAdID VARCHAR, OpenstatSourceID VARCHAR, UTMSource VARCHAR, UTMMedium VARCHAR, UTMCampaign VARCHAR, UTMContent VARCHAR, UTMTerm VARCHAR, FromTag VARCHAR, HasGCLID SMALLINT, RefererHash BIGINT, URLHash BIGINT, CLID INTEGER); \ No newline at end of file diff --git a/pg_mooncake/queries.sql b/pg_mooncake/queries.sql new file mode 100644 index 0000000000..31f65fc898 --- /dev/null +++ b/pg_mooncake/queries.sql @@ -0,0 +1,43 @@ +SELECT COUNT(*) FROM hits; +SELECT COUNT(*) FROM hits WHERE AdvEngineID <> 0; +SELECT SUM(AdvEngineID), COUNT(*), AVG(ResolutionWidth) FROM hits; +SELECT AVG(UserID) FROM hits; +SELECT COUNT(DISTINCT UserID) FROM hits; +SELECT COUNT(DISTINCT SearchPhrase) FROM hits; +SELECT MIN(EventDate), MAX(EventDate) FROM hits; +SELECT AdvEngineID, COUNT(*) FROM hits WHERE AdvEngineID <> 0 GROUP BY AdvEngineID ORDER BY COUNT(*) DESC; +SELECT RegionID, COUNT(DISTINCT UserID) AS u FROM hits GROUP BY RegionID ORDER BY u DESC LIMIT 10; +SELECT RegionID, SUM(AdvEngineID), COUNT(*) AS c, AVG(ResolutionWidth), COUNT(DISTINCT UserID) FROM hits GROUP BY RegionID ORDER BY c DESC LIMIT 10; +SELECT MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhoneModel ORDER BY u DESC LIMIT 10; +SELECT MobilePhone, MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhone, MobilePhoneModel ORDER BY u DESC LIMIT 10; +SELECT SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10; +SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10; +SELECT SearchEngineID, SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, SearchPhrase ORDER BY c DESC LIMIT 10; +SELECT UserID, COUNT(*) FROM hits GROUP BY UserID ORDER BY COUNT(*) DESC LIMIT 10; +SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10; +SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase LIMIT 10; +SELECT UserID, extract(minute FROM EventTime) AS m, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, m, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10; +SELECT UserID FROM hits WHERE UserID = 435090932899640449; +SELECT COUNT(*) FROM hits WHERE URL LIKE '%google%'; +SELECT SearchPhrase, MIN(URL), COUNT(*) AS c FROM hits WHERE URL LIKE '%google%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10; +SELECT SearchPhrase, MIN(URL), MIN(Title), COUNT(*) AS c, COUNT(DISTINCT UserID) FROM hits WHERE Title LIKE '%Google%' AND URL NOT LIKE '%.google.%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10; +SELECT * FROM hits WHERE URL LIKE '%google%' ORDER BY EventTime LIMIT 10; +SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime LIMIT 10; +SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY SearchPhrase LIMIT 10; +SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime, SearchPhrase LIMIT 10; +SELECT CounterID, AVG(length(URL)) AS l, COUNT(*) AS c FROM hits WHERE URL <> '' GROUP BY CounterID HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25; +SELECT REGEXP_REPLACE(Referer, '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length(Referer)) AS l, COUNT(*) AS c, MIN(Referer) FROM hits WHERE Referer <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25; +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; +SELECT SearchEngineID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, ClientIP ORDER BY c DESC LIMIT 10; +SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10; +SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10; +SELECT URL, COUNT(*) AS c FROM hits GROUP BY URL ORDER BY c DESC LIMIT 10; +SELECT 1, URL, COUNT(*) AS c FROM hits GROUP BY 1, URL ORDER BY c DESC LIMIT 10; +SELECT ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3, COUNT(*) AS c FROM hits GROUP BY ClientIP, ClientIP - 1, ClientIP - 2, ClientIP - 3 ORDER BY c DESC LIMIT 10; +SELECT URL, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCountHits = 0 AND IsRefresh = 0 AND URL <> '' GROUP BY URL ORDER BY PageViews DESC LIMIT 10; +SELECT Title, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND DontCountHits = 0 AND IsRefresh = 0 AND Title <> '' GROUP BY Title ORDER BY PageViews DESC LIMIT 10; +SELECT URL, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND IsLink <> 0 AND IsDownload = 0 GROUP BY URL ORDER BY PageViews DESC LIMIT 10 OFFSET 1000; +SELECT TraficSourceID, SearchEngineID, AdvEngineID, CASE WHEN (SearchEngineID = 0 AND AdvEngineID = 0) THEN Referer ELSE '' END AS Src, URL AS Dst, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 GROUP BY