riemann-tools 0.0.3 → 0.0.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/bin/.riemann-net.swp +0 -0
- data/bin/riemann-riak +181 -0
- data/bin/riemann-riak-keys +12 -0
- data/bin/riemann-riak-ring +8 -0
- metadata +27 -2
Binary file
|
data/bin/riemann-riak
ADDED
@@ -0,0 +1,181 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# Forwards information on a Riak node to Riemann.
|
4
|
+
|
5
|
+
require File.expand_path('../../lib/riemann/tools', __FILE__)
|
6
|
+
|
7
|
+
require 'net/http'
|
8
|
+
require 'yajl/json_gem'
|
9
|
+
|
10
|
+
class Riemann::Tools::Riak
|
11
|
+
include Riemann::Tools
|
12
|
+
|
13
|
+
opt :riak_host, "Riak host", :default => "localhost"
|
14
|
+
opt :stats_port, "Riak HTTP port for stats", :default => 8098
|
15
|
+
opt :stats_path, "Riak HTTP stats path", :default => '/stats'
|
16
|
+
opt :node_name, "Riak erlang node name", :default => "riak@#{Socket.gethostname}"
|
17
|
+
|
18
|
+
opt :get_50_warning, "FSM 50% get time warning threshold (ms)", :default => 1000
|
19
|
+
opt :put_50_warning, "FSM 50% put time warning threshold (ms)", :default => 1000
|
20
|
+
opt :get_95_warning, "FSM 95% get time warning threshold (ms)", :default => 2000
|
21
|
+
opt :put_95_warning, "FSM 95% put time warning threshold (ms)", :default => 2000
|
22
|
+
opt :get_99_warning, "FSM 99% get time warning threshold (ms)", :default => 10000
|
23
|
+
opt :put_99_warning, "FSM 99% put time warning threshold (ms)", :default => 10000
|
24
|
+
|
25
|
+
def initialize
|
26
|
+
if `which escript` =~ /^\s*$/
|
27
|
+
puts "No escript; disabling ring/key checks."
|
28
|
+
@no_escript = true
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def check_ring
|
33
|
+
return if @no_escript
|
34
|
+
|
35
|
+
str = `#{File.expand_path(File.dirname(__FILE__))}/riemann-riak-ring #{opts[:node_name]}`.chomp
|
36
|
+
if str =~ /^TRUE/
|
37
|
+
report(
|
38
|
+
:host => opts[:riak_host],
|
39
|
+
:service => 'riak ring',
|
40
|
+
:state => 'ok',
|
41
|
+
:description => str
|
42
|
+
)
|
43
|
+
else
|
44
|
+
report(
|
45
|
+
:host => opts[:riak_host],
|
46
|
+
:service => 'riak ring',
|
47
|
+
:state => 'warning',
|
48
|
+
:description => str
|
49
|
+
)
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def check_keys
|
54
|
+
return if @no_escript
|
55
|
+
|
56
|
+
keys = `#{File.expand_path(File.dirname(__FILE__))}/riemann-riak-keys #{opts[:node_name]}`.chomp
|
57
|
+
if keys =~ /^\d+$/
|
58
|
+
report(
|
59
|
+
:host => opts[:riak_host],
|
60
|
+
:service => 'riak keys',
|
61
|
+
:state => 'ok',
|
62
|
+
:metric => keys.to_i,
|
63
|
+
:description => keys
|
64
|
+
)
|
65
|
+
else
|
66
|
+
report(
|
67
|
+
:host => opts[:riak_host],
|
68
|
+
:servie => 'riak keys',
|
69
|
+
:state => 'unknown',
|
70
|
+
:description => keys
|
71
|
+
)
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
def check_disk
|
76
|
+
gb = `du -s /var/lib/riak`.split(/\s+/).first.to_i / (1024.0**2)
|
77
|
+
report(
|
78
|
+
:host => opts[:riak_host],
|
79
|
+
:service => 'riak disk',
|
80
|
+
:state => 'ok',
|
81
|
+
:metric => gb,
|
82
|
+
:description => "#{gb} GB in /var/lib/riak/"
|
83
|
+
)
|
84
|
+
end
|
85
|
+
|
86
|
+
# Returns the riak stat for the given fsm type and percentile.
|
87
|
+
def fsm_stat(type, percentile)
|
88
|
+
"node_#{type}_fsm_time_#{percentile == 50 ? 'median' : percentile}"
