fkf9/ungleich-k8s
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

import rook manifests

Browse source
This commit is contained in:
Nico Schottelius 2021-06-06 16:42:35 +02:00
parent c011bb42f9
commit 5c25f8ca2c
7 changed files with 9822 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
rook.md
View file

@ -6,8 +6,7 @@ cd rook/cluster/examples/kubernetes/ceph
kubectl apply -f crds.yaml -f common.yaml kubectl apply -f crds.yaml -f common.yaml
kubectl apply -f operator.yaml kubectl apply -f operator.yaml
kubectl get -n rook-ceph pods --watch kubectl get -n rook-ceph pods --watch
kubectl apply -f cluster.yaml kubectl apply -f cluster.yaml
kubectl apply -f csi/cephfs/storageclass.yaml kubectl apply -f csi/rbd/storageclass.yaml
kubectl apply -f toolbox.yaml
``` ```

267
rook/cluster.yaml Normal file
View file

@ -0,0 +1,267 @@
#################################################################################################################
# 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 crds.yaml -f common.yaml -f operator.yaml
# kubectl create -f cluster.yaml
#################################################################################################################
apiVersion: ceph.rook.io/v1
kind: CephCluster
metadata:
name: rook-ceph
namespace: rook-ceph # namespace:cluster
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:v16.2.4-20210514
# This tag might not contain a new Ceph version, just security fixes from the underlying operating system, which will reduce vulnerabilities
image: ceph/ceph:v16.2.4
# 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
# WaitTimeoutForHealthyOSDInMinutes defines the time (in minutes) the operator would wait before an OSD can be stopped for upgrade or restart.
# If the timeout exceeds and OSD is not ok to stop, then the operator would skip upgrade for the current OSD and proceed with the next one
# if `continueUpgradeAfterChecksEvenIfNotHealthy` is `false`. If `continueUpgradeAfterChecksEvenIfNotHealthy` is `true`, then opertor would
# continue with the upgrade of an OSD even if its not ok to stop after the timeout. This timeout won't be applied if `skipUpgradeChecks` is `true`.
# The default wait timeout is 10 minutes.
waitTimeoutForHealthyOSDInMinutes: 10
mon:
# Set the number of mons to be started. Must be an odd number, and is generally recommended to be 3.
count: 3
# The mons should be on unique nodes. For production, at least 3 nodes are recommended for this reason.
# Mons should only be allowed on the same node for test environments where data loss is acceptable.
allowMultiplePerNode: false
mgr:
# When higher availability of the mgr is needed, increase the count to 2.
# In that case, one mgr will be active and one in standby. When Ceph updates which
# mgr is active, Rook will update the mgr services to match the active mgr.
count: 1
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.
- 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: true
# 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
# Provide internet protocol version. IPv6, IPv4 or empty string are valid options. Empty string would mean IPv4
#ipFamily: "IPv6"
# Ceph daemons to listen on both IPv4 and Ipv6 networks
#dualStack: false
# enable the crash collector for ceph daemon crash collection
crashCollector:
disable: false
# Uncomment daysToRetain to prune ceph crash entries older than the
# specified number of days.
#daysToRetain: 30
# enable log collector, daemons will log on files and rotate
# logCollector:
# enabled: true
# periodicity: 24h # SUFFIX may be 'h' for hours or 'd' for days.
# automate [data cleanup process](https://github.com/rook/rook/blob/master/Documentation/ceph-teardown.md#delete-the-data-on-hosts) in cluster destruction.
cleanupPolicy:
# Since cluster cleanup is destructive to data, confirmation is required.
# To destroy all Rook data on hosts during uninstall, confirmation must be set to "yes-really-destroy-data".
# This value should only be set when the cluster is about to be deleted. After the confirmation is set,
# Rook will immediately stop configuring the cluster and only wait for the delete command.
# If the empty string is set, Rook will not destroy any data on hosts during uninstall.
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:
# monitoring is a list of key-value pairs. It is injected into all the monitoring resources created by operator.
# These labels can be passed as LabelSelector to Prometheus
# monitoring:
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 other components
# mon:
# osd:
# prepareosd:
# mgr-sidecar:
# crashcollector:
# logcollector:
# 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:
# crushRoot: "custom-root" # specify a non-default root label for the CRUSH map
# 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
# - 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: true
# 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
# A duration in minutes that the operator will wait for the placement groups to become healthy (active+clean) after a drain was completed and OSDs came back up.
