新增GPU部分

2025-11-12 18:14:10 +08:00
parent 4b274a02c8
commit fd60868b97
15 changed files with 1220 additions and 96 deletions
--- a/69-202511-AI-GPU测试/rke-13014-cluster-security.yml
+++ b/69-202511-AI-GPU测试/rke-13014-cluster-security.yml
@@ -0,0 +1,231 @@
+nodes:
+  - address: 192.168.40.50
+    user: root
+    role:
+      - controlplane
+      - etcd
+      - worker
+    internal_address: 192.168.40.50
+    hostname_override: "master-192.168.40.50"
+    labels:
+      ingress-deploy: true
+      uavcloud.env: demo
+  - address: 192.168.119.105
+    user: root
+    role:
+      - worker
+    internal_address: 192.168.119.105
+    labels:
+      uavcloud.env: demo
+  - address: 192.168.119.106
+    user: root
+    role:
+      - worker
+    internal_address: 192.168.119.106
+    labels:
+      uavcloud.env: demo
+
+authentication:
+  strategy: x509
+  sans:
+    - "192.168.40.50"
+
+#private_registries:
+#  - url: 192.168.0.8:8033 # 私有镜像库地址
+#    user: admin
+#    password: "V2ryStr@ngPss"
+#    is_default: true
+
+##############################################################################
+
+# 默认值为false，如果设置为true，当发现不支持的Docker版本时，RKE不会报错
+ignore_docker_version: true
+
+# Set the name of the Kubernetes cluster
+cluster_name: rke-cluster
+
+kubernetes_version: v1.30.14-rancher1-1
+
+ssh_key_path: /root/.ssh/id_ed25519
+
+# Enable running cri-dockerd
+# Up to Kubernetes 1.23, kubelet contained code called dockershim
+# to support Docker runtime. The replacement is called cri-dockerd
+# and should be enabled if you want to keep using Docker as your
+# container runtime
+# Only available to enable in Kubernetes 1.21 and higher
+enable_cri_dockerd: true
+
+services:
+  etcd:
+    backup_config:
+      enabled: false
+      interval_hours: 72
+      retention: 3
+      safe_timestamp: false
+      timeout: 300
+    creation: 12h
+    extra_args:
+        election-timeout: 5000
+        heartbeat-interval: 500
+        cipher-suites: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA,TLS_RSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_256_GCM_SHA384,TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA
+    gid: 0
+    retention: 72h
+    snapshot: false
+    uid: 0
+
+  kube-api:
+    # IP range for any services created on Kubernetes
+    # This must match the service_cluster_ip_range in kube-controller
+    service_cluster_ip_range: 10.74.0.0/16
+    # Expose a different port range for NodePort services
+    service_node_port_range: 30000-40000
+    always_pull_images: true
+    pod_security_policy: false
+    # Add additional arguments to the kubernetes API server
+    # This WILL OVERRIDE any existing defaults
+    extra_args:
+      # Enable audit log to stdout
+      audit-log-path: "-"
+      # Increase number of delete workers
+      delete-collection-workers: 3
+      # Set the level of log output to warning-level
+      v: 1
+  kube-controller:
+    # CIDR pool used to assign IP addresses to pods in the cluster
+    cluster_cidr: 10.100.0.0/16
+    # IP range for any services created on Kubernetes
+    # This must match the service_cluster_ip_range in kube-api
+    service_cluster_ip_range: 10.74.0.0/16
+    # Add additional arguments to the kubernetes API server
+    # This WILL OVERRIDE any existing defaults
+    extra_args:
+      # Set the level of log output to debug-level
+      v: 1
+      # Enable RotateKubeletServerCertificate feature gate
+      feature-gates: RotateKubeletServerCertificate=true
+      # Enable TLS Certificates management
+      # https://kubernetes.io/docs/tasks/tls/managing-tls-in-a-cluster/
+      cluster-signing-cert-file: "/etc/kubernetes/ssl/kube-ca.pem"
+      cluster-signing-key-file: "/etc/kubernetes/ssl/kube-ca-key.pem"
+  kubelet:
+    # Base domain for the cluster
+    cluster_domain: cluster.local
+    # IP address for the DNS service endpoint
+    cluster_dns_server: 10.74.0.10
+    # Fail if swap is on
+    fail_swap_on: false
