Files
my-rook-config/deploy/examples/operator.yaml
T
Travis Nielsen 45ec32e513 core: declare stable concurrent cluster reconciles
The ROOK_RECONCILE_CONCURRENT_CLUSTERS feature was implemented
in v1.19. This feature has been stable, with no related issues
reported. The feature is tested in the CI with no known
stability issues. Let's declare this feature as stable.

Signed-off-by: Travis Nielsen <tnielsen@redhat.com>
2026-05-01 14:18:35 -06:00

297 lines
12 KiB
YAML

#################################################################################################################
# The deployment for the rook operator
# Contains the common settings for most Kubernetes deployments.
# For example, to create the rook-ceph cluster:
# kubectl create -f crds.yaml -f common.yaml -f operator.yaml
# kubectl create -f cluster.yaml
#
# Also see other operator sample files for variations of operator.yaml:
# - operator-openshift.yaml: Common settings for running in OpenShift
###############################################################################################################
# Rook Ceph Operator Config ConfigMap
# Use this ConfigMap to override Rook-Ceph Operator configurations.
# NOTE! Precedence will be given to this config if the same Env Var config also exists in the
# Operator Deployment.
# To move a configuration(s) from the Operator Deployment to this ConfigMap, add the config
# here. It is recommended to then remove it from the Deployment to eliminate any future confusion.
kind: ConfigMap
apiVersion: v1
metadata:
name: rook-ceph-operator-config
# should be in the namespace of the operator
namespace: rook-ceph # namespace:operator
data:
# The logging level for the operator: ERROR | WARNING | INFO | DEBUG
ROOK_LOG_LEVEL: "INFO"
# The address for the operator's controller-runtime metrics. 0 is disabled. :8080 serves metrics on port 8080.
ROOK_OPERATOR_METRICS_BIND_ADDRESS: "0"
# Allow using loop devices for osds in test clusters.
ROOK_CEPH_ALLOW_LOOP_DEVICES: "false"
# Delete unused generated CRUSH rules after the mgr starts. Disable this if
# you need Rook to leave custom CRUSH rules in place.
ROOK_DELETE_UNUSED_CRUSH_RULES: "true"
# Whether the OBC provisioner should watch on the ceph cluster namespace or not, if not default provisioner value is set
ROOK_OBC_WATCH_OPERATOR_NAMESPACE: "true"
# Custom prefix value for the OBC provisioner instead of ceph cluster namespace, do not set on existing cluster
# ROOK_OBC_PROVISIONER_NAME_PREFIX: "custom-prefix"
# Many OBC additional config fields may be risky for administrators to allow users control over.
# The safe and default-allowed fields are 'maxObjects' and 'maxSize'.
# Other fields should be considered risky. To allow all additional configs, use this value:
# "maxObjects,maxSize,bucketMaxObjects,bucketMaxSize,bucketPolicy,bucketLifecycle,bucketOwner"
# ROOK_OBC_ALLOW_ADDITIONAL_CONFIG_FIELDS: "maxObjects,maxSize" # default allowed configs
# Whether to start the discovery daemon to watch for raw storage devices on nodes in the cluster.
# This daemon does not need to run if you are only going to create your OSDs based on StorageClassDeviceSets with PVCs.
ROOK_ENABLE_DISCOVERY_DAEMON: "false"
# The timeout value (in seconds) of Ceph commands. It should be >= 1. If this variable is not set or is an invalid value, it's default to 15.
ROOK_CEPH_COMMANDS_TIMEOUT_SECONDS: "15"
