riemann-tools 1.1.1 → 1.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/ci.yml +2 -0
- data/.gitignore +2 -0
- data/.rubocop.yml +8 -0
- data/.ruby-version +1 -0
- data/CHANGELOG.md +60 -2
- data/Rakefile +17 -3
- data/bin/riemann-apache-status +1 -106
- data/bin/riemann-bench +2 -70
- data/bin/riemann-cloudant +1 -56
- data/bin/riemann-consul +1 -106
- data/bin/riemann-dir-files-count +1 -55
- data/bin/riemann-dir-space +1 -55
- data/bin/riemann-diskstats +1 -92
- data/bin/riemann-fd +2 -81
- data/bin/riemann-freeswitch +2 -119
- data/bin/riemann-haproxy +1 -58
- data/bin/riemann-health +0 -2
- data/bin/riemann-kvminstance +2 -22
- data/bin/riemann-md +8 -0
- data/bin/riemann-memcached +1 -37
- data/bin/riemann-net +0 -2
- data/bin/riemann-nginx-status +1 -85
- data/bin/riemann-ntp +0 -2
- data/bin/riemann-portcheck +1 -44
- data/bin/riemann-proc +1 -108
- data/bin/riemann-varnish +1 -54
- data/bin/riemann-wrapper +113 -0
- data/bin/riemann-zookeeper +1 -39
- data/bin/riemann-zpool +8 -0
- data/lib/riemann/tools/apache_status.rb +107 -0
- data/lib/riemann/tools/bench.rb +72 -0
- data/lib/riemann/tools/cloudant.rb +57 -0
- data/lib/riemann/tools/consul_health.rb +107 -0
- data/lib/riemann/tools/dir_files_count.rb +56 -0
- data/lib/riemann/tools/dir_space.rb +56 -0
- data/lib/riemann/tools/diskstats.rb +94 -0
- data/lib/riemann/tools/fd.rb +81 -0
- data/lib/riemann/tools/freeswitch.rb +119 -0
- data/lib/riemann/tools/haproxy.rb +59 -0
- data/lib/riemann/tools/health.rb +150 -19
- data/lib/riemann/tools/kvm.rb +23 -0
- data/lib/riemann/tools/md.rb +35 -0
- data/lib/riemann/tools/mdstat_parser.tab.rb +340 -0
- data/lib/riemann/tools/memcached.rb +38 -0
- data/lib/riemann/tools/net.rb +2 -1
- data/lib/riemann/tools/nginx_status.rb +86 -0
- data/lib/riemann/tools/ntp.rb +1 -0
- data/lib/riemann/tools/portcheck.rb +45 -0
- data/lib/riemann/tools/proc.rb +109 -0
- data/lib/riemann/tools/riemann_client_wrapper.rb +43 -0
- data/lib/riemann/tools/uptime_parser.tab.rb +323 -0
- data/lib/riemann/tools/varnish.rb +55 -0
- data/lib/riemann/tools/version.rb +1 -1
- data/lib/riemann/tools/zookeeper.rb +40 -0
- data/lib/riemann/tools/zpool.rb +40 -0
- data/lib/riemann/tools.rb +2 -20
- data/riemann-tools.gemspec +10 -1
- data/tools/riemann-aws/Rakefile +6 -9
- data/tools/riemann-aws/bin/riemann-aws-billing +2 -87
- data/tools/riemann-aws/bin/riemann-aws-rds-status +2 -62
- data/tools/riemann-aws/bin/riemann-aws-sqs-status +2 -44
- data/tools/riemann-aws/bin/riemann-aws-status +2 -77
- data/tools/riemann-aws/bin/riemann-elb-metrics +2 -162
- data/tools/riemann-aws/bin/riemann-s3-list +2 -81
- data/tools/riemann-aws/bin/riemann-s3-status +2 -96
- data/tools/riemann-aws/lib/riemann/tools/aws/billing.rb +87 -0
- data/tools/riemann-aws/lib/riemann/tools/aws/elb_metrics.rb +163 -0
- data/tools/riemann-aws/lib/riemann/tools/aws/rds_status.rb +63 -0
- data/tools/riemann-aws/lib/riemann/tools/aws/s3_list.rb +82 -0
- data/tools/riemann-aws/lib/riemann/tools/aws/s3_status.rb +97 -0
- data/tools/riemann-aws/lib/riemann/tools/aws/sqs_status.rb +45 -0
