Skip to content

Commit b6cf2d6

Browse files
Merge branch 'main' into glaredb
2 parents 3ebf32e + d81c922 commit b6cf2d6

File tree

12 files changed

+599
-49
lines changed

12 files changed

+599
-49
lines changed

index.html

Lines changed: 4 additions & 2 deletions
Large diffs are not rendered by default.

motherduck/benchmark.sh

Lines changed: 37 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
1+
#!/bin/bash
2+
3+
# Install
4+
5+
sudo apt-get update
6+
sudo apt-get install -y python3-pip
7+
pip install duckdb psutil
8+
9+
# Load the data
10+
11+
# Open https://app.motherduck.com/ and paste the contents of create.sql
12+
13+
# Then run:
14+
# COPY hits FROM 'https://clickhouse-public-datasets.s3.amazonaws.com/hits_compatible/hits.csv.gz'
15+
16+
# 4122 seconds
17+
18+
# Note: it does not support transactions,
19+
# and an attempt to query the table during leaded results in waiting on a global lock.
20+
21+
# Install the command line tool
22+
23+
wget https://github.com/duckdb/duckdb/releases/download/v0.9.2/duckdb_cli-linux-amd64.zip
24+
unzip duckdb_cli-linux-amd64.zip
25+
26+
./duckdb
27+
28+
# .open md:
29+
# Authenticate and obtain a token.
30+
# export motherduck_token=...
31+
32+
# Run the queries
33+
34+
./run.sh 2>&1 | tee log.txt
35+
36+
cat log.txt | grep -P '^\d|Killed|Segmentation' | sed -r -e 's/^.*(Killed|Segmentation).*$/null\nnull\nnull/' |
37+
awk '{ if (i % 3 == 0) { printf "[" }; printf $1; if (i % 3 != 2) { printf "," } else { print "]," }; ++i; }'

motherduck/create.sql

Lines changed: 108 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,108 @@
1+
CREATE TABLE hits
2+
(
3+
WatchID BIGINT NOT NULL,
4+
JavaEnable SMALLINT NOT NULL,
5+
Title TEXT,
6+
GoodEvent SMALLINT 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 SMALLINT NOT NULL,
14+
OS SMALLINT NOT NULL,
15+
UserAgent SMALLINT NOT NULL,
16+
URL TEXT,
17+
Referer TEXT,
18+
IsRefresh SMALLINT NOT NULL,
19+
RefererCategoryID SMALLINT NOT NULL,
20+
RefererRegionID INTEGER NOT NULL,
21+
URLCategoryID SMALLINT NOT NULL,
22+
URLRegionID INTEGER NOT NULL,
23+
ResolutionWidth SMALLINT NOT NULL,
24+
ResolutionHeight SMALLINT NOT NULL,
25+
ResolutionDepth SMALLINT NOT NULL,
26+
FlashMajor SMALLINT NOT NULL,
27+
FlashMinor SMALLINT NOT NULL,
28+
FlashMinor2 TEXT,
29+
NetMajor SMALLINT NOT NULL,
30+
NetMinor SMALLINT NOT NULL,
31+
UserAgentMajor SMALLINT NOT NULL,
32+
UserAgentMinor VARCHAR(255) NOT NULL,
33+
CookieEnable SMALLINT NOT NULL,
34+
JavascriptEnable SMALLINT NOT NULL,
35+
IsMobile SMALLINT NOT NULL,
36+
MobilePhone SMALLINT NOT NULL,
37+
MobilePhoneModel TEXT,
38+
Params TEXT,
39+
IPNetworkID INTEGER NOT NULL,
40+
TraficSourceID SMALLINT NOT NULL,
41+
SearchEngineID SMALLINT NOT NULL,
42+
SearchPhrase TEXT,
43+
AdvEngineID SMALLINT NOT NULL,
44+
IsArtifical SMALLINT NOT NULL,
45+
WindowClientWidth SMALLINT NOT NULL,
46+
WindowClientHeight SMALLINT NOT NULL,
47+
ClientTimeZone SMALLINT NOT NULL,
48+
ClientEventTime TIMESTAMP NOT NULL,
49+
SilverlightVersion1 SMALLINT NOT NULL,
50+
SilverlightVersion2 SMALLINT NOT NULL,
51+
SilverlightVersion3 INTEGER NOT NULL,
52+
SilverlightVersion4 SMALLINT NOT NULL,
53+
PageCharset TEXT,
54+
CodeVersion INTEGER NOT NULL,
55+
IsLink SMALLINT NOT NULL,
56+
IsDownload SMALLINT NOT NULL,
57+
IsNotBounce SMALLINT NOT NULL,
58+
FUniqID BIGINT NOT NULL,
59+
OriginalURL TEXT,
60+
HID INTEGER NOT NULL,
61+
IsOldCounter SMALLINT NOT NULL,
62+
IsEvent SMALLINT NOT NULL,
63+
IsParameter SMALLINT NOT NULL,
64+
DontCountHits SMALLINT NOT NULL,
65+
WithHash SMALLINT NOT NULL,
66+
HitColor CHAR NOT NULL,
67+
LocalEventTime TIMESTAMP NOT NULL,
68+
Age SMALLINT NOT NULL,
69+
Sex SMALLINT NOT NULL,
70+
Income SMALLINT NOT NULL,
71+
Interests SMALLINT NOT NULL,
72+
Robotness SMALLINT NOT NULL,
73+
RemoteIP INTEGER NOT NULL,
74+
WindowName INTEGER NOT NULL,
75+
OpenerName INTEGER NOT NULL,
76+
HistoryLength SMALLINT NOT NULL,
77+
BrowserLanguage TEXT,
78+
BrowserCountry TEXT,
79+
SocialNetwork TEXT,
80+
SocialAction TEXT,
81+
HTTPError SMALLINT 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 SMALLINT NOT NULL,
89+
SocialSourcePage TEXT,
90+
ParamPrice BIGINT NOT NULL,
91+
ParamOrderID TEXT,
92+
ParamCurrency TEXT,
93+
ParamCurrencyID SMALLINT NOT NULL,
94+
OpenstatServiceName TEXT,
95+
OpenstatCampaignID TEXT,
96+
OpenstatAdID TEXT,
97+
OpenstatSourceID TEXT,
98+
UTMSource TEXT,
99+
UTMMedium TEXT,
100+
UTMCampaign TEXT,
101+
UTMContent TEXT,
102+
UTMTerm TEXT,
103+
FromTag TEXT,
104+
HasGCLID SMALLINT NOT NULL,
105+
RefererHash BIGINT NOT NULL,
106+
URLHash BIGINT NOT NULL,
107+
CLID INTEGER NOT NULL
108+
);

