release: 1.3.3-rc2

Signed-off-by: David Ko <dko@suse.com>

README.md

@@ -30,10 +30,11 @@ The latest release of Longhorn is [![Releases](https://img.shields.io/github/rel
 
 ## Release Status
 
-| Release | Version | Type           |    
-| --------|---------|----------------|
-| 1.2     | 1.2.4   | Stable         |
-| 1.1     | 1.1.3   | Stable         |
+| Release | Version | Type   |    
+|---------|---------|--------|
+| 1.3     | 1.3.0   | Latest |
+| 1.2     | 1.2.4   | Stable |
+| 1.1     | 1.1.3   | Stable |
 
 ## Get Involved
 

chart/Chart.yaml

@@ -1,8 +1,8 @@
 apiVersion: v1
 name: longhorn
-version: 1.3.0
-appVersion: v1.3.0
-kubeVersion: ">=1.18.0-0"
+version: 1.3.3-rc2
+appVersion: v1.3.3-rc2
+kubeVersion: ">=1.18.0-0 <1.25.0-0"
 description: Longhorn is a distributed block storage system for Kubernetes.
 keywords:
 - longhorn

chart/README.md

@@ -18,7 +18,7 @@ Longhorn is 100% open source software. Project source code is spread across a nu
 ## Prerequisites
 
 1. A container runtime compatible with Kubernetes (Docker v1.13+, containerd v1.3.7+, etc.)
-2. Kubernetes v1.18+
+2. Kubernetes >= v1.18 and <= v1.24
 3. Make sure `bash`, `curl`, `findmnt`, `grep`, `awk` and `blkid` has been installed in all nodes of the Kubernetes cluster.
 4. Make sure `open-iscsi` has been installed, and the `iscsid` daemon is running on all nodes of the Kubernetes cluster. For GKE, recommended Ubuntu as guest OS image since it contains `open-iscsi` already.
 

chart/questions.yaml

@@ -17,7 +17,7 @@ questions:
     label: Longhorn Manager Image Repository
     group: "Longhorn Images Settings"
   - variable: image.longhorn.manager.tag
-    default: v1.3.0
+    default: v1.3.3-rc2
     description: "Specify Longhorn Manager Image Tag"
     type: string
     label: Longhorn Manager Image Tag
@@ -29,7 +29,7 @@ questions:
     label: Longhorn Engine Image Repository
     group: "Longhorn Images Settings"
   - variable: image.longhorn.engine.tag
-    default: v1.3.0
+    default: v1.3.3-rc2
     description: "Specify Longhorn Engine Image Tag"
     type: string
     label: Longhorn Engine Image Tag
@@ -41,7 +41,7 @@ questions:
     label: Longhorn UI Image Repository
     group: "Longhorn Images Settings"
   - variable: image.longhorn.ui.tag
-    default: v1.3.0
+    default: v1.3.3-rc2
     description: "Specify Longhorn UI Image Tag"
     type: string
     label: Longhorn UI Image Tag
@@ -53,7 +53,7 @@ questions:
     label: Longhorn Instance Manager Image Repository
     group: "Longhorn Images Settings"
   - variable: image.longhorn.instanceManager.tag
-    default: v1_20220611
+    default: v1_20230317
     description: "Specify Longhorn Instance Manager Image Tag"
     type: string
     label: Longhorn Instance Manager Image Tag
@@ -65,7 +65,7 @@ questions:
     label: Longhorn Share Manager Image Repository
     group: "Longhorn Images Settings"
   - variable: image.longhorn.shareManager.tag
-    default: v1_20220531
+    default: v1_20230320
     description: "Specify Longhorn Share Manager Image Tag"
     type: string
     label: Longhorn Share Manager Image Tag
@@ -77,7 +77,7 @@ questions:
     label: Longhorn Backing Image Manager Image Repository
     group: "Longhorn Images Settings"
   - variable: image.longhorn.backingImageManager.tag
-    default: v3_20220609
+    default: v3_20230320
     description: "Specify Longhorn Backing Image Manager Image Tag"
     type: string
     label: Longhorn Backing Image Manager Image Tag
@@ -89,7 +89,7 @@ questions:
     label: Longhorn CSI Attacher Image Repository
     group: "Longhorn CSI Driver Images"
   - variable: image.csi.attacher.tag
-    default: v3.2.1
+    default: v3.4.0
     description: "Specify CSI attacher image tag. Leave blank to autodetect."
     type: string
     label: Longhorn CSI Attacher Image Tag
@@ -113,7 +113,7 @@ questions:
     label: Longhorn CSI Node Driver Registrar Image Repository
     group: "Longhorn CSI Driver Images"
   - variable: image.csi.nodeDriverRegistrar.tag
-    default: v2.3.0
+    default: v2.5.0
     description: "Specify CSI Node Driver Registrar image tag. Leave blank to autodetect."
     type: string
     label: Longhorn CSI Node Driver Registrar Image Tag
@@ -142,6 +142,18 @@ questions:
     type: string
     label: Longhorn CSI Driver Snapshotter Image Tag
     group: "Longhorn CSI Driver Images"
+  - variable: image.csi.livenessProbe.repository
+    default: longhornio/livenessprobe
+    description: "Specify CSI liveness probe image repository. Leave blank to autodetect."
+    type: string
+    label: Longhorn CSI Liveness Probe Image Repository
+    group: "Longhorn CSI Liveness Probe Images"
+  - variable: image.csi.livenessProbe.tag
+    default: v2.8.0
+    description: "Specify CSI liveness probe image tag. Leave blank to autodetect."
+    type: string
+    label: Longhorn CSI Liveness Probe Image Tag
+    group: "Longhorn CSI Driver Images"
 - variable: privateRegistry.registryUrl
   label: Private registry URL
   description: "URL of private registry. Leave blank to apply system default registry."
@@ -330,6 +342,16 @@ The available volume spec options are:
     type: int
     min: 0
     default: 300
+  - variable: defaultSettings.failedBackupTTL
+    label: Failed Backup Time to Live
+    description: "In minutes. This setting determines how long Longhorn will keep the backup resource that was failed. Set to 0 to disable the auto-deletion.
+Failed backups will be checked and cleaned up during backupstore polling which is controlled by **Backupstore Poll Interval** setting.
+Hence this value determines the minimal wait interval of the cleanup. And the actual cleanup interval is multiple of **Backupstore Poll Interval**.
+Disabling **Backupstore Poll Interval** also means to disable failed backup auto-deletion."
+    group: "Longhorn Default Settings"
+    type: int
+    min: 0
+    default: 1440
   - variable: defaultSettings.autoSalvage
     label: Automatic salvage
     description: "If enabled, volumes will be automatically salvaged when all the replicas become faulty e.g. due to network disconnection. Longhorn will try to figure out which replica(s) are usable, then use them for the volume. By default true."
@@ -378,6 +400,19 @@ If this setting is enabled, Longhorn will **not** block `kubectl drain` action o
     group: "Longhorn Default Settings"
     type: boolean
     default: "false"
+  - variable: defaultSettings.nodeDrainPolicy
+    label: Node Drain Policy
+    description: "Define the policy to use when a node with the last healthy replica of a volume is drained.
+- **block-if-contains-last-replica** Longhorn will block the drain when the node contains the last healthy replica of a volume.
+- **allow-if-replica-is-stopped** Longhorn will allow the drain when the node contains the last healthy replica of a volume but the replica is stopped. WARNING: possible data loss if the node is removed after draining. Select this option if you want to drain the node and do in-place upgrade/maintenance.
+- **always-allow** Longhorn will allow the drain even though the node contains the last healthy replica of a volume. WARNING: possible data loss if the node is removed after draining. Also possible data corruption if the last replica was running during the draining."
+    group: "Longhorn Default Settings"
+    type: enum
+    options:
+      - "block-if-contains-last-replica"
+      - "allow-if-replica-is-stopped"
+      - "always-allow"
+    default: "block-if-contains-last-replica"
   - variable: defaultSettings.mkfsExt4Parameters
     label: Custom mkfs.ext4 parameters
     description: "Allows setting additional filesystem creation parameters for ext4. For older host kernels it might be necessary to disable the optional ext4 metadata_csum feature by specifying `-O ^64bit,^metadata_csum`."
@@ -670,3 +705,9 @@ WARNING:
   label: Pod Security Policy
   type: boolean
   group: "Other Settings"
+- variable: global.cattle.windowsCluster.enabled
+  default: "false"
+  description: "Enable this to allow Longhorn to run on the Rancher deployed Windows cluster."
+  label: Rancher Windows Cluster
+  type: boolean
+  group: "Other Settings"

