thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-25 00:52:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Redshift serverless

Browse Source
This commit is contained in:
Alexey Milovidov 2022-07-03 00:25:00 +02:00
parent 070349feb6
commit aefe64742d
15 changed files with 536 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
benchmark/compatible/databend/README.md Normal file
View File

@ -0,0 +1 @@
It failed to load the data.

90
benchmark/compatible/databend/benchmark.sh Normal file
View File

@ -0,0 +1,90 @@
#!/bin/bash
mkdir databend && cd databend
curl -LJO 'https://github.com/datafuselabs/databend/releases/download/v0.7.113-nightly/databend-v0.7.113-nightly-x86_64-unknown-linux-musl.tar.gz'
tar xzvf 'databend-v0.7.113-nightly-x86_64-unknown-linux-musl.tar.gz'
echo 'dir = "metadata/_logs"
admin_api_address = "127.0.0.1:8101"
grpc_api_address = "127.0.0.1:9101"
[raft_config]
id = 1
single = true
raft_dir = "metadata/datas"' > databend-meta.toml
./bin/databend-meta -c ./databend-meta.toml > meta.log 2>&1 &
curl -I 'http://127.0.0.1:8101/v1/health'
echo '[log]
level = "INFO"
dir = "benddata/_logs"
[query]
# For admin RESET API.
admin_api_address = "127.0.0.1:8001"
# Metrics.
metric_api_address = "127.0.0.1:7071"
# Cluster flight RPC.
flight_api_address = "127.0.0.1:9091"
# Query MySQL Handler.
mysql_handler_host = "127.0.0.1"
mysql_handler_port = 3307
# Query ClickHouse Handler.
clickhouse_handler_host = "127.0.0.1"
clickhouse_handler_port = 9001
# Query ClickHouse HTTP Handler.
clickhouse_http_handler_host = "127.0.0.1"
clickhouse_http_handler_port = 8125
# Query HTTP Handler.
http_handler_host = "127.0.0.1"
http_handler_port = 8081
tenant_id = "tenant1"
cluster_id = "cluster1"
[meta]
# databend-meta grpc api address.
address = "127.0.0.1:9101"
username = "root"
password = "root"
[storage]
# fs|s3
type = "fs"
[storage.fs]
data_path = "benddata/datas"' > databend-query.toml
./bin/databend-query -c ./databend-query.toml > query.log 2>&1 &
curl https://clickhouse.com/ | sh
sudo ./clickhouse install
# Load the data
curl 'http://default@localhost:8124/' --data-binary @create.sql
wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.csv.gz'
gzip -d hits.csv.gz
# Note: if I run
# clickhouse-client --time --query "INSERT INTO hits FORMAT TSV" < hits.tsv
# it panics:
# ERROR common_tracing::panic_hook: panicked at 'called `Result::unwrap()` on an `Err` value: SendError
# Note: if I run
# curl -XPUT 'http://root:@127.0.0.1:8000/v1/streaming_load' -H 'insert_sql: insert into hits format CSV' -H 'skip_header: 0' -H 'field_delimiter: ,' -H 'record_delimiter: \n' -F 'upload=@"./hits.csv"'
# curl: (55) Send failure: Broken pipe
# This is not entirely correct, but starts to work:
# curl -XPUT 'http://root:@127.0.0.1:8000/v1/streaming_load' -H 'insert_sql: insert into hits format TSV' -H 'skip_header: 0' -H 'field_delimiter: \t' -H 'record_delimiter: \n' -F 'upload=@"./hits.tsv"'
# and fails after 7 minutes 38 seconds without loading any data:
# Code: 4000, displayText = invalid data (Expected to have terminated string literal.) (while in processor thread 5).
# the diagnostics is terrible.

109
benchmark/compatible/databend/create.sql Normal file
View File

@ -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
)
CLUSTER BY (CounterID, EventDate, UserID, EventTime, WatchID);

43
benchmark/compatible/databend/queries.sql Normal file
View File

@ -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;

20
benchmark/compatible/databend/run.sh Executable file
View File

@ -0,0 +1,20 @@
#!/bin/bash
TRIES=3
QUERY_NUM=1
cat queries.sql | while read query; do
sync
echo 3 | sudo tee /proc/sys/vm/drop_caches >/dev/null
echo -n "["
for i in $(seq 1 $TRIES); do
RES=$(clickhouse-client --time --format=Null --query="$query" 2>&1 ||:)
[[ "$?" == "0" ]] && echo -n "${RES}" || echo -n "null"
[[ "$i" != $TRIES ]] && echo -n ", "
echo "${QUERY_NUM},${i},${RES}" >> result.csv
done
echo "],"
QUERY_NUM=$((QUERY_NUM + 1))
done

1
benchmark/compatible/monetdb/README.md
View File

@ -1 +0,0 @@
MonetDB failed to install.

