54 Telco機能 (DPDK、SR-IOV、CPUアイソレーション、huge pages、NUMAなど) #

apiVersion: controlplane.cluster.x-k8s.io/v1beta2
kind: RKE2ControlPlane
metadata:
  name: single-node-cluster
  namespace: default
spec:
  infrastructureRef:
    apiGroup: infrastructure.cluster.x-k8s.io
    kind: Metal3MachineTemplate
    name: single-node-cluster-controlplane
  replicas: 1
  version: ${RKE2_VERSION}
  rolloutStrategy:
    type: "RollingUpdate"
    rollingUpdate:
      maxSurge: 0
  serverConfig:
    cni: calico
    cniMultusEnable: true
  agentConfig:
    format: ignition
    additionalUserData:
      config: |
        variant: fcos
        version: 1.4.0
        storage:
          files:
          - path: /var/lib/rancher/rke2/server/manifests/configmap-sriov-custom-auto.yaml
            overwrite: true
            contents:
              inline: |
                apiVersion: v1
                kind: ConfigMap
                metadata:
                  name: sriov-custom-auto-config
                  namespace: kube-system
                data:
                  config.json: |
                    [
                        {
                          "resourceName": "${RESOURCE_NAME1}",
                          "interface": "${SRIOV-NIC-NAME1}",
                          "pfname": "${PF_NAME1}",
                          "driver": "${DRIVER_NAME1}",
                          "numVFsToCreate": ${NUM_VFS1}
                        },
                        {
                          "resourceName": "${RESOURCE_NAME2}",
                          "interface": "${SRIOV-NIC-NAME2}",
                          "pfname": "${PF_NAME2}",
                          "driver": "${DRIVER_NAME2}",
                          "numVFsToCreate": ${NUM_VFS2}
                        }
                    ]
            mode: 0644
            user:
              name: root
            group:
              name: root
          - path: /var/lib/rancher/rke2/server/manifests/sriov-crd.yaml
            overwrite: true
            contents:
              inline: |
                apiVersion: helm.cattle.io/v1
                kind: HelmChart
                metadata:
                  name: sriov-crd
                  namespace: kube-system
                spec:
                  chart: oci://registry.suse.com/edge/charts/sriov-crd
                  targetNamespace: sriov-network-operator
                  version: 306.0.4+up1.6.0
                  createNamespace: true
          - path: /var/lib/rancher/rke2/server/manifests/sriov-network-operator.yaml
            overwrite: true
            contents:
              inline: |
                apiVersion: helm.cattle.io/v1
                kind: HelmChart
                metadata:
                  name: sriov-network-operator
                  namespace: kube-system
                spec:
                  chart: oci://registry.suse.com/edge/charts/sriov-network-operator
                  targetNamespace: sriov-network-operator
                  version: 306.0.4+up1.6.0
                  createNamespace: true
        kernel_arguments:
          should_exist:
            - intel_iommu=on
            - iommu=pt
            - idle=poll
            - mce=off
            - hugepagesz=1G hugepages=40
            - hugepagesz=2M hugepages=0
            - default_hugepagesz=1G
            - irqaffinity=${NON-ISOLATED_CPU_CORES}
            - isolcpus=domain,nohz,managed_irq,${ISOLATED_CPU_CORES}
            - nohz_full=${ISOLATED_CPU_CORES}
            - rcu_nocbs=${ISOLATED_CPU_CORES}
            - rcu_nocb_poll
            - nosoftlockup
            - nowatchdog
            - nohz=on
            - nmi_watchdog=0
            - skew_tick=1
            - quiet
        systemd:
          units:
          - name: rke2-preinstall.service
            enabled: true
            contents: |
              [Unit]
              Description=rke2-preinstall
              Wants=network-online.target
              Before=rke2-install.service
              ConditionPathExists=!/run/cluster-api/bootstrap-success.complete
              [Service]
              Type=oneshot
              User=root
              ExecStartPre=/bin/sh -c "mount -L config-2 /mnt"
              ExecStart=/bin/sh -c "sed -i \"s/BAREMETALHOST_UUID/$(jq -r .uuid /mnt/openstack/latest/meta_data.json)/\" /etc/rancher/rke2/config.yaml"
              ExecStart=/bin/sh -c "echo \"node-name: $(jq -r .name /mnt/openstack/latest/meta_data.json)\" >> /etc/rancher/rke2/config.yaml"
              ExecStart=/bin/sh -c "echo \"node-label:\" >> /etc/rancher/rke2/config.yaml"
              ExecStart=/bin/sh -c "echo \"  - metal3.io/uuid=$(jq -r .uuid /mnt/openstack/latest/meta_data.json)\" >> /etc/rancher/rke2/config.yaml"
              ExecStartPost=/bin/sh -c "umount /mnt"
              [Install]
              WantedBy=multi-user.target
          # rke2-traefik-deployment.service unit to be removed once "traefik" being the default ingress controller (starting with RKE2 v1.36)
          - name: rke2-traefik-deployment.service
            enabled: true
            contents: |
              [Unit]
              Description=rke2-traefik-deployment
              Wants=rke2-preinstall.service
              Before=rke2-install.service
              ConditionPathExists=!/run/cluster-api/bootstrap-success.complete
              [Service]
              Type=oneshot
              User=root
              ExecStart=/bin/sh -c "echo \"ingress-controller: traefik\" >> /etc/rancher/rke2/config.yaml"
              [Install]
              WantedBy=multi-user.target
          - name: cpu-partitioning.service
            enabled: true
            contents: |
              [Unit]
              Description=cpu-partitioning
              Wants=network-online.target
              After=network.target network-online.target
              [Service]
              Type=oneshot
              User=root
              ExecStart=/bin/sh -c "echo isolated_cores=${ISOLATED_CPU_CORES} > /etc/tuned/cpu-partitioning-variables.conf"
              ExecStartPost=/bin/sh -c "tuned-adm profile cpu-partitioning"
              ExecStartPost=/bin/sh -c "systemctl enable tuned.service"
              [Install]
              WantedBy=multi-user.target
          - name: performance-settings.service
            enabled: true
            contents: |
              [Unit]
              Description=performance-settings
              Wants=network-online.target
              After=network.target network-online.target cpu-partitioning.service
              [Service]
              Type=oneshot
              User=root
              ExecStart=/bin/sh -c "/opt/performance-settings/performance-settings.sh"
              [Install]
              WantedBy=multi-user.target
          - name: sriov-custom-auto-vfs.service
            enabled: true
            contents: |
              [Unit]
              Description=SRIOV Custom Auto VF Creation
              Wants=network-online.target  rke2-server.target
              After=network.target network-online.target rke2-server.target
              [Service]
              User=root
              Type=forking
              TimeoutStartSec=900
              ExecStart=/bin/sh -c "while ! /var/lib/rancher/rke2/bin/kubectl --kubeconfig=/etc/rancher/rke2/rke2.yaml wait --for condition=ready nodes --all ; do sleep 2 ; done"
              ExecStartPost=/bin/sh -c "while [ $(/var/lib/rancher/rke2/bin/kubectl --kubeconfig=/etc/rancher/rke2/rke2.yaml get sriovnetworknodestates.sriovnetwork.openshift.io --ignore-not-found --no-headers -A | wc -l) -eq 0 ]; do sleep 1; done"
              ExecStartPost=/bin/sh -c "/opt/sriov/sriov-auto-filler.sh"
              RemainAfterExit=yes
              KillMode=process
              [Install]
              WantedBy=multi-user.target
    kubelet:
      extraArgs:
      - provider-id=metal3://BAREMETALHOST_UUID
    nodeName: "localhost.localdomain"