full_container_scheme/4.monitor/prometheus/2.configmap.yml

59 lines
1.9 KiB
YAML

apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: monitor
data:
prometheus.yml: |
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.
alerting:
alertmanagers:
- static_configs:
- targets:
- 10.10.10.160:9093
rule_files:
- "/etc/prometheus/rules.yml"
scrape_configs:
- job_name: "prometheus"
static_configs:
- targets: ["localhost:9090"]
- job_name: "alertmanager"
static_configs:
- targets: ["10.10.10.160:9093"]
- job_name: 'consul-app-prometheus'
metrics_path: "/actuator/prometheus"
consul_sd_configs: # 配置基于consul的服务发现
- server: 172.16.5.37:8500 # consul
refresh_interval: 10s # 刷新间隔
services: ['application']
relabel_configs: # 把__meta_consul_service_id 映射主机名
- source_labels: [__meta_consul_service_id]
separator: ;
regex: (.*)
target_label: 'instance'
replacement: $1
action: replace
- source_labels: [__meta_consul_service_address] #映射主机IP
separator: ;
regex: (.*)
target_label: 'ip'
replacement: $1
action: replace
- source_labels: [__meta_consul_service]
target_label: 'service'
rules.yml: |
groups:
- name: jvm告警
rules:
- alert: 频繁FullGC
expr: increase(jvm_gc_pause_seconds_sum[5m]) > 1
for: 1m
labels:
severity: 警告
annotations:
summary: "检测到频繁的 Full GC"
description: "{{$labels.instance}} 正在经历频繁的 Full GC 事件"