riemann-tools 1.0.0 → 1.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/dependabot.yml +11 -0
- data/.github/workflows/ci.yml +13 -0
- data/.github/workflows/codeql-analysis.yml +72 -0
- data/.rubocop.yml +32 -0
- data/CHANGELOG.md +31 -2
- data/README.markdown +8 -24
- data/Rakefile +4 -2
- data/SECURITY.md +42 -0
- data/bin/riemann-apache-status +92 -78
- data/bin/riemann-bench +54 -49
- data/bin/riemann-cloudant +44 -40
- data/bin/riemann-consul +82 -76
- data/bin/riemann-dir-files-count +53 -47
- data/bin/riemann-dir-space +53 -47
- data/bin/riemann-diskstats +78 -75
- data/bin/riemann-fd +68 -48
- data/bin/riemann-freeswitch +108 -103
- data/bin/riemann-haproxy +46 -40
- data/bin/riemann-health +4 -343
- data/bin/riemann-kvminstance +18 -13
- data/bin/riemann-memcached +35 -29
- data/bin/riemann-net +4 -104
- data/bin/riemann-nginx-status +74 -67
- data/bin/riemann-ntp +4 -33
- data/bin/riemann-portcheck +40 -31
- data/bin/riemann-proc +96 -90
- data/bin/riemann-varnish +51 -45
- data/bin/riemann-zookeeper +38 -34
- data/lib/riemann/tools/health.rb +347 -0
- data/lib/riemann/tools/net.rb +104 -0
- data/lib/riemann/tools/ntp.rb +41 -0
- data/lib/riemann/tools/version.rb +1 -1
- data/lib/riemann/tools.rb +37 -40
- data/riemann-tools.gemspec +4 -1
- data/tools/riemann-aws/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-aws/bin/riemann-aws-billing +72 -66
- data/tools/riemann-aws/bin/riemann-aws-rds-status +55 -41
- data/tools/riemann-aws/bin/riemann-aws-sqs-status +37 -31
- data/tools/riemann-aws/bin/riemann-aws-status +63 -51
- data/tools/riemann-aws/bin/riemann-elb-metrics +149 -148
- data/tools/riemann-aws/bin/riemann-s3-list +70 -65
- data/tools/riemann-aws/bin/riemann-s3-status +85 -82
- data/tools/riemann-chronos/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-chronos/bin/riemann-chronos +136 -119
- data/tools/riemann-docker/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-docker/bin/riemann-docker +163 -174
- data/tools/riemann-elasticsearch/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-elasticsearch/bin/riemann-elasticsearch +155 -147
- data/tools/riemann-marathon/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-marathon/bin/riemann-marathon +138 -122
- data/tools/riemann-mesos/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-mesos/bin/riemann-mesos +125 -110
- data/tools/riemann-munin/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-munin/bin/riemann-munin +28 -22
- data/tools/riemann-rabbitmq/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-rabbitmq/bin/riemann-rabbitmq +226 -222
- data/tools/riemann-riak/{Rakefile.rb → Rakefile} +2 -0
- data/tools/riemann-riak/bin/riemann-riak +281 -289
- data/tools/riemann-riak/riak_status/riak_status.rb +39 -39
- metadata +65 -16
@@ -1,140 +1,157 @@
|
|
1
1
|
#!/usr/bin/env ruby
|
2
|
-
|
2
|
+
# frozen_string_literal: true
|
3
3
|
|
4
|
-
|
5
|
-
|
6
|
-
class Riemann::Tools::Chronos
|
7
|
-
include Riemann::Tools
|
8
|
-
|
9
|
-
require 'faraday'
|
10
|
-
require 'json'
|
11
|
-
require 'uri'
|
4
|
+
Process.setproctitle($PROGRAM_NAME)
|
12
5
|
|
13
|
-
|
14
|
-
opt :open_timeout, 'Faraday open timeout', type: :int, default: 1
