166 lines
4.1 KiB
Markdown
166 lines
4.1 KiB
Markdown
> 本文作者：丁辉
|
||
|
||
# N9e对接Kube-Prometheus-Stack
|
||
|
||
## 更新Kube-Prometheus-Stack
|
||
|
||
1. 编写 values.yaml
|
||
|
||
```bash
|
||
vi kube-prometheus-stack-values.yaml
|
||
```
|
||
|
||
2. 内容如下
|
||
|
||
```yaml
|
||
prometheusOperator:
|
||
admissionWebhooks:
|
||
patch:
|
||
enabled: true
|
||
image:
|
||
registry: registry.aliyuncs.com # 配置国内镜像加速
|
||
repository: google_containers/kube-webhook-certgen
|
||
grafana:
|
||
enabled: false
|
||
alertmanager:
|
||
enabled: false
|
||
defaultRules:
|
||
create: false
|
||
# 这些设置表明所提及的选择器（规则、服务监视器、Pod 监视器和抓取配置）将具有独立的配置，而不会基于 Helm 图形值。（否则你的 ServiceMonitor 可能不会被自动发现）
|
||
prometheus:
|
||
prometheusSpec:
|
||
ruleSelectorNilUsesHelmValues: false
|
||
serviceMonitorSelectorNilUsesHelmValues: false
|
||
podMonitorSelectorNilUsesHelmValues: false
|
||
probeSelectorNilUsesHelmValues: false
|
||
scrapeConfigSelectorNilUsesHelmValues: false
|
||
# 服务器上启用 --web.enable-remote-write-receiver 标志
|
||
enableRemoteWriteReceiver: true
|
||
# 启用 Prometheus 中被禁用的特性
|
||
enableFeatures:
|
||
- remote-write-receiver
|
||
# 挂载持久化存储
|
||
storageSpec:
|
||
volumeClaimTemplate:
|
||
spec:
|
||
# 选择默认的 sc 创建存储（我已在集群内准备 nfs-client）
|
||
storageClassName:
|
||
accessModes: ["ReadWriteOnce"]
|
||
resources:
|
||
requests:
|
||
storage: 10Gi # 根据自己的需求申请 pvc 大小
|
||
# 挂载本地时区
|
||
volumes:
|
||
- name: timezone
|
||
hostPath:
|
||
path: /usr/share/zoneinfo/Asia/Shanghai
|
||
volumeMounts:
|
||
- name: timezone
|
||
mountPath: /etc/localtime
|
||
readOnly: true
|
||
```
|
||
|
||
3. 更新
|
||
|
||
```bash
|
||
helm upgrade kube-prometheus-stack -f kube-prometheus-stack-values.yaml --set "kube-state-metrics.image.registry=k8s.dockerproxy.com" prometheus-community/kube-prometheus-stack -n monitor
|
||
```
|
||
|
||
## 更新N9e
|
||
|
||
1. 获取 nightingale-center svc
|
||
|
||
```bash
|
||
kubectl get svc nightingale-center -n monitor | grep -v NAME | awk '{print $3}'
|
||
```
|
||
|
||
2. 编写 values.yaml
|
||
|
||
```bash
|
||
vi n9e-values.yaml
|
||
```
|
||
|
||
内容如下
|
||
|
||
```yaml
|
||
expose:
|
||
type: clusterIP # 使用 clusterIP
|
||
|
||
externalURL: https://hello.n9e.info # 改为自己的外部服务访问地址
|
||
|
||
persistence:
|
||
enabled: true
|
||
|
||
categraf:
|
||
internal:
|
||
docker_socket: unix:///var/run/docker.sock # 如果您的kubernetes运行时是容器或其他，则清空此变量。
|
||
|
||
n9e:
|
||
internal:
|
||
image:
|
||
repository: flashcatcloud/nightingale
|
||
tag: latest # 使用最新版镜像
|
||
|
||
prometheus:
|
||
type: external
|
||
external:
|
||
host: "10.43.119.105" # 这里添加 nightingale-center svc
|
||
port: "9090"
|
||
username: ""
|
||
password: ""
|
||
podAnnotations: {}
|
||
```
|
||
|
||
3. 更新
|
||
|
||
```bash
|
||
helm upgrade nightingale ./n9e-helm -n monitor -f n9e-values.yaml
|
||
```
|
||
|
||
4. 编写 ServiceMonitor
|
||
|
||
```bash
|
||
vi n9e-servicemonitor.yaml
|
||
```
|
||
|
||
内容如下
|
||
|
||
```yaml
|
||
apiVersion: monitoring.coreos.com/v1
|
||
kind: ServiceMonitor
|
||
metadata:
|
||
name: n9e-center-monitor
|
||
namespace: monitor
|
||
spec:
|
||
endpoints:
|
||
- path: /metrics
|
||
port: port
|
||
namespaceSelector:
|
||
matchNames:
|
||
- monitor
|
||
selector:
|
||
matchLabels:
|
||
app: n9e
|
||
```
|
||
|
||
5. 部署
|
||
|
||
```bash
|
||
kubectl apply -f n9e-servicemonitor.yaml
|
||
```
|
||
|
||
6. N9e 添加数据源
|
||
|
||
```bash
|
||
http://kube-prometheus-stack-prometheus:9090/
|
||
```
|
||
|
||
|
||
## 问题记录
|
||
|
||
> ```
|
||
> WARNING writer/writer.go:129 push data with remote write:http://10.43.119.105:9090/api/v1/write request got status code: 400, response body: out of order sample
|
||
> WARNING writer/writer.go:79 post to http://10.43.119.105:9090/api/v1/write got error: push data with remote write:http://10.43.119.105:9090/api/v1/write request got status code: 400, response body: out of order sample
|
||
> ```
|
||
>
|
||
> 上报数据 400, 暂时没有思路咋解决 |