- data/tools/riemann-aws/lib/riemann/tools/aws/status.rb +74 -0
- data/tools/riemann-chronos/Rakefile +6 -9
- data/tools/riemann-chronos/bin/riemann-chronos +1 -154
- data/tools/riemann-chronos/lib/riemann/tools/chronos.rb +157 -0
- data/tools/riemann-docker/Rakefile +5 -8
- data/tools/riemann-docker/bin/riemann-docker +2 -200
- data/tools/riemann-docker/lib/riemann/tools/docker.rb +200 -0
- data/tools/riemann-elasticsearch/Rakefile +6 -9
- data/tools/riemann-elasticsearch/bin/riemann-elasticsearch +1 -167
- data/tools/riemann-elasticsearch/lib/riemann/tools/elasticsearch.rb +170 -0
- data/tools/riemann-marathon/Rakefile +6 -9
- data/tools/riemann-marathon/bin/riemann-marathon +1 -156
- data/tools/riemann-marathon/lib/riemann/tools/marathon.rb +159 -0
- data/tools/riemann-mesos/Rakefile +6 -9
- data/tools/riemann-mesos/bin/riemann-mesos +1 -139
- data/tools/riemann-mesos/lib/riemann/tools/mesos.rb +142 -0
- data/tools/riemann-munin/Rakefile +5 -8
- data/tools/riemann-munin/bin/riemann-munin +1 -36
- data/tools/riemann-munin/lib/riemann/tools/munin.rb +37 -0
- data/tools/riemann-rabbitmq/Rakefile +6 -9
- data/tools/riemann-rabbitmq/bin/riemann-rabbitmq +1 -266
- data/tools/riemann-rabbitmq/lib/riemann/tools/rabbitmq.rb +269 -0
- data/tools/riemann-riak/Rakefile +5 -8
- data/tools/riemann-riak/bin/riemann-riak +1 -316
- data/tools/riemann-riak/bin/riemann-riak-keys +0 -1
- data/tools/riemann-riak/bin/riemann-riak-ring +0 -1
- data/tools/riemann-riak/lib/riemann/tools/riak.rb +317 -0
- metadata +64 -10
- data/.travis.yml +0 -31
- data/tools/riemann-riak/riak_status/key_count.erl +0 -13
- data/tools/riemann-riak/riak_status/riak_status.rb +0 -152
- data/tools/riemann-riak/riak_status/ringready.erl +0 -9
data/bin/riemann-diskstats
CHANGED
@@ -2,98 +2,7 @@
|
|
2
2
|
# frozen_string_literal: true
|
3
3
|
|
4
4
|
Process.setproctitle($PROGRAM_NAME)
|
5
|
-
require 'rubygems'
|
6
|
-
require 'riemann/tools'
|
7
5
|
|
8
|
-
|
9
|
-
module Tools
|
10
|
-
class Diskstats
|
11
|
-
include Riemann::Tools
|
12
|
-
|
13
|
-
opt :devices, 'Devices to monitor', type: :strings, default: nil
|
14
|
-
opt :ignore_devices, 'Devices to ignore', type: :strings, default: nil
|
15
|
-
|
16
|
-
def initialize
|
17
|
-
@old_state = nil
|
18
|
-
end
|
19
|
-
|
20
|
-
def state
|
21
|
-
f = File.read('/proc/diskstats')
|
22
|
-
state = f.split("\n").reject { |d| d =~ /(ram|loop)/ }.each_with_object({}) do |line, s|
|
23
|
-
next unless line =~ /^(?:\s+\d+){2}\s+([\w\d\-]+) (.*)$/
|
24
|
-
|
25
|
-
dev = Regexp.last_match(1)
|
26
|
-
|
27
|
-
['reads reqs',
|
28
|
-
'reads merged',
|
29
|
-
'reads sector',
|
30
|
-
'reads time',
|
31
|
-
'writes reqs',
|
32
|
-
'writes merged',
|
33
|
-
'writes sector',
|
34
|
-
'writes time',
|
35
|
-
'io reqs',
|
36
|
-
'io time',
|
37
|
-
'io weighted',].map do |service|
|
38
|
-
"#{dev} #{service}"
|
39
|
-
end.zip( # rubocop:disable Style/MultilineBlockChain
|
40
|
-
Regexp.last_match(2).split(/\s+/).map(&:to_i),
|
41
|
-
).each do |service, value|
|
42
|
-
s[service] = value
