Skip to content

Commit e30aebe

Browse files
authored
Merge pull request #397 from ClickHouse/reintroduce-oxla
Revert "Temporarily remove Oxla"
2 parents 4fd03cb + bed277a commit e30aebe

5 files changed

Lines changed: 273 additions & 0 deletions

File tree

oxla/benchmark.sh

Lines changed: 37 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
1+
#!/bin/bash -e
2+
3+
# docker
4+
sudo apt install docker.io
5+
6+
# base
7+
sudo apt-get install -y postgresql-client curl wget apt-transport-https ca-certificates software-properties-common gnupg2 parallel
8+
sudo DEBIAN_FRONTEND=noninteractive apt-get install -y build-essential
9+
10+
# download dataset
11+
echo "Download dataset."
12+
wget --continue 'https://datasets.clickhouse.com/hits_compatible/hits.csv.gz'
13+
echo "Unpack dataset."
14+
gzip -d -f hits.csv.gz
15+
mkdir data
16+
mv hits.csv data
17+
18+
# get and configure Oxla image
19+
echo "Install and run Oxla."
20+
21+
docker run --rm -p 5432:5432 -v data:/data --name oxlacontainer public.ecr.aws/oxla/release:1.53.0-beta > /dev/null 2>&1 &
22+
sleep 30 # waiting for container start and db initialisation (leader election, etc.)
23+
24+
# create table and ingest data
25+
export PGCLIENTENCODING=UTF8
26+
27+
PGPASSWORD=oxla psql -h localhost -U oxla -t < create.sql
28+
echo "Insert data."
29+
PGPASSWORD=oxla psql -h localhost -U oxla -t -c '\timing' -c "COPY hits FROM '/data/hits.csv';"
30+
31+
# get ingested data size
32+
echo "data size after ingest:"
33+
PGPASSWORD=oxla psql -h localhost -U oxla -t -c '\timing' -c "SELECT pg_total_relation_size('hits');"
34+
35+
# run benchmark
36+
echo "running benchmark..."
37+
./run.sh

