Merge branch 'main' into adamg/datafusion-vortex

Author: AdamGS

README.md

@@ -248,7 +248,7 @@ We also introduced the [Hardware Benchmark](https://benchmark.clickhouse.com/har
 - [x] Bigquery (without publishing)
 - [x] Snowflake
 - [ ] Rockset
-- [ ] CockroachDB
+- [x] CockroachDB
 - [ ] CockroachDB Serverless
 - [ ] Databricks
 - [ ] Planetscale (without publishing)
@@ -294,7 +294,7 @@ We also introduced the [Hardware Benchmark](https://benchmark.clickhouse.com/har
 - [x] Tablespace
 - [x] Tembo
 - [x] Cloudberry
-- [ ] Daft
+- [x] Daft
 - [x] Pandas
 - [x] Polars
 - [x] OctoSQL

aurora-mysql/README.md

@@ -38,7 +38,7 @@ Load the data
 
 ```
 wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
-gzip -d hits.tsv.gz
+gzip -d -f hits.tsv.gz
 
 mysql -h "${FQDN}" -u admin --password="${PASSWORD}" test < create.sql
 

aurora-postgresql/README.md

@@ -37,7 +37,7 @@ Load the data
 
 ```
 wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
-gzip -d hits.tsv.gz
+gzip -d -f hits.tsv.gz
 
 psql -U postgres -h "${FQDN}" -t -c 'CREATE DATABASE test'
 psql -U postgres -h "${FQDN}" test -t < create.sql

bigquery/README.md

@@ -19,7 +19,7 @@ source .bashrc
 Load the data:
 ```
 wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.csv.gz'
-gzip -d hits.csv.gz
+gzip -d -f hits.csv.gz
 
 time bq load --source_format CSV --allow_quoted_newlines=1 test.hits hits.csv
 ```

bytehouse/NOTES.md

@@ -200,7 +200,7 @@ Will try CSV.
 
 ```
 wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.csv.gz'
-gzip -d hits.csv.gz
+gzip -d -f hits.csv.gz
 ```
 
 Now it started to work:

bytehouse/README.md

@@ -29,7 +29,7 @@ export warehouse='test'
 
 ```
 wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.csv.gz'
-gzip -d hits.csv.gz
+gzip -d -f hits.csv.gz
 ```
 
 Load the data:

cedardb/benchmark.sh

@@ -0,0 +1,41 @@
+#!/bin/bash -e
+
+# docker
+sudo apt-get update
+sudo apt-get install -y  docker.io postgresql-client gzip
+
+# download dataset
+echo "Downloading dataset..."
+wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
+echo "Unpacking dataset..."
+gzip -d hits.tsv.gz
+mkdir data
+mv hits.tsv data
+chmod -R 777 data
+rm -rf db
+mkdir db
+
+# get and configure CedarDB image
+echo "Starting CedarDB..." 
+docker run --rm -p 5432:5432 -v ./data:/data -v ./db:/var/lib/cedardb/data -e CEDAR_PASSWORD=test --name cedardb cedardb/cedardb:latest > /dev/null 2>&1 &
+
+# wait for container to start
+until pg_isready -h localhost --dbname postgres -U postgres > /dev/null 2>&1; do sleep 1; done
+
+# create table and ingest data
+PGPASSWORD=test  psql -h localhost -U postgres -t < create.sql
+echo "Inserting data..."
+PGPASSWORD=test time psql -h localhost -U postgres -t -c '\timing' -c "COPY hits FROM '/data/hits.tsv';"
+
+# get ingested data size
+echo "data size after ingest:"
+PGPASSWORD=test psql -h localhost -U postgres -t -c '\timing' -c "SELECT pg_total_relation_size('hits');"
+
+# run benchmark
+echo "running benchmark..."
+./run.sh 2>&1 | tee log.txt
+
+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; }'

cedardb/create.sql

@@ -0,0 +1,109 @@
+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,
+    primary key (counterid, eventdate, userid, eventtime, watchid)
+);
+

