🚀 Prometheus
参考
Helm
Bash | |
---|---|
1 |
|
-
repo
-
查看
Bash 1
helm repo list
-
添加
Bash 1
helm repo add 仓库名称 仓库地址
-
更新
Bash 1
helm repo update
-
-
release
-
查看
Bash 1
helm list -A
-
卸载
Bash 1
helm uninstall [release]
-
安装
Bash 1
helm install [release] 仓库名称/包名 -n 命名空间 --create-namespace
-
-
upgrade
-
查看
Bash 1
helm show values 仓库名称/包名
Bash 1
helm get values [release] -n 命名空间
-
修改
Bash 1
helm upgrade [release] 仓库名称/包名 -n 命名空间 -f values.yaml
-
rollback
Bash 1
helm rollback [release] 版本号 -n 命名空间
Bash 1
helm history [release] -n 命名空间
-
Prometheus
-
添加 prometheus-community 仓库
Bash 1
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
-
安装 prometheus
Bash 1
helm install prometheus prometheus-community/kube-prometheus-stack --namespace prometheus --create-namespace
-
让服务暴露出来
YAML 1 2 3 4 5 6 7 8 9 10 11 12 13
# values-prometheus.yaml prometheus: prometheusSpec: service: type: NodePort grafana: service: type: NodePort alertmanager: service: type: NodePort
Bash 1
helm upgrade prometheus prometheus-community/kube-prometheus-stack -n prometheus -f values-prometheus.yaml
-
康康服务
Bash 1
kubectl get svc -n prometheus
GPU Operator
-
导入仓库
Bash 1
helm repo add nvidia https://helm.ngc.nvidia.com/nvidia
-
安装 GPU Operator
Bash 1
helm install gpu-operator nvidia/gpu-operator -n gpu-operator --create-namespace
-
暴露服务
YAML 1 2 3 4
# values-gpu-operator.yaml dcgmExporter: service: type: NodePort
Bash 1
helm upgrade gpu-operator nvidia/gpu-operator -n gpu-operator -f values-gpu-operator.yaml
-
康康服务
Bash 1
kubectl get svc -n gpu-operator