55
benchmark/compatible/redshift-serverless/README.md Normal file
View File

@ -0,0 +1,55 @@
This benchmark is not automated.
Go to AWS Redshift service.
Try Redshift Serverless. Use the default configuration.
The cluster will take a few minutes to start.
Go to "Query Editor". Establishing a connection takes around 10 seconds.
Run the CREATE TABLE statement you find in `create.sql`.
Note: Redshift prefers VARCHAR(MAX) instead of TEXT.
Then press on the "Load data".
This will generate a statement:
```
COPY dev.public.hits FROM 's3://clickhouse-public-datasets/hits_compatible/hits.csv.gz' GZIP
IAM_ROLE 'arn:aws:iam::...:role/service-role/AmazonRedshift-CommandsAccessRole-...'
FORMAT AS CSV DELIMITER ',' QUOTE '"'
REGION AS 'eu-central-1'
```
> Elapsed time: 32m 13.7s
It also have run 2380 "queries" for this task.
Namespace configuration,
General Information, Storage used:
30.3 GB
Change admin user password:
dev, fGH4{dbas7
It's very difficult to find how to connect to it:
https://docs.aws.amazon.com/redshift/latest/mgmt/serverless-connecting.html
We will run the queries from another server with `psql` client.
```
sudo apt-get install -y postgresql-client
echo "*:*:*:*:your_password" > .pgpass
chmod 400 .pgpass
psql -h default.111111111111.eu-central-1.redshift-serverless.amazonaws.com -U dev -d dev -p 5439
```
Then run the benchmark:
```
export HOST=...
./run.sh 2>&1 | tee log.txt
cat log.txt | grep -oP 'Time: \d+\.\d+ ms|ERROR' | sed -r -e 's/Time: ([0-9]+\.[0-9]+) ms/\1/' |
awk '{ if ($1 == "ERROR") { skip = 1 } else { if (i % 3 == 0) { printf "[" }; printf skip ? "null" : ($1 / 1000); if (i % 3 != 2) { printf "," } else { print "]," }; ++i; skip = 0; } }'
```

109
benchmark/compatible/redshift-serverless/create.sql Normal file
View File

@ -0,0 +1,109 @@
CREATE TABLE hits
(
WatchID BIGINT NOT NULL,
JavaEnable SMALLINT NOT NULL,
Title VARCHAR(MAX) 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 VARCHAR(MAX) NOT NULL,
Referer VARCHAR(MAX) 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 VARCHAR(MAX) NOT NULL,
NetMajor SMALLINT NOT NULL,
NetMinor SMALLINT NOT NULL,
UserAgentMajor SMALLINT NOT NULL,
UserAgentMinor VARCHAR(MAX) NOT NULL,
CookieEnable SMALLINT NOT NULL,
JavascriptEnable SMALLINT NOT NULL,
IsMobile SMALLINT NOT NULL,
MobilePhone SMALLINT NOT NULL,
MobilePhoneModel VARCHAR(MAX) NOT NULL,
Params VARCHAR(MAX) NOT NULL,
IPNetworkID INTEGER NOT NULL,
TraficSourceID SMALLINT NOT NULL,
SearchEngineID SMALLINT NOT NULL,
SearchPhrase VARCHAR(MAX) 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 VARCHAR(MAX) NOT NULL,
CodeVersion INTEGER NOT NULL,
IsLink SMALLINT NOT NULL,
IsDownload SMALLINT NOT NULL,
IsNotBounce SMALLINT NOT NULL,
FUniqID BIGINT NOT NULL,
OriginalURL VARCHAR(MAX) 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 VARCHAR(MAX) 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 VARCHAR(MAX) NOT NULL,
BrowserCountry VARCHAR(MAX) NOT NULL,
SocialNetwork VARCHAR(MAX) NOT NULL,
SocialAction VARCHAR(MAX) 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 VARCHAR(MAX) NOT NULL,
ParamPrice BIGINT NOT NULL,
ParamOrderID VARCHAR(MAX) NOT NULL,
ParamCurrency VARCHAR(MAX) NOT NULL,
ParamCurrencyID SMALLINT NOT NULL,
OpenstatServiceName VARCHAR(MAX) NOT NULL,
OpenstatCampaignID VARCHAR(MAX) NOT NULL,
OpenstatAdID VARCHAR(MAX) NOT NULL,
OpenstatSourceID VARCHAR(MAX) NOT NULL,
UTMSource VARCHAR(MAX) NOT NULL,
UTMMedium VARCHAR(MAX) NOT NULL,
UTMCampaign VARCHAR(MAX) NOT NULL,
UTMContent VARCHAR(MAX) NOT NULL,
UTMTerm VARCHAR(MAX) NOT NULL,
FromTag VARCHAR(MAX) 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)
);