oxla/create.sql

Lines changed: 109 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,109 @@
1+
CREATE TABLE hits
2+
(
3+
WatchID BIGINT NOT NULL,
4+
JavaEnable INT NOT NULL,
5+
Title TEXT NOT NULL,
6+
GoodEvent INT NOT NULL,
7+
EventTime TIMESTAMP NOT NULL,
8+
EventDate Date NOT NULL,
9+
CounterID INTEGER NOT NULL,
10+
ClientIP INTEGER NOT NULL,
11+
RegionID INTEGER NOT NULL,
12+
UserID BIGINT NOT NULL,
13+
CounterClass INT NOT NULL,
14+
OS INT NOT NULL,
15+
UserAgent INT NOT NULL,
16+
URL TEXT NOT NULL,
17+
Referer TEXT NOT NULL,
18+
IsRefresh INT NOT NULL,
19+
RefererCategoryID INT NOT NULL,
20+
RefererRegionID INTEGER NOT NULL,
21+
URLCategoryID INT NOT NULL,
22+
URLRegionID INTEGER NOT NULL,
23+
ResolutionWidth INT NOT NULL,
24+
ResolutionHeight INT NOT NULL,
25+
ResolutionDepth INT NOT NULL,
26+
FlashMajor INT NOT NULL,
27+
FlashMinor INT NOT NULL,
28+
FlashMinor2 TEXT NOT NULL,
29+
NetMajor INT NOT NULL,
30+
NetMinor INT NOT NULL,
31+
UserAgentMajor INT NOT NULL,
32+
UserAgentMinor TEXT NOT NULL,
33+
CookieEnable INT NOT NULL,
34+
JavascriptEnable INT NOT NULL,
35+
IsMobile INT NOT NULL,
36+
MobilePhone INT NOT NULL,
37+
MobilePhoneModel TEXT NOT NULL,
38+
Params TEXT NOT NULL,
39+
IPNetworkID INTEGER NOT NULL,
40+
TraficSourceID INT NOT NULL,
41+
SearchEngineID INT NOT NULL,
42+
SearchPhrase TEXT NOT NULL,
43+
AdvEngineID INT NOT NULL,
44+
IsArtifical INT NOT NULL,
45+
WindowClientWidth INT NOT NULL,
46+
WindowClientHeight INT NOT NULL,
47+
ClientTimeZone INT NOT NULL,
48+
ClientEventTime TIMESTAMP NOT NULL,
49+
SilverlightVersion1 INT NOT NULL,
50+
SilverlightVersion2 INT NOT NULL,
51+
SilverlightVersion3 INTEGER NOT NULL,
52+
SilverlightVersion4 INT NOT NULL,
53+
PageCharset TEXT NOT NULL,
54+
CodeVersion INTEGER NOT NULL,
55+
IsLink INT NOT NULL,
56+
IsDownload INT NOT NULL,
57+
IsNotBounce INT NOT NULL,
58+
FUniqID BIGINT NOT NULL,
59+
OriginalURL TEXT NOT NULL,
60+
HID INTEGER NOT NULL,
61+
IsOldCounter INT NOT NULL,
62+
IsEvent INT NOT NULL,
63+
IsParameter INT NOT NULL,
64+
DontCountHits INT NOT NULL,
65+
WithHash INT NOT NULL,
66+
HitColor CHAR NOT NULL,
67+
LocalEventTime TIMESTAMP NOT NULL,
68+
Age INT NOT NULL,
69+
Sex INT NOT NULL,
70+
Income INT NOT NULL,
71+
Interests INT NOT NULL,
72+
Robotness INT NOT NULL,
73+
RemoteIP INTEGER NOT NULL,
74+
WindowName INTEGER NOT NULL,
75+
OpenerName INTEGER NOT NULL,
76+
HistoryLength INT NOT NULL,
77+
BrowserLanguage TEXT NOT NULL,
78+
BrowserCountry TEXT NOT NULL,
79+
SocialNetwork TEXT NOT NULL,
80+
SocialAction TEXT NOT NULL,
81+
HTTPError INT NOT NULL,
82+
SendTiming INTEGER NOT NULL,
83+
DNSTiming INTEGER NOT NULL,
84+
ConnectTiming INTEGER NOT NULL,
85+
ResponseStartTiming INTEGER NOT NULL,
86+
ResponseEndTiming INTEGER NOT NULL,
87+
FetchTiming INTEGER NOT NULL,
88+
SocialSourceNetworkID INT NOT NULL,
89+
SocialSourcePage TEXT NOT NULL,
90+
ParamPrice BIGINT NOT NULL,
91+
ParamOrderID TEXT NOT NULL,
92+
ParamCurrency TEXT NOT NULL,
93+
ParamCurrencyID INT NOT NULL,
94+
OpenstatServiceName TEXT NOT NULL,
95+
OpenstatCampaignID TEXT NOT NULL,
96+
OpenstatAdID TEXT NOT NULL,
97+
OpenstatSourceID TEXT NOT NULL,
98+
UTMSource TEXT NOT NULL,
99+
UTMMedium TEXT NOT NULL,
100+
UTMCampaign TEXT NOT NULL,
101+
UTMContent TEXT NOT NULL,
102+
UTMTerm TEXT NOT NULL,
103+
FromTag TEXT NOT NULL,
104+
HasGCLID INT NOT NULL,
105+
RefererHash BIGINT NOT NULL,
106+
URLHash BIGINT NOT NULL,
107+
CLID INTEGER NOT NULL
108+
);
109+
CREATE INDEX hits ON hits(CounterID, EventDate, UserID, EventTime, WatchID);

oxla/queries.sql

Lines changed: 43 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,43 @@
1+
SELECT COUNT(*) FROM hits;
2+
SELECT COUNT(*) FROM hits WHERE AdvEngineID <> 0;
3+
SELECT SUM(AdvEngineID), COUNT(*), AVG(ResolutionWidth) FROM hits;
4+
SELECT AVG(UserID) FROM hits;
5+
SELECT COUNT(DISTINCT UserID) FROM hits;
6+
SELECT COUNT(DISTINCT SearchPhrase) FROM hits;
7+
SELECT MIN(EventDate), MAX(EventDate) FROM hits;
8+
SELECT AdvEngineID, COUNT(*) FROM hits WHERE AdvEngineID <> 0 GROUP BY AdvEngineID ORDER BY COUNT(*) DESC;
9+
SELECT RegionID, COUNT(DISTINCT UserID) AS u FROM hits GROUP BY RegionID ORDER BY u DESC LIMIT 10;
10+
SELECT RegionID, SUM(AdvEngineID), COUNT(*) AS c, AVG(ResolutionWidth), COUNT(DISTINCT UserID) FROM hits GROUP BY RegionID ORDER BY c DESC LIMIT 10;
11+
SELECT MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhoneModel ORDER BY u DESC LIMIT 10;
12+
SELECT MobilePhone, MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhone, MobilePhoneModel ORDER BY u DESC LIMIT 10;
13+
SELECT SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
14+
SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
15+
SELECT SearchEngineID, SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, SearchPhrase ORDER BY c DESC LIMIT 10;
16+
SELECT UserID, COUNT(*) FROM hits GROUP BY UserID ORDER BY COUNT(*) DESC LIMIT 10;
17+
SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
18+
SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase LIMIT 10;
19+
SELECT UserID, extract(minute FROM EventTime) AS m, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, m, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
20+
SELECT UserID FROM hits WHERE UserID = 435090932899640449;
21+
SELECT COUNT(*) FROM hits WHERE URL LIKE '%google%';
22+
SELECT SearchPhrase, MIN(URL), COUNT(*) AS c FROM hits WHERE URL LIKE '%google%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
23+
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;
24+
SELECT * FROM hits WHERE URL LIKE '%google%' ORDER BY EventTime LIMIT 10;
25+
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime LIMIT 10;
26+
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY SearchPhrase LIMIT 10;
27+
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime, SearchPhrase LIMIT 10;
28+
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;
29+
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;
30+
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;
31+
SELECT SearchEngineID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, ClientIP ORDER BY c DESC LIMIT 10;
32+
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
33+
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
34+
SELECT URL, COUNT(*) AS c FROM hits GROUP BY URL ORDER BY c DESC LIMIT 10;
35+
SELECT 1, URL, COUNT(*) AS c FROM hits GROUP BY 1, URL ORDER BY c DESC LIMIT 10;
36+
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;
37+
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;
38+
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;
39+
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;
40+
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;
41+
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;
42+
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;
43+
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;

