kubernetes_health_checker 0.0.0.3 → 0.0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/kubernetes_health_checker +76 -36
- data/bin/kubernetes_health_checkerd +5 -0
- metadata +17 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8a44862baa23546298cbe135442791f9413b092f
|
4
|
+
data.tar.gz: 158d714234ec07627bd6e9fce0834aa906506ce8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 55c4048409051f6b23a8760be6640d6441673eb4b90a6df9e88cf7700b836ed5c93e5549df2d08eef30bd19639a1ef1ef564d549a4f08bec5057f52073b1da31
|
7
|
+
data.tar.gz: cae075720d0244dadc3e9c3a529afb09d4766f779a9d78d3792083338e01093bab0393da590c2ca70fe1c4a668013d0878b75ae2f4e6fb9ebba94ff557400be4
|
@@ -2,6 +2,7 @@
|
|
2
2
|
|
3
3
|
require 'rubygems'
|
4
4
|
require 'thor'
|
5
|
+
require 'byebug'
|
5
6
|
require 'json'
|
6
7
|
|
7
8
|
module KubernetesHealthChecker
|
@@ -17,34 +18,19 @@ module KubernetesHealthChecker
|
|
17
18
|
|
18
19
|
ALERT_STATUSES = ['CrashLoopBackOff'].freeze
|
19
20
|
|
20
|
-
|
21
|
-
opts = options.inject({}){|memo,(k,v)| memo[k.to_sym] = v; memo}
|
22
|
-
@alert_threshold = opts[:alert_threshold] || 5
|
23
|
-
@slack_channel = opts[:channel] || '@rohan'
|
24
|
-
@namespace = opts[:namespace] || 'default'
|
25
|
-
@test = opts[:test] || false
|
26
|
-
|
27
|
-
raise 'must provide a url to POST alert to' if !opts[:url]
|
28
|
-
@url = opts[:url]
|
29
|
-
|
30
|
-
if @test
|
31
|
-
path = File.expand_path('../mock_output.txt', __FILE__)
|
32
|
-
output = File.read(path)
|
33
|
-
else
|
34
|
-
output = `kubectl get pods --namespace #{options[:namespace]}`
|
35
|
-
end
|
36
|
-
|
37
|
-
message = ''
|
38
|
-
rows = output.split("\n")
|
39
|
-
rows.each_with_index do |row, index|
|
40
|
-
next if index == 0
|
41
|
-
row = row.split(" ")
|
42
|
-
response = check_pod_state(pod_name: row[0], status: row[2], restarts: row[3].to_i)
|
21
|
+
RUN_INTERVAL = 10
|
43
22
|
|
44
|
-
|
23
|
+
def start
|
24
|
+
set_defaults(options)
|
25
|
+
run_validations if !@test
|
26
|
+
while true
|
27
|
+
puts 'starting...'
|
28
|
+
output = get_cli_output
|
29
|
+
message = construct_message(output)
|
30
|
+
send_alert(message) if !message.empty?
|
31
|
+
puts 'sleeping...'
|
32
|
+
sleep RUN_INTERVAL
|
45
33
|
end
|
46
|
-
|
47
|
-
send_alert(message) if !message.empty?