chart/templates/crds.yaml

@@ -1055,6 +1055,7 @@ metadata:
     longhorn-manager: ""
   name: engineimages.longhorn.io
 spec:
+  preserveUnknownFields: false
   conversion:
     strategy: Webhook
     webhook:
@@ -1086,7 +1087,7 @@ spec:
       jsonPath: .spec.image
       name: Image
       type: string
-    - description: Number of volumes are using the engine image
+    - description: Number of resources using the engine image
       jsonPath: .status.refCount
       name: RefCount
       type: integer
@@ -1128,7 +1129,7 @@ spec:
       jsonPath: .spec.image
       name: Image
       type: string
-    - description: Number of volumes are using the engine image
+    - description: Number of resources using the engine image
       jsonPath: .status.refCount
       name: RefCount
       type: integer
@@ -1411,6 +1412,30 @@ spec:
                   type: object
                 nullable: true
                 type: object
+              conditions:
+                items:
+                  properties:
+                    lastProbeTime:
+                      description: Last time we probed the condition.
+                      type: string
+                    lastTransitionTime:
+                      description: Last time the condition transitioned from one status to another.
+                      type: string
+                    message:
+                      description: Human-readable message indicating details about last transition.
+                      type: string
+                    reason:
+                      description: Unique, one-word, CamelCase reason for the condition's last transition.
+                      type: string
+                    status:
+                      description: Status is the status of the condition. Can be True, False, Unknown.
+                      type: string
+                    type:
+                      description: Type is the type of the condition.
+                      type: string
+                  type: object
+                nullable: true
+                type: array
               currentImage:
                 type: string
               currentReplicaAddressMap:
@@ -1725,6 +1750,7 @@ metadata:
     longhorn-manager: ""
   name: nodes.longhorn.io
 spec:
+  preserveUnknownFields: false
   conversion:
     strategy: Webhook
     webhook:
@@ -2115,7 +2141,7 @@ spec:
       jsonPath: .spec.groups
       name: Groups
       type: string
-    - description: Should be one of "backup" or "snapshot"
+    - description: Should be one of "snapshot", "snapshot-force-create", "snapshot-cleanup", "snapshot-delete", "backup" or "backup-force-create"
       jsonPath: .spec.task
       name: Task
       type: string
@@ -2177,10 +2203,14 @@ spec:
                 description: The retain count of the snapshot/backup.
                 type: integer
               task:
-                description: The recurring job type. Can be "snapshot" or "backup".
+                description: The recurring job task. Can be "snapshot", "snapshot-force-create", "snapshot-cleanup", "snapshot-delete", "backup" or "backup-force-create".
                 enum:
                 - snapshot
+                - snapshot-force-create
+                - snapshot-cleanup
+                - snapshot-delete
                 - backup
+                - backup-force-create
                 type: string
             type: object
           status:
@@ -2355,6 +2385,30 @@ spec:
           status:
             description: ReplicaStatus defines the observed state of the Longhorn replica
             properties:
+              conditions:
+                items:
+                  properties:
+                    lastProbeTime:
+                      description: Last time we probed the condition.
+                      type: string
+                    lastTransitionTime:
+                      description: Last time the condition transitioned from one status to another.
+                      type: string
+                    message:
+                      description: Human-readable message indicating details about last transition.
+                      type: string
+                    reason:
+                      description: Unique, one-word, CamelCase reason for the condition's last transition.
+                      type: string
+                    status:
+                      description: Status is the status of the condition. Can be True, False, Unknown.
+                      type: string
+                    type:
+                      description: Type is the type of the condition.
+                      type: string
+                  type: object
+                nullable: true
+                type: array
               currentImage:
                 type: string
               currentState:
@@ -2714,6 +2768,7 @@ metadata:
     longhorn-manager: ""
   name: volumes.longhorn.io
 spec:
+  preserveUnknownFields: false
   conversion:
     strategy: Webhook
     webhook:
@@ -2897,7 +2952,11 @@ spec:
                     task:
                       enum:
                       - snapshot
+                      - snapshot-force-create
+                      - snapshot-cleanup
+                      - snapshot-delete
                       - backup
+                      - backup-force-create
                       type: string
                   type: object
                 type: array

chart/templates/daemonset-sa.yaml

@@ -31,6 +31,9 @@ spec:
         command:
         - longhorn-manager
         - -d
+        {{- if eq .Values.longhornManager.log.format "json" }}
+        - -j
+        {{- end }}
         - daemon
         - --engine-image
         - "{{ template "registry_url" . }}{{ .Values.image.longhorn.engine.repository }}:{{ .Values.image.longhorn.engine.tag }}"
@@ -92,15 +95,25 @@ spec:
       - name: {{ .Values.privateRegistry.registrySecret }}
       {{- end }}
       {{- if .Values.longhornManager.priorityClass }}
-      priorityClassName: {{ .Values.longhornManager.priorityClass | quote}}
+      priorityClassName: {{ .Values.longhornManager.priorityClass | quote }}
       {{- end }}
-      {{- if .Values.longhornManager.tolerations }}
+      {{- if or .Values.longhornManager.tolerations .Values.global.cattle.windowsCluster.enabled }}
       tolerations:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.tolerations }}
+{{ toYaml .Values.global.cattle.windowsCluster.tolerations | indent 6 }}
+        {{- end }}
+        {{- if .Values.longhornManager.tolerations }}
 {{ toYaml .Values.longhornManager.tolerations | indent 6 }}
+        {{- end }}
       {{- end }}
-      {{- if .Values.longhornManager.nodeSelector }}
+      {{- if or .Values.longhornManager.nodeSelector .Values.global.cattle.windowsCluster.enabled }}
       nodeSelector:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.nodeSelector }}
+{{ toYaml .Values.global.cattle.windowsCluster.nodeSelector | indent 8 }}
+        {{- end }}
+        {{- if .Values.longhornManager.nodeSelector }}
 {{ toYaml .Values.longhornManager.nodeSelector | indent 8 }}
+        {{- end }}
       {{- end }}
       serviceAccountName: longhorn-service-account
   updateStrategy:
@@ -114,6 +127,10 @@ metadata:
     app: longhorn-manager
   name: longhorn-backend
   namespace: {{ include "release_namespace" . }}
+  {{- if .Values.longhornManager.serviceAnnotations }}
+  annotations:
+{{ toYaml .Values.longhornManager.serviceAnnotations | indent 4 }}
+  {{- end }}
 spec:
   type: {{ .Values.service.manager.type }}
   sessionAffinity: ClientIP

