prometheus（docker）安装和报警 -- nginx域名监控

红太狼 2021-09-20 11:30 637阅读 0赞

软件组件：  
prometheus  
alertmanager  
prometheus-webhook-dingtalk

nginx-vts-exporter  
nginx

(\#\#\#--add-module=../nginx-module-vts/)

1、安装prometheus  
2、安装alertmanager  
3、nginx-vts-exporter

\#cat docker-compose.yml  
version: '2'  
services:  
alertmanager:  
image: docker.io/prom/alertmanager  
container\_name: alertmanager  
ports:  
\- 9093  
volumes:  
\- /etc/prometheus/alertmanager.yml:/etc/prometheus/alertmanager.yml  
network\_mode: host  
prometheus:  
image: prom/prometheus  
container\_name: prometheus  
ports:  
\- 9090  
volumes:  
\- /etc/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml  
\- /data/prometheus-data:/prometheus-data  
\- /etc/prometheus/rules.yml:/etc/prometheus/rules.yml  
  
network\_mode: host  
  
nginx-vts-exporter:  
image: sophos/nginx-vts-exporter  
container\_name: nginx-vts-exporter  
ports:  
\- 9913  
environment:  
\- NGINX\_STATUS=http://127.0.0.1:11111/vt-status/format/json  
network\_mode: host

\#\#cat /etc/prometheus/prometheus.yml

\# my global config  
global:  
scrape\_interval: 15s \# Set the scrape interval to every 15 seconds. Default is every 1 minute.  
evaluation\_interval: 15s \# Evaluate rules every 15 seconds. The default is every 1 minute.  
\# scrape\_timeout is set to the global default (10s).

\# Alertmanager configuration  
alerting:  
alertmanagers:  
\- static\_configs:  
\- targets: \[ "127.0.0.1:9093"\]

\# Load rules once and periodically evaluate them according to the global 'evaluation\_interval'.  
rule\_files:  
\- "/etc/prometheus/rules.yml"  
\# - "second\_rules.yml"

\# A scrape configuration containing exactly one endpoint to scrape:  
\# Here it's Prometheus itself.  
scrape\_configs:  
\# The job name is added as a label \`job=<job\_name>\` to any timeseries scraped from this config.  
\- job\_name: 'prometheus'

\# metrics\_path defaults to '/metrics'  
\# scheme defaults to 'http'.

static\_configs:  
\- targets: \['localhost:9090'\]  
\- job\_name: 'prometheus\_nginx'  
static\_configs:  
\- targets: \['127.0.0.1:9913'\]  
\- job\_name: 'docker'  
static\_configs:  
\- targets: \['192.168.0.200:9999'\]

\#cat /etc/prometheus/rules.yml  
groups:

\- name: test-rule  
rules:  
\- alert: NodeFilesystemUsage  
expr: (node\_filesystem\_size\{device="rootfs"\} - node\_filesystem\_free\{device="rootfs"\}) / node\_filesystem\_size\{device="rootfs"\} \* 100 > 80  
for: 2m  
labels:  
team: node  
annotations:  
summary: "\{ \{$labels.instance\}\}: High Filesystem usage detected"  
description: "\{ \{$labels.instance\}\}: Filesystem usage is above 80% (current value is: \{ \{ $value \}\}"

\- alert: NodeMemoryUsage  
expr: nginx\_server\_bytes > 100  
for: 2m  
labels:  
team: node  
annotations:  
summary: "nginx\_server\_bytes too 100"  
description: "\{ \{$labels.instance\}\}: nginx\_server\_bytes (current value is: \{ \{ $value \}\}"

\#cat /etc/prometheus/alertmanager.yml  
global:  
resolve\_timeout: 5m

route:  
group\_by: \['alertname'\]  
group\_wait: 10s  
group\_interval: 10s  
repeat\_interval: 5m  
receiver: 'send\_to\_dingding\_webhook1'

receivers:  
\- name: 'send\_to\_dingding\_webhook1'  
webhook\_configs:  
\- send\_resolved: true  
url: 'http://127.0.0.1:8060/dingtalk/webhook1/send'

inhibit\_rules:  
\- source\_match:  
severity: 'critical'  
target\_match:  
severity: 'warning'  
equal: \['alertname', 'dev', 'instance'\]

\#  
nohup ./prometheus-webhook-dingtalk --web.listen-address=":8060" --ding.profile="webhook1=https://oapi.dingtalk.com/robot/send?access\_token=682fdfb7c9b83670f32a0a1549187ff16fe36ebc2dcfab9747cd3122dbefa6dd" &

\#\#启动  
docker-compose up -d

4、安装nginx (略)  
\--user=nginx --group=nginx --prefix=/opt/app/nginx --with-http\_v2\_module --with-http\_ssl\_module --with-http\_sub\_module --with-http\_stub\_status\_module --with-http\_gzip\_static\_module --with-pcre --add-module=../nginx-module-vts/ --with-http\_image\_filter\_module=dynamic

配置nginx.conf  
http \{  
vhost\_traffic\_status\_zone;

vhost\_traffic\_status\_filter\_by\_host on;  
...  
\}

server\{

listen 11111;  
server\_name 127.0.0.1;  
location /vt-status \{  
stub\_status on;  
access\_log off;

\}  
location /vt-status \{  
vhost\_traffic\_status\_display;  
vhost\_traffic\_status\_display\_format html;  
\}

转载于:https://www.cnblogs.com/Qing-840/p/9263487.html