|
48
34
|
end
|
49
35
|
|
50
36
|
desc 'version', 'Prints version'
|
@@ -53,7 +39,36 @@ module KubernetesHealthChecker
|
|
53
39
|
end
|
54
40
|
|
55
41
|
no_commands do
|
42
|
+
def set_defaults(options)
|
43
|
+
opts = options.inject({}){|memo,(k,v)| memo[k.to_sym] = v; memo}
|
44
|
+
@alert_threshold = opts[:alert_threshold] || 5
|
45
|
+
@slack_channel = opts[:channel] || '@rohan'
|
46
|
+
@namespace = opts[:namespace] || 'default'
|
47
|
+
@test = opts[:test] || false
|
48
|
+
@url = opts[:url]
|
49
|
+
@pods_data = {}
|
50
|
+
end
|
51
|
+
|
52
|
+
def run_validations
|
53
|
+
raise 'must provide a url to POST alert to' if !@url
|
54
|
+
end
|
55
|
+
|
56
|
+
def get_cli_output
|
57
|
+
if @test
|
58
|
+
# so hacky, but pulls from second mock output if
|
59
|
+
# it's the second time running to test state changes
|
60
|
+
file_name = @pods_data.empty? ? '../mock_output.txt' : '../mock_output_two.txt'
|
61
|
+
path = File.expand_path(file_name, __FILE__)
|
62
|
+
output = File.read(path)
|
63
|
+
else
|
64
|
+
output = `kubectl get pods --namespace #{@namespace}`
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
56
68
|
def send_alert(message)
|
69
|
+
puts "Sending message: #{message}"
|
70
|
+
return if @test
|
71
|
+
|
57
72
|
payload = {
|
58
73
|
channel: @slack_channel,
|
59
74
|
username: 'kubernetes_health_check_bot',
|
@@ -64,19 +79,44 @@ module KubernetesHealthChecker
|
|
64
79
|
`curl -X POST --data-urlencode 'payload=#{JSON.generate(payload)}' #{@url}`
|
65
80
|
end
|
66
81
|
|
67
|
-
def
|
68
|
-
|
69
|
-
|
82
|
+
def get_pod_message(pod_name:, new_status:, new_restarts:)
|
83
|
+
old_restarts = @pods_data[pod_name][:restarts]
|
84
|
+
old_status = @pods_data[pod_name][:status]
|
85
|
+
text = ""
|
86
|
+
|
87
|
+
if !@pods_data[pod_name].empty? && old_restarts == new_restarts && old_status == new_status
|
88
|
+
# we've already alerted from this state, skip
|
89
|
+
elsif ALERT_STATUSES.include?(new_status)
|
90
|
+
text = "Pod *#{pod_name}* is in status: *#{new_status}*.\n"
|
91
|
+
elsif new_restarts > @alert_threshold
|
92
|
+
text = "Pod *#{pod_name}* has restarted *#{new_restarts}* times and has status: *#{new_status}*.\n"
|
93
|
+
end
|
94
|
+
|
95
|
+
text
|
96
|
+
end
|
97
|
+
|
98
|
+
def construct_message(output)
|
99
|
+
message = ''
|
100
|
+
new_pod_store = {}
|
101
|
+
|
102
|
+
rows = output.split("\n")
|
103
|
+
rows.each_with_index do |row, index|
|
104
|
+
next if index == 0
|
105
|
+
|
106
|
+
row = row.split(" ")
|
107
|
+
pod_name = row[0]
|
108
|
+
status = row[2]
|
109
|
+
restarts = row[3].to_i
|
110
|
+
|
111
|
+
@pods_data[pod_name] ||= {}
|
112
|
+
message += get_pod_message(pod_name: pod_name, new_status: status, new_restarts: restarts)
|
70
113
|
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
elsif restarts > @alert_threshold
|
75
|
-
should_alert = true
|
76
|
-
text = "Pod *#{pod_name}* has restarted *#{restarts}* times and has status: *#{status}*.\n"
|
114
|
+
# update our data store for the pods
|
115
|
+
@pods_data[pod_name][:status] = status
|
116
|
+
@pods_data[pod_name][:restarts] = restarts
|
77
117
|
end
|
78
118
|
|
79
|
-
|
119
|
+
message
|
80
120
|
end
|
81
121
|
end
|
82
122
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: kubernetes_health_checker
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.0.
|
4
|
+
version: 0.0.0.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Rohan Sahai
|
@@ -24,6 +24,20 @@ dependencies:
|
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: daemons
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
27
41
|
- !ruby/object:Gem::Dependency
|
28
42
|
name: byebug
|
29
43
|
requirement: !ruby/object:Gem::Requirement
|
@@ -43,10 +57,12 @@ description: Simple script to send slack notifications for pods that are crashin
|
|
43
57
|
email: rohan@sah.ai
|
44
58
|
executables:
|
45
59
|
- kubernetes_health_checker
|
60
|
+
- kubernetes_health_checkerd
|
46
61
|
extensions: []
|
47
62
|
extra_rdoc_files: []
|
48
63
|
files:
|
49
64
|
- bin/kubernetes_health_checker
|
65
|
+
- bin/kubernetes_health_checkerd
|
50
66
|
- bin/mock_output.txt
|
51
67
|
homepage: http://rubygems.org/gems/kubernetes_health_checker
|
52
68
|
licenses:
|