# Operator will continue with the next drain if the timeout exceeds. It only works if `managePodBudgets` is `true`.
# No values or 0 means that the operator will wait until the placement groups are healthy before unblocking the next drain.
pgHealthCheckTimeout: 0
# 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

1151
rook/common.yaml Normal file
View file

File diff suppressed because it is too large Load diff

7758
rook/crds.yaml Normal file
View file

File diff suppressed because it is too large Load diff

515
rook/operator.yaml Normal file
View file

@ -0,0 +1,515 @@
#################################################################################################################
# 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: INFO | DEBUG
ROOK_LOG_LEVEL: "INFO"
# Enable the CSI driver.
# To run the non-default version of the CSI driver, see the override-able image properties in operator.yaml
ROOK_CSI_ENABLE_CEPHFS: "true"
# Enable the default version of the CSI RBD driver. To start another version of the CSI driver, see image properties below.
ROOK_CSI_ENABLE_RBD: "true"
ROOK_CSI_ENABLE_GRPC_METRICS: "false"
# Set to true to enable host networking for CSI CephFS and RBD nodeplugins. This may be necessary
# in some network configurations where the SDN does not provide access to an external cluster or
# there is significant drop in read/write performance.
# CSI_ENABLE_HOST_NETWORK: "true"
# Set logging level for csi containers.
# Supported values from 0 to 5. 0 for general useful logs, 5 for trace level verbosity.
# CSI_LOG_LEVEL: "0"
# OMAP generator will generate the omap mapping between the PV name and the RBD image.
# CSI_ENABLE_OMAP_GENERATOR need to be enabled when we are using rbd mirroring feature.
# By default OMAP generator sidecar is deployed with CSI provisioner pod, to disable
# it set it to false.
# CSI_ENABLE_OMAP_GENERATOR: "false"
# set to false to disable deployment of snapshotter container in CephFS provisioner pod.
CSI_ENABLE_CEPHFS_SNAPSHOTTER: "true"
# set to false to disable deployment of snapshotter container in RBD provisioner pod.
CSI_ENABLE_RBD_SNAPSHOTTER: "true"
# Enable cephfs kernel driver instead of ceph-fuse.
# If you disable the kernel client, your application may be disrupted during upgrade.
# See the upgrade guide: https://rook.io/docs/rook/master/ceph-upgrade.html
# NOTE! cephfs quota is not supported in kernel version < 4.17
CSI_FORCE_CEPHFS_KERNEL_CLIENT: "true"
# (Optional) policy for modifying a volume's ownership or permissions when the RBD PVC is being mounted.
# supported values are documented at https://kubernetes-csi.github.io/docs/support-fsgroup.html
CSI_RBD_FSGROUPPOLICY: "ReadWriteOnceWithFSType"
# (Optional) policy for modifying a volume's ownership or permissions when the CephFS PVC is being mounted.
# supported values are documented at https://kubernetes-csi.github.io/docs/support-fsgroup.html
CSI_CEPHFS_FSGROUPPOLICY: "ReadWriteOnceWithFSType"
# (Optional) Allow starting unsupported ceph-csi image
ROOK_CSI_ALLOW_UNSUPPORTED_VERSION: "false"
