Public Repository

Last pushed: 2 years ago
Short Description
ubuntu 14.10, hadoop 2.6.0 (single node setup), tajo 0.10.0
Full Description

Hadoop 2.6.0 / tajo 0.10.0 / ubuntu 14.10

Pull the image

sudo docker pull cdecl/hadoop-tajo:2.6.0

Start a container

sudo docker run -i -t  --name tajo cdecl/hadoop-tajo:2.6.0 /etc/bootstrap.sh -bash

root@0bfa9279e282:/# jps
129 NameNode
243 DataNode
392 SecondaryNameNode
617 NodeManager
938 Jps
527 ResourceManager

Testing


# hive tsql 
# /usr/local/tajo/bin/tsql 
$tajo_home/bin/tsql
default> \d country 

table name: default.country
table path: file:/root/data/country.csv
store type: CSV
number of rows: unknown
volume: 9.1 kB
Options:
        'text.delimiter'=','

schema:
no      INT4
name    TEXT
fname   TEXT
default> SELECT * FROM country limit 5;
no,  name,  fname
-------------------------------
,  Islamic State of Afghanistan,
2,  Albania,  Republic of Albania
3,  Algeria,  People's Democratic Republic of Algeria
4,  Andorra,  Principality of Andorra
5,  Angola,  Republic of Angola
(5 rows, 0.819 sec, 8.9 KiB selected)
default> SELECT COUNT(*) FROM country;
Progress: 0%, response time: 1.784 sec
Progress: 0%, response time: 1.789 sec
Progress: 0%, response time: 2.197 sec
Progress: 100%, response time: 2.865 sec
?count
-------------------------------
269
(1 rows, 2.865 sec, 4 B selected)
default> SELECT SUBSTR(name,1,1) pre, COUNT(*) cnt FROM country GROUP BY SUBSTR(name,1,1);
Progress: 0%, response time: 0.318 sec
Progress: 0%, response time: 0.319 sec
Progress: 100%, response time: 0.486 sec
pre,  cnt
-------------------------------
,  1
A,  18
I,  10
Z,  2
N,  17
M,  24
T,  14
P,  14
V,  4
J,  6
B,  23
Q,  2
C,  21
L,  9
",  8
D,  4
Y,  1
F,  8
W,  2
O,  1
H,  6
G,  15
E,  7
U,  8
K,  6
S,  33
R,  5
(27 rows, 0.486 sec, 119 B selected)

Docker Pull Command
Owner
cdecl