rook-ceph

#################################################################################################################
# Define the settings for the rook-ceph cluster with common settings for a production cluster.
# All nodes with available raw devices will be used for the Ceph cluster. At least three nodes are required
# in this example. See the documentation for more details on storage settings available.

# For example, to create the cluster:
#   kubectl create -f common.yaml
#   kubectl create -f operator.yaml
#   kubectl create -f cluster.yaml
#################################################################################################################

apiVersion: ceph.rook.io/v1
kind: CephCluster
metadata:
  name: rook-ceph
  namespace: rook-ceph
spec:
  cephVersion:
    # The container image used to launch the Ceph daemon pods (mon, mgr, osd, mds, rgw).
    # v13 is mimic, v14 is nautilus, and v15 is octopus.
    # RECOMMENDATION: In production, use a specific version tag instead of the general v14 flag, which pulls the latest release and could result in different
    # versions running within the cluster. See tags available at https://hub.docker.com/r/ceph/ceph/tags/.
    # If you want to be more precise, you can always use a timestamp tag such ceph/ceph:v15.2.4-20200630
    # This tag might not contain a new Ceph version, just security fixes from the underlying operating system, which will reduce vulnerabilities
    image: ceph/ceph:v15.2.4
    # Whether to allow unsupported versions of Ceph. Currently `nautilus` and `octopus` are supported.
    # Future versions such as `pacific` would require this to be set to `true`.
    # Do not set to true in production.
    allowUnsupported: false
  # The path on the host where configuration files will be persisted. Must be specified.
  # Important: if you reinstall the cluster, make sure you delete this directory from each host or else the mons will fail to start on the new cluster.
  # In Minikube, the '/data' directory is configured to persist across reboots. Use "/data/rook" in Minikube environment.
  dataDirHostPath: /var/lib/rook
  # Whether or not upgrade should continue even if a check fails
  # This means Ceph's status could be degraded and we don't recommend upgrading but you might decide otherwise
  # Use at your OWN risk
  # To understand Rook's upgrade process of Ceph, read https://rook.io/docs/rook/master/ceph-upgrade.html#ceph-version-upgrades
  skipUpgradeChecks: false
  # Whether or not continue if PGs are not clean during an upgrade
  continueUpgradeAfterChecksEvenIfNotHealthy: false
  # set the amount of mons to be started
  mon:
    count: 2
    allowMultiplePerNode: false
  mgr:
    modules:
    # Several modules should not need to be included in this list. The "dashboard" and "monitoring" modules
    # are already enabled by other settings in the cluster CR and the "rook" module is always enabled.
    - name: pg_autoscaler
      enabled: true
  # enable the ceph dashboard for viewing cluster status
  dashboard:
    enabled: true
    # serve the dashboard under a subpath (useful when you are accessing the dashboard via a reverse proxy)
    # urlPrefix: /ceph-dashboard
    # serve the dashboard at the given port.
    # port: 8443
    # serve the dashboard using SSL
    ssl: false
  # enable prometheus alerting for cluster
  monitoring:
    # requires Prometheus to be pre-installed
    enabled: false
    # namespace to deploy prometheusRule in. If empty, namespace of the cluster will be used.
    # Recommended:
    # If you have a single rook-ceph cluster, set the rulesNamespace to the same namespace as the cluster or keep it empty.
    # If you have multiple rook-ceph clusters in the same k8s cluster, choose the same namespace (ideally, namespace with prometheus
    # deployed) to set rulesNamespace for all the clusters. Otherwise, you will get duplicate alerts with multiple alert definitions.
    rulesNamespace: rook-ceph
  network:
    # enable host networking
    #provider: host
    # EXPERIMENTAL: enable the Multus network provider
    #provider: multus
    #selectors:
      # The selector keys are required to be `public` and `cluster`.
      # Based on the configuration, the operator will do the following:
      #   1. if only the `public` selector key is specified both public_network and cluster_network Ceph settings will listen on that interface
      #   2. if both `public` and `cluster` selector keys are specified the first one will point to 'public_network' flag and the second one to 'cluster_network'
      #
      # In order to work, each selector value must match a NetworkAttachmentDefinition object in Multus
      #
      #public: public-conf --> NetworkAttachmentDefinition object name in Multus
      #cluster: cluster-conf --> NetworkAttachmentDefinition object name in Multus
  # enable the crash collector for ceph daemon crash collection
  crashCollector:
    disable: false
  cleanupPolicy:
    # cleanup should only be added to the cluster when the cluster is about to be deleted.
    # After any field of the cleanup policy is set, Rook will stop configuring the cluster as if the cluster is about
    # to be destroyed in order to prevent these settings from being deployed unintentionally.
    # To signify that automatic deletion is desired, use the value "yes-really-destroy-data". Only this and an empty
    # string are valid values for this field.
    confirmation: ""
    # sanitizeDisks represents settings for sanitizing OSD disks on cluster deletion
    sanitizeDisks:
      # method indicates if the entire disk should be sanitized or simply ceph's metadata
      # in both case, re-install is possible
      # possible choices are 'complete' or 'quick' (default)
