From 8281d5acb621a9e1a0beeb911ae427597acb1fe9 Mon Sep 17 00:00:00 2001 From: "David E. Wheeler" Date: Mon, 29 Dec 2025 14:23:36 -0500 Subject: [PATCH] Add pg_clickhouse It dupes the clickhouse benchmark config to load data (except that column names are lowercase) and the Postgres config to run the queries. All queries push down to ClickHouse without error. --- pg_clickhouse/README.md | 22 +++++ pg_clickhouse/benchmark.sh | 17 ++++ pg_clickhouse/clickhouse.sh | 50 +++++++++++ pg_clickhouse/create-postgres.sql | 121 ++++++++++++++++++++++++++ pg_clickhouse/create-tuned-memory.sql | 109 +++++++++++++++++++++++ pg_clickhouse/create-tuned.sql | 111 +++++++++++++++++++++++ pg_clickhouse/create.sql | 110 +++++++++++++++++++++++ pg_clickhouse/postgres.sh | 71 +++++++++++++++ pg_clickhouse/queries.sql | 43 +++++++++ pg_clickhouse/run.sh | 14 +++ pg_clickhouse/template.json | 12 +++ 11 files changed, 680 insertions(+) create mode 100644 pg_clickhouse/README.md create mode 100755 pg_clickhouse/benchmark.sh create mode 100755 pg_clickhouse/clickhouse.sh create mode 100644 pg_clickhouse/create-postgres.sql create mode 100644 pg_clickhouse/create-tuned-memory.sql create mode 100644 pg_clickhouse/create-tuned.sql create mode 100644 pg_clickhouse/create.sql create mode 100755 pg_clickhouse/postgres.sh create mode 100644 pg_clickhouse/queries.sql create mode 100755 pg_clickhouse/run.sh create mode 100644 pg_clickhouse/template.json diff --git a/pg_clickhouse/README.md b/pg_clickhouse/README.md new file mode 100644 index 000000000..15326156b --- /dev/null +++ b/pg_clickhouse/README.md @@ -0,0 +1,22 @@ +pg_clickhouse ClickBench +======================== + +This ClickBench configuration benchmarks [pg_clickhouse] running inside +PostgreSQL and pushing queries down to a ClickHouse database. Files: + +* `benchmark.sh`: Runs the benchmark +* `clickhouse.sh`: Installs ClickHouse and loads it with data; based on the + [ClickHouse benchmark script](../clickhouse/benchmark.sh) +* `create-postgres.sql`: Loads pg_clickhouse into Postgres and creates the + foreign table +* `create-tuned-memory.sql`, `create-tuned.sql`, and `create.sql`: Scripts + that create the ClickHouse table, copied from the [ClickHouse + Config](../clickhouse/) +* `postgres.sh`: Installs, configures, and starts PostgreSQL; based on the + [PostgreSQL benchmark script](../postgresql/benchmark.sh) +* `queries.sql`: The benchmark queries, identical to the [PostgreSQL + queries](../postgresql/queries.sql) +* `README.md`: This file +* `run.sh`: Runs the benchmark; identical too the [PostgreSQL run + script](../postgresql/run.sh) +* `template.json`: Describes this benchmark configuration diff --git a/pg_clickhouse/benchmark.sh b/pg_clickhouse/benchmark.sh new file mode 100755 index 000000000..0d6d797da --- /dev/null +++ b/pg_clickhouse/benchmark.sh @@ -0,0 +1,17 @@ +#!/bin/bash + +# apt-get update -y +# env DEBIAN_FRONTEND=noninteractive apt-get install -y wget curl sudo + +# Install and start ClickHouse and Postgres +./clickhouse.sh "$@" +./postgres.sh + +# Run the queries +./run.sh 2>&1 | tee log.txt + +echo -n "Data size: " +clickhouse-client --query "SELECT total_bytes FROM system.tables WHERE name = 'hits' AND database = 'default'" + +cat log.txt | grep -oP 'Time: \d+\.\d+ ms|psql: error' | sed -r -e 's/Time: ([0-9]+\.