-
Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathconf.yml
More file actions
296 lines (295 loc) · 8.58 KB
/
conf.yml
File metadata and controls
296 lines (295 loc) · 8.58 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
general:
company: Server Density
company-logo: sdlogo.png
header: This is how our infrastructure performs
sub-header: Metrics from the last 24 hours.
header-image: main-image.png
statuspage: serverdensity # url, optional. If used open page to get status.
timeframe: 24
stack:
- Php
- Python
- MongoDB
- Apache Storm
- Kafka
- Zookeeper
- Redis
- Nginx
- Ubuntu Linux
round: 0 # optional
infrastructure:
- title: Api Requests
subtitle: Serving thousands of requests a day
title_layout: left # optional,
size: 100 # optional
tag: loadbalancing
metrics:
- metrickey: plugins.ApiStatsD.TokenProxyHandler_aggregated_count
calculation:
- sum
- max
sum_title: Requests via Api
sum_unit: per day
sum_stat: 412
max_title: Peak
max_unit: q/s
max_stat: 1341
style: circle-filled
- metrickey: plugins.ApiStatsD.SessionProxyHandler_aggregated_count
cumulative: True
calculation:
- sum
- max
sum_title: Requests via UI
sum_unit: per day
max_title: Peak
max_unit: q/s
- metrickey: memory.memPhysUsed
si_unit: mb
calculation:
- average
average_title: Used memory
- metrickey: cpuStats.ALL.usr
cumulative: False
calculation:
- average
- max
average_title: CPU usage
average_unit: percent
max_title: Peak
max_unit: "%"
- metrickey: loadAvrg
cumulative: False
calculation:
- average
- max
average_title: Load Average
average_unit: avg / min
max_title: Peak
- title: Inventory usage
subtitle: How people use our api to look at the inventory
title_layout: left # optional,
size: 50 # optional
group: Cluster1
metrics:
- metrickey: plugins.StatsD.devices_update_count
calculation:
- sum
- average
- max
sum_title: Devices updated
sum_unit: per day
average_title: avg
average_unit: / min
max_title: Peak
- metrickey: plugins.StatsD.devices_view_count
calculation:
- sum
- average
- max
sum_title: Devices viewed
sum_unit: per day
average_title: avg
average_unit: / min
max_title: Peak
- metrickey: plugins.StatsD.services_update_count
calculation:
- sum
- average
- max
sum_title: Services updated
sum_unit: per day
average_title: avg
average_unit: / min
max_title: Peak
- metrickey: plugins.StatsD.services_view_count
calculation:
- sum
- average
- max
sum_title: Services viewed
sum_unit: per day
average_title: avg
average_unit: / min
max_title: Peak
- title: Inventory Servers
subtitle: The servers that handle our inventory
title_layout: right
size: 50
group: Cluster1
metrics:
- calculation:
- average
average_stat: 2
average_title: Servers
- metrickey: cpuStats.ALL.usr
calculation:
- average
- max
average_title: CPU usage
average_unit: percent
max_title: Peak
max_unit: "%"
- metrickey: loadAvrg
calculation:
- average
- max
average_title: Load Average
max_title: Peak
- metrickey: memory.memPhysUsed
si_unit: mb
calculation:
- average
average_title: Memory used
# - title: Notifications
# subtitle: Notifications is handled by storm, it does a splendid job.
# title_layout: right # optional,
# size: 50 # optional
# tag: storm-notifications
# metrics:
# - metrickey: plugins.StatsD.NotificationsBolt_requests
# calculation:
# - sum
# - max
# sum_title: Sent
# average_title: Sent Notifications
# average_unit: per day
# max_title: Peak
# max_unit: / min
- title: Alerts
subtitle: The amount of alerts we see every day
title_layout: left # optional,
size: 100 # optional
tag: alerts
metrics:
- metrickey: plugins.StatsD.triggered_count_count
calculation:
- sum
- max
sum_title: Alerts triggered
sum_unit: per day
max_title: Peak
style: circle-filled
- metrickey: memory.memPhysUsed
si_unit: mb
calculation:
- average
average_title: Memory used
- metrickey: cpuStats.ALL.usr
cumulative: False
calculation:
- average
- max
average_title: CPU usage
average_unit: percent
max_title: Peak
max_unit: "%"
- metrickey: loadAvrg
cumulative: False
calculation:
- average
average_title: Load Average
- title: Website monitoring
subtitle: We do a lot of service checks in 24h
title_layout: right
size: 100
group: V2Directors
metrics:
- metrickey: plugins.StatsD.send_count
calculation:
- sum
- max
sum_title: Checks sent
sum_unit: per day
max_title: Peak
max_unit: / min
style: circle-filled
- metrickey: memory.memPhysUsed
si_unit: mb
calculation:
- average
average_title: Memory used
- metrickey: cpuStats.ALL.usr
cumulative: False
calculation:
- average
- max
average_title: CPU usage
average_unit: percent
max_title: Peak
max_unit: "%"
- metrickey: loadAvrg
cumulative: False
calculation:
- average
average_title: Load Average
average_unit: avg / min
# - title: Inventory
# subtitle: We monitor a lot of devices and services
# image_layout: left
# title_layout: right
# image: kitten.jpg
# size: 100
# tag: hperm
# metrics:
# - metrickey: plugins.InventoryCount.services
# calculation:
# - max
# max_title: Services
# - metrickey: plugins.InventoryCount.non-cloud devices
# calculation:
# - max
# max_title: Devices
# - metrickey: plugins.InventoryCount.cloud devices
# calculation:
# - max
# max_title: Cloud devices
- title: Load Balancing
subtitle: The total amount of traffic we handle through load balancers
title_layout: left
group: V2LoadBalancers
metrics:
- calculation:
- average
average_title: Servers
average_stat: 14
- metrickey: networkTraffic.eth0.rxMByteS
si_unit: mb
calculation:
- sum
- max
sum_title: Traffic recieved internally # internal traffic
sum_unit: per day
max_title: Peak
max_unit: / min
multiplier: 60
- metrickey: networkTraffic.eth0.txMByteS
calculation:
- sum
- max
sum_title: Traffic sent internally
si_unit: mb
sum_unit: per day
max_title: Peak
max_unit: / min
multiplier: 60
- metrickey: networkTraffic.eth1.rxMByteS
si_unit: mb
calculation:
- sum
- max
sum_title: Traffic recieved externally
sum_unit: per day
max_title: Peak
max_unit: / min
multiplier: 60
- metrickey: networkTraffic.eth1.txMByteS
si_unit: mb
calculation:
- sum
- max
sum_title: Traffic sent externally
sum_unit: per day
max_title: Peak
max_unit: / min
multiplier: 60