# Rook Discover toleration. Will tolerate all taints with all keys.
# (Optional) Rook Discover tolerations list. Put here list of taints you want to tolerate in YAML format.
# DISCOVER_TOLERATIONS: |
# - effect: NoSchedule
# key: node-role.kubernetes.io/control-plane
# operator: Exists
# - effect: NoExecute
# key: node-role.kubernetes.io/etcd
# operator: Exists
# (Optional) Rook Discover priority class name to set on the pod(s)
# DISCOVER_PRIORITY_CLASS_NAME: "<PriorityClassName>"
# (Optional) Discover Agent NodeAffinity.
# DISCOVER_AGENT_NODE_AFFINITY: |
# requiredDuringSchedulingIgnoredDuringExecution:
# nodeSelectorTerms:
# - matchExpressions:
# - key: myKey
# operator: DoesNotExist
# (Optional) Discover Agent Pod Labels.
# DISCOVER_AGENT_POD_LABELS: "key1=value1,key2=value2"
# Disable automatic orchestration when new devices are discovered
ROOK_DISABLE_DEVICE_HOTPLUG: "false"
# The duration between discovering devices in the rook-discover daemonset.
ROOK_DISCOVER_DEVICES_INTERVAL: "60m"
# DISCOVER_DAEMON_RESOURCES: |
# - name: DISCOVER_DAEMON_RESOURCES
# resources:
# limits:
# memory: 512Mi
# requests:
# cpu: 100m
# memory: 128Mi
# Whether to create all Rook pods to run on the host network, for example in environments where a CNI is not enabled
ROOK_ENFORCE_HOST_NETWORK: "false"
# RevisionHistoryLimit value for all deployments created by rook.
# ROOK_REVISION_HISTORY_LIMIT: "3"
# Custom label to identify node hostname. If not set `kubernetes.io/hostname` will be used
ROOK_CUSTOM_HOSTNAME_LABEL: ""
---
# CSI operator resources managed by the admin.
# These CRs define the configuration for CSI drivers deployed by the ceph-csi-operator.
# Customize these as needed for your environment.
# ImageSet ConfigMap defines the container images used by the CSI drivers.
apiVersion: v1
kind: ConfigMap
metadata:
name: rook-csi-operator-image-set-configmap
namespace: rook-ceph # namespace:operator
data:
provisioner: "registry.k8s.io/sig-storage/csi-provisioner:v6.1.1"
attacher: "registry.k8s.io/sig-storage/csi-attacher:v4.11.0"
resizer: "registry.k8s.io/sig-storage/csi-resizer:v2.1.0"
snapshotter: "registry.k8s.io/sig-storage/csi-snapshotter:v8.5.0"
registrar: "registry.k8s.io/sig-storage/csi-node-driver-registrar:v2.16.0"
plugin: "quay.io/cephcsi/cephcsi:v3.16.2"
addons: "quay.io/csiaddons/k8s-sidecar:v0.14.0"
---
# OperatorConfig defines the default settings for all CSI drivers.
apiVersion: csi.ceph.io/v1
kind: OperatorConfig
metadata:
name: ceph-csi-operator-config
namespace: rook-ceph # namespace:operator
spec:
driverSpecDefaults:
log:
verbosity: 0
imageSet:
name: rook-csi-operator-image-set-configmap
enableMetadata: true
generateOMapInfo: false
fsGroupPolicy: File
deployCsiAddons: true
cephFsClientType: kernel
nodePlugin:
priorityClassName: "system-node-critical"
kubeletDirPath: /var/lib/kubelet
enableSeLinuxHostMount: false
controllerPlugin:
priorityClassName: "system-cluster-critical"
replicas: 1
deploymentStrategy:
type: Recreate
---
# RBD CSI Driver
apiVersion: csi.ceph.io/v1
kind: Driver
metadata:
name: rook-ceph.rbd.csi.ceph.com # csi-provisioner-name
namespace: rook-ceph # namespace:operator
spec:
fsGroupPolicy: File
nodePlugin:
updateStrategy:
type: RollingUpdate
controllerPlugin: {}
---
# CephFS CSI Driver
apiVersion: csi.ceph.io/v1
kind: Driver
metadata:
name: rook-ceph.cephfs.csi.ceph.com # csi-provisioner-name
namespace: rook-ceph # namespace:operator
spec:
fsGroupPolicy: File
cephFsClientType: kernel
nodePlugin:
updateStrategy:
type: RollingUpdate
controllerPlugin: {}
---
# OLM: BEGIN OPERATOR DEPLOYMENT
apiVersion: apps/v1
kind: Deployment
metadata:
name: rook-ceph-operator
namespace: rook-ceph # namespace:operator
labels:
operator: rook
storage-backend: ceph
app.kubernetes.io/name: rook-ceph
app.kubernetes.io/instance: rook-ceph
app.kubernetes.io/component: rook-ceph-operator
app.kubernetes.io/part-of: rook-ceph-operator
spec:
selector:
matchLabels:
app: rook-ceph-operator
strategy:
type: Recreate
replicas: 1
template:
metadata:
labels:
app: rook-ceph-operator
spec:
tolerations:
- effect: NoExecute
key: node.kubernetes.io/unreachable
operator: Exists
tolerationSeconds: 5
serviceAccountName: rook-ceph-system
containers:
- name: rook-ceph-operator
image: docker.io/rook/ceph:master
args: ["ceph", "operator"]
securityContext:
runAsNonRoot: true
runAsUser: 2016
runAsGroup: 2016
capabilities:
drop: ["ALL"]
volumeMounts:
- mountPath: /var/lib/rook
name: rook-config
- mountPath: /etc/ceph
name: default-config-dir
env:
# If the operator should only watch for cluster CRDs in the same namespace, set this to "true".
# If this is not set to true, the operator will watch for cluster CRDs in all namespaces.
- name: ROOK_CURRENT_NAMESPACE_ONLY
value: "false"
# The default is 1, which means each cluster is reconciled sequentially within the operator.
# When set to a value greater than 1, the operator can reconcile multiple clusters concurrently,
# and all logging will be interleaved in the same operator log.
# Changing this value requires restarting the operator pod.
- name: ROOK_RECONCILE_CONCURRENT_CLUSTERS
value: "1"
# Whether to start pods as privileged that mount a host path, which includes the Ceph mon, osd pods and csi provisioners(if logrotation is on).
# Set this to true if SELinux is enabled (e.g. OpenShift) to workaround the anyuid issues.
# For more details see https://github.com/rook/rook/issues/1314#issuecomment-355799641
- name: ROOK_HOSTPATH_REQUIRES_PRIVILEGED
value: "false"
# Whether to run Ceph mon pods as root (runAsUser: 0) at the pod level.
# Set this to true if mon pods are CrashLooping on SELinux-enabled systems despite other settings.
# For more context, see https://github.com/rook/rook/issues/15564
- name: ROOK_CEPH_MON_RUN_AS_ROOT
value: "false"
# Provide customised regex as the values using comma. For eg. regex for rbd based volume, value will be like "(?i)rbd[0-9]+".
# In case of more than one regex, use comma to separate between them.
# Default regex will be "(?i)dm-[0-9]+,(?i)rbd[0-9]+,(?i)nbd[0-9]+"
# Add regex expression after putting a comma to blacklist a disk
# If value is empty, the default regex will be used.
- name: DISCOVER_DAEMON_UDEV_BLACKLIST
value: "(?i)dm-[0-9]+,(?i)rbd[0-9]+,(?i)nbd[0-9]+"
# Time to wait until the node controller will move Rook pods to other
# nodes after detecting an unreachable node.
# Pods affected by this setting are:
# mgr, rbd, mds, rgw, nfs, PVC based mons and osds, and ceph toolbox
# The value used in this variable replaces the default value of 300 secs
# added automatically by k8s as Toleration for
# <node.kubernetes.io/unreachable>
# The total amount of time to reschedule Rook pods in healthy nodes
# before detecting a <not ready node> condition will be the sum of:
# --> node-monitor-grace-period: 40 seconds (k8s kube-controller-manager flag)
# --> ROOK_UNREACHABLE_NODE_TOLERATION_SECONDS: 5 seconds
- name: ROOK_UNREACHABLE_NODE_TOLERATION_SECONDS
value: "5"
# The name of the node to pass with the downward API
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
# The pod name to pass with the downward API
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
# The pod namespace to pass with the downward API
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
# Recommended resource requests and limits, if desired
#resources:
# limits:
# memory: 512Mi
# requests:
# cpu: 200m
# memory: 128Mi
# Uncomment it to run lib bucket provisioner in multithreaded mode
#- name: LIB_BUCKET_PROVISIONER_THREADS
# value: "5"
# Uncomment these two settings to run the operator on the host network
# hostNetwork: true
# dnsPolicy: ClusterFirstWithHostNet
volumes:
- name: rook-config
emptyDir: {}
- name: default-config-dir
emptyDir: {}
# OLM: END OPERATOR DEPLOYMENT