# The default version of CSI supported by Rook will be started. To change the version
# of the CSI driver to something other than what is officially supported, change
# these images to the desired release of the CSI driver.
# ROOK_CSI_CEPH_IMAGE: "quay.io/cephcsi/cephcsi:v3.3.1"
# ROOK_CSI_REGISTRAR_IMAGE: "k8s.gcr.io/sig-storage/csi-node-driver-registrar:v2.0.1"
# ROOK_CSI_RESIZER_IMAGE: "k8s.gcr.io/sig-storage/csi-resizer:v1.0.1"
# ROOK_CSI_PROVISIONER_IMAGE: "k8s.gcr.io/sig-storage/csi-provisioner:v2.0.4"
# ROOK_CSI_SNAPSHOTTER_IMAGE: "k8s.gcr.io/sig-storage/csi-snapshotter:v4.0.0"
# ROOK_CSI_ATTACHER_IMAGE: "k8s.gcr.io/sig-storage/csi-attacher:v3.0.2"
# (Optional) set user created priorityclassName for csi plugin pods.
# CSI_PLUGIN_PRIORITY_CLASSNAME: "system-node-critical"
# (Optional) set user created priorityclassName for csi provisioner pods.
# CSI_PROVISIONER_PRIORITY_CLASSNAME: "system-cluster-critical"
# CSI CephFS plugin daemonset update strategy, supported values are OnDelete and RollingUpdate.
# Default value is RollingUpdate.
# CSI_CEPHFS_PLUGIN_UPDATE_STRATEGY: "OnDelete"
# CSI RBD plugin daemonset update strategy, supported values are OnDelete and RollingUpdate.
# Default value is RollingUpdate.
# CSI_RBD_PLUGIN_UPDATE_STRATEGY: "OnDelete"
# kubelet directory path, if kubelet configured to use other than /var/lib/kubelet path.
# ROOK_CSI_KUBELET_DIR_PATH: "/var/lib/kubelet"
# Labels to add to the CSI CephFS Deployments and DaemonSets Pods.
# ROOK_CSI_CEPHFS_POD_LABELS: "key1=value1,key2=value2"
# Labels to add to the CSI RBD Deployments and DaemonSets Pods.
# ROOK_CSI_RBD_POD_LABELS: "key1=value1,key2=value2"
# (Optional) CephCSI provisioner NodeAffinity(applied to both CephFS and RBD provisioner).
# CSI_PROVISIONER_NODE_AFFINITY: "role=storage-node; storage=rook, ceph"
# (Optional) CephCSI provisioner tolerations list(applied to both CephFS and RBD provisioner).
# Put here list of taints you want to tolerate in YAML format.
# CSI provisioner would be best to start on the same nodes as other ceph daemons.
# CSI_PROVISIONER_TOLERATIONS: |
# - effect: NoSchedule
# key: node-role.kubernetes.io/controlplane
# operator: Exists
# - effect: NoExecute
# key: node-role.kubernetes.io/etcd
# operator: Exists
# (Optional) CephCSI plugin NodeAffinity(applied to both CephFS and RBD plugin).
# CSI_PLUGIN_NODE_AFFINITY: "role=storage-node; storage=rook, ceph"
# (Optional) CephCSI plugin tolerations list(applied to both CephFS and RBD plugin).
# Put here list of taints you want to tolerate in YAML format.
# CSI plugins need to be started on all the nodes where the clients need to mount the storage.
# CSI_PLUGIN_TOLERATIONS: |
# - effect: NoSchedule
# key: node-role.kubernetes.io/controlplane
# operator: Exists
# - effect: NoExecute
# key: node-role.kubernetes.io/etcd
# operator: Exists
# (Optional) CephCSI RBD provisioner NodeAffinity(if specified, overrides CSI_PROVISIONER_NODE_AFFINITY).
# CSI_RBD_PROVISIONER_NODE_AFFINITY: "role=rbd-node"
# (Optional) CephCSI RBD provisioner tolerations list(if specified, overrides CSI_PROVISIONER_TOLERATIONS).