|
43
|
-
end
|
44
|
-
end
|
45
|
-
|
46
|
-
# Filter interfaces
|
47
|
-
if (is = opts[:devices])
|
48
|
-
state = state.select do |service, _value|
|
49
|
-
is.include? service.split(' ').first
|
50
|
-
end
|
51
|
-
end
|
52
|
-
|
53
|
-
if (ign = opts[:ignore_devices])
|
54
|
-
state = state.reject do |service, _value|
|
55
|
-
ign.include? service.split(' ').first
|
56
|
-
end
|
57
|
-
end
|
58
|
-
|
59
|
-
state
|
60
|
-
end
|
61
|
-
|
62
|
-
def tick
|
63
|
-
state = self.state
|
64
|
-
|
65
|
-
if @old_state
|
66
|
-
state.each do |service, metric|
|
67
|
-
if service =~ /io reqs$/
|
68
|
-
report(
|
69
|
-
service: "diskstats #{service}",
|
70
|
-
metric: metric,
|
71
|
-
state: 'ok',
|
72
|
-
)
|
73
|
-
else
|
74
|
-
delta = metric - @old_state[service]
|
75
|
-
|
76
|
-
report(
|
77
|
-
service: "diskstats #{service}",
|
78
|
-
metric: (delta.to_f / opts[:interval]),
|
79
|
-
state: 'ok',
|
80
|
-
)
|
81
|
-
end
|
82
|
-
|
83
|
-
next unless service =~ /io time$/
|
84
|
-
|
85
|
-
report(
|
86
|
-
service: "diskstats #{service.gsub(/time/, 'util')}",
|
87
|
-
metric: (delta.to_f / (opts[:interval] * 1000)),
|
88
|
-
state: 'ok',
|
89
|
-
)
|
90
|
-
end
|
91
|
-
end
|
92
|
-
|
93
|
-
@old_state = state
|
94
|
-
end
|
95
|
-
end
|
96
|
-
end
|
97
|
-
end
|
6
|
+
require 'riemann/tools/diskstats'
|
98
7
|
|
99
8
|
Riemann::Tools::Diskstats.run
|
data/bin/riemann-fd
CHANGED
@@ -3,85 +3,6 @@
|
|
3
3
|
|
4
4
|
Process.setproctitle($PROGRAM_NAME)
|
5
5
|
|
6
|
-
|
7
|
-
# By default reports the total system fd usage, can also report usage of individual processes
|
6
|
+
require 'riemann/tools/fd'
|
8
7
|
|
9
|
-
|
10
|
-
|
11
|
-
module Riemann
|
12
|
-
module Tools
|
13
|
-
class Health
|
14
|
-
include Riemann::Tools
|
15
|
-
|
16
|
-
opt :fd_sys_warning, 'open file descriptor threshold for system', default: 800
|
17
|
-
opt :fd_sys_critical, 'open file descriptor critical threshold for system', default: 900
|
18
|
-
opt :fd_proc_warning, 'open file descriptor threshold for process', default: 800
|
19
|
-
opt :fd_proc_critical, 'open file descriptor critical threshold for process', default: 900
|
20
|
-
opt :processes, 'list of processes to measure fd usage in addition to system total', type: :ints
|
21
|
-
|
22
|
-
def initialize
|
23
|
-
@limits = {
|
24
|
-
fd: { critical: opts[:fd_sys_critical], warning: opts[:fd_sys_warning] },
|
25
|
-
process: { critical: opts[:fd_proc_critical], warning: opts[:fd_proc_warning] },
|
26
|
-
}
|
27
|
-
ostype = `uname -s`.chomp.downcase
|
28
|
-
case ostype
|
29
|
-
when 'freebsd'
|
30
|
-
@fd = method :freebsd_fd
|
31
|
-
else
|
32
|
-
puts "WARNING: OS '#{ostype}' not explicitly supported. Falling back to Linux" unless ostype == 'linux'
|
33
|
-
@fd = method :linux_fd
|
34
|
-
end
|
35
|
-
end
|
36
|
-
|
37
|
-
def alert(service, state, metric, description)
|
38
|
-
report(
|
39
|
-
service: service.to_s,
|
40
|
-
state: state.to_s,
|
41
|
-
metric: metric.to_f,
|
42
|
-
description: description,
|
43
|
-
)
|
44
|
-
end
|
45
|
-
|
46
|
-
def freebsd_fd
|
47
