fluent-plugin-webhdfs 0.2.1 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.travis.yml +0 -1
- data/README.md +12 -1
- data/fluent-plugin-webhdfs.gemspec +2 -1
- data/lib/fluent/plugin/out_webhdfs.rb +12 -7
- metadata +19 -19
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 08f6f306b0cc2e49582bc066e03d3460c69fd245
|
4
|
+
data.tar.gz: deb9774da6e4d8da83a844603254e4e3a069d78d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6dc0afebf5e982bcdfa12ae746f17925e4ddc4889a8d0fa4087d3d4d866889f9b3879b75b02a03ebcd833ce39d3815e614da2fc19305e14163101e7d3236c9e6
|
7
|
+
data.tar.gz: ddd01525b9bc7536eed1a36055298cddee927b7a8be8b1feb5ac913e07766faad050d2ff8c2d2203a12ad4a1ec79e587893f7b03faf989b4cbf7c9a07ab7576c
|
data/.travis.yml
CHANGED
data/README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
# fluent-plugin-webhdfs
|
2
2
|
|
3
|
-
Fluentd output plugin to write data into Hadoop HDFS over WebHDFS/HttpFs.
|
3
|
+
[Fluentd](http://fluentd.org/) output plugin to write data into Hadoop HDFS over WebHDFS/HttpFs.
|
4
4
|
|
5
5
|
WebHDFSOutput slices data by time (specified unit), and store these data as hdfs file of plain text. You can specify to:
|
6
6
|
|
@@ -26,6 +26,17 @@ To store data by time,tag,json (same with 'type file') over WebHDFS:
|
|
26
26
|
path /path/on/hdfs/access.log.%Y%m%d_%H.log
|
27
27
|
</match>
|
28
28
|
|
29
|
+
If you want JSON object only (without time or tag or both on header of lines), specify it by `output_include_time` or `output_include_tag` (default true):
|
30
|
+
|
31
|
+
<match access.**>
|
32
|
+
type webhdfs
|
33
|
+
host namenode.your.cluster.local
|
34
|
+
port 50070
|
35
|
+
path /path/on/hdfs/access.log.%Y%m%d_%H.log
|
36
|
+
output_include_time false
|
37
|
+
output_include_tag false
|
38
|
+
</match>
|
39
|
+
|
29
40
|
To specify namenode, `namenode` is also available:
|
30
41
|
|
31
42
|
<match access.**>
|
@@ -2,12 +2,13 @@
|
|
2
2
|
|
3
3
|
Gem::Specification.new do |gem|
|
4
4
|
gem.name = "fluent-plugin-webhdfs"
|
5
|
-
gem.version = "0.2.
|
5
|
+
gem.version = "0.2.2"
|
6
6
|
gem.authors = ["TAGOMORI Satoshi"]
|
7
7
|
gem.email = ["tagomoris@gmail.com"]
|
8
8
|
gem.summary = %q{Fluentd plugin to write data on HDFS over WebHDFS, with flexible formatting}
|
9
9
|
gem.description = %q{For WebHDFS and HttpFs of Hadoop HDFS}
|
10
10
|
gem.homepage = "https://github.com/fluent/fluent-plugin-webhdfs"
|
11
|
+
gem.license = "APLv2"
|
11
12
|
|
12
13
|
gem.files = `git ls-files`.split($\)
|
13
14
|
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
@@ -50,6 +50,11 @@ class Fluent::WebHDFSOutput < Fluent::TimeSlicedOutput
|
|
50
50
|
require 'webhdfs'
|
51
51
|
end
|
52
52
|
|
53
|
+
# Define `log` method for v0.10.42 or earlier
|
54
|
+
unless method_defined?(:log)
|
55
|
+
define_method("log") { $log }
|
56
|
+
end
|
57
|
+
|
53
58
|
def configure(conf)
|
54
59
|
if conf['path']
|
55
60
|
if conf['path'].index('%S')
|
@@ -125,7 +130,7 @@ class Fluent::WebHDFSOutput < Fluent::TimeSlicedOutput
|
|
125
130
|
begin
|
126
131
|
client.list('/')
|
127
132
|
rescue => e
|
128
|
-
|
133
|
+
log.warn "webhdfs check request failed. (namenode: #{client.host}:#{client.port}, error: #{e.message})"
|
129
134
|
available = false
|
130
135
|
end
|
131
136
|
available
|
@@ -138,11 +143,11 @@ class Fluent::WebHDFSOutput < Fluent::TimeSlicedOutput
|
|
138
143
|
super
|
139
144
|
|
140
145
|
if namenode_available(@client)
|
141
|
-
|
146
|
+
log.info "webhdfs connection confirmed: #{@namenode_host}:#{@namenode_port}"
|
142
147
|
return
|
143
148
|
end
|
144
149
|
if @client_standby && namenode_available(@client_standby)
|
145
|
-
|
150
|
+
log.info "webhdfs connection confirmed: #{@standby_namenode_host}:#{@standby_namenode_port}"
|
146
151
|
return
|
147
152
|
end
|
148
153
|
|
@@ -166,7 +171,7 @@ class Fluent::WebHDFSOutput < Fluent::TimeSlicedOutput
|
|
166
171
|
def namenode_failover
|
167
172
|
if @standby_namenode
|
168
173
|
@client, @client_standby = @client_standby, @client
|
169
|
-
|
174
|
+
log.warn "Namenode failovered, now using #{@client.host}:#{@client.port}."
