typhoon/digital-ocean/flatcar-linux/kubernetes/butane/worker.yaml
Dalton Hubble 1786e34f33 Revert Graceful Node Shutdown feature
* Disable Kubelet Graceful Node Shutdown on worker nodes (enabled in
Kubernetes v1.25.0 https://github.com/poseidon/typhoon/pull/1222)
* Graceful node shutdown shutdown allows 30s for critical pods to
shutdown and 15s for regular pods to shutdown before releasing the
inhibitor lock to allow the host to shutdown
* Unfortunately, both pods and the node are shutdown at the same
time at the end of the 45s period without further configuration
options. As a result, regular pods and the node are shutdown at the
same time. In practice, enabling this feature leaves Error or Completed
pods in kube-apiserver state until manually cleaned up. This feature
is not ready for general use
* Fix issue where Error/Completed pods are accumulating whenever any
node restarts (or auto-updates), visible in kubectl get pods
* This issue wasn't apparent in initial testing and seems to only
affect non-critical pods (due to critical pods being killed earlier)
But its very apparent on our real clusters

Rel: https://github.com/kubernetes/kubernetes/issues/110755
2022-09-10 14:58:44 -07:00

138 lines
4.9 KiB
YAML

variant: flatcar
version: 1.0.0
systemd:
units:
- name: docker.service
enabled: true
- name: locksmithd.service
mask: true
- name: kubelet.path
enabled: true
contents: |
[Unit]
Description=Watch for kubeconfig
[Path]
PathExists=/etc/kubernetes/kubeconfig
[Install]
WantedBy=multi-user.target
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
- name: kubelet.service
contents: |
[Unit]
Description=Kubelet
Requires=docker.service
After=docker.service
Requires=coreos-metadata.service
After=coreos-metadata.service
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.25.0
EnvironmentFile=/run/metadata/coreos
ExecStartPre=/bin/mkdir -p /etc/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
# Podman, rkt, or runc run container processes, whereas docker run
# is a client to a daemon and requires workarounds to use within a
# systemd unit. https://github.com/moby/moby/issues/6791
ExecStartPre=/usr/bin/docker run -d \
--name kubelet \
--privileged \
--pid host \
--network host \
-v /etc/cni/net.d:/etc/cni/net.d:ro \
-v /etc/kubernetes:/etc/kubernetes:ro \
-v /etc/machine-id:/etc/machine-id:ro \
-v /usr/lib/os-release:/etc/os-release:ro \
-v /lib/modules:/lib/modules:ro \
-v /run:/run \
-v /sys/fs/cgroup:/sys/fs/cgroup \
-v /var/lib/calico:/var/lib/calico:ro \
-v /var/lib/containerd:/var/lib/containerd \
-v /var/lib/kubelet:/var/lib/kubelet:rshared \
-v /var/log:/var/log \
-v /opt/cni/bin:/opt/cni/bin \
$${KUBELET_IMAGE} \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--config=/etc/kubernetes/kubelet.yaml \
--container-runtime-endpoint=unix:///run/containerd/containerd.sock \
--hostname-override=$${COREOS_DIGITALOCEAN_IPV4_PRIVATE_0} \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--node-labels=node.kubernetes.io/node
ExecStart=docker logs -f kubelet
ExecStop=docker stop kubelet
ExecStopPost=docker rm kubelet
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
- name: delete-node.service
enabled: true
contents: |
[Unit]
Description=Delete Kubernetes node on shutdown
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.25.0
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/true
ExecStop=/bin/bash -c '/usr/bin/docker run -v /var/lib/kubelet:/var/lib/kubelet:ro --entrypoint /usr/local/bin/kubectl $${KUBELET_IMAGE} --kubeconfig=/var/lib/kubelet/kubeconfig delete node $HOSTNAME'
[Install]
WantedBy=multi-user.target
storage:
directories:
- path: /etc/kubernetes
mode: 0755
files:
- path: /etc/kubernetes/kubelet.yaml
mode: 0644
contents:
inline: |
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
authentication:
anonymous:
enabled: false
webhook:
enabled: true
x509:
clientCAFile: /etc/kubernetes/ca.crt
authorization:
mode: Webhook
cgroupDriver: systemd
clusterDNS:
- ${cluster_dns_service_ip}
clusterDomain: ${cluster_domain_suffix}
healthzPort: 0
featureGates:
LocalStorageCapacityIsolationFSQuotaMonitoring: false
rotateCertificates: true
staticPodPath: /etc/kubernetes/manifests
readOnlyPort: 0
resolvConf: /run/systemd/resolve/resolv.conf
volumePluginDir: /var/lib/kubelet/volumeplugins
- path: /etc/systemd/logind.conf.d/inhibitors.conf
contents:
inline: |
[Login]
InhibitDelayMaxSec=45s
- path: /etc/sysctl.d/max-user-watches.conf
mode: 0644
contents:
inline: |
fs.inotify.max_user_watches=16184