|
-
sys_used = Integer(`sysctl -n kern.openfiles`)
|
48
|
-
if sys_used > @limits[:fd][:critical]
|
49
|
-
alert 'fd sys', :critical, sys_used, "system is using #{sys_used} fds"
|
50
|
-
elsif sys_used > @limits[:fd][:warning]
|
51
|
-
alert 'fd sys', :warning, sys_used, "system is using #{sys_used} fds"
|
52
|
-
else
|
53
|
-
alert 'fd sys', :ok, sys_used, "system is using #{sys_used} fds"
|
54
|
-
end
|
55
|
-
end
|
56
|
-
|
57
|
-
def linux_fd
|
58
|
-
sys_used = Integer(`lsof | wc -l`)
|
59
|
-
if sys_used > @limits[:fd][:critical]
|
60
|
-
alert 'fd sys', :critical, sys_used, "system is using #{sys_used} fds"
|
61
|
-
elsif sys_used > @limits[:fd][:warning]
|
62
|
-
alert 'fd sys', :warning, sys_used, "system is using #{sys_used} fds"
|
63
|
-
else
|
64
|
-
alert 'fd sys', :ok, sys_used, "system is using #{sys_used} fds"
|
65
|
-
end
|
66
|
-
|
67
|
-
opts[:processes]&.each do |process|
|
68
|
-
used = Integer(`lsof -p #{process} | wc -l`)
|
69
|
-
name, _pid = `ps axo comm,pid | grep -w #{process}`.split
|
70
|
-
if used > @limits[:process][:critical]
|
71
|
-
alert "fd #{name} #{process}", :critical, used, "process #{name} #{process} is using #{used} fds"
|
72
|
-
elsif used > @limits[:process][:warning]
|
73
|
-
alert "fd #{name} #{process}", :warning, used, "process #{name} #{process} is using #{used} fds"
|
74
|
-
else
|
75
|
-
alert "fd #{name} #{process}", :ok, used, "process #{name} #{process} is using #{used} fds"
|
76
|
-
end
|
77
|
-
end
|
78
|
-
end
|
79
|
-
|
80
|
-
def tick
|
81
|
-
@fd.call
|
82
|
-
end
|
83
|
-
end
|
84
|
-
end
|
85
|
-
end
|
86
|
-
|
87
|
-
Riemann::Tools::Health.run
|
8
|
+
Riemann::Tools::Fd.run
|
data/bin/riemann-freeswitch
CHANGED
@@ -1,125 +1,8 @@
|
|
1
1
|
#!/usr/bin/env ruby
|
2
2
|
# frozen_string_literal: true
|
3
3
|
|
4
|
-
require 'English'
|
5
|
-
|
6
4
|
Process.setproctitle($PROGRAM_NAME)
|
7
5
|
|
8
|
-
require
|
9
|
-
|
10
|
-
module Riemann
|
11
|
-
module Tools
|
12
|
-
class FreeSWITCH
|
13
|
-
include Riemann::Tools
|
14
|
-
|
15
|
-
opt :calls_warning, 'Calls warning threshold', default: 100
|
16
|
-
opt :calls_critical, 'Calls critical threshold', default: 300
|
17
|
-
opt :pid_file, 'FreeSWITCH daemon pidfile', type: String, default: '/var/run/freeswitch/freeswitch.pid'
|
18
|
-
|
19
|
-
def initialize
|
20
|
-
@limits = {
|
21
|
-
calls: { critical: opts[:calls_critical], warning: opts[:calls_warning] },
|
22
|
-
}
|
23
|
-
end
|
24
|
-
|
25
|
-
def dead_proc?(pid)
|
26
|
-
Process.getpgid(pid)
|
27
|
-
false
|
28
|
-
rescue Errno::ESRCH
|
29
|
-
true
|
30
|
-
end
|
31
|
-
|
32
|
-
def alert(service, state, metric, description)
|
33
|
-
report(
|
34
|
-
service: service.to_s,
|
35
|
-
state: state.to_s,
|
36
|
-
metric: metric.to_f,
|
37
|
-
description: description,
|
38
|
-
)
|
39
|
-
end
|
40
|
-
|
41
|
-
def exec_with_timeout(cmd, timeout)
|
42
|
-
pid = Process.spawn(cmd, { %i[err out] => :close, :pgroup => true })
|
43
|
-
begin
|
44
|
-
Timeout.timeout(timeout) do
|
45
|
-
Process.waitpid(pid, 0)
|
46
|
-
$CHILD_STATUS.exitstatus.zero?