|
170
175
|
end
|
171
176
|
end
|
172
177
|
|
@@ -199,18 +204,18 @@ class Fluent::WebHDFSOutput < Fluent::TimeSlicedOutput
|
|
199
204
|
begin
|
200
205
|
send_data(hdfs_path, chunk.read)
|
201
206
|
rescue => e
|
202
|
-
|
207
|
+
log.warn "failed to communicate hdfs cluster, path: #{hdfs_path}"
|
203
208
|
|
204
209
|
raise e if !@client_standby || failovered
|
205
210
|
|
206
211
|
if is_standby_exception(e) && namenode_available(@client_standby)
|
207
|
-
|
212
|
+
log.warn "Seems the connected host status is not active (maybe due to failovers). Gonna try another namenode immediately."
|
208
213
|
namenode_failover
|
209
214
|
failovered = true
|
210
215
|
retry
|
211
216
|
end
|
212
217
|
if ((@error_history.size + 1) >= @failures_before_use_standby) && namenode_available(@client_standby)
|
213
|
-
|
218
|
+
log.warn "Too many failures. Try to use the standby namenode instead."
|
214
219
|
namenode_failover
|
215
220
|
failovered = true
|
216
221
|
retry
|
metadata
CHANGED
@@ -1,83 +1,83 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: fluent-plugin-webhdfs
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- TAGOMORI Satoshi
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2014-03-07 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rake
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- -
|
17
|
+
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '0'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- -
|
24
|
+
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: fluentd
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- -
|
31
|
+
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: '0'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- -
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: fluent-mixin-plaintextformatter
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- -
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
47
|
version: 0.2.1
|
48
48
|
type: :runtime
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- -
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: 0.2.1
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: fluent-mixin-config-placeholders
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - ~>
|
59
|
+
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: 0.2.0
|
62
62
|
type: :runtime
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- - ~>
|
66
|
+
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: 0.2.0
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: webhdfs
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- -
|
73
|
+
- - ">="
|
74
74
|
- !ruby/object:Gem::Version
|
75
75
|
version: 0.5.3
|
76
76
|
type: :runtime
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
|
-
- -
|
80
|
+
- - ">="
|
81
81
|
- !ruby/object:Gem::Version
|
82
82
|
version: 0.5.3
|
83
83
|
description: For WebHDFS and HttpFs of Hadoop HDFS
|
@@ -87,8 +87,8 @@ executables: []
|
|
87
87
|
extensions: []
|
88
88
|
extra_rdoc_files: []
|
89
89
|
files:
|
90
|
-
- .gitignore
|
91
|
-
- .travis.yml
|
90
|
+
- ".gitignore"
|
91
|
+
- ".travis.yml"
|
92
92
|
- Gemfile
|
93
93
|
- LICENSE.txt
|
94
94
|
- README.md
|
@@ -98,7 +98,8 @@ files:
|
|
98
98
|
- test/helper.rb
|
99
99
|
- test/plugin/test_out_webhdfs.rb
|
100
100
|
homepage: https://github.com/fluent/fluent-plugin-webhdfs
|
101
|
-
licenses:
|
101
|
+
licenses:
|
102
|
+
- APLv2
|
102
103
|
metadata: {}
|
103
104
|
post_install_message:
|
104
105
|
rdoc_options: []
|
@@ -106,21 +107,20 @@ require_paths:
|
|
106
107
|
- lib
|
107
108
|
required_ruby_version: !ruby/object:Gem::Requirement
|
108
109
|
requirements:
|
109
|
-
- -
|
110
|
+
- - ">="
|
110
111
|
- !ruby/object:Gem::Version
|
111
112
|
version: '0'
|
112
113
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
113
114
|
requirements:
|
114
|
-
- -
|
115
|
+
- - ">="
|
115
116
|
- !ruby/object:Gem::Version
|
116
117
|
version: '0'
|
117
118
|
requirements: []
|
118
119
|
rubyforge_project:
|
119
|
-
rubygems_version: 2.
|
120
|
+
rubygems_version: 2.2.2
|
120
121
|
signing_key:
|
121
122
|
specification_version: 4
|
122
123
|
summary: Fluentd plugin to write data on HDFS over WebHDFS, with flexible formatting
|
123
124
|
test_files:
|
124
125
|
- test/helper.rb
|
125
126
|
- test/plugin/test_out_webhdfs.rb
|
126
|
-
has_rdoc:
|