motherduck/log.txt

Lines changed: 215 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,215 @@
1+
SELECT COUNT(*) FROM hits;
2+
3+
0.21968004433438182
4+
0.3162029208615422
5+
0.21604336006566882
6+
SELECT COUNT(*) FROM hits WHERE AdvEngineID <> 0;
7+
8+
0.33489555725827813
9+
0.29951094510033727
10+
0.21411490021273494
11+
SELECT SUM(AdvEngineID), COUNT(*), AVG(ResolutionWidth) FROM hits;
12+
13+
0.4648742200806737
14+
0.3040045131929219
15+
0.30952421203255653
16+
SELECT AVG(UserID) FROM hits;
17+
18+
0.6499226209707558
19+
0.22191201290115714
20+
0.2888053017668426
21+
SELECT COUNT(DISTINCT UserID) FROM hits;
22+
23+
0.7704195859842002
24+
0.921060211956501
25+
0.819766622968018
26+
SELECT COUNT(DISTINCT SearchPhrase) FROM hits;
27+
28+
1.9447067943401635
29+
1.2225632020272315
30+
1.3308632392436266
31+
SELECT MIN(EventDate), MAX(EventDate) FROM hits;
32+
33+
0.2486483482643962
34+
0.22854855004698038
35+
0.20795917278155684
36+
SELECT AdvEngineID, COUNT(*) FROM hits WHERE AdvEngineID <> 0 GROUP BY AdvEngineID ORDER BY COUNT(*) DESC;
37+
38+
0.22081567207351327
39+
0.2213178831152618
40+
0.2327750907279551
41+
SELECT RegionID, COUNT(DISTINCT UserID) AS u FROM hits GROUP BY RegionID ORDER BY u DESC LIMIT 10;
42+
43+
1.3735258071683347
44+
1.2279518628492951
45+
1.0233631990849972
46+
SELECT RegionID, SUM(AdvEngineID), COUNT(*) AS c, AVG(ResolutionWidth), COUNT(DISTINCT UserID) FROM hits GROUP BY RegionID ORDER BY c DESC LIMIT 10;
47+
48+
1.277890115045011
49+
1.3313516019843519
50+
1.1260047918185592
51+
SELECT MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhoneModel ORDER BY u DESC LIMIT 10;
52+
53+
0.6073150201700628
54+
0.2593280617147684
55+
0.3234165138565004
56+
SELECT MobilePhone, MobilePhoneModel, COUNT(DISTINCT UserID) AS u FROM hits WHERE MobilePhoneModel <> '' GROUP BY MobilePhone, MobilePhoneModel ORDER BY u DESC LIMIT 10;
57+
58+
0.34701970824971795
59+
0.32168390695005655
60+
0.3142702719196677
61+
SELECT SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
62+
63+
1.0892055933363736
64+
1.1165755479596555
65+
0.8717481149360538
66+
SELECT SearchPhrase, COUNT(DISTINCT UserID) AS u FROM hits WHERE SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY u DESC LIMIT 10;
67+
68+
1.5503880502656102
69+
1.6257044719532132
70+
1.464306827634573
71+
SELECT SearchEngineID, SearchPhrase, COUNT(*) AS c FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, SearchPhrase ORDER BY c DESC LIMIT 10;
72+
73+
0.9123282572254539
74+
0.7499142647720873
75+
0.8189653856679797
76+
SELECT UserID, COUNT(*) FROM hits GROUP BY UserID ORDER BY COUNT(*) DESC LIMIT 10;
77+
78+
0.9769321829080582
79+
0.8805147060193121
80+
0.8598887426778674
81+
SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
82+
83+
1.8943038629367948
84+
2.4523583548143506
85+
2.457844952121377
86+
SELECT UserID, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, SearchPhrase LIMIT 10;
87+
88+
2.4018522929400206
89+
2.1315763420425355
90+
2.188034536782652
91+
SELECT UserID, extract(minute FROM EventTime) AS m, SearchPhrase, COUNT(*) FROM hits GROUP BY UserID, m, SearchPhrase ORDER BY COUNT(*) DESC LIMIT 10;
92+
93+
7.007666043005884
94+
5.863597965799272
95+
5.461284582037479
96+
SELECT UserID FROM hits WHERE UserID = 435090932899640449;
97+
98+
0.24364612391218543
99+
0.325953362043947
100+
0.3064295807853341
101+
SELECT COUNT(*) FROM hits WHERE URL LIKE '%google%';
102+
103+
15.391365340910852
104+
0.8924880139529705
105+
0.8800020259805024
106+
SELECT SearchPhrase, MIN(URL), COUNT(*) AS c FROM hits WHERE URL LIKE '%google%' AND SearchPhrase <> '' GROUP BY SearchPhrase ORDER BY c DESC LIMIT 10;