43
benchmark/compatible/redshift-serverless/queries.sql Normal file
View File

@ -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;

46
benchmark/compatible/redshift-serverless/result/serverless.txt Normal file
View File

@ -0,0 +1,46 @@
Load time: 32m 13.7s
Data size: 30.3 GB
[0.436955,0.390225,0.387823],
[2.74529,0.280571,0.198074],
[7.24569,0.295612,0.386568],
[null,null,null],
[3.98825,0.488446,0.325645],
[4.24601,0.538891,0.690124],
[7.25492,0.288505,0.207515],
[5.99594,0.212732,0.281278],
[6.17534,0.681868,0.586073],
[6.37779,1.37865,1.31614],
[6.41405,0.549735,0.421345],
[6.64688,0.445678,0.477323],
[4.2294,0.361772,0.520471],
[4.73701,0.788258,0.743465],
[4.49038,0.670446,0.52727],
[6.19886,0.663381,0.583588],
[5.9867,0.679607,0.672772],
[2.76661,0.567555,0.51494],
[6.20219,0.816422,0.760568],
[2.51526,0.053,0.025066],
[2.96003,0.282737,0.226979],
[6.79648,0.57495,0.400798],
[6.37854,0.92746,1.05793],
[25.8462,0.902664,0.905365],
[5.00521,0.247895,0.308836],
[6.38373,0.308781,0.244082],
[4.25427,0.229966,0.247201],
[5.98382,0.398218,0.455249],
[null,null,null],
[6.52367,1.35877,1.30562],
[7.36935,0.536226,0.582304],
[7.05948,0.621982,0.639653],
[4.62901,0.954522,0.908651],
[4.95273,1.03062,1.10289],
[4.71404,1.06378,1.04157],
[4.8201,0.499996,0.575546],
[5.32757,0.566517,0.562058],
[5.37681,0.626458,0.658628],
[5.23137,0.470622,0.540079],
[6.09326,0.561312,0.574978],
[4.86561,0.595546,0.534209],
[4.34256,0.433804,0.414541],
[4.19814,0.288269,0.415328]

10
benchmark/compatible/redshift-serverless/run.sh Normal file
View File

@ -0,0 +1,10 @@
#!/bin/bash
TRIES=3
cat queries.sql | while read query; do
echo "$query";
for i in $(seq 1 $TRIES); do
psql -h "${HOST}" -U awsuser -d dev -p 5439 -t -c 'SET enable_result_cache_for_session = off' -c '\timing' -c "$query" | grep 'Time'
done;
done;

4
benchmark/compatible/redshift/README.md
View File

@ -47,8 +47,8 @@ Then run the benchmark:
export HOST=...
./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; }'
cat log.txt | grep -oP 'Time: \d+\.\d+ ms|ERROR' | sed -r -e 's/Time: ([0-9]+\.[0-9]+) ms/\1/' |
awk '{ if ($1 == "ERROR") { skip = 1 } else { if (i % 3 == 0) { printf "[" }; printf skip ? "null" : ($1 / 1000); if (i % 3 != 2) { printf "," } else { print "]," }; ++i; skip = 0; } }'
```
`SELECT sum(used * 1048576) FROM stv_node_storage_capacity`

4
benchmark/compatible/redshift/result/4x.ra3.xplus.txt
View File

@ -4,7 +4,7 @@ Data size: 30 794 579 968
[0.081437,0.022376,0.022491],
[2.54868,0.024112,0.024072],
[2.62053,0.049948,0.049768],
[2.57591,0.020689,0.020651],
[null,null,null],
[0.62714,0.447655,0.43262],
[1.14153,1.09479,1.09441],
[0.153399,0.053941,0.048224],
@ -29,7 +29,7 @@ Data size: 30 794 579 968
[4.17199,0.469457,0.476302],
[6.24746,0.470935,0.482502],
[6.00065,2.08332,2.08059],
[0.695955,0.078488,0.077928],
[null,null,null],
[22.2567,18.5376,18.3441],
[5.37492,0.868068,0.849486],
[7.29067,1.06155,1.11209],

3
benchmark/compatible/starrocks/README.md Normal file
View File

@ -0,0 +1,3 @@
It requires providing an email for downloading.
But then the button on the website does not work and it does not download.
I cannot find the packages anywhere.

3
benchmark/compatible/starrocks/benchmark.sh Normal file
View File

@ -0,0 +1,3 @@
#!/bin/bash
# Install