      method: quick
      # dataSource indicate where to get random bytes from to write on the disk
      # possible choices are 'zero' (default) or 'random'
      # using random sources will consume entropy from the system and will take much more time then the zero source
      dataSource: zero
      # iteration overwrite N times instead of the default (1)
      # takes an integer value
      iteration: 1
    # allowUninstallWithVolumes defines how the uninstall should be performed
    # If set to true, cephCluster deletion does not wait for the PVs to be deleted.
    allowUninstallWithVolumes: false
  # To control where various services will be scheduled by kubernetes, use the placement configuration sections below.
  # The example under 'all' would have all services scheduled on kubernetes nodes labeled with 'role=storage-node' and
  # tolerate taints with a key of 'storage-node'.
#  placement:
#    all:
#      nodeAffinity:
#        requiredDuringSchedulingIgnoredDuringExecution:
#          nodeSelectorTerms:
#          - matchExpressions:
#            - key: role
#              operator: In
#              values:
#              - storage-node
#      podAffinity:
#      podAntiAffinity:
#      topologySpreadConstraints:
#      tolerations:
#      - key: storage-node
#        operator: Exists
# The above placement information can also be specified for mon, osd, and mgr components
#    mon:
# Monitor deployments may contain an anti-affinity rule for avoiding monitor
# collocation on the same node. This is a required rule when host network is used
# or when AllowMultiplePerNode is false. Otherwise this anti-affinity rule is a
# preferred rule with weight: 50.
#    osd:
#    mgr:
#    cleanup:
  annotations:
#    all:
#    mon:
#    osd:
#    cleanup:
#    prepareosd:
# If no mgr annotations are set, prometheus scrape annotations will be set by default.
#    mgr:
  labels:
#    all:
#    mon:
#    osd:
#    cleanup:
#    mgr:
#    prepareosd:
  resources:
# The requests and limits set here, allow the mgr pod to use half of one CPU core and 1 gigabyte of memory
#    mgr:
#      limits:
#        cpu: "500m"
#        memory: "1024Mi"
#      requests:
#        cpu: "500m"
#        memory: "1024Mi"
# The above example requests/limits can also be added to the mon and osd components
#    mon:
#    osd:
#    prepareosd:
#    crashcollector:
#    cleanup:
  # The option to automatically remove OSDs that are out and are safe to destroy.
  removeOSDsIfOutAndSafeToRemove: false
#  priorityClassNames:
#    all: rook-ceph-default-priority-class
#    mon: rook-ceph-mon-priority-class
#    osd: rook-ceph-osd-priority-class
#    mgr: rook-ceph-mgr-priority-class
  storage: # cluster level storage configuration and selection
    useAllNodes: true
    useAllDevices: true
    #deviceFilter:
    config:
      # metadataDevice: "md0" # specify a non-rotational storage so ceph-volume will use it as block db device of bluestore.
      # databaseSizeMB: "1024" # uncomment if the disks are smaller than 100 GB
      # journalSizeMB: "1024"  # uncomment if the disks are 20 GB or smaller
      # osdsPerDevice: "1" # this value can be overridden at the node or device level
      # encryptedDevice: "true" # the default value for this option is "false"
# Individual nodes and their config can be specified as well, but 'useAllNodes' above must be set to false. Then, only the named
# nodes below will be used as storage resources.  Each node's 'name' field should match their 'kubernetes.io/hostname' label.
#    nodes:
#    - name: "172.17.4.201"
#      devices: # specific devices to use for storage can be specified for each node
#      - name: "sdb"
#      - name: "nvme01" # multiple osds can be created on high performance devices
#        config:
#          osdsPerDevice: "5"
#      - name: "/dev/disk/by-id/ata-ST4000DM004-XXXX" # devices can be specified using full udev paths
#      config: # configuration can be specified at the node level which overrides the cluster level config
#        storeType: filestore
#    - name: "172.17.4.301"
#      deviceFilter: "^sd."
  # The section for configuring management of daemon disruptions during upgrade or fencing.
  disruptionManagement:
    # If true, the operator will create and manage PodDisruptionBudgets for OSD, Mon, RGW, and MDS daemons. OSD PDBs are managed dynamically
    # via the strategy outlined in the [design](https://github.com/rook/rook/blob/master/design/ceph/ceph-managed-disruptionbudgets.md). The operator will
    # block eviction of OSDs by default and unblock them safely when drains are detected.
    managePodBudgets: false
    # A duration in minutes that determines how long an entire failureDomain like `region/zone/host` will be held in `noout` (in addition to the
    # default DOWN/OUT interval) when it is draining. This is only relevant when  `managePodBudgets` is `true`. The default value is `30` minutes.
    osdMaintenanceTimeout: 30
    # If true, the operator will create and manage MachineDisruptionBudgets to ensure OSDs are only fenced when the cluster is healthy.
    # Only available on OpenShift.
    manageMachineDisruptionBudgets: false
    # Namespace in which to watch for the MachineDisruptionBudgets.
    machineDisruptionBudgetNamespace: openshift-machine-api

  # healthChecks
  # Valid values for daemons are 'mon', 'osd', 'status'
  healthCheck:
    daemonHealth:
      mon:
        disabled: false
        interval: 45s
      osd:
        disabled: false
        interval: 60s
      status:
        disabled: false
        interval: 60s
    # Change pod liveness probe, it works for all mon,mgr,osd daemons
    livenessProbe:
      mon:
        disabled: false
      mgr:
        disabled: false
      osd:
        disabled: false