nagios-zfs 0.1.1 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +9 -6
- data/features/check_zpool_capacity.feature +2 -2
- data/features/check_zpool_health.feature +19 -0
- data/features/step_definitions/dev_steps.rb +9 -0
- data/lib/nagios/zfs/version.rb +1 -1
- data/lib/nagios/zfs/zpool.rb +10 -1
- data/lib/nagios/zfs/zpool_plugin.rb +11 -3
- data/spec/nagios/zfs/zpool_plugin_spec.rb +85 -20
- data/spec/nagios/zfs/zpool_spec.rb +15 -0
- metadata +7 -5
data/README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2
2
|
|
3
3
|
Check ZFS Zpool health and capacity via Nagios.
|
4
4
|
|
5
|
-
**NOTE: This is an early prototype!**
|
6
|
-
|
7
5
|
## Installation
|
8
6
|
|
9
7
|
Install it via RubyGems:
|
@@ -18,11 +16,16 @@ Zpools.
|
|
18
16
|
$ check_zpool --help
|
19
17
|
|
20
18
|
A Zpool is in a critical state if the pool capacity jumps over a certain
|
21
|
-
rate (performance usually starts to suck
|
19
|
+
rate (performance usually starts to suck at 80%) or when the pool is
|
22
20
|
faulted.
|
23
|
-
The status will be warning if your Zpool is degraded
|
24
|
-
|
25
|
-
Take a look at the
|
21
|
+
The status will be warning if your Zpool is degraded or if the capacity
|
22
|
+
breaks your warning threshold.
|
23
|
+
Take a look at the
|
24
|
+
[features](https://github.com/bjoernalbers/nagios-zfs/tree/master/features)
|
25
|
+
...
|
26
|
+
|
27
|
+
This plugin works successfully under Oracle Solaris 11 (ZFS VERSION:
|
28
|
+
11.11,REV=2009.11.11).
|
26
29
|
|
27
30
|
## Contributing
|
28
31
|
|
@@ -20,8 +20,8 @@ Feature: Check zpool capacity
|
|
20
20
|
Then the status should be ok
|
21
21
|
|
22
22
|
Scenario: Display actual capacity
|
23
|
-
When I run `check_zpool -p tank -w
|
24
|
-
Then the stdout should contain "
|
23
|
+
When I run `check_zpool -p tank -w 81 -c 82`
|
24
|
+
Then the stdout should contain "80%"
|
25
25
|
|
26
26
|
#NOTE: This currently does not work!
|
27
27
|
#Scenario: Unknown zpool name
|
@@ -0,0 +1,19 @@
|
|
1
|
+
Feature: Check zpool health
|
2
|
+
|
3
|
+
In order to sleep well
|
4
|
+
As the "data storage guy"
|
5
|
+
I want to check the health of my ZFS storage pools.
|
6
|
+
|
7
|
+
Scenario Outline:
|
8
|
+
Given the zpool "tank" has a capacity of 80%
|
9
|
+
And the health from zpool "tank" is "<health>"
|
10
|
+
When I run `check_zpool -p tank -w 81 -c 82`
|
11
|
+
Then the status should be <status>
|
12
|
+
And the stdout should contain "<health>"
|
13
|
+
|
14
|
+
Examples:
|
15
|
+
| health | status |
|
16
|
+
| FAULTED | critical |
|
17
|
+
| DEGRADED | warning |
|
18
|
+
| ONLINE | ok |
|
19
|
+
| SICK | unknown |
|
@@ -1,9 +1,18 @@
|
|
1
|
+
Before do
|
2
|
+
@aruba_timeout_seconds = 10
|
3
|
+
end
|
4
|
+
|
1
5
|
Given(/^the zpool "(.*?)" has a capacity of (\d+)%$/) do |name, capacity|
|
2
6
|
cmd = "zpool list -H -o name,cap #{name}"
|
3
7
|
out = "#{name}\t#{capacity}%\n"
|
4
8
|
double_cmd(cmd, :puts => out)
|
5
9
|
end
|
6
10
|
|
11
|
+
Given(/^the health from zpool "(.*?)" is "(.*?)"$/) do |name, health|
|
12
|
+
cmd = "zpool list -H -o health #{name}"
|
13
|
+
double_cmd(cmd, :puts => "#{health}\n")
|
14
|
+
end
|
15
|
+
|
7
16
|
Then(/^the status should be (unknown|critical|warning|ok)$/) do |status|
|
8
17
|
exit_status =
|
9
18
|
case status
|
