Merge branch 'main' of github.com:ClickHouse/ClickBench into versions…

…-23.5

.github/workflows/generate-results.yml

@@ -0,0 +1,29 @@
+name: "Generate index.html"
+on:
+  push:
+    branches:    
+      - main
+
+permissions:
+  contents: write
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    env: 
+      CI_COMMIT_MESSAGE: "[bot] update index.html"
+      CI_COMMIT_AUTHOR: github
+    steps:
+    - uses: actions/[email protected]
+    - if: github.event.commits[0].message != env.CI_COMMIT_MESSAGE
+      run: |
+        bash generate-results.sh
+        git config --global user.name "${{ env.CI_COMMIT_AUTHOR }}"
+        git config --global user.email "${{ env.CI_COMMIT_AUTHOR }}@users.noreply.github.com"
+
+        git add -A
+        if git status | grep -q modified
+        then
+          git commit -m "${{ env.CI_COMMIT_MESSAGE }}"
+          git push
+        fi

README.md

@@ -253,6 +253,7 @@ We also introduced the [Hardware Benchmark](https://benchmark.clickhouse.com/har
 - [ ] ScyllaDB
 - [x] Elasticsearch
 - [ ] Apache Ignite
+- [ ] Motherduck
 - [x] Infobright
 - [ ] Actian Vector
 - [ ] Manticore Search
@@ -272,6 +273,7 @@ We also introduced the [Hardware Benchmark](https://benchmark.clickhouse.com/har
 - [ ] YDB
 - [ ] OceanBase
 - [ ] Boilingdata
+- [x] Byteconity
 
 By default, all tests are run on c6a.4xlarge VM in AWS with 500 GB gp2.
 

aurora-mysql/README.md

@@ -37,7 +37,7 @@ mysql -h "${HOST}" -u admin --password="${PASSWORD}" -e "CREATE DATABASE test"
 Load the data
 
 ```
-wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
+wget --no-verbose --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
 gzip -d hits.tsv.gz
 
 mysql -h "${HOST}" -u admin --password="${PASSWORD}" test < create.sql

aurora-postgresql/README.md

@@ -36,7 +36,7 @@ chmod 400 .pgpass
 Load the data
 
 ```
-wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
+wget --no-verbose --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
 gzip -d hits.tsv.gz
 
 psql -U postgres -h "${HOST}" -t -c 'CREATE DATABASE test'