|
15
|
-
opt :path_prefix, 'Chronos path prefix for proxied installations e.g. "chronos" for target http://localhost/chronos/metrics', default: "/"
|
16
|
-
opt :chronos_host, 'Chronos host', default: "localhost"
|
17
|
-
opt :chronos_port, 'Chronos port', type: :int, default: 4400
|
6
|
+
require 'riemann/tools'
|
18
7
|
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
8
|
+
module Riemann
|
9
|
+
module Tools
|
10
|
+
class Chronos
|
11
|
+
include Riemann::Tools
|
12
|
+
|
13
|
+
require 'faraday'
|
14
|
+
require 'json'
|
15
|
+
require 'uri'
|
16
|
+
|
17
|
+
opt :read_timeout, 'Faraday read timeout', type: :int, default: 2
|
18
|
+
opt :open_timeout, 'Faraday open timeout', type: :int, default: 1
|
19
|
+
opt :path_prefix,
|
20
|
+
'Chronos path prefix for proxied installations e.g. "chronos" for target http://localhost/chronos/metrics', default: '/'
|
21
|
+
opt :chronos_host, 'Chronos host', default: 'localhost'
|
22
|
+
opt :chronos_port, 'Chronos port', type: :int, default: 4400
|
23
|
+
|
24
|
+
def initialize
|
25
|
+
options[:interval] = 60
|
26
|
+
options[:ttl] = 120
|
27
|
+
end
|
23
28
|
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
29
|
+
# Handles HTTP connections and GET requests safely
|
30
|
+
def safe_get(uri)
|
31
|
+
# Handle connection timeouts
|
32
|
+
response = nil
|
33
|
+
begin
|
34
|
+
connection = Faraday.new(uri)
|
35
|
+
response = connection.get do |req|
|
36
|
+
req.options[:timeout] = options[:read_timeout]
|
37
|
+
req.options[:open_timeout] = options[:open_timeout]
|
38
|
+
end
|
39
|
+
rescue StandardError => e
|
40
|
+
report(
|
41
|
+
host: uri.host,
|
42
|
+
service: 'chronos health',
|
43
|
+
state: 'critical',
|
44
|
+
description: "HTTP connection error: #{e.class} - #{e.message}",
|
45
|
+
)
|
33
46
|
end
|
34
|
-
|
35
|
-
report(:host => uri.host,
|
36
|
-
:service => "chronos health",
|
37
|
-
:state => "critical",
|
38
|
-
:description => "HTTP connection error: #{e.class} - #{e.message}"
|
39
|
-
)
|
47
|
+
response
|
40
48
|
end
|
41
|
-
response
|
42
|
-
end
|
43
49
|
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
+
def health_url
|
51
|
+
path_prefix = options[:path_prefix]
|
52
|
+
path_prefix[0] = '' if path_prefix[0] == '/'
|
53
|
+
path_prefix[path_prefix.length - 1] = '' if path_prefix[path_prefix.length - 1] == '/'
|
54
|
+
"http://#{options[:chronos_host]}:#{options[:chronos_port]}#{path_prefix.length.positive? ? '/' : ''}#{path_prefix}/metrics"
|
55
|
+
end
|
50
56
|
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
+
def jobs_url
|
58
|
+
path_prefix = options[:path_prefix]
|
59
|
+
path_prefix[0] = '' if path_prefix[0] == '/'
|
60
|
+
path_prefix[path_prefix.length - 1] = '' if path_prefix[path_prefix.length - 1] == '/'
|
61
|
+
"http://#{options[:chronos_host]}:#{options[:chronos_port]}#{path_prefix.length.positive? ? '/' : ''}#{path_prefix}/scheduler/jobs"
|
62
|
+
end
|
57
63
|
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
64
|
+
def tick
|
65
|
+
tick_health
|
66
|
+
tick_jobs
|
67
|
+
end
|
68
|
+
|
69
|
+
def tick_health
|
70
|
+
uri = URI(health_url)
|
71
|
+
response = safe_get(uri)
|
72
|
+
|
73
|
+
return if response.nil?
