remoteHadoopGem 0.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/remoteHadoopGem.rb +108 -0
- metadata +46 -0
@@ -0,0 +1,108 @@
|
|
1
|
+
require "uuidtools"
|
2
|
+
|
3
|
+
class RemoteHadoopGem
|
4
|
+
|
5
|
+
#
|
6
|
+
# ****** commandToHadoop ******
|
7
|
+
#
|
8
|
+
# function to run a command in a remote hadoop machine
|
9
|
+
# require:
|
10
|
+
# 1) username (to access the machine via ssh)
|
11
|
+
# 2) host (IP of the hadoop machine)
|
12
|
+
# 3) keyPathFile (path of the private key to access the machine)
|
13
|
+
# 4) command to execute
|
14
|
+
|
15
|
+
def self.commandToHadoop(username, host, keyPathFile, command)
|
16
|
+
res=`ssh -i "#{keyPathFile}" -o StrictHostKeyChecking=no "#{username}"@"#{host}" "export PATH=/hadoop/bin/:$PATH; cd /hadoop/; #{command}"`
|
17
|
+
return "#{res}"
|
18
|
+
end
|
19
|
+
|
20
|
+
#
|
21
|
+
# ****** commandToHadoopJobID ******
|
22
|
+
#
|
23
|
+
# function to run a command in a remote hadoop machine; returns the <job-id>
|
24
|
+
# require:
|
25
|
+
# 1) username (to access the machine via ssh)
|
26
|
+
# 2) host (IP of the hadoop machine)
|
27
|
+
# 3) keyPathFile (path of the private key to access the machine)
|
28
|
+
# 4) command to execute
|
29
|
+
|
30
|
+
def self.commandToHadoopJobID(username, host, keyPathFile, command)
|
31
|
+
# create a file with a random name to obtained the jobID
|
32
|
+
filename="tempJobID_"+UUIDTools::UUID.random_create.to_s
|
33
|
+
`ssh -n -f -i "#{keyPathFile}" "#{username}"@"#{host}" 'sh -c "export PATH=/hadoop/bin/:$PATH; cd /hadoop/; nohup #{command} >/dev/null 2>#{filename}.txt & " '`
|
34
|
+
res=`sleep 5; ssh -i "#{keyPathFile}" "#{username}"@"#{host}" "cat /hadoop/#{filename}.txt | grep 'Running job' " `
|
35
|
+
`ssh -i "#{keyPathFile}" "#{username}"@"#{host}" "rm /hadoop/#{filename}.txt"`
|
36
|
+
jobid=res.split[6]
|
37
|
+
|
38
|
+
return "#{jobid}"
|
39
|
+
end
|
40
|
+
|
41
|
+
#
|
42
|
+
# ****** copyFileTo ******
|
43
|
+
#
|
44
|
+
# function to copy a file in a remote hadoop machine
|
45
|
+
# require:
|
46
|
+
# 1) username (to access the machine via ssh)
|
47
|
+
# 2) host (IP of the hadoop machine)
|
48
|
+
# 3) keyPathFile (path of the private key to access the machine)
|
49
|
+
# 4) filePath (path of the local file)
|
50
|
+
# 5) destFilePath (path on the remote hadoop node)
|
51
|
+
|
52
|
+
def self.copyFileTo(username, host, keyPathFile, filePath, destFilePath)
|
53
|
+
res=`scp -r -i "#{keyPathFile}" -o StrictHostKeyChecking=no #{filePath} "#{username}"@"#{host}":#{destFilePath}`
|
54
|
+
end
|
55
|
+
|
56
|
+
#
|
57
|
+
# ****** readFileFrom ******
|
58
|
+
#
|
59
|
+
# function to read a file from a remote hadoop machine
|
60
|
+
# require:
|
61
|
+
# 1) username (to access the machine via ssh)
|
62
|
+
# 2) host (IP of the hadoop machine)
|
63
|
+
# 3) keyPathFile (path of the private key to access the machine)
|
64
|
+
# 4) destFilePath (path of the remote file to read)
|
65
|
+
#
|
66
|
+
|
67
|
+
def self.readFileFrom(username, host, keyPathFile, destFilePath)
|
68
|
+
res=`ssh -i "#{keyPathFile}" -o StrictHostKeyChecking=no "#{username}"@"#{host}" "cat #{destFilePath}"`
|
69
|
+
return "#{res}"
|
70
|
+
end
|
71
|
+
|
72
|
+
#
|
73
|
+
# ****** jobsList ******
|
74
|
+
#
|
75
|
+
# function to list the running jobs in a remote hadoop machine
|
76
|
+
# require:
|
77
|
+
# 1) username (to access the machine via ssh)
|
78
|
+
# 2) host (IP of the hadoop machine)
|
79
|
+
# 3) keyPathFile (path of the private key to access the machine)
|
80
|
+
#
|
81
|
+
|
82
|
+
def self.jobsList(username, host, keyPathFile)
|
83
|
+
res=`ssh -i "#{keyPathFile}" -o StrictHostKeyChecking=no "#{username}"@"#{host}" "export PATH=/hadoop/bin/:$PATH; cd /hadoop/; hadoop job -list "`
|
84
|
+
return "#{res}"
|
85
|
+
end
|
86
|
+
|
87
|
+
#
|
88
|
+
# ****** jobStatus ******
|
89
|
+
#
|
90
|
+
# function to read the status of a running job in a remote hadoop machine
|
91
|
+
# require:
|
92
|
+
# 1) username (to access the machine via ssh)
|
93
|
+
# 2) host (IP of the hadoop machine)
|
94
|
+
# 3) keyPathFile (path of the private key to access the machine)
|
95
|
+
# 4) job_id (id of the job)
|
96
|
+
#
|
97
|
+
|
98
|
+
def self.jobStatus(username, host, keyPathFile, job_id)
|
99
|
+
res=`ssh -i "#{keyPathFile}" -o StrictHostKeyChecking=no "#{username}"@"#{host}" "export PATH=/hadoop/bin/:$PATH; cd /hadoop/; hadoop job -status #{job_id} "`
|
100
|
+
return "#{res}"
|
101
|
+
end
|
102
|
+
|
103
|
+
|
104
|
+
def self.cleanTempFiles(username, host, keyPathFile)
|
105
|
+
`ssh -i "#{keyPathFile}" -o StrictHostKeyChecking=no "#{username}"@"#{host}" "export PATH=/hadoop/bin/:$PATH; cd /hadoop/; rm ./tempJobID_* "`
|
106
|
+
end
|
107
|
+
|
108
|
+
end
|
metadata
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: remoteHadoopGem
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Fraternale
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-08-06 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: A simple test gem
|
15
|
+
email: f.seby87@gmail.com
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- lib/remoteHadoopGem.rb
|
21
|
+
homepage: ''
|
22
|
+
licenses:
|
23
|
+
- MIT
|
24
|
+
post_install_message:
|
25
|
+
rdoc_options: []
|
26
|
+
require_paths:
|
27
|
+
- lib
|
28
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
29
|
+
none: false
|
30
|
+
requirements:
|
31
|
+
- - ! '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
35
|
+
none: false
|
36
|
+
requirements:
|
37
|
+
- - ! '>='
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
version: '0'
|
40
|
+
requirements: []
|
41
|
+
rubyforge_project:
|
42
|
+
rubygems_version: 1.8.25
|
43
|
+
signing_key:
|
44
|
+
specification_version: 3
|
45
|
+
summary: Hola!
|
46
|
+
test_files: []
|