chart/templates/default-setting.yaml

@@ -20,8 +20,27 @@ data:
     {{ if not (kindIs "invalid" .Values.defaultSettings.defaultDataLocality) }}default-data-locality: {{ .Values.defaultSettings.defaultDataLocality }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.defaultLonghornStaticStorageClass) }}default-longhorn-static-storage-class: {{ .Values.defaultSettings.defaultLonghornStaticStorageClass }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.backupstorePollInterval) }}backupstore-poll-interval: {{ .Values.defaultSettings.backupstorePollInterval }}{{ end }}
-    {{ if not (kindIs "invalid" .Values.defaultSettings.taintToleration) }}taint-toleration: {{ .Values.defaultSettings.taintToleration }}{{ end }}
-    {{ if not (kindIs "invalid" .Values.defaultSettings.systemManagedComponentsNodeSelector) }}system-managed-components-node-selector: {{ .Values.defaultSettings.systemManagedComponentsNodeSelector }}{{ end }}
+    {{ if not (kindIs "invalid" .Values.defaultSettings.failedBackupTTL) }}failed-backup-ttl: {{ .Values.defaultSettings.failedBackupTTL }}{{ end }}
+    {{- if or (not (kindIs "invalid" .Values.defaultSettings.taintToleration)) (.Values.global.cattle.windowsCluster.enabled) }}
+    taint-toleration: {{ $windowsDefaultSettingTaintToleration := list }}{{ $defaultSettingTaintToleration := list -}}
+      {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.defaultSetting.taintToleration -}}
+        {{- $windowsDefaultSettingTaintToleration = .Values.global.cattle.windowsCluster.defaultSetting.taintToleration -}}
+      {{- end -}}
+      {{- if not (kindIs "invalid" .Values.defaultSettings.taintToleration) -}}
+        {{- $defaultSettingTaintToleration = .Values.defaultSettings.taintToleration -}}
+      {{- end -}}
+      {{- $taintToleration := list $windowsDefaultSettingTaintToleration $defaultSettingTaintToleration }}{{ join ";" (compact $taintToleration) -}}
+    {{- end }}
+    {{- if or (not (kindIs "invalid" .Values.defaultSettings.systemManagedComponentsNodeSelector)) (.Values.global.cattle.windowsCluster.enabled) }}
+    system-managed-components-node-selector: {{ $windowsDefaultSettingNodeSelector := list }}{{ $defaultSettingNodeSelector := list -}}
+      {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.defaultSetting.systemManagedComponentsNodeSelector -}}
+        {{ $windowsDefaultSettingNodeSelector = .Values.global.cattle.windowsCluster.defaultSetting.systemManagedComponentsNodeSelector -}}
+      {{- end -}}
+      {{- if not (kindIs "invalid" .Values.defaultSettings.systemManagedComponentsNodeSelector) -}}
+        {{- $defaultSettingNodeSelector = .Values.defaultSettings.systemManagedComponentsNodeSelector -}}
+      {{- end -}}
+      {{- $nodeSelector := list $windowsDefaultSettingNodeSelector $defaultSettingNodeSelector }}{{ join ";" (compact $nodeSelector) -}}
+    {{- end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.priorityClass) }}priority-class: {{ .Values.defaultSettings.priorityClass }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.autoSalvage) }}auto-salvage: {{ .Values.defaultSettings.autoSalvage }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.autoDeletePodWhenVolumeDetachedUnexpectedly) }}auto-delete-pod-when-volume-detached-unexpectedly: {{ .Values.defaultSettings.autoDeletePodWhenVolumeDetachedUnexpectedly }}{{ end }}
@@ -29,6 +48,7 @@ data:
     {{ if not (kindIs "invalid" .Values.defaultSettings.replicaZoneSoftAntiAffinity) }}replica-zone-soft-anti-affinity: {{ .Values.defaultSettings.replicaZoneSoftAntiAffinity }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.nodeDownPodDeletionPolicy) }}node-down-pod-deletion-policy: {{ .Values.defaultSettings.nodeDownPodDeletionPolicy }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.allowNodeDrainWithLastHealthyReplica) }}allow-node-drain-with-last-healthy-replica: {{ .Values.defaultSettings.allowNodeDrainWithLastHealthyReplica }}{{ end }}
+    {{ if not (kindIs "invalid" .Values.defaultSettings.nodeDrainPolicy) }}node-drain-policy: {{ .Values.defaultSettings.nodeDrainPolicy }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.mkfsExt4Parameters) }}mkfs-ext4-parameters: {{ .Values.defaultSettings.mkfsExt4Parameters }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.disableReplicaRebuild) }}disable-replica-rebuild: {{ .Values.defaultSettings.disableReplicaRebuild }}{{ end }}
     {{ if not (kindIs "invalid" .Values.defaultSettings.replicaReplenishmentWaitInterval) }}replica-replenishment-wait-interval: {{ .Values.defaultSettings.replicaReplenishmentWaitInterval }}{{ end }}

chart/templates/deployment-driver.yaml

@@ -67,6 +67,10 @@ spec:
           - name: CSI_SNAPSHOTTER_IMAGE
             value: "{{ template "registry_url" . }}{{ .Values.image.csi.snapshotter.repository }}:{{ .Values.image.csi.snapshotter.tag }}"
           {{- end }}
+          {{- if and .Values.image.csi.livenessProbe.repository .Values.image.csi.livenessProbe.tag }}
+          - name: CSI_LIVENESS_PROBE_IMAGE
+            value: "{{ template "registry_url" . }}{{ .Values.image.csi.livenessProbe.repository }}:{{ .Values.image.csi.livenessProbe.tag }}"
+          {{- end }}
           {{- if .Values.csi.attacherReplicaCount }}
           - name: CSI_ATTACHER_REPLICA_COUNT
             value: {{ .Values.csi.attacherReplicaCount | quote }}
@@ -89,15 +93,25 @@ spec:
       - name: {{ .Values.privateRegistry.registrySecret }}
       {{- end }}
       {{- if .Values.longhornDriver.priorityClass }}
-      priorityClassName: {{ .Values.longhornDriver.priorityClass | quote}}
+      priorityClassName: {{ .Values.longhornDriver.priorityClass | quote }}
       {{- end }}
-      {{- if .Values.longhornDriver.tolerations }}
+      {{- if or .Values.longhornDriver.tolerations .Values.global.cattle.windowsCluster.enabled }}
       tolerations:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.tolerations }}
+{{ toYaml .Values.global.cattle.windowsCluster.tolerations | indent 6 }}
+        {{- end }}
+        {{- if .Values.longhornDriver.tolerations }}
 {{ toYaml .Values.longhornDriver.tolerations | indent 6 }}
+        {{- end }}
       {{- end }}
-      {{- if .Values.longhornDriver.nodeSelector }}
+      {{- if or .Values.longhornDriver.nodeSelector .Values.global.cattle.windowsCluster.enabled }}
       nodeSelector:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.nodeSelector }}
+{{ toYaml .Values.global.cattle.windowsCluster.nodeSelector | indent 8 }}
+        {{- end }}
+        {{- if .Values.longhornDriver.nodeSelector }}
 {{ toYaml .Values.longhornDriver.nodeSelector | indent 8 }}
+        {{- end }}
       {{- end }}
       serviceAccountName: longhorn-service-account
       securityContext:

chart/templates/deployment-ui.yaml

@@ -6,7 +6,7 @@ metadata:
   name: longhorn-ui
   namespace: {{ include "release_namespace" . }}
 spec:
-  replicas: 1
+  replicas: {{ .Values.longhornUI.replicas }}
   selector:
     matchLabels:
       app: longhorn-ui
@@ -15,6 +15,18 @@ spec:
       labels: {{- include "longhorn.labels" . | nindent 8 }}
         app: longhorn-ui
     spec:
+      affinity:
+        podAntiAffinity:
+          preferredDuringSchedulingIgnoredDuringExecution:
+          - weight: 1
+            podAffinityTerm:
+              labelSelector:
+                matchExpressions:
+                - key: app
+                  operator: In
+                  values:
+                  - longhorn-ui
+              topologyKey: kubernetes.io/hostname
       containers:
       - name: longhorn-ui
         image: {{ template "registry_url" . }}{{ .Values.image.longhorn.ui.repository }}:{{ .Values.image.longhorn.ui.tag }}
@@ -46,15 +58,25 @@ spec:
       - name: {{ .Values.privateRegistry.registrySecret }}
       {{- end }}
       {{- if .Values.longhornUI.priorityClass }}
-      priorityClassName: {{ .Values.longhornUI.priorityClass | quote}}
+      priorityClassName: {{ .Values.longhornUI.priorityClass | quote }}
       {{- end }}
-      {{- if .Values.longhornUI.tolerations }}
+      {{- if or .Values.longhornUI.tolerations .Values.global.cattle.windowsCluster.enabled }}
       tolerations:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.tolerations }}
+{{ toYaml .Values.global.cattle.windowsCluster.tolerations | indent 6 }}
+        {{- end }}
+        {{- if .Values.longhornUI.tolerations }}
 {{ toYaml .Values.longhornUI.tolerations | indent 6 }}
+        {{- end }}
       {{- end }}
-      {{- if .Values.longhornUI.nodeSelector }}
+      {{- if or .Values.longhornUI.nodeSelector .Values.global.cattle.windowsCluster.enabled }}
       nodeSelector:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.nodeSelector }}
+{{ toYaml .Values.global.cattle.windowsCluster.nodeSelector | indent 8 }}
+        {{- end }}
+        {{- if .Values.longhornUI.nodeSelector }}
 {{ toYaml .Values.longhornUI.nodeSelector | indent 8 }}
+        {{- end }}
       {{- end }}
 ---
 kind: Service