bigquery/README.md

@@ -19,7 +19,7 @@ source .bashrc
 
 Load the data:
 ```
-wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.csv.gz'
+wget --no-verbose --continue 'https://datasets.clickhouse.com/hits_compatible/hits.csv.gz'
 gzip -d hits.csv.gz
 
 time bq load --source_format CSV --allow_quoted_newlines=1 test.hits hits.csv

byconity/README.md

@@ -0,0 +1,17 @@
+[ByConity](https://github.com/ByConity/ByConity)
+
+Even though ByConity is a fork of ClickHouse, there are some
+differences:
+
+- it does not have some new features/optimizations since it was a fork of
+  ClickHouse (21.8).
+- it supports transactions
+- this setup uses HDFS
+
+But some of this has a cost, so let's see what is it.
+
+The benchmark uses local in docker setup, so it is far from reality, but
+still.
+
+Note, that almost all setup was copied from the [ByConity repository](https://github.com/ByConity/ByConity/tree/master/docker/local-deploy),
+and I did some modifications to use pre-built images.

byconity/benchmark.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+docker-compose up -d
+sleep 5
+
+hdfs/create_users.sh
+
+function byconity()
+{
+    docker-compose exec -T server clickhouse-client --port 52145 "$@"
+}
+export -f byconity
+
+byconity --time -n < create.sql
+wget --no-verbose --continue 'https://datasets.clickhouse.com/hits_compatible/hits.tsv.gz'
+pigz -fkd hits.tsv.gz
+byconity --database bench --query "INSERT INTO hits FORMAT TSV" < hits.tsv
+
+# NOTE: sometimes may hung due to docker-compose, using docker directly may help
+./run.sh
+
+byconity --enable_multiple_tables_for_cnch_parts=1 --query "SELECT sum(bytes_on_disk) FROM system.cnch_parts WHERE table = 'hits' AND database = 'bench'"
+
+docker-compose down --volumes

byconity/create.sql

@@ -0,0 +1,111 @@
+CREATE DATABASE bench Engine=Cnch;
+CREATE TABLE bench.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)
+)
+ENGINE = CnchMergeTree()

byconity/docker-compose.yml

@@ -0,0 +1,105 @@
+---
+version: "3"
+
+# NOTE:
+# - you cannot use network_mode=host (to optimize out network overhead) because hadoop does not work without DNS.
+
+services:
+  # hdfs / remote fs
+  hdfs:
+    image: gchq/hdfs:3.3
+    command: namenode
+    container_name: hdfs-namenode
+    ports:
+      - 9871:9870
+    environment:
+      HADOOP_CONF_DIR: /etc/hadoop/conf
+    volumes:
+      - ./hdfs:/etc/hadoop/conf:ro
+      - /var/log/hadoop
+      - /data1
+      - /data2
+
+  hdfs-datanode:
+    depends_on:
+      - hdfs
+    image: gchq/hdfs:3.3
+    command: datanode
+    container_name: hdfs-datanode
+    environment:
+      HADOOP_CONF_DIR: /etc/hadoop/conf
+    volumes:
+      - ./hdfs:/etc/hadoop/conf:ro
+      - /var/log/hadoop
+      - /data1
+      - /data2
+
+  # foundation db / catalog
+  fdb:
+    image: foundationdb/foundationdb:7.1.24
+    environment:
+      FDB_NETWORKING_MODE: container
+      FDB_COORDINATOR_PORT: 4550
+      FDB_PORT: 4550
+    container_name: fdb-0
+
+  # byconity:
+  tso:
+    image: byconity/byconity:0.1.0-GA
+    environment:
+      PATH: /usr/sbin:/usr/bin:/sbin:/bin:/opt/byconity/bin
+    command: bash -c "fdbcli -C /config/fdb.cluster --exec \"configure new single ssd\"; tso-server --config-file /config/tso.yml"
+    depends_on:
+      - fdb
+      - hdfs
+    volumes:
+      - ./simple/:/config/:ro
+    container_name: tso-0
+
+  server:
+    image: byconity/byconity:0.1.0-GA
+    environment:
+      PATH: /usr/sbin:/usr/bin:/sbin:/bin:/opt/byconity/bin
+    command: bash -c "curl --retry 10 --retry-delay 5 --retry-connrefused --retry-max-time 120 --max-time 120 tso-0:18845 && clickhouse-server --config-file /config/server.yml"
+    depends_on:
+      - tso
+      - hdfs
+    ports:
+      - "9000:52145"
+      - "8124:21557"
+    container_name: server-0
+    volumes:
+      - ./simple/:/config/:ro
+
+  worker-write:
+    image: byconity/byconity:0.1.0-GA
+    environment:
+      PATH: /usr/sbin:/usr/bin:/sbin:/bin:/opt/byconity/bin
+    command: bash -c "curl --retry 10 --retry-delay 5 --retry-connrefused --retry-max-time 120 --max-time 120 server:21557 && clickhouse-server --config-file /config/worker.yml"
+    depends_on:
+      - server
+    container_name: worker-write-0
+    volumes:
+      - ./simple/:/config/:ro
+
+  worker-default:
+    image: byconity/byconity:0.1.0-GA
+    environment:
+      PATH: /usr/sbin:/usr/bin:/sbin:/bin:/opt/byconity/bin
+    command: bash -c "curl --retry 10 --retry-delay 5 --retry-connrefused --retry-max-time 120 --max-time 120 server:21557 && clickhouse-server --config-file /config/worker.yml"
+    depends_on:
+      - server
+    container_name: worker-default-0
+    volumes:
+      - ./simple/:/config/:ro
+
+  daemon-manager:
+    image: byconity/byconity:0.1.0-GA
+    environment:
+      PATH: /usr/sbin:/usr/bin:/sbin:/bin:/opt/byconity/bin
+    command: bash -c "curl --retry 10 --retry-delay 5 --retry-connrefused --retry-max-time 120 --max-time 120 server:21557 && daemon-manager --config-file ./config/daemon-manager.yml"
+    depends_on:
+      - server
+    container_name: daemon-manager-0
+    volumes:
+      - ./simple/:/config/:ro

byconity/hdfs/core-site.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<configuration>
+	<property>
+		<name>fs.defaultFS</name>
+		<value>hdfs://hdfs-namenode:9000</value>
+	</property>
+</configuration>

byconity/hdfs/create_users.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+set -e -x
+docker exec hdfs-namenode hdfs dfs -mkdir /user
+docker exec hdfs-namenode hdfs dfs -mkdir /user/clickhouse
+docker exec hdfs-namenode hdfs dfs -chown clickhouse /user/clickhouse
+docker exec hdfs-namenode hdfs dfs -chmod -R 775 /user/clickhouse 

byconity/hdfs/hdfs-site.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<configuration>
+	<property><name>dfs.namenode.name.dir</name><value>/data1/dfs/name,/data2/dfs/name</value></property>
+	<property><name>dfs.datanode.data.dir</name><value>/data1/dfs/data,/data2/dfs/data</value></property>
+	<property><name>dfs.replication</name><value>1</value></property>
+	<property><name>dfs.namenode.http-address</name><value>0.0.0.0:9870</value></property>
+</configuration>

byconity/hdfs/log4j.properties

@@ -0,0 +1,4 @@
+log4j.rootLogger=INFO, stdout
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss} %-5p %c{1}:%L - %m%n