data/lib/nagios/zfs/version.rb
CHANGED
data/lib/nagios/zfs/zpool.rb
CHANGED
@@ -1,6 +1,8 @@
|
|
1
1
|
module Nagios
|
2
2
|
module ZFS
|
3
3
|
class Zpool
|
4
|
+
KNOWN_POOL_HEALTHS = %(ONLINE DEGRADED FAULTED)
|
5
|
+
|
4
6
|
attr_reader :name
|
5
7
|
|
6
8
|
def initialize(name)
|
@@ -13,7 +15,14 @@ module Nagios
|
|
13
15
|
end
|
14
16
|
|
15
17
|
def query
|
16
|
-
@query ||= `zpool list -H -o name,cap #{
|
18
|
+
@query ||= `zpool list -H -o name,cap #{name}`
|
19
|
+
end
|
20
|
+
|
21
|
+
def health
|
22
|
+
@health ||= `zpool list -H -o health #{name}`.strip
|
23
|
+
raise "unknown health: #{@health}" unless
|
24
|
+
KNOWN_POOL_HEALTHS.include?(@health)
|
25
|
+
@health
|
17
26
|
end
|
18
27
|
end
|
19
28
|
end
|
@@ -24,11 +24,11 @@ module Nagios
|
|
24
24
|
end
|
25
25
|
|
26
26
|
def critical?
|
27
|
-
critical_capacity?
|
27
|
+
critical_capacity? || critical_health?
|
28
28
|
end
|
29
29
|
|
30
30
|
def warning?
|
31
|
-
warning_capacity?
|
31
|
+
warning_capacity? || warning_health?
|
32
32
|
end
|
33
33
|
|
34
34
|
# No explicite ok check.
|
@@ -37,7 +37,7 @@ module Nagios
|
|
37
37
|
end
|
38
38
|
|
39
39
|
def message
|
40
|
-
"#{zpool.name} #{zpool.capacity}%"
|
40
|
+
"#{zpool.name} #{zpool.health} (#{zpool.capacity}%)"
|
41
41
|
end
|
42
42
|
|
43
43
|
private
|
@@ -50,6 +50,14 @@ module Nagios
|
|
50
50
|
zpool.capacity >= config[:warning]
|
51
51
|
end
|
52
52
|
|
53
|
+
def critical_health?
|
54
|
+
zpool.health == 'FAULTED'
|
55
|
+
end
|
56
|
+
|
57
|
+
def warning_health?
|
58
|
+
zpool.health == 'DEGRADED'
|
59
|
+
end
|
60
|
+
|
53
61
|
def zpool
|
54
62
|
@zpool ||= Zpool.new(config[:zpool])
|
55
63
|
end
|
@@ -14,20 +14,64 @@ module Nagios
|
|
14
14
|
let(:argv) { [] }
|
15
15
|
|
16
16
|
it 'raises an error without pool name' do
|
17
|
+
ZpoolPlugin.any_instance.stub(:puts) # Don't mess up our spec output.
|
17
18
|
expect { plugin }.to raise_error(SystemExit)
|
18
19
|
end
|
19
20
|
end
|
20
21
|
|
21
22
|
describe '#critical?' do
|
22
|
-
|
23
|
+
before do
|
24
|
+
plugin.stub(:critical_capacity?).and_return(false)
|
25
|
+
plugin.stub(:critical_health?).and_return(false)
|
26
|
+
end
|
27
|
+
|
28
|
+
it 'is true when capacity is critical' do
|
23
29
|
plugin.should_receive(:critical_capacity?).and_return(true)
|
24
30
|
expect(plugin.critical?).to be(true)
|
25
31
|
end
|
26
32
|
|
27
|
-
it '
|
33
|
+
it 'is true when health is critical' do
|
34
|
+
plugin.should_receive(:critical_health?).and_return(true)
|
35
|
+
expect(plugin.critical?).to be(true)
|
36
|
+
end
|
37
|
+
|
38
|
+
it 'is false when capacity is not critical' do
|
28
39
|
plugin.should_receive(:critical_capacity?).and_return(false)
|
29
40
|
expect(plugin.critical?).to be(false)
|
30
41
|
end
|
42
|
+
|
43
|
+
it 'is false when health is not critical' do
|
44
|
+
plugin.should_receive(:critical_health?).and_return(false)
|
45
|
+
expect(plugin.critical?).to be(false)
|
46
|
+
end
|
47
|
+
|
48
|
+
end
|
49
|
+
|
50
|
+
describe '#warning?' do
|
51
|
+
before do
|
52
|
+
plugin.stub(:warning_capacity?).and_return(false)
|
53
|
+
plugin.stub(:warning_health?).and_return(false)
|
54
|
+
end
|
55
|
+
|
56
|
+
it 'is true when capacity is warning' do
|
57
|
+
plugin.should_receive(:warning_capacity?).and_return(true)
|