chart/templates/deployment-webhook.yaml

@@ -54,15 +54,25 @@ spec:
       - name: {{ .Values.privateRegistry.registrySecret }}
       {{- end }}
       {{- if .Values.longhornDriver.priorityClass }}
-      priorityClassName: {{ .Values.longhornDriver.priorityClass | quote}}
+      priorityClassName: {{ .Values.longhornDriver.priorityClass | quote }}
       {{- end }}
-      {{- if .Values.longhornDriver.tolerations }}
+      {{- if or .Values.longhornDriver.tolerations .Values.global.cattle.windowsCluster.enabled }}
       tolerations:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.tolerations }}
+{{ toYaml .Values.global.cattle.windowsCluster.tolerations | indent 6 }}
+        {{- end }}
+        {{- if .Values.longhornDriver.tolerations }}
 {{ toYaml .Values.longhornDriver.tolerations | indent 6 }}
+        {{- end }}
       {{- end }}
-      {{- if .Values.longhornDriver.nodeSelector }}
+      {{- if or .Values.longhornDriver.nodeSelector .Values.global.cattle.windowsCluster.enabled }}
       nodeSelector:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.nodeSelector }}
+{{ toYaml .Values.global.cattle.windowsCluster.nodeSelector | indent 8 }}
+        {{- end }}
+        {{- if .Values.longhornDriver.nodeSelector }}
 {{ toYaml .Values.longhornDriver.nodeSelector | indent 8 }}
+        {{- end }}
       {{- end }}
       serviceAccountName: longhorn-service-account
 ---
@@ -133,14 +143,24 @@ spec:
       - name: {{ .Values.privateRegistry.registrySecret }}
       {{- end }}
       {{- if .Values.longhornDriver.priorityClass }}
-      priorityClassName: {{ .Values.longhornDriver.priorityClass | quote}}
+      priorityClassName: {{ .Values.longhornDriver.priorityClass | quote }}
       {{- end }}
-      {{- if .Values.longhornDriver.tolerations }}
+      {{- if or .Values.longhornDriver.tolerations .Values.global.cattle.windowsCluster.enabled }}
       tolerations:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.tolerations }}
+{{ toYaml .Values.global.cattle.windowsCluster.tolerations | indent 6 }}
+        {{- end }}
+        {{- if .Values.longhornDriver.tolerations }}
 {{ toYaml .Values.longhornDriver.tolerations | indent 6 }}
+        {{- end }}
       {{- end }}
-      {{- if .Values.longhornDriver.nodeSelector }}
+      {{- if or .Values.longhornDriver.nodeSelector .Values.global.cattle.windowsCluster.enabled }}
       nodeSelector:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.nodeSelector }}
+{{ toYaml .Values.global.cattle.windowsCluster.nodeSelector | indent 8 }}
+        {{- end }}
+        {{- if or .Values.longhornDriver.nodeSelector }}
 {{ toYaml .Values.longhornDriver.nodeSelector | indent 8 }}
+        {{- end }}
       {{- end }}
       serviceAccountName: longhorn-service-account

chart/templates/ingress.yaml

@@ -11,7 +11,7 @@ metadata:
   labels: {{- include "longhorn.labels" . | nindent 4 }}
     app: longhorn-ingress
   annotations:
-    {{- if .Values.ingress.tls }}
+    {{- if .Values.ingress.secureBackends }}
     ingress.kubernetes.io/secure-backends: "true"
     {{- end }}
     {{- range $key, $value := .Values.ingress.annotations }}

chart/templates/postupgrade-job.yaml

@@ -35,14 +35,24 @@ spec:
       - name: {{ .Values.privateRegistry.registrySecret }}
       {{- end }}
       {{- if .Values.longhornManager.priorityClass }}
-      priorityClassName: {{ .Values.longhornManager.priorityClass | quote}}
+      priorityClassName: {{ .Values.longhornManager.priorityClass | quote }}
       {{- end }}
       serviceAccountName: longhorn-service-account
-      {{- if .Values.longhornManager.tolerations }}
+      {{- if or .Values.longhornManager.tolerations .Values.global.cattle.windowsCluster.enabled }}
       tolerations:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.tolerations }}
+{{ toYaml .Values.global.cattle.windowsCluster.tolerations | indent 6 }}
+        {{- end }}
+        {{- if .Values.longhornManager.tolerations }}
 {{ toYaml .Values.longhornManager.tolerations | indent 6 }}
+        {{- end }}
       {{- end }}
-      {{- if .Values.longhornManager.nodeSelector }}
+      {{- if or .Values.longhornManager.nodeSelector .Values.global.cattle.windowsCluster.enabled }}
       nodeSelector:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.nodeSelector }}
+{{ toYaml .Values.global.cattle.windowsCluster.nodeSelector | indent 8 }}
+        {{- end }}
+        {{- if .Values.longhornManager.nodeSelector }}
 {{ toYaml .Values.longhornManager.nodeSelector | indent 8 }}
+        {{- end }}
       {{- end }}

chart/templates/storageclass.yaml

@@ -21,10 +21,10 @@ data:
       staleReplicaTimeout: "30"
       fromBackup: ""
       {{- if .Values.persistence.defaultFsType }}
-      fsType: "{{.Values.persistence.defaultFsType}}"
+      fsType: "{{ .Values.persistence.defaultFsType }}"
       {{- end }}
       {{- if .Values.persistence.migratable }}
-      migratable: "{{.Values.persistence.migratable}}"
+      migratable: "{{ .Values.persistence.migratable }}"
       {{- end }}    
       {{- if .Values.persistence.backingImage.enable }}
       backingImage: {{ .Values.persistence.backingImage.name }}

chart/templates/uninstall-job.yaml

@@ -36,14 +36,24 @@ spec:
       - name: {{ .Values.privateRegistry.registrySecret }}
       {{- end }}
       {{- if .Values.longhornManager.priorityClass }}
-      priorityClassName: {{ .Values.longhornManager.priorityClass | quote}}
+      priorityClassName: {{ .Values.longhornManager.priorityClass | quote }}
       {{- end }}
       serviceAccountName: longhorn-service-account
-      {{- if .Values.longhornManager.tolerations }}
+      {{- if or .Values.longhornManager.tolerations .Values.global.cattle.windowsCluster.enabled }}
       tolerations:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.tolerations }}
+{{ toYaml .Values.global.cattle.windowsCluster.tolerations | indent 6 }}
+        {{- end }}
+        {{- if .Values.longhornManager.tolerations }}
 {{ toYaml .Values.longhornManager.tolerations | indent 6 }}
+        {{- end }}
       {{- end }}
-      {{- if .Values.longhornManager.nodeSelector }}
+      {{- if or .Values.longhornManager.nodeSelector .Values.global.cattle.windowsCluster.enabled }}
       nodeSelector:
+        {{- if and .Values.global.cattle.windowsCluster.enabled .Values.global.cattle.windowsCluster.nodeSelector }}
+{{ toYaml .Values.global.cattle.windowsCluster.nodeSelector | indent 8 }}
+        {{- end }}
+        {{- if or .Values.longhornManager.nodeSelector }}
 {{ toYaml .Values.longhornManager.nodeSelector | indent 8 }}
+        {{- end }}
       {{- end }}

chart/values.yaml

@@ -4,27 +4,43 @@
 global:
   cattle:
     systemDefaultRegistry: ""
+    windowsCluster:
+      # Enable this to allow Longhorn to run on the Rancher deployed Windows cluster
+      enabled: false
+      # Tolerate Linux node taint
+      tolerations:
+      - key: "cattle.io/os"
+        value: "linux"
+        effect: "NoSchedule"
+        operator: "Equal"
+      # Select Linux nodes
+      nodeSelector:
+        kubernetes.io/os: "linux"
+      # Recognize toleration and node selector for Longhorn run-time created components
+      defaultSetting:
+        taintToleration: cattle.io/os=linux:NoSchedule
+        systemManagedComponentsNodeSelector: kubernetes.io/os:linux
 