107+
108+
1.0099374479614198
109+
0.7060354948043823
110+
0.7063306840136647
111+
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;
112+
113+
8.954986380413175
114+
4.095173366833478
115+
3.279917892999947
116+
SELECT * FROM hits WHERE URL LIKE '%google%' ORDER BY EventTime LIMIT 10;
117+
118+
23.613256133161485
119+
19.25096853263676
120+
23.278139277826995
121+
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime LIMIT 10;
122+
123+
1.5025351103395224
124+
0.7977945390157402
125+
0.6170151601545513
126+
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY SearchPhrase LIMIT 10;
127+
128+
0.46431142510846257
129+
0.4349544760771096
130+
0.36817489471286535
131+
SELECT SearchPhrase FROM hits WHERE SearchPhrase <> '' ORDER BY EventTime, SearchPhrase LIMIT 10;
132+
133+
0.5523030371405184
134+
0.5110767548903823
135+
0.3649540198966861
136+
SELECT CounterID, AVG(STRLEN(URL)) AS l, COUNT(*) AS c FROM hits WHERE URL <> '' GROUP BY CounterID HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
137+
138+
4.98280710587278
139+
2.0472186598926783
140+
2.6902666091918945
141+
SELECT REGEXP_REPLACE(Referer, '^https?://(?:www.)?([^/]+)/.*$', '1') AS k, AVG(STRLEN(Referer)) AS l, COUNT(*) AS c, MIN(Referer) FROM hits WHERE Referer <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
142+
143+
6.719612340908498
144+
4.538661384955049
145+
4.369533614721149
146+
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;
147+
148+
3.358773229178041
149+
3.1345412940718234
150+
3.100874589756131
151+
SELECT SearchEngineID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY SearchEngineID, ClientIP ORDER BY c DESC LIMIT 10;
152+
153+
2.000370934139937
154+
1.3284917967393994
155+
1.2289274740032852
156+
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits WHERE SearchPhrase <> '' GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
157+
158+
3.7089375513605773
159+
2.681138473097235
160+
1.91789041319862
161+
SELECT WatchID, ClientIP, COUNT(*) AS c, SUM(IsRefresh), AVG(ResolutionWidth) FROM hits GROUP BY WatchID, ClientIP ORDER BY c DESC LIMIT 10;
162+
163+
7.777549963910133
164+
7.958697326015681
165+
7.435122138820589
166+
SELECT URL, COUNT(*) AS c FROM hits GROUP BY URL ORDER BY c DESC LIMIT 10;
167+
168+
9.89957385417074
169+
6.938831991981715
170+
5.757995248306543
171+
SELECT 1, URL, COUNT(*) AS c FROM hits GROUP BY 1, URL ORDER BY c DESC LIMIT 10;
172+
173+
5.393568014726043
174+
5.632281670346856
175+
5.551704770885408
176+
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;
177+
178+
1.4525640471838415
179+
0.8954971083439887
180+
0.9103033309802413
181+
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;
182+
183+
0.22383009875193238
184+
0.2152935261838138
185+
0.21353887394070625
186+
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;
187+
188+
0.2124440912157297
189+
0.20737810991704464
190+
0.20923770079389215
191+
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;
192+
193+
0.2175677828490734
194+
0.23641109932214022
195+
0.22010038886219263
196+
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;
197+
198+
0.24250942608341575
199+
0.21723396237939596
200+
0.2134688631631434
201+
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;
202+
203+
0.21473077218979597
204+
0.2085639163851738
205+
0.251109620090574
206+
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;
207+
208+
0.21749612782150507
209+
0.24898552894592285
210+
0.20936914114281535
211+
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;
212+
213+
0.2193519319407642
214+
0.2155164610594511
215+
0.20863541215658188

0 commit comments

Comments
 (0)