# Put here list of taints you want to tolerate in YAML format.
# CSI provisioner would be best to start on the same nodes as other ceph daemons.
# CSI_RBD_PROVISIONER_TOLERATIONS: |
# - key: node.rook.io/rbd
# operator: Exists
# (Optional) CephCSI RBD plugin NodeAffinity(if specified, overrides CSI_PLUGIN_NODE_AFFINITY).
# CSI_RBD_PLUGIN_NODE_AFFINITY: "role=rbd-node"
# (Optional) CephCSI RBD plugin tolerations list(if specified, overrides CSI_PLUGIN_TOLERATIONS).
# Put here list of taints you want to tolerate in YAML format.
# CSI plugins need to be started on all the nodes where the clients need to mount the storage.
# CSI_RBD_PLUGIN_TOLERATIONS: |
# - key: node.rook.io/rbd
# operator: Exists
# (Optional) CephCSI CephFS provisioner NodeAffinity(if specified, overrides CSI_PROVISIONER_NODE_AFFINITY).
# CSI_CEPHFS_PROVISIONER_NODE_AFFINITY: "role=cephfs-node"
# (Optional) CephCSI CephFS provisioner tolerations list(if specified, overrides CSI_PROVISIONER_TOLERATIONS).
# Put here list of taints you want to tolerate in YAML format.
# CSI provisioner would be best to start on the same nodes as other ceph daemons.
# CSI_CEPHFS_PROVISIONER_TOLERATIONS: |
# - key: node.rook.io/cephfs
# operator: Exists
# (Optional) CephCSI CephFS plugin NodeAffinity(if specified, overrides CSI_PLUGIN_NODE_AFFINITY).
# CSI_CEPHFS_PLUGIN_NODE_AFFINITY: "role=cephfs-node"
# (Optional) CephCSI CephFS plugin tolerations list(if specified, overrides CSI_PLUGIN_TOLERATIONS).
# Put here list of taints you want to tolerate in YAML format.
# CSI plugins need to be started on all the nodes where the clients need to mount the storage.
# CSI_CEPHFS_PLUGIN_TOLERATIONS: |
# - key: node.rook.io/cephfs
# operator: Exists
# (Optional) CEPH CSI RBD provisioner resource requirement list, Put here list of resource
# requests and limits you want to apply for provisioner pod
# CSI_RBD_PROVISIONER_RESOURCE: |
# - name : csi-provisioner
# resource:
# requests:
# memory: 128Mi
# cpu: 100m
# limits:
# memory: 256Mi
# cpu: 200m
# - name : csi-resizer
# resource:
# requests:
# memory: 128Mi
# cpu: 100m
# limits:
# memory: 256Mi
# cpu: 200m
# - name : csi-attacher
# resource:
# requests:
# memory: 128Mi
# cpu: 100m
# limits:
# memory: 256Mi
# cpu: 200m
# - name : csi-snapshotter
# resource:
# requests:
# memory: 128Mi
# cpu: 100m
# limits:
# memory: 256Mi
# cpu: 200m
# - name : csi-rbdplugin
# resource:
# requests:
# memory: 512Mi
# cpu: 250m
# limits:
# memory: 1Gi
# cpu: 500m
# - name : liveness-prometheus
# resource:
# requests:
# memory: 128Mi
# cpu: 50m
# limits:
# memory: 256Mi
# cpu: 100m
# (Optional) CEPH CSI RBD plugin resource requirement list, Put here list of resource
# requests and limits you want to apply for plugin pod
# CSI_RBD_PLUGIN_RESOURCE: |
# - name : driver-registrar
# resource:
# requests:
# memory: 128Mi
# cpu: 50m
# limits:
# memory: 256Mi
# cpu: 100m
# - name : csi-rbdplugin
# resource:
# requests:
# memory: 512Mi
# cpu: 250m
# limits:
# memory: 1Gi
# cpu: 500m
# - name : liveness-prometheus
# resource:
# requests:
# memory: 128Mi
# cpu: 