 image:
   longhorn:
     engine:
       repository: longhornio/longhorn-engine
-      tag: v1.3.0
+      tag: v1.3.3-rc2
     manager:
       repository: longhornio/longhorn-manager
-      tag: v1.3.0
+      tag: v1.3.3-rc2
     ui:
       repository: longhornio/longhorn-ui
-      tag: v1.3.0
+      tag: v1.3.3-rc2
     instanceManager:
       repository: longhornio/longhorn-instance-manager
-      tag: v1_20220611
+      tag: v1_20230317
     shareManager:
       repository: longhornio/longhorn-share-manager
-      tag: v1_20220531
+      tag: v1_20230320
     backingImageManager:
       repository: longhornio/backing-image-manager
-      tag: v3_20220609
+      tag: v3_20230320
   csi:
     attacher:
       repository: longhornio/csi-attacher
@@ -41,6 +57,9 @@ image:
     snapshotter:
       repository: longhornio/csi-snapshotter
       tag: v3.0.3
+    livenessProbe:
+      repository: longhornio/livenessprobe
+      tag: v2.8.0
   pullPolicy: IfNotPresent
 
 service:
@@ -92,6 +111,7 @@ defaultSettings:
   defaultReplicaCount: ~
   defaultLonghornStaticStorageClass: ~
   backupstorePollInterval: ~
+  failedBackupTTL: ~
   taintToleration: ~
   systemManagedComponentsNodeSelector: ~
   priorityClass: ~
@@ -101,6 +121,7 @@ defaultSettings:
   replicaZoneSoftAntiAffinity: ~
   nodeDownPodDeletionPolicy: ~
   allowNodeDrainWithLastHealthyReplica: ~
+  nodeDrainPolicy : ~
   mkfsExt4Parameters: ~
   disableReplicaRebuild: ~
   replicaReplenishmentWaitInterval: ~
@@ -125,6 +146,9 @@ privateRegistry:
   registrySecret: ~
 
 longhornManager:
+  log:
+    ## Allowed values are `plain` or `json`.
+    format: plain
   priorityClass: ~
   tolerations: []
   ## If you want to set tolerations for Longhorn Manager DaemonSet, delete the `[]` in the line above
@@ -138,6 +162,11 @@ longhornManager:
   ## and uncomment this example block
   #  label-key1: "label-value1"
   #  label-key2: "label-value2"
+  serviceAnnotations: {}
+  ## If you want to set annotations for the Longhorn Manager service, delete the `{}` in the line above
+  ## and uncomment this example block
+  #  annotation-key1: "annotation-value1"
+  #  annotation-key2: "annotation-value2"
 
 longhornDriver:
   priorityClass: ~
@@ -155,6 +184,7 @@ longhornDriver:
   #  label-key2: "label-value2"
 
 longhornUI:
+  replicas: 2
   priorityClass: ~
   tolerations: []
   ## If you want to set tolerations for Longhorn UI Deployment, delete the `[]` in the line above
@@ -169,19 +199,6 @@ longhornUI:
   #  label-key1: "label-value1"
   #  label-key2: "label-value2"
 
-resources: {}
-  # We usually recommend not to specify default resources and to leave this as a conscious
-  # choice for the user. This also increases chances charts run on environments with little
-  # resources, such as Minikube. If you do want to specify resources, uncomment the following
-  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
-  # limits:
-  #  cpu: 100m
-  #  memory: 128Mi
-  # requests:
-  #  cpu: 100m
-  #  memory: 128Mi
-  #
-
 ingress:
   ## Set to true to enable ingress record generation
   enabled: false
@@ -193,9 +210,11 @@ ingress:
   host: sslip.io
 
   ## Set this to true in order to enable TLS on the ingress record
-  ## A side effect of this will be that the backend service will be connected at port 443
   tls: false
 
+  ## Enable this in order to enable that the backend service will be connected at port 443
+  secureBackends: false
+
   ## If TLS is set to true, you must declare what secret will store the key/certificate for TLS
   tlsSecret: longhorn.local-tls
 

deploy/longhorn-images.txt

@@ -3,9 +3,10 @@ longhornio/csi-provisioner:v2.1.2
 longhornio/csi-resizer:v1.2.0
 longhornio/csi-snapshotter:v3.0.3
 longhornio/csi-node-driver-registrar:v2.5.0
-longhornio/backing-image-manager:v3_20220609
-longhornio/longhorn-engine:v1.3.0
-longhornio/longhorn-instance-manager:v1_20220611
-longhornio/longhorn-manager:v1.3.0
-longhornio/longhorn-share-manager:v1_20220531
-longhornio/longhorn-ui:v1.3.0
+longhornio/livenessprobe:v2.8.0
+longhornio/backing-image-manager:v3_20230320
+longhornio/longhorn-engine:v1.3.3-rc2
+longhornio/longhorn-instance-manager:v1_20230317
+longhornio/longhorn-manager:v1.3.3-rc2
+longhornio/longhorn-share-manager:v1_20230320
+longhornio/longhorn-ui:v1.3.3-rc2

