-
-
Notifications
You must be signed in to change notification settings - Fork 131
/
stack-swarmprom.yml
240 lines (220 loc) · 6.68 KB
/
stack-swarmprom.yml
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
version: "3.7"
x-default-opts:
&default-opts
logging:
options:
max-size: "1m"
# driver: "gelf"
# options:
# gelf-address: "udp://127.0.0.1:5000"
networks:
net: {}
proxy:
external: true
volumes:
prometheus:
driver: rexray/dobs
driver_opts:
size: 10
grafana:
driver: rexray/dobs
driver_opts:
size: 1
alertmanager:
driver: rexray/dobs
driver_opts:
size: 1
configs:
dockerd_config:
file: ./swarmprom/dockerd-exporter/Caddyfile
node_rules:
file: ./swarmprom/prometheus/rules/swarm_node.rules.yml
task_rules:
file: ./swarmprom/prometheus/rules/swarm_task.rules.yml
services:
dockerd-exporter:
<<: *default-opts
image: stefanprodan/caddy
networks:
- net
environment:
- DOCKER_GWBRIDGE_IP=172.18.0.1
configs:
- source: dockerd_config
target: /etc/caddy/Caddyfile
deploy:
mode: global
resources:
limits:
memory: 128M
reservations:
memory: 64M
cadvisor:
<<: *default-opts
image: google/cadvisor
networks:
- net
command: -logtostderr -docker_only
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
- /:/rootfs:ro
- /var/run:/var/run
- /sys:/sys:ro
- /var/lib/docker/:/var/lib/docker:ro
deploy:
mode: global
resources:
limits:
memory: 128M
reservations:
memory: 64M
grafana:
<<: *default-opts
image: stefanprodan/swarmprom-grafana:5.3.4
networks:
- net
- proxy
environment:
- GF_SECURITY_ADMIN_USER=${ADMIN_USER:-admin}
- GF_SECURITY_ADMIN_PASSWORD=${ADMIN_PASSWORD:-admin}
- GF_USERS_ALLOW_SIGN_UP=false
#- GF_SERVER_ROOT_URL=${GF_SERVER_ROOT_URL:-localhost}
#- GF_SMTP_ENABLED=${GF_SMTP_ENABLED:-false}
#- GF_SMTP_FROM_ADDRESS=${GF_SMTP_FROM_ADDRESS:[email protected]}
#- GF_SMTP_FROM_NAME=${GF_SMTP_FROM_NAME:-Grafana}
#- GF_SMTP_HOST=${GF_SMTP_HOST:-smtp:25}
#- GF_SMTP_USER=${GF_SMTP_USER}
#- GF_SMTP_PASSWORD=${GF_SMTP_PASSWORD}
volumes:
- grafana:/var/lib/grafana
deploy:
mode: replicated
replicas: 1
labels:
traefik.http.routers.grafana.rule: Host(`grafana.dogvs.cat`)
traefik.http.routers.grafana.entryPoints: websecure
traefik.http.routers.grafana.service: grafana
traefik.http.services.grafana.loadbalancer.server.port: 3000
placement:
constraints:
- node.role == manager
resources:
limits:
memory: 128M
reservations:
memory: 64M
alertmanager:
<<: *default-opts
image: stefanprodan/swarmprom-alertmanager:v0.14.0
networks:
- net
- proxy
environment:
- SLACK_URL=${SLACK_URL:-https://hooks.slack.com/services/TOKEN}
- SLACK_CHANNEL=${SLACK_CHANNEL:-general}
- SLACK_USER=${SLACK_USER:-alertmanager}
command:
- '--config.file=/etc/alertmanager/alertmanager.yml'
- '--storage.path=/alertmanager'
volumes:
- alertmanager:/alertmanager
deploy:
mode: replicated
replicas: 1
labels:
traefik.http.routers.alertmanager.rule: Host(`alertmanager.dogvs.cat`)
traefik.http.routers.alertmanager.entryPoints: websecure
traefik.http.routers.alertmanager.service: alertmanager
traefik.http.routers.alertmanager.middlewares: alertmanager-auth
traefik.http.services.alertmanager.loadbalancer.server.port: 9093
traefik.http.middlewares.alertmanager-auth.basicauth.users: ${AM_USER:-admin}:${AM_PASSWORD:-$2y$05$oZcj4FgdSFEYNCH0EH/3Vu7Hp72gkvEadHzMsDhGFkbvS/ZrKMKfK}
placement:
constraints:
- node.role == manager
resources:
limits:
memory: 128M
reservations:
memory: 64M
unsee:
<<: *default-opts
image: cloudflare/unsee:v0.8.0
networks:
- net
- proxy
environment:
- "ALERTMANAGER_URIS=default:http://alertmanager:9093"
deploy:
mode: replicated
replicas: 1
labels:
traefik.http.routers.unsee.rule: Host(`unsee.dogvs.cat`)
traefik.http.routers.unsee.entryPoints: websecure
traefik.http.routers.unsee.service: unsee
traefik.http.routers.unsee.middlewares: unsee-auth
traefik.http.services.unsee.loadbalancer.server.port: 9094
traefik.http.middlewares.unsee-auth.basicauth.users: ${UNSEE_USER:-admin}:${UNSEE_PASSWORD:-$2y$05$oZcj4FgdSFEYNCH0EH/3Vu7Hp72gkvEadHzMsDhGFkbvS/ZrKMKfK}
# - com.df.users=${ADMIN_USER:-admin}:${ADMIN_PASSWORD:-admin}
node-exporter:
<<: *default-opts
image: stefanprodan/swarmprom-node-exporter:v0.16.0
networks:
- net
environment:
- NODE_ID={{.Node.ID}}
volumes:
- /proc:/host/proc:ro
- /sys:/host/sys:ro
- /:/rootfs:ro
- /etc/hostname:/etc/nodename
command:
- '--path.sysfs=/host/sys'
- '--path.procfs=/host/proc'
- '--collector.textfile.directory=/etc/node-exporter/'
- '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
# no collectors are explicitely enabled here, because the defaults are just fine,
# see https://github.com/prometheus/node_exporter
# disable ipvs collector because it barfs the node-exporter logs full with errors on my centos 7 vm's
- '--no-collector.ipvs'
deploy:
mode: global
resources:
limits:
memory: 128M
reservations:
memory: 64M
prometheus:
<<: *default-opts
image: stefanprodan/swarmprom-prometheus:v2.5.0
networks:
- net
- proxy
command:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--storage.tsdb.retention=24h'
volumes:
- prometheus:/prometheus
configs:
- source: node_rules
target: /etc/prometheus/swarm_node.rules.yml
- source: task_rules
target: /etc/prometheus/swarm_task.rules.yml
deploy:
mode: replicated
replicas: 1
labels:
traefik.http.routers.prom.rule: Host(`prom.dogvs.cat`)
traefik.http.routers.prom.entryPoints: websecure
traefik.http.routers.prom.service: prom
traefik.http.routers.prom.middlewares: prom-auth
traefik.http.services.prom.loadbalancer.server.port: 9090
traefik.http.middlewares.prom-auth.basicauth.users: ${KIBANA_USER:-admin}:${KIBANA_PASSWORD:-$2y$05$oZcj4FgdSFEYNCH0EH/3Vu7Hp72gkvEadHzMsDhGFkbvS/ZrKMKfK}
placement:
constraints:
- node.role == manager
resources:
limits:
memory: 2048M
reservations:
memory: 128M