typhoon/bare-metal/flatcar-linux/kubernetes/butane/worker.yaml
Dalton Hubble 393a38deff Configure Graceful Node Shutdown and lengthen max inhibitor delay
* Configure Kubelet Graceful Node Shutdown to detect system shutdown
events and stop running containers gracefully when possible
* Allow up to 30s for critical pods to gracefully shutdown
* Allow up to 15s for regular pods to gracefully shutdown
* Node will be marked as NotReady promptly, instead of having to
wait for health checks
* Kubelet uses systemd inhibitor locks to delay shutdown for a limited
number of seconds
* Raise the default max inhibitor time from 5s to 45s

Verify systemd inhibitor locks are present:

```
sudo systemd-inhibit --list
WHO     UID USER PID  COMM    WHAT     WHY                                        MODE
kubelet 0   root 4581 kubelet shutdown Kubelet needs time to handle node shutdown delay
```

Tail journal logs and then shutdown a node via systemctl reboot
or via the cloud console to watch container shutdown

Rel:

* https://kubernetes.io/blog/2021/04/21/graceful-node-shutdown-beta/
* https://kubernetes.io/docs/reference/config-api/kubelet-config.v1beta1/
* https://github.com/kubernetes/kubernetes/issues/107043
* https://github.com/coreos/fedora-coreos-tracker/issues/821
* https://www.freedesktop.org/software/systemd/man/systemd-inhibit.html
* https://github.com/kubernetes/kubernetes/blob/release-1.24/pkg/kubelet/nodeshutdown/nodeshutdown_manager_linux.go
* https://github.com/godbus/dbus/blob/master/conn.go
2022-08-28 10:37:33 -07:00

143 lines
4.8 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
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.25.0
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=${domain_name} \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--node-labels=node.kubernetes.io/node \
%{~ for label in compact(split(",", node_labels)) ~}
--node-labels=${label} \
%{~ endfor ~}
%{~ for taint in compact(split(",", node_taints)) ~}
--register-with-taints=${taint} \
%{~ endfor ~}
--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
storage:
directories:
- path: /etc/kubernetes
mode: 0755
files:
- path: /etc/hostname
mode: 0644
contents:
inline:
${domain_name}
- 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
shutdownGracePeriod: 45s
shutdownGracePeriodCriticalPods: 30s
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
passwd:
users:
- name: core
ssh_authorized_keys:
- ${ssh_authorized_key}