|
47
|
-
end
|
48
|
-
rescue Timeout::Error
|
49
|
-
Process.kill(15, -Process.getpgid(pid))
|
50
|
-
puts "Killed pid: #{pid}"
|
51
|
-
false
|
52
|
-
end
|
53
|
-
end
|
54
|
-
|
55
|
-
def tick
|
56
|
-
# Determine how many current calls I have according to FreeSWITCH
|
57
|
-
fs_calls = `fs_cli -x "show calls count"| grep -Po '^\\d+'`.to_i
|
58
|
-
|
59
|
-
# Determine how many current channels I have according to FreeSWITCH
|
60
|
-
fs_channels = `fs_cli -x "show channels count"| grep -Po '^\\d+'`.to_i
|
61
|
-
|
62
|
-
# Determine how many conferences I have according to FreeSWITCH
|
63
|
-
fs_conferences = `fs_cli -x "conference list"| grep -Pco '^Conference'`.to_i
|
64
|
-
|
65
|
-
# Try to read pidfile. If it fails use Devil's dummy PID
|
66
|
-
begin
|
67
|
-
fs_pid = File.read(opts[:pid_file]).to_i
|
68
|
-
rescue StandardError
|
69
|
-
puts "Couldn't read pidfile: #{opts[:pid_file]}"
|
70
|
-
fs_pid = -666
|
71
|
-
end
|
72
|
-
|
73
|
-
fs_threads = fs_pid.positive? ? `ps huH p #{fs_pid} | wc -l`.to_i : 0
|
74
|
-
|
75
|
-
# Submit calls to riemann
|
76
|
-
if fs_calls > @limits[:calls][:critical]
|
77
|
-
alert 'FreeSWITCH current calls', :critical, fs_calls, "Number of calls are #{fs_calls}"
|
78
|
-
elsif fs_calls > @limits[:calls][:warning]
|
79
|
-
alert 'FreeSWITCH current calls', :warning, fs_calls, "Number of calls are #{fs_calls}"
|
80
|
-
else
|
81
|
-
alert 'FreeSWITCH current calls', :ok, fs_calls, "Number of calls are #{fs_calls}"
|
82
|
-
end
|
83
|
-
|
84
|
-
# Submit channels to riemann
|
85
|
-
if fs_channels > @limits[:calls][:critical]
|
86
|
-
alert 'FreeSWITCH current channels', :critical, fs_channels, "Number of channels are #{fs_channels}"
|
87
|
-
elsif fs_channels > @limits[:calls][:warning]
|
88
|
-
alert 'FreeSWITCH current channels', :warning, fs_channels, "Number of channels are #{fs_channels}"
|
89
|
-
else
|
90
|
-
alert 'FreeSWITCH current channels', :ok, fs_channels, "Number of channels are #{fs_channels}"
|
91
|
-
end
|
92
|
-
|
93
|
-
# Submit conferences to riemann
|
94
|
-
if fs_conferences > @limits[:calls][:critical]
|
95
|
-
alert 'FreeSWITCH current conferences', :critical, fs_conferences,
|
96
|
-
"Number of conferences are #{fs_conferences}"
|
97
|
-
elsif fs_conferences > @limits[:calls][:warning]
|
98
|
-
alert 'FreeSWITCH current conferences', :warning, fs_conferences,
|
99
|
-
"Number of conferences are #{fs_conferences}"
|
100
|
-
else
|
101
|
-
alert 'FreeSWITCH current conferences', :ok, fs_conferences, "Number of conferences are #{fs_conferences}"
|
102
|
-
end
|
103
|
-
|
104
|
-
# Submit threads to riemann
|
105
|
-
alert 'FreeSWITCH current threads', :ok, fs_threads, "Number of threads are #{fs_threads}" if fs_threads
|
106
|
-
|
107
|
-
# Submit status to riemann
|
108
|
-
if dead_proc?(fs_pid)
|
109
|
-
alert 'FreeSWITCH status', :critical, -1, 'FreeSWITCH service status: not running'
|
110
|
-
else
|
111
|
-
alert 'FreeSWITCH status', :ok, nil, 'FreeSWITCH service status: running'
|
112
|
-
end
|
113
|
-
|
114
|
-
# Submit CLI status to riemann using timeout in case it's unresponsive
|
115
|
-
if exec_with_timeout('fs_cli -x status', 2)
|
116
|
-
alert 'FreeSWITCH CLI status', :ok, nil, 'FreeSWITCH CLI status: responsive'
|
117
|
-
else
|
118
|
-
alert 'FreeSWITCH CLI status', :critical, -1, 'FreeSWITCH CLI status: not responding'