58
|
+
expect(plugin.warning?).to be(true)
|
59
|
+
end
|
60
|
+
|
61
|
+
it 'is true when health is warning' do
|
62
|
+
plugin.should_receive(:warning_health?).and_return(true)
|
63
|
+
expect(plugin.warning?).to be(true)
|
64
|
+
end
|
65
|
+
|
66
|
+
it 'is false when capacity is not warning' do
|
67
|
+
plugin.should_receive(:warning_capacity?).and_return(false)
|
68
|
+
expect(plugin.warning?).to be(false)
|
69
|
+
end
|
70
|
+
|
71
|
+
it 'is false when health is not warning' do
|
72
|
+
plugin.should_receive(:warning_health?).and_return(false)
|
73
|
+
expect(plugin.warning?).to be(false)
|
74
|
+
end
|
31
75
|
end
|
32
76
|
|
33
77
|
describe '#critical_capacity?' do
|
@@ -38,29 +82,17 @@ module Nagios
|
|
38
82
|
plugin.stub(:config).and_return({:critical => 80})
|
39
83
|
end
|
40
84
|
|
41
|
-
it '
|
85
|
+
it 'is true when capacity exceeds critical threshold' do
|
42
86
|
zpool.should_receive(:capacity).and_return(80)
|
43
87
|
expect(plugin.send(:critical_capacity?)).to be(true)
|
44
88
|
end
|
45
89
|
|
46
|
-
it '
|
90
|
+
it 'is false when capacity does not exceed critical threshold' do
|
47
91
|
zpool.should_receive(:capacity).and_return(79)
|
48
92
|
expect(plugin.send(:critical_capacity?)).to be(false)
|
49
93
|
end
|
50
94
|
end
|
51
95
|
|
52
|
-
describe '#warning?' do
|
53
|
-
it 'returns true when capacity is warning' do
|
54
|
-
plugin.should_receive(:warning_capacity?).and_return(true)
|
55
|
-
expect(plugin.warning?).to be(true)
|
56
|
-
end
|
57
|
-
|
58
|
-
it 'returns false when capacity is not warning' do
|
59
|
-
plugin.should_receive(:warning_capacity?).and_return(false)
|
60
|
-
expect(plugin.warning?).to be(false)
|
61
|
-
end
|
62
|
-
end
|
63
|
-
|
64
96
|
describe '#warning_capacity?' do
|
65
97
|
let(:zpool) { double('zpool') }
|
66
98
|
|
@@ -69,17 +101,49 @@ module Nagios
|
|
69
101
|
plugin.stub(:config).and_return({:warning => 80})
|
70
102
|
end
|
71
103
|
|
72
|
-
it '
|
104
|
+
it 'is true when capacity exceeds warning threshold' do
|
73
105
|
zpool.should_receive(:capacity).and_return(80)
|
74
106
|
expect(plugin.send(:warning_capacity?)).to be(true)
|
75
107
|
end
|
76
108
|
|
77
|
-
it '
|
109
|
+
it 'is false when capacity does not exceed warning threshold' do
|
78
110
|
zpool.should_receive(:capacity).and_return(79)
|
79
111
|
expect(plugin.send(:warning_capacity?)).to be(false)
|
80
112
|
end
|
81
113
|
end
|
82
114
|
|
115
|
+
describe '#critical_health?' do
|
116
|
+
let(:zpool) { double('zpool') }
|
117
|
+
|
118
|
+
before { plugin.stub(:zpool).and_return(zpool) }
|
119
|
+
|
120
|
+
it 'is true with a faulted pool' do
|
121
|
+
zpool.should_receive(:health).and_return('FAULTED')
|
122
|
+
expect(plugin.send(:critical_health?)).to be(true)
|
123
|
+
end
|
124
|
+
|
125
|
+
it 'is false without a faulted pool' do
|
126
|
+
zpool.should_receive(:health).and_return('DEGRADED')
|
127
|
+
expect(plugin.send(:critical_health?)).to be(false)
|
128
|
+
end
|
129
|
+
end
|
130
|
+
|
131
|
+
describe '#warning_health?' do
|
132
|
+
let(:zpool) { double('zpool') }
|
133
|
+
|
134
|
+
before { plugin.stub(:zpool).and_return(zpool) }
|
135
|
+
|
136
|
+
it 'is true with a degraded pool' do
|
137
|
+
zpool.should_receive(:health).and_return('DEGRADED')
|
138
|
+