TraficSourceID, SearchEngineID, AdvEngineID, Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000; +SELECT URLHash, EventDate, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND TraficSourceID IN (-1, 6) AND RefererHash = 3594120000172545465 GROUP BY URLHash, EventDate ORDER BY PageViews DESC LIMIT 10 OFFSET 100; +SELECT WindowClientWidth, WindowClientHeight, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-01' AND EventDate <= '2013-07-31' AND IsRefresh = 0 AND DontCountHits = 0 AND URLHash = 2868770270353813622 GROUP BY WindowClientWidth, WindowClientHeight ORDER BY PageViews DESC LIMIT 10 OFFSET 10000; +SELECT DATE_TRUNC('minute', EventTime) AS M, COUNT(*) AS PageViews FROM hits WHERE CounterID = 62 AND EventDate >= '2013-07-14' AND EventDate <= '2013-07-15' AND IsRefresh = 0 AND DontCountHits = 0 GROUP BY DATE_TRUNC('minute', EventTime) ORDER BY DATE_TRUNC('minute', EventTime) LIMIT 10 OFFSET 1000; diff --git a/pg_mooncake/results/c6a.4xlarge.json b/pg_mooncake/results/c6a.4xlarge.json new file mode 100644 index 0000000000..62c6d0a9d2 --- /dev/null +++ b/pg_mooncake/results/c6a.4xlarge.json @@ -0,0 +1,58 @@ +{ + "system": "PostgreSQL with pg_mooncake", + "date": "2024-10-29", + "machine": "c6a.4xlarge, 500gb gp2", + "cluster_size": 1, + "comment": "", + + "tags": ["C", "columnstore-oriented", "PostgreSQL compatible"], + + "load_time": 576, + "data_size": 14619781667, + + "result": [ + [0.333547,0.165206,0.16618], + [0.34874,0.181874,0.186519], + [0.375516,0.209602,0.208003], + [0.374779,0.20563,0.202141], + [0.655907,0.470776,0.476025], + [0.811535,0.621098,0.617142], + [0.352581,0.185143,0.189729], + [0.35307,0.189816,0.187887], + [0.754761,0.563032,0.565512], + [0.976081,0.788516,0.784232], + [0.437576,0.265566,0.264314], + [0.468294,0.298822,0.297582], + [0.751214,0.555403,0.558728], + [1.081,0.878788,0.876646], + [0.807973,0.614561,0.616568], + [0.708347,0.525092,0.523602], + [1.41608,1.18459,1.21673], + [1.34287,1.1069,1.11835], + [2.77724,2.5253,2.54778], + [0.357902,0.186381,0.188127], + [1.58039,1.36808,1.37581], + [1.39031,1.18988,1.2049], + [2.17306,1.98628,1.9969], + [9.51484,9.30506,9.28642], + [0.614986,0.438261,0.43887], + [0.501505,0.322119,0.325232], + [0.629834,0.449862,0.449517], + [1.49412,1.29332,1.3048], + [3.93177,3.78288,3.79152], + [4.44172,4.28355,4.28702], + [0.866795,0.678543,0.67622], + [0.951833,0.755319,0.756616], + [6.24173,5.76983,5.90668], + [5.39507,5.07192,5.08586], + [5.27414,4.98546,5.07566], + [0.905852,0.693322,0.692577], + [0.241896,0.079152,0.073739], + [0.226789,0.065884,0.061194], + [0.230049,0.068799,0.068422], + [0.298764,0.123202,0.119528], + [0.209631,0.049452,0.052057], + [0.207916,0.047673,0.046621], + [0.205543,0.046252,0.047773] +] +} diff --git a/pg_mooncake/run.sh b/pg_mooncake/run.sh new file mode 100755 index 0000000000..6e931ab1c2 --- /dev/null +++ b/pg_mooncake/run.sh @@ -0,0 +1,12 @@ +#!/bin/bash + +TRIES=3 +CONNECTION=postgres://postgres:pg_mooncake@localhost:5432/postgres + +cat queries.sql | while read query; do + echo "$query" + ( + echo '\timing' + yes "$query" | head -n $TRIES + ) | psql $CONNECTION | grep 'Time' +done \ No newline at end of file From 8c2ba941ebd05a3dc1b7c77e03a111e23434a1fd Mon Sep 17 00:00:00 2001 From: paurora17 Date: Thu, 9 Jan 2025 20:54:17 -0800 Subject: [PATCH 2/2] create readme --- pg_mooncake/README.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 pg_mooncake/README.md diff --git a/pg_mooncake/README.md b/pg_mooncake/README.md new file mode 100644 index 0000000000..c274359b9c --- /dev/null +++ b/pg_mooncake/README.md @@ -0,0 +1,19 @@ +# pg_mooncake + +pg_mooncake is a Postgres extension that adds columnstore tables and vectorized execution (DuckDB). + +The extension is maintained by [Mooncake Labs](https://mooncake.dev) + +- [repo](https://github.com/Mooncake-Labs/pg_mooncake/) +- [docs](https://pgmooncake.com/docs) + +This benchmarks pg_mooncake `v0.1.0`. + +## Run the benchmark. + +1. Spin up a `c6a.4xlarge` instance with Ubuntu Server 22.04 LTS, Root 500GB gp2 SSD, no EBS optimized. +2. SSH into the instance and close repo. git clone `https://github.com/ClickHouse/ClickBench`. +3. Navigate to pg_mooncake directory. cd ClickBench/pg_mooncake. +4. Run the benchmark via `./benchmark.sh`. + +For any questions, join our [slack](https://join.slack.com/t/mooncakelabs/shared_invite/zt-2sepjh5hv-rb9jUtfYZ9bvbxTCUrsEEA).