|
119
|
-
end
|
120
|
-
end
|
121
|
-
end
|
122
|
-
end
|
123
|
-
end
|
6
|
+
require 'riemann/tools/freeswitch'
|
124
7
|
|
125
|
-
Riemann::Tools::
|
8
|
+
Riemann::Tools::Freeswitch.run
|
data/bin/riemann-haproxy
CHANGED
@@ -3,63 +3,6 @@
|
|
3
3
|
|
4
4
|
Process.setproctitle($PROGRAM_NAME)
|
5
5
|
|
6
|
-
|
7
|
-
|
8
|
-
require File.expand_path('../lib/riemann/tools', __dir__)
|
9
|
-
|
10
|
-
module Riemann
|
11
|
-
module Tools
|
12
|
-
class Haproxy
|
13
|
-
include Riemann::Tools
|
14
|
-
require 'net/http'
|
15
|
-
require 'csv'
|
16
|
-
|
17
|
-
opt :stats_url, 'Full url to haproxy stats (eg: https://user:password@host.com:9999/stats)', required: true,
|
18
|
-
type: :string
|
19
|
-
|
20
|
-
def initialize
|
21
|
-
@uri = URI("#{opts[:stats_url]};csv")
|
22
|
-
end
|
23
|
-
|
24
|
-
def tick
|
25
|
-
csv.each do |row|
|
26
|
-
row = row.to_hash
|
27
|
-
ns = "haproxy #{row['pxname']} #{row['svname']}"
|
28
|
-
row.each do |property, metric|
|
29
|
-
next if property.nil? || property == 'pxname' || property == 'svname'
|
30
|
-
|
31
|
-
report(
|
32
|
-
host: @uri.host,
|
33
|
-
service: "#{ns} #{property}",
|
34
|
-
metric: metric.to_f,
|
35
|
-
tags: ['haproxy'],
|
36
|
-
)
|
37
|
-
end
|
38
|
-
|
39
|
-
report(
|
40
|
-
host: @uri.host,
|
41
|
-
service: "#{ns} state",
|
42
|
-
state: (%w[UP OPEN].include?(row['status']) ? 'ok' : 'critical'),
|
43
|
-
tags: ['haproxy'],
|
44
|
-
)
|
45
|
-
end
|
46
|
-
end
|
47
|
-
|
48
|
-
def csv
|
49
|
-
http = Net::HTTP.new(@uri.host, @uri.port)
|
50
|
-
http.use_ssl = true if @uri.scheme == 'https'
|
51
|
-
http.start do |h|
|
52
|
-
get = Net::HTTP::Get.new(@uri.request_uri)
|
53
|
-
unless @uri.userinfo.nil?
|
54
|
-
userinfo = @uri.userinfo.split(':')
|
55
|
-
get.basic_auth userinfo[0], userinfo[1]
|
56
|
-
end
|
57
|
-
h.request get
|
58
|
-
end
|
59
|
-
CSV.parse(http.body.split('# ')[1], { headers: true })
|
60
|
-
end
|
61
|
-
end
|
62
|
-
end
|
63
|
-
end
|
6
|
+
require 'riemann/tools/haproxy'
|
64
7
|
|
65
8
|
Riemann::Tools::Haproxy.run
|
data/bin/riemann-health
CHANGED
data/bin/riemann-kvminstance
CHANGED
@@ -3,26 +3,6 @@
|
|
3
3
|
|
4
4
|
Process.setproctitle($PROGRAM_NAME)
|
5
5
|
|
6
|
-
require
|
6
|
+
require 'riemann/tools/kvm'
|
7
7
|
|
8
|
-
|
9
|
-
module Tools
|
10
|
-
class KVM
|
11
|
-
include Riemann::Tools
|
12
|
-
|
13
|
-
def tick
|
14
|
-
# determine how many instances I have according to libvirt
|
15
|
-
kvm_instances = `LANG=C virsh list | grep -c running`
|
16
|
-
|
17
|
-
# submit them to riemann
|
18
|
-
report(
|
19
|
-
service: 'KVM Running VMs',
|
20
|
-
metric: kvm_instances.to_i,
|
21
|
-
state: 'info',
|
22
|
-
)
|
23
|
-
end
|
24
|
-
end
|
25
|
-
end
|
26
|
-
end
|
27
|
-
|
28
|
-
Riemann::Tools::KVM.run
|
8
|
+
Riemann::Tools::Kvm.run
|
data/bin/riemann-md
ADDED
data/bin/riemann-memcached
CHANGED
@@ -3,42 +3,6 @@
|
|
3
3
|
|
4
4
|
Process.setproctitle($PROGRAM_NAME)
|
5
5
|
|
6
|
-
|
7
|
-
|
8
|
-
require File.expand_path('../lib/riemann/tools', __dir__)
|
9
|
-
|
10
|
-
module Riemann
|
11
|
-
module Tools
|
12
|
-
class Memcached
|
13
|
-
include Riemann::Tools
|
14
|
-
require 'socket'
|
15
|
-
|
16
|
-
opt :memcached_host, 'Memcached hostname', default: 'localhost'
|
17
|
-
opt :memcached_port, 'Memcached port', default: 11_211
|
18
|
-
|
19
|
-
def tick
|
20
|
-