50m
# limits:
# memory: 256Mi
# cpu: 100m
# (Optional) CEPH CSI CephFS provisioner resource requirement list, Put here list of resource
# requests and limits you want to apply for provisioner pod
# CSI_CEPHFS_PROVISIONER_RESOURCE: |
# - name : csi-provisioner
# resource:
# requests:
# memory: 128Mi
# cpu: 100m
# limits:
# memory: 256Mi
# cpu: 200m
# - name : csi-resizer
# resource:
# requests:
# memory: 128Mi
# cpu: 100m
# limits:
# memory: 256Mi
# cpu: 200m
# - name : csi-attacher
# resource:
# requests:
# memory: 128Mi
# cpu: 100m
# limits:
# memory: 256Mi
# cpu: 200m
# - name : csi-cephfsplugin
# resource:
# requests:
# memory: 512Mi
# cpu: 250m
# limits:
# memory: 1Gi
# cpu: 500m
# - name : liveness-prometheus
# resource:
# requests:
# memory: 128Mi
# cpu: 50m
# limits:
# memory: 256Mi
# cpu: 100m
# (Optional) CEPH CSI CephFS plugin resource requirement list, Put here list of resource
# requests and limits you want to apply for plugin pod
# CSI_CEPHFS_PLUGIN_RESOURCE: |
# - name : driver-registrar
# resource:
# requests:
# memory: 128Mi
# cpu: 50m
# limits:
# memory: 256Mi
# cpu: 100m
# - name : csi-cephfsplugin
# resource:
# requests:
# memory: 512Mi
# cpu: 250m
# limits:
# memory: 1Gi
# cpu: 500m
# - name : liveness-prometheus
# resource:
# requests:
# memory: 128Mi
# cpu: 50m
# limits:
# memory: 256Mi
# cpu: 100m
# Configure CSI CSI Ceph FS grpc and liveness metrics port
# CSI_CEPHFS_GRPC_METRICS_PORT: "9091"
# CSI_CEPHFS_LIVENESS_METRICS_PORT: "9081"
# Configure CSI RBD grpc and liveness metrics port
# CSI_RBD_GRPC_METRICS_PORT: "9090"
# CSI_RBD_LIVENESS_METRICS_PORT: "9080"
# Whether the OBC provisioner should watch on the operator namespace or not, if not the namespace of the cluster will be used
ROOK_OBC_WATCH_OPERATOR_NAMESPACE: "true"
# Whether to enable the flex driver. By default it is enabled and is fully supported, but will be deprecated in some future release
# in favor of the CSI driver.
ROOK_ENABLE_FLEX_DRIVER: "false"
# 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"
# Enable volume replication controller
CSI_ENABLE_VOLUME_REPLICATION: "false"
# CSI_VOLUME_REPLICATION_IMAGE: "quay.io/csiaddons/volumereplication-operator:v0.1.0"
# (Optional) Admission controller NodeAffinity.
# ADMISSION_CONTROLLER_NODE_AFFINITY: "role=storage-node; storage=rook, ceph"
# (Optional) Admission controller tolerations list. Put here list of taints you want to tolerate in YAML format.
# Admission controller would be best to start on the same nodes as other ceph daemons.
# ADMISSION_CONTROLLER_TOLERATIONS: |
# - effect: NoSchedule
# key: node-role.kubernetes.io/controlplane
# operator: Exists
# - effect: NoExecute
# key: node-role.kubernetes.io/etcd
# operator: Exists
---
# 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
spec:
selector:
matchLabels:
app: rook-ceph-operator
replicas: 1
template:
metadata:
labels:
app: rook-ceph-operator
spec:
serviceAccountName: rook-ceph-system
containers:
- name: rook-ceph-operator
image: rook/ceph:master
args: ["ceph", "operator"]
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"