deploy/longhorn.yaml

@@ -13,7 +13,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
 spec:
   privileged: true
   allowPrivilegeEscalation: true
@@ -49,7 +49,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
 ---
 # Source: longhorn/templates/default-setting.yaml
 apiVersion: v1
@@ -60,7 +60,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
 data:
   default-setting.yaml: |-
 ---
@@ -73,7 +73,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
 data:
   storageclass.yaml: |
     kind: StorageClass
@@ -103,7 +103,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: backingimagedatasources.longhorn.io
 spec:
@@ -274,7 +274,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: backingimagemanagers.longhorn.io
 spec:
@@ -459,7 +459,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: backingimages.longhorn.io
 spec:
@@ -634,7 +634,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: backups.longhorn.io
 spec:
@@ -827,7 +827,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: backuptargets.longhorn.io
 spec:
@@ -1010,7 +1010,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: backupvolumes.longhorn.io
 spec:
@@ -1174,10 +1174,11 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: engineimages.longhorn.io
 spec:
+  preserveUnknownFields: false
   conversion:
     strategy: Webhook
     webhook:
@@ -1209,7 +1210,7 @@ spec:
       jsonPath: .spec.image
       name: Image
       type: string
-    - description: Number of volumes are using the engine image
+    - description: Number of resources using the engine image
       jsonPath: .status.refCount
       name: RefCount
       type: integer
@@ -1251,7 +1252,7 @@ spec:
       jsonPath: .spec.image
       name: Image
       type: string
-    - description: Number of volumes are using the engine image
+    - description: Number of resources using the engine image
       jsonPath: .status.refCount
       name: RefCount
       type: integer
@@ -1365,7 +1366,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: engines.longhorn.io
 spec:
@@ -1538,6 +1539,30 @@ spec:
                   type: object
                 nullable: true
                 type: object
+              conditions:
+                items:
+                  properties:
+                    lastProbeTime:
+                      description: Last time we probed the condition.
+                      type: string
+                    lastTransitionTime:
+                      description: Last time the condition transitioned from one status to another.
+                      type: string
+                    message:
+                      description: Human-readable message indicating details about last transition.
+                      type: string
+                    reason:
+                      description: Unique, one-word, CamelCase reason for the condition's last transition.
+                      type: string
+                    status:
+                      description: Status is the status of the condition. Can be True, False, Unknown.
+                      type: string
+                    type:
+                      description: Type is the type of the condition.
+                      type: string
+                  type: object
+                nullable: true
+                type: array
               currentImage:
                 type: string
               currentReplicaAddressMap:
@@ -1686,7 +1711,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: instancemanagers.longhorn.io
 spec:
@@ -1856,10 +1881,11 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: nodes.longhorn.io
 spec:
+  preserveUnknownFields: false
   conversion:
     strategy: Webhook
     webhook:
@@ -2086,7 +2112,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: orphans.longhorn.io
 spec:
@@ -2255,7 +2281,7 @@ spec:
       jsonPath: .spec.groups
       name: Groups
       type: string
-    - description: Should be one of "backup" or "snapshot"
+    - description: Should be one of "snapshot", "snapshot-force-create", "snapshot-cleanup", "snapshot-delete", "backup" or "backup-force-create"
       jsonPath: .spec.task
       name: Task
       type: string
@@ -2317,10 +2343,14 @@ spec:
                 description: The retain count of the snapshot/backup.
                 type: integer
               task:
-                description: The recurring job type. Can be "snapshot" or "backup".
+                description: The recurring job task. Can be "snapshot", "snapshot-force-create", "snapshot-cleanup", "snapshot-delete", "backup" or "backup-force-create".
                 enum:
                 - snapshot
+                - snapshot-force-create
+                - snapshot-cleanup
+                - snapshot-delete
                 - backup
+                - backup-force-create
                 type: string
             type: object
           status:
@@ -2352,7 +2382,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: replicas.longhorn.io
 spec:
@@ -2499,6 +2529,30 @@ spec:
           status:
             description: ReplicaStatus defines the observed state of the Longhorn replica
             properties:
+              conditions:
+                items:
+                  properties:
+                    lastProbeTime:
+                      description: Last time we probed the condition.
+                      type: string
+                    lastTransitionTime:
+                      description: Last time the condition transitioned from one status to another.
+                      type: string
+                    message:
+                      description: Human-readable message indicating details about last transition.
+                      type: string
+                    reason:
+                      description: Unique, one-word, CamelCase reason for the condition's last transition.
+                      type: string
+                    status:
+                      description: Status is the status of the condition. Can be True, False, Unknown.
+                      type: string
+                    type:
+                      description: Type is the type of the condition.
+                      type: string
+                  type: object
+                nullable: true
+                type: array
               currentImage:
                 type: string
               currentState:
@@ -2544,7 +2598,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: settings.longhorn.io
 spec:
@@ -2635,7 +2689,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: sharemanagers.longhorn.io
 spec:
@@ -2746,7 +2800,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: snapshots.longhorn.io
 spec:
@@ -2870,10 +2924,11 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     longhorn-manager: ""
   name: volumes.longhorn.io
 spec:
+  preserveUnknownFields: false
   conversion:
     strategy: Webhook
     webhook:
@@ -3057,7 +3112,11 @@ spec:
                     task:
                       enum:
                       - snapshot
+                      - snapshot-force-create
+                      - snapshot-cleanup
+                      - snapshot-delete
                       - backup
+                      - backup-force-create
                       type: string
                   type: object
                 type: array
@@ -3201,7 +3260,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
 rules:
 - apiGroups:
   - apiextensions.k8s.io
@@ -3262,7 +3321,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
@@ -3280,7 +3339,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
   namespace: longhorn-system
 rules:
 - apiGroups:
@@ -3300,7 +3359,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
   namespace: longhorn-system
 roleRef:
   apiGroup: rbac.authorization.k8s.io
@@ -3321,7 +3380,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-manager
   name: longhorn-backend
   namespace: longhorn-system
@@ -3342,7 +3401,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-ui
   name: longhorn-frontend
   namespace: longhorn-system
@@ -3363,7 +3422,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-conversion-webhook
   name: longhorn-conversion-webhook
   namespace: longhorn-system
@@ -3384,7 +3443,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-admission-webhook
   name: longhorn-admission-webhook
   namespace: longhorn-system
@@ -3405,7 +3464,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
   name: longhorn-engine-manager
   namespace: longhorn-system
 spec:
@@ -3421,7 +3480,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
   name: longhorn-replica-manager
   namespace: longhorn-system
 spec:
@@ -3437,7 +3496,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-manager
   name: longhorn-manager
   namespace: longhorn-system
@@ -3450,16 +3509,16 @@ spec:
       labels:
         app.kubernetes.io/name: longhorn
         app.kubernetes.io/instance: longhorn
-        app.kubernetes.io/version: v1.3.0
+        app.kubernetes.io/version: v1.3.3-rc2
         app: longhorn-manager
     spec:
       initContainers:
       - name: wait-longhorn-admission-webhook
-        image: longhornio/longhorn-manager:v1.3.0
+        image: longhornio/longhorn-manager:v1.3.3-rc2
         command: ['sh', '-c', 'while [ $(curl -m 1 -s -o /dev/null -w "%{http_code}" -k https://longhorn-admission-webhook:9443/v1/healthz) != "200" ]; do echo waiting; sleep 2; done']
       containers:
       - name: longhorn-manager
-        image: longhornio/longhorn-manager:v1.3.0
+        image: longhornio/longhorn-manager:v1.3.3-rc2
         imagePullPolicy: IfNotPresent
         securityContext:
           privileged: true
@@ -3468,15 +3527,15 @@ spec:
         - -d
         - daemon
         - --engine-image
-        - "longhornio/longhorn-engine:v1.3.0"
+        - "longhornio/longhorn-engine:v1.3.3-rc2"
         - --instance-manager-image
-        - "longhornio/longhorn-instance-manager:v1_20220611"
+        - "longhornio/longhorn-instance-manager:v1_20230317"
         - --share-manager-image
-        - "longhornio/longhorn-share-manager:v1_20220531"
+        - "longhornio/longhorn-share-manager:v1_20230320"
         - --backing-image-manager-image
-        - "longhornio/backing-image-manager:v3_20220609"
+        - "longhornio/backing-image-manager:v3_20230320"
         - --manager-image
-        - "longhornio/longhorn-manager:v1.3.0"
+        - "longhornio/longhorn-manager:v1.3.3-rc2"
         - --service-account
         - longhorn-service-account
         ports:
@@ -3536,7 +3595,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
 spec:
   replicas: 1
   selector:
@@ -3547,23 +3606,23 @@ spec:
       labels:
         app.kubernetes.io/name: longhorn
         app.kubernetes.io/instance: longhorn
-        app.kubernetes.io/version: v1.3.0
+        app.kubernetes.io/version: v1.3.3-rc2
         app: longhorn-driver-deployer
     spec:
       initContainers:
         - name: wait-longhorn-manager
-          image: longhornio/longhorn-manager:v1.3.0
+          image: longhornio/longhorn-manager:v1.3.3-rc2
           command: ['sh', '-c', 'while [ $(curl -m 1 -s -o /dev/null -w "%{http_code}" http://longhorn-backend:9500/v1) != "200" ]; do echo waiting; sleep 2; done']
       containers:
         - name: longhorn-driver-deployer
-          image: longhornio/longhorn-manager:v1.3.0
+          image: longhornio/longhorn-manager:v1.3.3-rc2
           imagePullPolicy: IfNotPresent
           command:
           - longhorn-manager
           - -d
           - deploy-driver
           - --manager-image
-          - "longhornio/longhorn-manager:v1.3.0"
+          - "longhornio/longhorn-manager:v1.3.3-rc2"
           - --manager-url
           - http://longhorn-backend:9500/v1
           env:
@@ -3589,6 +3648,8 @@ spec:
             value: "longhornio/csi-resizer:v1.2.0"
           - name: CSI_SNAPSHOTTER_IMAGE
             value: "longhornio/csi-snapshotter:v3.0.3"
+          - name: CSI_LIVENESS_PROBE_IMAGE
+            value: "longhornio/livenessprobe:v2.8.0"
       serviceAccountName: longhorn-service-account
       securityContext:
         runAsUser: 0
@@ -3600,12 +3661,12 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-ui
   name: longhorn-ui
   namespace: longhorn-system
 spec:
-  replicas: 1
+  replicas: 2
   selector:
     matchLabels:
       app: longhorn-ui
@@ -3614,12 +3675,24 @@ spec:
       labels:
         app.kubernetes.io/name: longhorn
         app.kubernetes.io/instance: longhorn
-        app.kubernetes.io/version: v1.3.0
+        app.kubernetes.io/version: v1.3.3-rc2
         app: longhorn-ui
     spec:
+      affinity:
+        podAntiAffinity:
+          preferredDuringSchedulingIgnoredDuringExecution:
+          - weight: 1
+            podAffinityTerm:
+              labelSelector:
+                matchExpressions:
+                - key: app
+                  operator: In
+                  values:
+                  - longhorn-ui
+              topologyKey: kubernetes.io/hostname
       containers:
       - name: longhorn-ui
-        image: longhornio/longhorn-ui:v1.3.0
+        image: longhornio/longhorn-ui:v1.3.3-rc2
         imagePullPolicy: IfNotPresent
         volumeMounts:
         - name : nginx-cache
@@ -3651,7 +3724,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-conversion-webhook
   name: longhorn-conversion-webhook
   namespace: longhorn-system
@@ -3665,7 +3738,7 @@ spec:
       labels:
         app.kubernetes.io/name: longhorn
         app.kubernetes.io/instance: longhorn
-        app.kubernetes.io/version: v1.3.0
+        app.kubernetes.io/version: v1.3.3-rc2
         app: longhorn-conversion-webhook
     spec:
       affinity:
@@ -3682,7 +3755,7 @@ spec:
               topologyKey: kubernetes.io/hostname
       containers:
       - name: longhorn-conversion-webhook
-        image: longhornio/longhorn-manager:v1.3.0
+        image: longhornio/longhorn-manager:v1.3.3-rc2
         imagePullPolicy: IfNotPresent
         securityContext:
           runAsUser: 2000
@@ -3711,7 +3784,7 @@ metadata:
   labels:
     app.kubernetes.io/name: longhorn
     app.kubernetes.io/instance: longhorn
-    app.kubernetes.io/version: v1.3.0
+    app.kubernetes.io/version: v1.3.3-rc2
     app: longhorn-admission-webhook
   name: longhorn-admission-webhook
   namespace: longhorn-system
@@ -3725,7 +3798,7 @@ spec:
       labels:
         app.kubernetes.io/name: longhorn
         app.kubernetes.io/instance: longhorn
-        app.kubernetes.io/version: v1.3.0
+        app.kubernetes.io/version: v1.3.3-rc2
         app: longhorn-admission-webhook
     spec:
       affinity:
@@ -3742,14 +3815,14 @@ spec:
               topologyKey: kubernetes.io/hostname
       initContainers:
       - name: wait-longhorn-conversion-webhook
-        image: longhornio/longhorn-manager:v1.3.0
+        image: longhornio/longhorn-manager:v1.3.3-rc2
         command: ['sh', '-c', 'while [ $(curl -m 1 -s -o /dev/null -w "%{http_code}" -k https://longhorn-conversion-webhook:9443/v1/healthz) != "200" ]; do echo waiting; sleep 2; done']
         imagePullPolicy: IfNotPresent
         securityContext:
           runAsUser: 2000
       containers:
       - name: longhorn-admission-webhook
-        image: longhornio/longhorn-manager:v1.3.0
+        image: longhornio/longhorn-manager:v1.3.3-rc2
         imagePullPolicy: IfNotPresent
         securityContext:
           runAsUser: 2000