sock = TCPSocket.new(opts[:memcached_host], opts[:memcached_port])
|
21
|
-
sock.print("stats\r\n")
|
22
|
-
sock.flush
|
23
|
-
stats = sock.gets
|
24
|
-
|
25
|
-
loop do
|
26
|
-
stats = sock.gets
|
27
|
-
break if stats.strip == 'END'
|
28
|
-
|
29
|
-
m = stats.match(/STAT (\w+) (\S+)/)
|
30
|
-
report(
|
31
|
-
host: opts[:memcached_host].dup,
|
32
|
-
service: "memcached #{m[1]}",
|
33
|
-
metric: m[2].to_f,
|
34
|
-
state: 'ok',
|
35
|
-
tags: ['memcached'],
|
36
|
-
)
|
37
|
-
end
|
38
|
-
sock.close
|
39
|
-
end
|
40
|
-
end
|
41
|
-
end
|
42
|
-
end
|
6
|
+
require 'riemann/tools/memcached'
|
43
7
|
|
44
8
|
Riemann::Tools::Memcached.run
|
data/bin/riemann-net
CHANGED
data/bin/riemann-nginx-status
CHANGED
@@ -3,90 +3,6 @@
|
|
3
3
|
|
4
4
|
Process.setproctitle($PROGRAM_NAME)
|
5
5
|
|
6
|
-
|
7
|
-
# See http://wiki.nginx.org/HttpStubStatusModule for configuring Nginx appropriately
|
8
|
-
|
9
|
-
require File.expand_path('../lib/riemann/tools', __dir__)
|
10
|
-
|
11
|
-
module Riemann
|
12
|
-
module Tools
|
13
|
-
class NginxStatus
|
14
|
-
include Riemann::Tools
|
15
|
-
require 'net/http'
|
16
|
-
require 'uri'
|
17
|
-
|
18
|
-
opt :uri, 'Nginx Stub Status URI', default: 'http://localhost:8080/nginx_status'
|
19
|
-
opt :checks, 'Which metrics to report.', type: :strings,
|
20
|
-
default: %w[active accepted handled requests reading writing waiting]
|
21
|
-
opt :active_warning, 'Active connections warning threshold', default: 0
|
22
|
-
opt :active_critical, 'Active connections critical threshold', default: 0
|
23
|
-
opt :reading_warning, 'Reading connections warning threshold', default: 0
|
24
|
-
opt :reading_critical, 'Reading connections critical threshold', default: 0
|
25
|
-
opt :writing_warning, 'Writing connections warning threshold', default: 0
|
26
|
-
opt :writing_critical, 'Writing connections critical threshold', default: 0
|
27
|
-
opt :waiting_warning, 'Waiting connections warning threshold', default: 0
|
28
|
-
opt :waiting_critical, 'Waiting connections critical threshold', default: 0
|
29
|
-
|
30
|
-
def initialize
|
31
|
-
@uri = URI.parse(opts[:uri])
|
32
|
-
|
33
|
-
# sample response:
|
34
|
-
#
|
35
|
-
# Active connections: 1
|
36
|
-
# server accepts handled requests
|
37
|
-
# 39 39 39
|
38
|
-
# Reading: 0 Writing: 1 Waiting: 0
|
39
|
-
@keys = %w[active accepted handled requests reading writing waiting]
|
40
|
-
@re = /Active connections: (\d+) \n.+\n (\d+) (\d+) (\d+) \nReading: (\d+) Writing: (\d+) Waiting: (\d+)/m
|
41
|
-
end
|
42
|
-
|
43
|
-
def state(key, value)
|
44
|
-
if opts.key? "#{key}_critical".to_sym
|
45
|
-
critical_threshold = opts["#{key}_critical".to_sym]
|
46
|
-
return 'critical' if critical_threshold.positive? && (value >= critical_threshold)
|
47
|
-
end
|
48
|
-
|
49
|
-
if opts.key? "#{key}_warning".to_sym
|
50
|
-
warning_threshold = opts["#{key}_warning".to_sym]
|
51
|
-
return 'warning' if warning_threshold.positive? && (value >= warning_threshold)
|
52
|
-
end
|
53
|
-
|
54
|
-
'ok'
|
55
|
-
end
|
56
|
-
|
57
|
-
def tick
|
58
|
-
response = nil
|
59
|
-
begin
|
60
|
-
response = Net::HTTP.get(@uri)
|
61
|
-
rescue StandardError => e
|
62
|
-
report(
|
63
|
-
service: 'nginx health',
|
64
|
-
state: 'critical',
|
65
|
-
description: "Connection error: #{e.class} - #{e.message}",
|
66
|
-
)
|
67
|
-
end
|
68
|
-
|
69
|
-
return if response.nil?