cedardb/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::bigint), SUM(ResolutionWidth::bigint + 1), SUM(ResolutionWidth::bigint + 2), SUM(ResolutionWidth::bigint + 3), SUM(ResolutionWidth::bigint + 4), SUM(ResolutionWidth::bigint + 5), SUM(ResolutionWidth::bigint + 6), SUM(ResolutionWidth::bigint + 7), SUM(ResolutionWidth::bigint + 8), SUM(ResolutionWidth::bigint + 9), SUM(ResolutionWidth::bigint + 10), SUM(ResolutionWidth::bigint + 11), SUM(ResolutionWidth::bigint + 12), SUM(ResolutionWidth::bigint + 13), SUM(ResolutionWidth::bigint + 14), SUM(ResolutionWidth::bigint + 15), SUM(ResolutionWidth::bigint + 16), SUM(ResolutionWidth::bigint + 17), SUM(ResolutionWidth::bigint + 18), SUM(ResolutionWidth::bigint + 19), SUM(ResolutionWidth::bigint + 20), SUM(ResolutionWidth::bigint + 21), SUM(ResolutionWidth::bigint + 22), SUM(ResolutionWidth::bigint + 23), SUM(ResolutionWidth::bigint + 24), SUM(ResolutionWidth::bigint + 25), SUM(ResolutionWidth::bigint + 26), SUM(ResolutionWidth::bigint + 27), SUM(ResolutionWidth::bigint + 28), SUM(ResolutionWidth::bigint + 29), SUM(ResolutionWidth::bigint + 30), SUM(ResolutionWidth::bigint + 31), SUM(ResolutionWidth::bigint + 32), SUM(ResolutionWidth::bigint + 33), SUM(ResolutionWidth::bigint + 34), SUM(ResolutionWidth::bigint + 35), SUM(ResolutionWidth::bigint + 36), SUM(ResolutionWidth::bigint + 37), SUM(ResolutionWidth::bigint + 38), SUM(ResolutionWidth::bigint + 39), SUM(ResolutionWidth::bigint + 40), SUM(ResolutionWidth::bigint + 41), SUM(ResolutionWidth::bigint + 42), SUM(ResolutionWidth::bigint + 43), SUM(ResolutionWidth::bigint + 44), SUM(ResolutionWidth::bigint + 45), SUM(ResolutionWidth::bigint + 46), SUM(ResolutionWidth::bigint + 47), SUM(ResolutionWidth::bigint + 48), SUM(ResolutionWidth::bigint + 49), SUM(ResolutionWidth::bigint + 50), SUM(ResolutionWidth::bigint + 51), SUM(ResolutionWidth::bigint + 52), SUM(ResolutionWidth::bigint + 53), SUM(ResolutionWidth::bigint + 54), SUM(ResolutionWidth::bigint + 55), SUM(ResolutionWidth::bigint + 56), SUM(ResolutionWidth::bigint + 57), SUM(ResolutionWidth::bigint + 58), SUM(ResolutionWidth::bigint + 59), SUM(ResolutionWidth::bigint + 60), SUM(ResolutionWidth::bigint + 61), SUM(ResolutionWidth::bigint + 62), SUM(ResolutionWidth::bigint + 63), SUM(ResolutionWidth::bigint + 64), SUM(ResolutionWidth::bigint + 65), SUM(ResolutionWidth::bigint + 66), SUM(ResolutionWidth::bigint + 67), SUM(ResolutionWidth::bigint + 68), SUM(ResolutionWidth::bigint + 69), SUM(ResolutionWidth::bigint + 70), SUM(ResolutionWidth::bigint + 71), SUM(ResolutionWidth::bigint + 72), SUM(ResolutionWidth::bigint + 73), SUM(ResolutionWidth::bigint + 74), SUM(ResolutionWidth::bigint + 75), SUM(ResolutionWidth::bigint + 76), SUM(ResolutionWidth::bigint + 77), SUM(ResolutionWidth::bigint + 78), SUM(ResolutionWidth::bigint + 79), SUM(ResolutionWidth::bigint + 80), SUM(ResolutionWidth::bigint + 81), SUM(ResolutionWidth::bigint + 82), SUM(ResolutionWidth::bigint + 83), SUM(ResolutionWidth::bigint + 84), SUM(ResolutionWidth::bigint + 85), SUM(ResolutionWidth::bigint + 86), SUM(ResolutionWidth::bigint + 87), SUM(ResolutionWidth::bigint + 88), SUM(ResolutionWidth::bigint + 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;

cedardb/results/c6a.4xlarge.json

@@ -0,0 +1,54 @@
+{
+    "system": "CedarDB",
+    "date": "2025-05-13",
+    "machine": "c6a.4xlarge, 500gb gp2",
+    "cluster_size": 1,
+    "tags": ["C++", "column-oriented", "PostgreSQL compatible"],
+    "load_time": 678.319,
+    "data_size": 34178593296,
+    "result": [
+[0.045546,0.01239,0.009761],
+[0.068054,0.003996,0.00395],
+[0.075834,0.028006,0.029268],
+[0.079261,0.026982,0.025895],
+[0.136197,0.128637,0.127705],
+[1.49167,0.2131,0.21466],
+[0.035958,0.028353,0.025267],
+[0.019709,0.004367,0.004137],
+[0.277884,0.222673,0.224794],
+[0.298195,0.297072,0.302439],
+[0.079287,0.031605,0.032011],
+[0.073052,0.033233,0.033808],
+[0.189603,0.179199,0.177913],
+[0.314636,0.320284,0.315986],
+[0.197241,0.19097,0.192531],
+[0.153453,0.151451,0.149093],
+[0.436293,0.433139,0.435853],
+[0.406462,0.407494,0.406696],
+[1.32138,0.763988,0.746778],
+[0.003121,0.001525,0.001504],
+[14.1902,1.48478,0.28938],
+[2.39374,0.645003,0.384866],
+[18.7271,9.36254,4.73712],
+[116.117,152.357,145.965],
+[3.89221,0.007532,0.006329],
+[0.009266,0.009319,0.009302],
+[0.007104,0.006846,0.006431],
+[13.0675,1.67841,0.29181],
+[11.0241,3.27706,3.23834],
+[0.075202,0.022927,0.02772],
+[2.93094,0.089051,0.097671],
+[2.69473,0.135952,0.138472],
+[0.978692,0.991592,0.968237],
+[9.97283,1.11121,1.09719],
+[1.08623,1.09635,1.08831],
+[0.162726,0.141096,0.139401],
+[0.020747,0.014121,0.013001],
+[0.023358,0.007492,0.007233],
+[0.009018,0.00338,0.003532],
+[0.036507,0.027613,0.026543],
+[0.017446,0.00351,0.003404],
+[0.01379,0.003111,0.003029],
+[0.011919,0.004089,0.004237]
+]
+}