Fix the kured reboot command

This commit is contained in:
Marco Nenciarini 2022-02-09 11:47:39 +01:00
parent b123845937
commit 573155e5b7
No known key found for this signature in database
GPG Key ID: 589F03F01BA55038
3 changed files with 21 additions and 142 deletions

View File

@ -1,141 +0,0 @@
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: kured
rules:
# Allow kured to read spec.unschedulable
# Allow kubectl to drain/uncordon
#
# NB: These permissions are tightly coupled to the bundled version of kubectl; the ones below
# match https://github.com/kubernetes/kubernetes/blob/v1.19.4/staging/src/k8s.io/kubectl/pkg/cmd/drain/drain.go
#
- apiGroups: [""]
resources: ["nodes"]
verbs: ["get", "patch"]
- apiGroups: [""]
resources: ["pods"]
verbs: ["list","delete","get"]
- apiGroups: ["apps"]
resources: ["daemonsets"]
verbs: ["get"]
- apiGroups: [""]
resources: ["pods/eviction"]
verbs: ["create"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: kured
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: kured
subjects:
- kind: ServiceAccount
name: kured
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
namespace: kube-system
name: kured
rules:
# Allow kured to lock/unlock itself
- apiGroups: ["apps"]
resources: ["daemonsets"]
resourceNames: ["kured"]
verbs: ["update"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
namespace: kube-system
name: kured
subjects:
- kind: ServiceAccount
namespace: kube-system
name: kured
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: kured
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: kured
namespace: kube-system
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kured # Must match `--ds-name`
namespace: kube-system # Must match `--ds-namespace`
spec:
selector:
matchLabels:
name: kured
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
name: kured
spec:
serviceAccountName: kured
tolerations:
- key: node-role.kubernetes.io/master
effect: NoSchedule
hostPID: true # Facilitate entering the host mount namespace via init
restartPolicy: Always
containers:
- name: kured
image: registry.opensuse.org/kubic/kured:1.9.1
# If you find yourself here wondering why there is no
# :latest tag on Docker Hub,see the FAQ in the README
imagePullPolicy: Always
securityContext:
privileged: true # Give permission to nsenter /proc/1/ns/mnt
env:
# Pass in the name of the node on which this pod is scheduled
# for use with drain/uncordon operations and lock acquisition
- name: KURED_NODE_ID
valueFrom:
fieldRef:
fieldPath: spec.nodeName
command:
- /usr/bin/kured
# - --force-reboot=false
# - --drain-grace-period=-1
# - --skip-wait-for-delete-timeout=0
# - --drain-timeout=0
# - --period=1h
# - --ds-namespace=kube-system
# - --ds-name=kured
# - --lock-annotation=weave.works/kured-node-lock
# - --lock-ttl=0
# - --prometheus-url=http://prometheus.monitoring.svc.cluster.local
# - --alert-filter-regexp=^RebootRequired$
# - --alert-firing-only=false
# - --reboot-sentinel=/var/run/reboot-required
# - --prefer-no-schedule-taint=""
# - --reboot-sentinel-command=""
# - --slack-hook-url=https://hooks.slack.com/...
# - --slack-username=prod
# - --slack-channel=alerting
# - --notify-url="" # See also shoutrrr url format
# - --message-template-drain=Draining node %s
# - --message-template-drain=Rebooting node %s
# - --blocking-pod-selector=runtime=long,cost=expensive
# - --blocking-pod-selector=name=temperamental
# - --blocking-pod-selector=...
# - --reboot-days=sun,mon,tue,wed,thu,fri,sat
# - --reboot-delay=90s
# - --start-time=0:00
# - --end-time=23:59:59
# - --time-zone=UTC
# - --annotate-nodes=false
# - --lock-release-delay=30m
# - --log-format=text

20
kured/patch.yaml Normal file
View File

@ -0,0 +1,20 @@
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kured
namespace: kube-system
spec:
selector:
matchLabels:
name: kured
template:
metadata:
labels:
name: kured
spec:
serviceAccountName: kured
containers:
- name: kured
command:
- /usr/bin/kured
- --reboot-command=/usr/bin/systemctl reboot

View File

@ -124,7 +124,7 @@ resource "hcloud_server" "first_control_plane" {
provisioner "local-exec" { provisioner "local-exec" {
command = <<-EOT command = <<-EOT
set -ex set -ex
kubectl -n kube-system apply ${path.module}/config/kured.yaml --kubeconfig ${path.module}/kubeconfig.yaml kubectl -n kube-system apply -k ${dirname(local_file.kured_config.filename)} --kubeconfig ${path.module}/kubeconfig.yaml
EOT EOT
} }