|
70
|
-
|
71
|
-
report(
|
72
|
-
service: 'nginx health',
|
73
|
-
state: 'ok',
|
74
|
-
description: 'Nginx status connection ok',
|
75
|
-
)
|
76
|
-
|
77
|
-
values = @re.match(response).to_a[1, 7].map(&:to_i)
|
78
|
-
|
79
|
-
@keys.zip(values).each do |key, value|
|
80
|
-
report({
|
81
|
-
service: "nginx #{key}",
|
82
|
-
metric: value,
|
83
|
-
state: state(key, value),
|
84
|
-
tags: ['nginx'],
|
85
|
-
})
|
86
|
-
end
|
87
|
-
end
|
88
|
-
end
|
89
|
-
end
|
90
|
-
end
|
6
|
+
require 'riemann/tools/nginx_status'
|
91
7
|
|
92
8
|
Riemann::Tools::NginxStatus.run
|
data/bin/riemann-ntp
CHANGED
data/bin/riemann-portcheck
CHANGED
@@ -3,49 +3,6 @@
|
|
3
3
|
|
4
4
|
Process.setproctitle($PROGRAM_NAME)
|
5
5
|
|
6
|
-
|
7
|
-
# (c) Max Voit 2017
|
8
|
-
|
9
|
-
require File.expand_path('../lib/riemann/tools', __dir__)
|
10
|
-
|
11
|
-
module Riemann
|
12
|
-
module Tools
|
13
|
-
class Portcheck
|
14
|
-
include Riemann::Tools
|
15
|
-
require 'socket'
|
16
|
-
|
17
|
-
opt :hostname, 'Host, defaults to localhost', default: `hostname`.chomp
|
18
|
-
opt :ports, "List of ports to check, e.g. '-r 80 443'", type: :ints
|
19
|
-
|
20
|
-
def initialize
|
21
|
-
@hostname = opts.fetch(:hostname)
|
22
|
-
@ports = opts.fetch(:ports)
|
23
|
-
end
|
24
|
-
|
25
|
-
def tick
|
26
|
-
@ports.each do |thisport|
|
27
|
-
# try opening tcp connection with 5s timeout;
|
28
|
-
# if this fails, the port is considered closed
|
29
|
-
portopen = begin
|
30
|
-
Socket.tcp(@hostname, thisport, connect_timeout: 5) { true }
|
31
|
-
rescue StandardError
|
32
|
-
false
|
33
|
-
end
|
34
|
-
state = if portopen
|
35
|
-
'ok'
|
36
|
-
else
|
37
|
-
'critical'
|
38
|
-
end
|
39
|
-
report(
|
40
|
-
host: @hostname.to_s,
|
41
|
-
service: "port #{thisport}",
|
42
|
-
state: state.to_s,
|
43
|
-
tags: ['portcheck'],
|
44
|
-
)
|
45
|
-
end
|
46
|
-
end
|
47
|
-
end
|
48
|
-
end
|
49
|
-
end
|
6
|
+
require 'riemann/tools/portcheck'
|
50
7
|
|
51
8
|
Riemann::Tools::Portcheck.run
|