deploy/prerequisite/longhorn-iscsi-installation.yaml

@@ -26,11 +26,11 @@ spec:
           - bash
           - -c
           - *cmd
-        image: alpine:3.12
+        image: alpine:3.17
         securityContext:
           privileged: true
       containers:
       - name: sleep
-        image: k8s.gcr.io/pause:3.1
+        image: registry.k8s.io/pause:3.1
   updateStrategy:
     type: RollingUpdate

deploy/prerequisite/longhorn-nfs-installation.yaml

@@ -31,6 +31,6 @@ spec:
           privileged: true
       containers:
       - name: sleep
-        image: k8s.gcr.io/pause:3.1
+        image: registry.k8s.io/pause:3.1
   updateStrategy:
     type: RollingUpdate

enhancements/20200331-replace-filesystem-id-key-in-disk-map.md

@@ -15,7 +15,7 @@ https://github.com/longhorn/longhorn/issues/972
 1. Previously Longhorn is using filesystem ID as keys to the map of disks on the node. But we found there is no guarantee that filesystem ID won't change after the node reboots for certain filesystems e.g. XFS.
 1. We want to enable the ability to configure CRD directly, prepare for the CRD based API access in the future
 1. We also need to make sure previously implemented safe guards are not impacted by this change:
-    1. If a disk was accidentally umounted on the node, we should detect that and stop replica from scheduling into it.
+    1. If a disk was accidentally unmounted on the node, we should detect that and stop replica from scheduling into it.
     1. We shouldn't allow user to add two disks pointed to the same filesystem
 
 ### Non-goals

enhancements/20200625-volume-deletion-flows.md

@@ -75,4 +75,4 @@ No special upgrade strategy is necessary. Once the user upgrades to the new vers
 
 ### Notes
 - There is interest in allowing the user to decide on whether or not to retain the `Persistent Volume` (and possibly `Persistent Volume Claim`) for certain use cases such as restoring from a `Backup`. However, this would require changes to the way `go-rancher` generates the `Go` client that we use so that `Delete` requests against resources are able to take inputs.
-- In the case that a `Volume` is provisioned from a `Storage Class` (and set to be `Deleted` once the `Persistent Volume Claim` utilizing that `Volume` has been deleted), the `Volume` should still be deleted properly regardless of how the deletion was initiated. If the `Volume` is deleted from the UI, the call that the `Volume Controller` makes to delete the `Persistent Volume` would only trigger one more deletion call from the `CSI` server to delete the `Volume`, which would return successfully and allow the `Persistent Volume` to be deleted and the `Volume` to be deleted as wekk. If the `Volume` is deleted because of the `Persistent Volume Claim`, the `CSI` server would be able to successfully make a `Volume` deletion call before deleting the `Persistent Volume`. The `Volume Controller` would have no additional resources to delete and be able to finish deletion of the `Volume`.
+- In the case that a `Volume` is provisioned from a `Storage Class` (and set to be `Deleted` once the `Persistent Volume Claim` utilizing that `Volume` has been deleted), the `Volume` should still be deleted properly regardless of how the deletion was initiated. If the `Volume` is deleted from the UI, the call that the `Volume Controller` makes to delete the `Persistent Volume` would only trigger one more deletion call from the `CSI` server to delete the `Volume`, which would return successfully and allow the `Persistent Volume` to be deleted and the `Volume` to be deleted as well. If the `Volume` is deleted because of the `Persistent Volume Claim`, the `CSI` server would be able to successfully make a `Volume` deletion call before deleting the `Persistent Volume`. The `Volume Controller` would have no additional resources to delete and be able to finish deletion of the `Volume`.

enhancements/20200727-add-replica-eviction-support-for-disks-and-nodes.md

@@ -16,7 +16,7 @@ https://github.com/longhorn/longhorn/issues/298
 
 ## Proposal
 1. Add `Eviction Requested` with `true` and `false` selection buttons for disks and nodes. This is for user to evict or cancel the eviction of the disks or the nodes.
-2. Add new `evictionRequested` field to `Node.Spec`, `Node.Spec.disks` Spec and `Replica.Status`. These will help tracking the request from user and trigger replica controller to update `Replica.Status` and volume controler to do the eviction. And this will reconcile with `scheduledReplica` of selected disks on the nodes.
+2. Add new `evictionRequested` field to `Node.Spec`, `Node.Spec.disks` Spec and `Replica.Status`. These will help tracking the request from user and trigger replica controller to update `Replica.Status` and volume controller to do the eviction. And this will reconcile with `scheduledReplica` of selected disks on the nodes.
 3. Display `fail to evict` error message to `Dashboard` and any other eviction errors to the `Event log`.
 
 ### User Stories
@@ -47,7 +47,7 @@ From an API perspective, the call to set `Eviction Requested` to `true` or `fals
 ### Implementation Overview
 
 1. On `Longhorn UI` `Node` page, for nodes eviction, adding `Eviction Requested` `true` and `false` options in the `Edit Node` sub-selection, next to `Node Scheduling`. For disks eviction, adding `Eviction Requested` `true` and `false` options in `Edit node and disks` sub-selection under `Operation` column next to each disk `Scheduling` options. This is for user to evict or cancel the eviction of the disks or the nodes.
-2. Add new `evictionRequested` field to `Node.Spec`, `Node.Spec.disks` Spec and `Replica.Status`. These will help tracking the request from user and trigger replica controller to update `Replica.Status` and volume controler to do the eviction. And this will reconcile with `scheduledReplica` of selected disks on the nodes.
+2. Add new `evictionRequested` field to `Node.Spec`, `Node.Spec.disks` Spec and `Replica.Status`. These will help tracking the request from user and trigger replica controller to update `Replica.Status` and volume controller to do the eviction. And this will reconcile with `scheduledReplica` of selected disks on the nodes.
 3. Add a informer in `Replica Controller` to get these information and update `evictionRequested` field in `Replica.Status`.
 4. Once `Eviction Requested` has been set to `true` for disks or nodes, the `evictionRequested` fields for the disks and nodes will be set to `true` (default is `false`).
 5. `Replica Controller` will update `evictionRequested` field in `Replica.Status` and `Volume Controller` to get these information from it's replicas.
@@ -61,7 +61,7 @@ From an API perspective, the call to set `Eviction Requested` to `true` or `fals
 #### Manual Test Plan For Disks and Nodes Eviction
 Positive Case:
 
-For both `Replica Node Level Soft Anti-Affinity` has been enabled and disabled. Also the volume can be 'Attaced' or 'Detached'.
+For both `Replica Node Level Soft Anti-Affinity` has been enabled and disabled. Also the volume can be 'Attached' or 'Detached'.
 1. User can select one or more disks or nodes for eviction. Select `Eviction Requested` to `true` on the disabled disks or nodes, Longhorn should start rebuild replicas for the volumes which have replicas on the eviction disks or nodes, and after rebuild success, the replica number on the evicted disks or nodes should be 0. E.g. When there are 3 nodes in the cluster, and with `Replica Node Level Soft Anti-Affinity` is set to `false`, disable one node, and create a volume with replica count 2. And then evict one of them, the eviction should get stuck, then set `Replica Node Level Soft Anti-Affinity` to `true`, the eviction should go through.
 