[0-9]+) ms/\1/; s/^.*psql: error.*$/null/' | + awk '{ if (i % 3 == 0) { printf "[" }; if ($1 == "null") { printf $1 } else { printf $1 / 1000 }; if (i % 3 != 2) { printf "," } else { print "]," }; ++i; }' diff --git a/pg_clickhouse/clickhouse.sh b/pg_clickhouse/clickhouse.sh new file mode 100755 index 000000000..b739d13cc --- /dev/null +++ b/pg_clickhouse/clickhouse.sh @@ -0,0 +1,50 @@ +#!/bin/bash + +# Install + +if [ ! -x /usr/bin/clickhouse ] +then + cd /tmp || exit + curl https://clickhouse.com/ | sh + sudo ./clickhouse install --noninteractive + rm clickhouse + cd - || exit +fi + +# Optional: if you want to use higher compression: +if (( 0 )); then + echo " +compression: + case: + method: zstd + " | sudo tee /etc/clickhouse-server/config.d/compression.yaml +fi; + +sudo clickhouse start + +for _ in {1..300} +do + clickhouse-client --query "SELECT 1" && break + sleep 1 +done + +# Determine which set of files to use depending on the type of run +if [ "$1" != "" ] && [ "$1" != "tuned" ] && [ "$1" != "tuned-memory" ]; then + echo "Error: command line argument must be one of {'', 'tuned', 'tuned-memory'}" + exit 1 +elif [ ! -z "$1" ]; then + SUFFIX="-$1" +fi + +# Load the data + +clickhouse-client < create"$SUFFIX".sql + +# seq 1 | xargs -P100 -I{} bash -c 'wget --continue --progress=dot:giga https://datasets.clickhouse.com/hits_compatible/athena_partitioned/hits_{}.parquet' +seq 0 99 | xargs -P100 -I{} bash -c 'wget --continue --progress=dot:giga https://datasets.clickhouse.com/hits_compatible/athena_partitioned/hits_{}.parquet' +mkdir -p /var/lib/clickhouse/user_files +sudo mv hits_*.parquet /var/lib/clickhouse/user_files/ +sudo chown clickhouse:clickhouse /var/lib/clickhouse/user_files/hits_*.parquet + +echo -n "Load time: " +clickhouse-client --time --query "INSERT INTO hits SELECT * FROM file('hits_*.parquet')" --max-insert-threads $(( $(nproc) / 4 )) diff --git a/pg_clickhouse/create-postgres.sql b/pg_clickhouse/create-postgres.sql new file mode 100644 index 000000000..b108fb9a0 --- /dev/null +++ b/pg_clickhouse/create-postgres.sql @@ -0,0 +1,121 @@ +BEGIN; + +CREATE EXTENSION IF NOT EXISTS pg_clickhouse; +CREATE SERVER ch_srv FOREIGN DATA WRAPPER clickhouse_fdw + OPTIONS(driver 'binary', host 'localhost', dbname 'default'); +CREATE USER MAPPING FOR CURRENT_USER SERVER ch_srv + OPTIONS (user 'default'); + +CREATE FOREIGN 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 +) SERVER ch_srv OPTIONS( + database 'default', + table_name 'hits', + engine 'MergeTree' +); + +COMMIT; diff --git a/pg_clickhouse/create-tuned-memory.sql b/pg_clickhouse/create-tuned-memory.sql new file mode 100644 index 000000000..978ae052f --- /dev/null +++ b/pg_clickhouse/create-tuned-memory.sql @@ -0,0 +1,109 @@ +CREATE OR REPLACE 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, +) +ENGINE = Memory; diff --git a/pg_clickhouse/create-tuned.sql b/pg_clickhouse/create-tuned.sql new file mode 100644 index 000000000..75234405f --- /dev/null +++ b/pg_clickhouse/create-tuned.sql @@ -0,0 +1,111 @@ +create OR REPLACE 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) +) +ENGINE = MergeTree +SETTINGS index_granularity = 1024; diff --git a/pg_clickhouse/create.sql b/pg_clickhouse/create.sql new file mode 100644 index 000000000..816982217 --- /dev/null +++ b/pg_clickhouse/create.sql @@ -0,0 +1,110 @@ +CREATE OR REPLACE 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) +) +ENGINE = MergeTree; diff --git a/pg_clickhouse/postgres.sh b/pg_clickhouse/postgres.sh new file mode 100755 index 000000000..e1558e993 --- /dev/null +++ b/pg_clickhouse/postgres.sh @@ -0,0 +1,71 @@ +#!