oxla/results/c6a.4xlarge.json

Lines changed: 56 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,56 @@
1+
{
2+
"system": "Oxla",
3+
"date": "2025-06-11",
4+
"machine": "c6a.4xlarge, 500gb gp2",
5+
"cluster_size": 1,
6+
"comment": "",
7+
"tags": ["C", "analytical"],
8+
"load_time": 635.603,
9+
"data_size": 17793214380,
10+
"result": [
11+
[0.052347,0.030264,0.030228],
12+
[0.062226,0.009381,0.010118],
13+
[0.040937,0.015792,0.020456],
14+
[2.132678,0.026229,0.024452],
15+
[1.017426,0.872372,0.944348],
16+
[1.063853,1.050624,1.055036],
17+
[0.028816,0.010628,0.011829],
18+
[0.033048,0.012598,0.014146],
19+
[1.641083,1.446135,1.490118],
20+
[1.717047,1.718439,1.675542],
21+
[0.167336,0.129325,0.139635],
22+
[0.284495,0.145598,0.139355],
23+
[0.811683,0.789845,0.780913],
24+
[1.592302,1.571212,1.582707],
25+
[0.849855,0.864973,0.864838],
26+
[0.939134,0.919764,0.988143],
27+
[2.641819,2.582476,2.637736],
28+
[2.661736,2.61648,2.616304],
29+
[4.426511,4.369487,4.422171],
30+
[0.063263,0.06312,0.057836],
31+
[0.715382,0.648103,0.643212],
32+
[0.691272,0.669008,0.668395],
33+
[4.979434,1.326322,1.330964],
34+
[30.535805,3.886141,3.880511],
35+
[0.114321,0.0908,0.093683],
36+
[0.127294,0.11026,0.109727],
37+
[0.162521,0.146817,0.144501],
38+
[0.618689,0.604913,0.602771],
39+
[48.945167,48.921188,48.977237]
40+
[0.090021,0.066386,0.083196],
41+
[0.431039,0.418915,0.402465],
42+
[0.700671,0.679638,0.677898],
43+
[9.445777,9.494664,8.816463],
44+
[5.692106,5.757299,5.616988],
45+
[5.769798,5.878441,6.109453],
46+
[0.704721,0.659585,0.648573],
47+
[0.109971,0.061908,0.059264],
48+
[0.072494,0.025726,0.022989],
49+
[0.083827,0.039265,0.038213],
50+
[0.176781,0.131152,0.130183],
51+
[0.109846,0.019355,0.009303],
52+
[0.089039,0.026107,0.02009],
53+
[0.027212,0.015049,0.017691]
54+
]
55+
}
56+

oxla/run.sh

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
#!/bin/bash
2+
3+
TRIES=3
4+
rm result.txt 2>/dev/null
5+
cat queries.sql | while read -r query; do
6+
sync
7+
echo 3 | sudo tee /proc/sys/vm/drop_caches
8+
9+
echo "$query";
10+
results=""
11+
if [[ "$query" == "SELECT NULL;" ]]; then
12+
results+="[null,null,null]"
13+
else
14+
results+="["
15+
for i in $(seq 1 $TRIES); do
16+
time=$(PGPASSWORD=oxla psql -h localhost -U oxla -t -c '\timing' -c "$query" | grep 'Time' | perl -nle 'm/Time: ([^ ]*) ms/; print $1 / 1000')
17+
echo "$time s"
18+
results+="$time,"
19+
done
20+
results=${results::-1}
21+
results+="]"
22+
fi
23+
echo "$results," >> result.txt
24+
done
25+
result=$(cat result.txt)
26+
result=${result::-1}
27+
echo "$result"
28+
rm result.txt 2>/dev/null

0 commit comments

Comments
 (0)