expect(plugin.send(:warning_health?)).to be(true)
|
139
|
+
end
|
140
|
+
|
141
|
+
it 'is false without a degraded pool' do
|
142
|
+
zpool.should_receive(:health).and_return('ONLINE')
|
143
|
+
expect(plugin.send(:warning_health?)).to be(false)
|
144
|
+
end
|
145
|
+
end
|
146
|
+
|
83
147
|
describe '#ok?' do
|
84
148
|
it 'always returns true' do
|
85
149
|
expect(plugin.ok?).to eq(true)
|
@@ -87,12 +151,13 @@ module Nagios
|
|
87
151
|
end
|
88
152
|
|
89
153
|
describe '#message' do
|
90
|
-
it 'includes the pool name and capcity' do
|
154
|
+
it 'includes the pool name, health and capcity' do
|
91
155
|
zpool = double('zpool')
|
92
156
|
zpool.should_receive(:name).and_return('tank')
|
157
|
+
zpool.should_receive(:health).and_return('ONLINE')
|
93
158
|
zpool.should_receive(:capacity).and_return(42)
|
94
159
|
plugin.stub(:zpool).and_return(zpool)
|
95
|
-
expect(plugin.message).to eq('tank 42%')
|
160
|
+
expect(plugin.message).to eq('tank ONLINE (42%)')
|
96
161
|
end
|
97
162
|
end
|
98
163
|
|
@@ -35,6 +35,21 @@ module Nagios
|
|
35
35
|
2.times { expect(zpool.send(:query)).to eq('chunky bacon') }
|
36
36
|
end
|
37
37
|
end
|
38
|
+
|
39
|
+
describe '#health' do
|
40
|
+
it 'returns and caches the health by command-line' do
|
41
|
+
zpool.should_receive(:`).with('zpool list -H -o health tank').
|
42
|
+
once.and_return("ONLINE\n")
|
43
|
+
2.times { expect(zpool.health).to eq('ONLINE') }
|
44
|
+
end
|
45
|
+
|
46
|
+
it 'raises an error with an unknown health' do
|
47
|
+
zpool.stub(:`).and_return("SICK\n")
|
48
|
+
expect { zpool.health }.to raise_error /unknown health: SICK/
|
49
|
+
end
|
50
|
+
|
51
|
+
it 'raises an error when the command returns a non-zero exit code'
|
52
|
+
end
|
38
53
|
end
|
39
54
|
end
|
40
55
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: nagios-zfs
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-10-
|
12
|
+
date: 2013-10-09 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: nagiosplugin
|
@@ -157,6 +157,7 @@ files:
|
|
157
157
|
- Rakefile
|
158
158
|
- bin/check_zpool
|
159
159
|
- features/check_zpool_capacity.feature
|
160
|
+
- features/check_zpool_health.feature
|
160
161
|
- features/step_definitions/dev_steps.rb
|
161
162
|
- features/support/env.rb
|
162
163
|
- lib/nagios/zfs.rb
|
@@ -182,7 +183,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
182
183
|
version: '0'
|
183
184
|
segments:
|
184
185
|
- 0
|
185
|
-
hash: -
|
186
|
+
hash: -1902865877853825615
|
186
187
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
187
188
|
none: false
|
188
189
|
requirements:
|
@@ -191,15 +192,16 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
191
192
|
version: '0'
|
192
193
|
segments:
|
193
194
|
- 0
|
194
|
-
hash: -
|
195
|
+
hash: -1902865877853825615
|
195
196
|
requirements: []
|
196
197
|
rubyforge_project:
|
197
198
|
rubygems_version: 1.8.23
|
198
199
|
signing_key:
|
199
200
|
specification_version: 3
|
200
|
-
summary: nagios-zfs-0.
|
201
|
+
summary: nagios-zfs-0.2.0
|
201
202
|
test_files:
|
202
203
|
- features/check_zpool_capacity.feature
|
204
|
+
- features/check_zpool_health.feature
|
203
205
|
- features/step_definitions/dev_steps.rb
|
204
206
|
- features/support/env.rb
|
205
207
|
- spec/nagios/zfs/zpool_plugin_spec.rb
|