/bin/bash + +set -eu + +PGVERSION=17 + +# Source: https://wiki.postgresql.org/wiki/Apt +sudo apt-get update -y +sudo env DEBIAN_FRONTEND=noninteractive apt-get install -y postgresql-common -y +sudo /usr/share/postgresql-common/pgdg/apt.postgresql.org.sh -y + +sudo apt-get update -y +sudo env DEBIAN_FRONTEND=noninteractive apt-get install -y "postgresql-$PGVERSION" "postgresql-server-dev-$PGVERSION" + +memory="$(awk '/MemTotal/ {print $2}' /proc/meminfo)" +threads="$(nproc)" +cpus=$(("$threads" / 2)) +# Shared buffers is set to 25% of memory in AWS RDS by default. We do the same. +# https://docs.aws.amazon.com/prescriptive-guidance/latest/tuning-postgresql-parameters/shared-buffers.html +shared_buffers=$(($memory / 4)) +# Effective cache size does not need to be perfect, but it should be somewhat +# close to the total memory minus what is expected to be used for queries. +# https://www.cybertec-postgresql.com/en/effective_cache_size-what-it-means-in-postgresql/ +effective_cache_size=$(("$memory" - ("$memory" / 4))) +# By default, max_worker_processes is set to in postgres. We want to be able to +# use all the threads for parallel workers so we increase it. We also add a +# small buffer of 15 for any other background workers that might be created. +max_worker_processes=$(("$threads" + 15)) +# Below we make sure to configure the rest of the parallel worker settings to +# match the number of cpu cores: +# https://www.crunchydata.com/blog/postgres-tuning-and-performance-for-analytics-data +# +# We also increase work_mem because we are doing an analytics workload to allow +# some more memory for sorting, aggregations, etc. +# +# It's necessary to increase max_wal_size to make the dataload not take very +# long. With the default value it's constantly checkpointing, and the PG logs +# warn you about that and tell you to increase max_wal_size. + +sudo tee /etc/postgresql/$PGVERSION/main/conf.d/clickbench.conf <&1 | tee pg_load_out.txt +if grep 'ERROR' pg_load_out.txt +then + exit 1 +fi diff --git a/pg_clickhouse/queries.sql b/pg_clickhouse/queries.sql new file mode 100644 index 000000000..31f65fc89 --- /dev/null +++ b/pg_clickhouse/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_clickhouse/run.sh b/pg_clickhouse/run.sh new file mode 100755 index 000000000..0d33e13a5 --- /dev/null +++ b/pg_clickhouse/run.sh @@ -0,0 +1,14 @@ +#!/bin/bash + +TRIES=3 + +cat queries.sql | while read -r query; do + sync + echo 3 | sudo tee /proc/sys/vm/drop_caches + + echo "$query" + ( + echo '\timing' + yes "$query" | head -n $TRIES + ) | sudo -u postgres psql -e --no-psqlrc --tuples-only test 2>&1 | grep -P 'Time|psql: error' +done diff --git a/pg_clickhouse/template.json b/pg_clickhouse/template.json new file mode 100644 index 000000000..bc3914bf1 --- /dev/null +++ b/pg_clickhouse/template.json @@ -0,0 +1,12 @@ +{ + "system": "pg_clickhouse", + "proprietary": "no", + "hardware": "cpu", + "tuned": "no", + "tags": [ + "C", + "column-oriented", + "PostgreSQL compatible", + "lukewarm-cold-run" + ] +}