|
74
|
+
|
75
|
+
if response.status != 200
|
76
|
+
report(
|
77
|
+
host: uri.host,
|
78
|
+
service: 'chronos health',
|
79
|
+
state: 'critical',
|
80
|
+
description: "HTTP connection error: #{response.status} - #{response.body}",
|
81
|
+
)
|
82
|
+
else
|
83
|
+
# Assuming that a 200 will give json
|
84
|
+
json = JSON.parse(response.body)
|
85
|
+
|
86
|
+
report(
|
87
|
+
host: uri.host,
|
88
|
+
service: 'chronos health',
|
89
|
+
state: 'ok',
|
90
|
+
)
|
91
|
+
|
92
|
+
json.each_pair do |t, d|
|
93
|
+
next unless d.respond_to? :each_pair
|
94
|
+
|
95
|
+
d.each_pair do |service, counters|
|
96
|
+
report(
|
97
|
+
host: uri.host,
|
98
|
+
service: "chronos_metric #{t} #{service}",
|
99
|
+
metric: 1,
|
100
|
+
tags: ['metric_name'],
|
101
|
+
ttl: 600,
|
102
|
+
)
|
103
|
+
next unless counters.respond_to? :each_pair
|
62
104
|
|
63
|
-
def tick_health
|
64
|
-
uri = URI(health_url)
|
65
|
-
response = safe_get(uri)
|
66
|
-
|
67
|
-
return if response.nil?
|
68
|
-
|
69
|
-
if response.status != 200
|
70
|
-
report(:host => uri.host,
|
71
|
-
:service => "chronos health",
|
72
|
-
:state => "critical",
|
73
|
-
:description => "HTTP connection error: #{response.status} - #{response.body}"
|
74
|
-
)
|
75
|
-
else
|
76
|
-
# Assuming that a 200 will give json
|
77
|
-
json = JSON.parse(response.body)
|
78
|
-
|
79
|
-
report(:host => uri.host,
|
80
|
-
:service => "chronos health",
|
81
|
-
:state => "ok")
|
82
|
-
|
83
|
-
json.each_pair do |t, d|
|
84
|
-
if d.respond_to? :each_pair
|
85
|
-
d.each_pair do |service, counters|
|
86
|
-
report(:host => uri.host,
|
87
|
-
:service => "chronos_metric #{t} #{service}",
|
88
|
-
:metric => 1,
|
89
|
-
:tags => ["metric_name"],
|
90
|
-
:ttl => 600
|
91
|
-
)
|
92
|
-
if counters.respond_to? :each_pair
|
93
105
|
counters.each_pair do |k, v|
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
106
|
+
next unless v.is_a? Numeric
|
107
|
+
|
108
|
+
report(
|
109
|
+
host: uri.host,
|
110
|
+
service: "chronos #{service} #{k}",
|
111
|
+
metric: v,
|
112
|
+
tags: ['metric', t.to_s],
|
113
|
+
ttl: 600,
|
114
|
+
)
|
102
115
|
end
|
103
116
|
end
|
104
117
|
end
|
105
118
|
end
|
106
119
|
end
|
107
|
-
end
|
108
|
-
end
|
109
120
|
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
121
|
+
def tick_jobs
|
122
|
+
uri = URI(jobs_url)
|
123
|
+
response = safe_get(uri)
|
124
|
+
|
125
|
+
return if response.nil?
|
126
|
+
|
127
|
+
if response.status != 200
|
128
|
+
report(
|
129
|
+
host: uri.host,
|
130
|
+
service: 'chronos health',
|
131
|
+
state: 'critical',
|
132
|
+
description: "HTTP connection error: #{response.status} - #{response.body}",
|
133
|
+
)
|
134
|
+
else
|
135
|
+
# Assuming that a 200 will give json
|
136
|
+
json = JSON.parse(response.body)
|
137
|
+
|
138
|
+
report(
|
139
|
+
host: uri.host,
|
140
|
+
service: 'chronos health',
|
141
|
+
state: 'ok',
|
142
|
+
)
|
143
|
+
|
144
|
+
json.each do |job|
|
145
|
+
job.each_pair do |k, v|
|
146
|
+
next unless v.is_a? Numeric
|
147
|
+
|
148
|
+
report(
|
149
|
+
host: uri.host,
|
150
|
+
service: "chronos job #{job['name']} #{k}",
|
151
|
+
metric: v,
|
152
|
+
ttl: 120,
|
153
|
+
)
|
154
|
+
end
|
138
155
|
end
|
139
156
|
end
|
140
157
|
end
|