+    # Set max pods to 250 instead of default 110
+    extra_binds:
+      - "/data/minio-pv:/hostStorage" # 不要修改 为minio的pv添加
+    extra_args:
+      max-pods: 122
+    # Optionally define additional volume binds to a service
+  scheduler:
+    extra_args:
+      # Set the level of log output to warning-level
+      v: 0
+      tls-cipher-suites: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA,TLS_RSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_256_GCM_SHA384,TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA
+  kubeproxy:
+    extra_args:
+      # Set the level of log output to warning-level
+      v: 1
+
+authorization:
+  mode: rbac
+
+addon_job_timeout: 30
+
+# Specify network plugin-in (canal, calico, flannel, weave, or none)
+network:
+  mtu: 1440
+  options:
+    flannel_backend_type: vxlan
+  plugin: calico
+  tolerations:
+    - key: "node.kubernetes.io/unreachable"
+      operator: "Exists"
+      effect: "NoExecute"
+      tolerationseconds: 300
+    - key: "node.kubernetes.io/not-ready"
+      operator: "Exists"
+      effect: "NoExecute"
+      tolerationseconds: 300
+
+# Specify DNS provider (coredns or kube-dns)
+dns:
+  provider: coredns
+  nodelocal: {}
+  # Available as of v1.1.0
+  update_strategy:
+    strategy: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 20%
+      maxSurge: 15%
+    linear_autoscaler_params:
+      cores_per_replica: 0.34
+      nodes_per_replica: 4
+      prevent_single_point_failure: true
+      min: 2
+      max: 3
+  tolerations:
+    - key: "node.kubernetes.io/unreachable"
+      operator: "Exists"
+      effect: "NoExecute"
+      tolerationseconds: 300
+    - key: "node.kubernetes.io/not-ready"
+      operator: "Exists"
+      effect: "NoExecute"
+      tolerationseconds: 300
+
+# Specify monitoring provider (metrics-server)
+monitoring:
+  provider: metrics-server
+  # Available as of v1.1.0
+  update_strategy:
+    strategy: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 8
+
+ingress:
+  provider: nginx
+  default_backend: true
+  http_port: 30500
+  https_port: 31500
+  extra_envs:
+    - name: TZ
+      value: Asia/Shanghai
+  node_selector:
+    ingress-deploy: true
+  options:
+    use-forwarded-headers: "true"
+    access-log-path: /var/log/nginx/access.log
+#    client-body-timeout: '6000'
+#    compute-full-forwarded-for: 'true'
+#    enable-underscores-in-headers: 'true'
+#    log-format-escape-json: 'true'
+#    log-format-upstream: >-
+#      { "msec": "$msec", "connection": "$connection", "connection_requests":
+#      "$connection_requests", "pid": "$pid", "request_id": "$request_id",
+#      "request_length": "$request_length", "remote_addr": "$remote_addr",
+#      "remote_user": "$remote_user", "remote_port": "$remote_port",
+#      "http_x_forwarded_for": "$http_x_forwarded_for", "time_local":
+#      "$time_local", "time_iso8601": "$time_iso8601", "request": "$request",
+#      "request_uri": "$request_uri", "args": "$args", "status": "$status",
+#      "body_bytes_sent": "$body_bytes_sent", "bytes_sent": "$bytes_sent",
+#      "http_referer": "$http_referer", "http_user_agent": "$http_user_agent",
+#      "http_host": "$http_host", "server_name": "$server_name", "request_time":
+#      "$request_time", "upstream": "$upstream_addr", "upstream_connect_time":
+#      "$upstream_connect_time", "upstream_header_time": "$upstream_header_time",
+#      "upstream_response_time": "$upstream_response_time",
+#      "upstream_response_length": "$upstream_response_length",
+#      "upstream_cache_status": "$upstream_cache_status", "ssl_protocol":
+#      "$ssl_protocol", "ssl_cipher": "$ssl_cipher", "scheme": "$scheme",
+#      "request_method": "$request_method", "server_protocol": "$server_protocol",
+#      "pipe": "$pipe", "gzip_ratio": "$gzip_ratio", "http_cf_ray": "$http_cf_ray",
+#      "geoip_country_code": "$geoip_country_code" }
+#    proxy-body-size: 5120m
+#    proxy-read-timeout: '6000'
+#    proxy-send-timeout: '6000'
+
+