# Rook Agent toleration. Will tolerate all taints with all keys.
# Choose between NoSchedule, PreferNoSchedule and NoExecute:
# - name: AGENT_TOLERATION
# value: "NoSchedule"
# (Optional) Rook Agent toleration key. Set this to the key of the taint you want to tolerate
# - name: AGENT_TOLERATION_KEY
# value: "<KeyOfTheTaintToTolerate>"
# (Optional) Rook Agent tolerations list. Put here list of taints you want to tolerate in YAML format.
# - name: AGENT_TOLERATIONS
# value: |
# - effect: NoSchedule
# key: node-role.kubernetes.io/controlplane
# operator: Exists
# - effect: NoExecute
# key: node-role.kubernetes.io/etcd
# operator: Exists
# (Optional) Rook Agent priority class name to set on the pod(s)
# - name: AGENT_PRIORITY_CLASS_NAME
# value: "<PriorityClassName>"
# (Optional) Rook Agent NodeAffinity.
# - name: AGENT_NODE_AFFINITY
# value: "role=storage-node; storage=rook,ceph"
# (Optional) Rook Agent mount security mode. Can by `Any` or `Restricted`.
# `Any` uses Ceph admin credentials by default/fallback.
# For using `Restricted` you must have a Ceph secret in each namespace storage should be consumed from and
# set `mountUser` to the Ceph user, `mountSecret` to the Kubernetes secret name.
# to the namespace in which the `mountSecret` Kubernetes secret namespace.
# - name: AGENT_MOUNT_SECURITY_MODE
# value: "Any"
# Set the path where the Rook agent can find the flex volumes
# - name: FLEXVOLUME_DIR_PATH
# value: "<PathToFlexVolumes>"
# Set the path where kernel modules can be found
# - name: LIB_MODULES_DIR_PATH
# value: "<PathToLibModules>"
# Mount any extra directories into the agent container
# - name: AGENT_MOUNTS
# value: "somemount=/host/path:/container/path,someothermount=/host/path2:/container/path2"
# Rook Discover toleration. Will tolerate all taints with all keys.
# Choose between NoSchedule, PreferNoSchedule and NoExecute:
# - name: DISCOVER_TOLERATION
# value: "NoSchedule"
# (Optional) Rook Discover toleration key. Set this to the key of the taint you want to tolerate
# - name: DISCOVER_TOLERATION_KEY
# value: "<KeyOfTheTaintToTolerate>"
# (Optional) Rook Discover tolerations list. Put here list of taints you want to tolerate in YAML format.
# - name: DISCOVER_TOLERATIONS
# value: |
# - effect: NoSchedule
# key: node-role.kubernetes.io/controlplane
# operator: Exists
# - effect: NoExecute
# key: node-role.kubernetes.io/etcd
# operator: Exists
# (Optional) Rook Discover priority class name to set on the pod(s)
# - name: DISCOVER_PRIORITY_CLASS_NAME
# value: "<PriorityClassName>"
# (Optional) Discover Agent NodeAffinity.
# - name: DISCOVER_AGENT_NODE_AFFINITY
# value: "role=storage-node; storage=rook, ceph"
# (Optional) Discover Agent Pod Labels.
# - name: DISCOVER_AGENT_POD_LABELS
# value: "key1=value1,key2=value2"
# The duration between discovering devices in the rook-discover daemonset.
- name: ROOK_DISCOVER_DEVICES_INTERVAL
value: "60m"
# Whether to start pods as privileged that mount a host path, which includes the Ceph mon and osd pods.
# 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"
# In some situations SELinux relabelling breaks (times out) on large filesystems, and doesn't work with cephfs ReadWriteMany volumes (last relabel wins).
# Disable it here if you have similar issues.
# For more details see https://github.com/rook/rook/issues/2417
- name: ROOK_ENABLE_SELINUX_RELABELING
value: "true"
# In large volumes it will take some time to chown all the files. Disable it here if you have performance issues.
# For more details see https://github.com/rook/rook/issues/2254
- name: ROOK_ENABLE_FSGROUP
value: "true"
# Disable automatic orchestration when new devices are discovered
- name: ROOK_DISABLE_DEVICE_HOTPLUG
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
# Uncomment it to run lib bucket provisioner in multithreaded mode
#- name: LIB_BUCKET_PROVISIONER_THREADS
# value: "5"
# Uncomment it to run rook operator on the host network
#hostNetwork: true
volumes:
- name: rook-config
emptyDir: {}
- name: default-config-dir
emptyDir: {}
# OLM: END OPERATOR DEPLOYMENT

74
rook/storageclass.yaml Normal file
View file

@ -0,0 +1,74 @@
apiVersion: ceph.rook.io/v1
kind: CephBlockPool
metadata:
name: replicapool
namespace: rook-ceph
spec:
failureDomain: host
replicated:
size: 3
# Disallow setting pool with replica 1, this could lead to data loss without recovery.
# Make sure you're *ABSOLUTELY CERTAIN* that is what you want
requireSafeReplicaSize: true
# gives a hint (%) to Ceph in terms of expected consumption of the total cluster capacity of a given pool
# for more info: https://docs.ceph.com/docs/master/rados/operations/placement-groups/#specifying-expected-pool-size
#targetSizeRatio: .5
---
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
name: rook-ceph-block
# Change "rook-ceph" provisioner prefix to match the operator namespace if needed
provisioner: rook-ceph.rbd.csi.ceph.com
parameters:
# clusterID is the namespace where the rook cluster is running
# If you change this namespace, also change the namespace below where the secret namespaces are defined
clusterID: rook-ceph # namespace:cluster
# If you want to use erasure coded pool with RBD, you need to create
# two pools. one erasure coded and one replicated.
# You need to specify the replicated pool here in the `pool` parameter, it is
# used for the metadata of the images.
# The erasure coded pool must be set as the `dataPool` parameter below.
#dataPool: ec-data-pool
pool: replicapool
# (optional) mapOptions is a comma-separated list of map options.
# For krbd options refer
# https://docs.ceph.com/docs/master/man/8/rbd/#kernel-rbd-krbd-options
# For nbd options refer
# https://docs.ceph.com/docs/master/man/8/rbd-nbd/#options
# mapOptions: lock_on_read,queue_depth=1024
# (optional) unmapOptions is a comma-separated list of unmap options.
# For krbd options refer
# https://docs.ceph.com/docs/master/man/8/rbd/#kernel-rbd-krbd-options
# For nbd options refer
# https://docs.ceph.com/docs/master/man/8/rbd-nbd/#options
# unmapOptions: force
# RBD image format. Defaults to "2".
imageFormat: "2"
# RBD image features. Available for imageFormat: "2". CSI RBD currently supports only `layering` feature.
imageFeatures: layering
# The secrets contain Ceph admin credentials. These are generated automatically by the operator
# in the same namespace as the cluster.
csi.storage.k8s.io/provisioner-secret-name: rook-csi-rbd-provisioner
csi.storage.k8s.io/provisioner-secret-namespace: rook-ceph # namespace:cluster
csi.storage.k8s.io/controller-expand-secret-name: rook-csi-rbd-provisioner
csi.storage.k8s.io/controller-expand-secret-namespace: rook-ceph # namespace:cluster
csi.storage.k8s.io/node-stage-secret-name: rook-csi-rbd-node
csi.storage.k8s.io/node-stage-secret-namespace: rook-ceph # namespace:cluster
# Specify the filesystem type of the volume. If not specified, csi-provisioner
# will set default as `ext4`. Note that `xfs` is not recommended due to potential deadlock
# in hyperconverged settings where the volume is mounted on the same node as the osds.
csi.storage.k8s.io/fstype: ext4
# uncomment the following to use rbd-nbd as mounter on supported nodes
# **IMPORTANT**: If you are using rbd-nbd as the mounter, during upgrade you will be hit a ceph-csi
# issue that causes the mount to be disconnected. You will need to follow special upgrade steps
# to restart your application pods. Therefore, this option is not recommended.
#mounter: rbd-nbd
allowVolumeExpansion: true
reclaimPolicy: Delete

54
rook/toolbox.yaml Normal file
View file

@ -0,0 +1,54 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: rook-ceph-tools
namespace: rook-ceph # namespace:cluster
labels:
app: rook-ceph-tools
spec:
replicas: 1
selector:
matchLabels:
app: rook-ceph-tools
template:
metadata:
labels:
app: rook-ceph-tools
spec:
dnsPolicy: ClusterFirstWithHostNet
containers:
- name: rook-ceph-tools
image: rook/ceph:master
command: ["/tini"]
args: ["-g", "--", "/usr/local/bin/toolbox.sh"]
imagePullPolicy: IfNotPresent
env:
- name: ROOK_CEPH_USERNAME
valueFrom:
secretKeyRef:
name: rook-ceph-mon
key: ceph-username
- name: ROOK_CEPH_SECRET
valueFrom:
secretKeyRef:
name: rook-ceph-mon
key: ceph-secret
volumeMounts:
- mountPath: /etc/ceph
name: ceph-config
- name: mon-endpoint-volume
mountPath: /etc/rook
volumes:
- name: mon-endpoint-volume
configMap:
name: rook-ceph-mon-endpoints
items:
- key: data
path: mon-endpoints
- name: ceph-config
emptyDir: {}
tolerations:
- key: "node.kubernetes.io/unreachable"
operator: "Exists"
effect: "NoExecute"
tolerationSeconds: 5