|
89
|
+
end
|
90
|
+
|
91
|
+
# Returns the alerts state for the given fsm.
|
92
|
+
def fsm_state(type, percentile, val)
|
93
|
+
limit = opts["#{type}_#{percentile}_warning".to_sym]
|
94
|
+
case val
|
95
|
+
when 0 .. limit
|
96
|
+
'ok'
|
97
|
+
when limit .. limit * 2
|
98
|
+
'warning'
|
99
|
+
else
|
100
|
+
'critical'
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
def check_stats
|
105
|
+
begin
|
106
|
+
res = Net::HTTP.start(opts[:riak_host], opts[:stats_port]) do |http|
|
107
|
+
http.get opts[:stats_path]
|
108
|
+
end
|
109
|
+
rescue => e
|
110
|
+
report(
|
111
|
+
:host => opts[:riak_host],
|
112
|
+
:service => 'riak',
|
113
|
+
:state => 'critical',
|
114
|
+
:description => "error fetching #{opts[:riak_host]}:#{opts[:stats_port]} #{e.class}, #{e.message}"
|
115
|
+
)
|
116
|
+
return
|
117
|
+
end
|
118
|
+
|
119
|
+
if res.code.to_i == 200
|
120
|
+
stats = JSON.parse(res.body)
|
121
|
+
else
|
122
|
+
report(
|
123
|
+
:host => opts[:riak_host],
|
124
|
+
:service => 'riak',
|
125
|
+
:state => 'critical',
|
126
|
+
:description => "stats returned HTTP #{res.code}:\n\n#{res.body}"
|
127
|
+
)
|
128
|
+
return
|
129
|
+
end
|
130
|
+
|
131
|
+
report(
|
132
|
+
:host => opts[:riak_host],
|
133
|
+
:service => 'riak',
|
134
|
+
:state => 'ok'
|
135
|
+
)
|
136
|
+
|
137
|
+
# Gets/puts/rr
|
138
|
+
[
|
139
|
+
'vnode_gets',
|
140
|
+
'vnode_puts',
|
141
|
+
'node_gets',
|
142
|
+
'node_puts',
|
143
|
+
'read_repairs'
|
144
|
+
].each do |s|
|
145
|
+
report(
|
146
|
+
:host => opts[:riak_host],
|
147
|
+
:service => s,
|
148
|
+
:state => 'ok',
|
149
|
+
:metric => stats[s]/60.0,
|
150
|
+
:description => "#{stats[s]/60.0}/sec"
|
151
|
+
)
|
152
|
+
end
|
153
|
+
|
154
|
+
# FSMs
|
155
|
+
['get', 'put'].each do |type|
|
156
|
+
[50, 95, 99].each do |percentile|
|
157
|
+
val = stats[fsm_stat(type, percentile)] || 0
|
158
|
+
val = 0 if val == 'undefined'
|
159
|
+
val /= 1000.0 # Convert us to ms
|
160
|
+
state = fsm_state(type, percentile, val)
|
161
|
+
report(
|
162
|
+
:host => opts[:riak_host],
|
163
|
+
:service => "riak #{type} #{percentile}",
|
164
|
+
:state => state,
|
165
|
+
:metric => val,
|
166
|
+
:description => "#{val} ms"
|
167
|
+
)
|
168
|
+
end
|
169
|
+
end
|
170
|
+
end
|
171
|
+
|
172
|
+
def tick
|
173
|
+
# This can utterly destroy a cluster, so we disable
|
174
|
+
# check_keys
|
175
|
+
check_stats
|
176
|
+
check_ring
|
177
|
+
check_disk
|
178
|
+
end
|
179
|
+
end
|
180
|
+
|
181
|
+
Riemann::Tools::Riak.run
|
@@ -0,0 +1,12 @@
|
|
1
|
+
#!/usr/bin/env escript
|
2
|
+
%%! -name riakstatuscheck@127.0.0.1 -setcookie riak -hidden
|
3
|
+
|
4
|
+
main([]) -> main(["riak@127.0.0.1"]);
|
5
|
+
main([Node]) ->
|
6
|
+
io:format("~w\n", [
|
7
|
+
lists:foldl(
|
8
|
+
fun({_VNode, Count}, Sum) -> Sum + Count end,
|
9
|
+
0,
|
10
|
+
rpc:call(list_to_atom(Node), riak_kv_bitcask_backend, key_counts, [])
|
11
|
+
)
|
12
|
+
]).
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: riemann-tools
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
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: 2012-04-
|
12
|
+
date: 2012-04-19 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: riemann-client
|
@@ -59,23 +59,48 @@ dependencies:
|
|
59
59
|
- - ! '>='
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: 0.2.1
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: yajl-ruby >= 1.1.0
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :runtime
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
62
78
|
description:
|
63
79
|
email: aphyr@aphyr.com
|
64
80
|
executables:
|
65
81
|
- riemann-net
|
82
|
+
- riemann-riak-ring
|
83
|
+
- riemann-riak-keys
|
66
84
|
- riemann-munin
|
85
|
+
- riemann-riak
|
67
86
|
- riemann-bench
|
68
87
|
- riemann-health
|
88
|
+
- .riemann-net.swp
|
69
89
|
extensions: []
|
70
90
|
extra_rdoc_files: []
|
71
91
|
files:
|
72
92
|
- lib/riemann/tools.rb
|
73
93
|
- bin/riemann-net
|
94
|
+
- bin/riemann-riak-ring
|
95
|
+
- bin/riemann-riak-keys
|
74
96
|
- bin/riemann-munin
|
97
|
+
- bin/riemann-riak
|
75
98
|
- bin/riemann-bench
|
76
99
|
- bin/riemann-health
|
77
100
|
- LICENSE
|
78
101
|
- README.markdown
|
102
|
+
- !binary |-
|
103
|
+
YmluLy5yaWVtYW5uLW5ldC5zd3A=
|
79
104
|
homepage: https://github.com/aphyr/riemann-tools
|
80
105
|
licenses: []
|
81
106
|
post_install_message:
|