 Negative Cases:
@@ -73,10 +73,10 @@ For `Replica Node Level Soft Anti-Affinity` is enabled, create 2 replicas on the
 
 For `Replica Node Level Soft Anti-Affinity` is disabled, create 1 replica on a disk, and evict this disk or node, the replica should goto the other disk of node.
 
-For node eviction, Longhorn will process the evition based on the disks for the node, this is like disk eviction. After eviction success, the replica number on the evicted node should be 0.
+For node eviction, Longhorn will process the eviction based on the disks for the node, this is like disk eviction. After eviction success, the replica number on the evicted node should be 0.
 
 #### Error Indication
-During the eviction, user can click the `Replicas Number` on the `Node` page, and set which replicas are left from eviction, and click the `Replica Name` will redirect user to the `Volume` page to set if there is any error for this volume. If there is any error during the rebuild, Longhorn should display the error message from UI. The error could be `failed to schedule a replica` due to disk space or based on schedule policy, can not find a valid disk to put the relica.
+During the eviction, user can click the `Replicas Number` on the `Node` page, and set which replicas are left from eviction, and click the `Replica Name` will redirect user to the `Volume` page to set if there is any error for this volume. If there is any error during the rebuild, Longhorn should display the error message from UI. The error could be `failed to schedule a replica` due to disk space or based on schedule policy, can not find a valid disk to put the replica.
 
 ### Upgrade strategy
 No special upgrade strategy is necessary. Once the user upgrades to the new version of `Longhorn`, these new capabilities will be accessible from the `longhorn-ui` without any special work.

enhancements/20200817-improve-node-failure-handling.md

@@ -61,12 +61,12 @@ Same as the Design
 ### Test plan
 1. Setup a cluster of 3 nodes
 1. Install Longhorn and set `Default Replica Count = 2` (because we will turn off one node)
-1. Create a SetfullSet with 2 pods using the command:
+1. Create a StatefulSet with 2 pods using the command:
     ```
     kubectl create -f https://raw.githubusercontent.com/longhorn/longhorn/master/examples/statefulset.yaml
     ```
 1. Create a volume + pv + pvc named `vol1` and create a deployment of default ubuntu named `shell` with the usage of pvc `vol1` mounted under `/mnt/vol1`
-1. Find the node which contains one pod of the StatefullSet/Deployment. Power off the node
+1. Find the node which contains one pod of the StatefulSet/Deployment. Power off the node
 
 #### StatefulSet
 ##### if `NodeDownPodDeletionPolicy ` is set to `do-nothing ` | `delete-deployment-pod`

enhancements/20200819-keep-a-local-replica-to-engine.md

@@ -119,7 +119,7 @@ UI modification:
    * On the right volume info panel, add a <div> to display `selectedVolume.dataLocality`
    * On the right volume panel, in the Health row, add an icon for data locality status. 
      Specifically, if  `dataLocality=best-effort` but there is not a local replica then display a warning icon.
-     Similar to the replica node redundancy wanring [here](https://github.com/longhorn/longhorn-ui/blob/0a52c1f0bef172d8ececdf4e1e953bfe78c86f29/src/routes/volume/detail/VolumeInfo.js#L47)
+     Similar to the replica node redundancy warning [here](https://github.com/longhorn/longhorn-ui/blob/0a52c1f0bef172d8ececdf4e1e953bfe78c86f29/src/routes/volume/detail/VolumeInfo.js#L47)
    * In the volume's actions dropdown, add a new action to update `dataLocality`
 1. In Rancher UI, add a parameter `dataLocality` when create storage class using Longhorn provisioner. 
    

enhancements/20200821-add-revision-counter-disable-support.md

@@ -15,7 +15,7 @@ https://github.com/longhorn/longhorn/issues/508
 1. By default 'DisableRevisionCounter' is 'false', but Longhorn provides an optional for user to disable it.
 2. Once user set 'DisableRevisionCounter' to 'true' globally or individually, this will improve Longhorn data path performance.
 3. And for 'DisableRevisionCounter' is 'true', Longhorn will keep the ability to find the most suitable replica to recover the volume when the engine is faulted(all the replicas are in 'ERR' state).
-4. Also during Longhorn Engine starting, with head file information it's unlikly to find out out of synced replicas. So will skip the check.
+4. Also during Longhorn Engine starting, with head file information it's unlikely to find out out of synced replicas. So will skip the check.
 
 ## Proposal
 
@@ -41,7 +41,7 @@ Or from StorageClass yaml file, user can set 'parameters' 'revisionCounterDisabl
 
 User can also set 'DisableRevisionCounter' for each individual volumes created by Longhorn UI this individual setting will over write the global setting.
 
-Once the volume has 'DisableRevisionCounter' to 'true', there won't be revision counter file. And the 'Automatic salvage' is 'true', when the engine is fauled, the engine will pick the most suitable replica as 'Source of Truth' to recover the volume.
+Once the volume has 'DisableRevisionCounter' to 'true', there won't be revision counter file. And the 'Automatic salvage' is 'true', when the engine is faulted, the engine will pick the most suitable replica as 'Source of Truth' to recover the volume.
 
 ### API changes
 
@@ -63,12 +63,12 @@ And for the API compatibility issues, always check the 'EngineImage.Statue.cliAP
 
 1. Add 'Volume.Spec.RevisionCounterDisabled', 'Replica.Spec.RevisionCounterDisabled' and 'Engine.Spec.RevisionCounterDisabled' to volume, replica and engine objects.
 2. Once 'RevisionCounterDisabled' is 'true', volume controller will set 'Volume.Spec.RevisionCounterDisabled' to true, 'Replica.Spec.RevisionCounterDisabled' and 'Engine.Spec.RevisionCounterDisabled' will set to true. And during 'ReplicaProcessCreate' and 'EngineProcessCreate' , this will be passed to engine replica process and engine controller process to start a replica and controller without revision counter.
-3. During 'ReplicaProcessCreate' and 'EngineProcessCreate', if 'Replica.Spec.RevisionCounterDisabled' or 'Engine.Spec.RevisionCounterDisabled' is true, it will pass extra parameter to engine replica to start replica without revision counter or to engine controller to start controller without revision counter support, otherwise keep it the same as current and engine replica will use the default value 'false' for this extra paramter. This is the same as the engine controller to set the 'salvageRequested' flag.
+3. During 'ReplicaProcessCreate' and 'EngineProcessCreate', if 'Replica.Spec.RevisionCounterDisabled' or 'Engine.Spec.RevisionCounterDisabled' is true, it will pass extra parameter to engine replica to start replica without revision counter or to engine controller to start controller without revision counter support, otherwise keep it the same as current and engine replica will use the default value 'false' for this extra parameter. This is the same as the engine controller to set the 'salvageRequested' flag.
 4. Add 'RevisionCounterDisabled' in 'ReplicaInfo', when engine controller start, it will get all replica information.
-4. For engine controlloer starting cases:
+4. For engine controller starting cases:
 - If revision counter is not disabled, stay with the current logic.
 - If revision counter is disabled, engine will not check the synchronization of the replicas.
-- If unexpected case (engine controller has revision counter diabled but any of the replica doesn't, or engine controller has revision counter enabled, but any of the replica doesn't), engine controller will log this as error and mark unmatched replicas to 'ERR'.
+- If unexpected case (engine controller has revision counter disabled but any of the replica doesn't, or engine controller has revision counter enabled, but any of the replica doesn't), engine controller will log this as error and mark unmatched replicas to 'ERR'.
 
 #### Add New Logic for Salvage
 

enhancements/20200821-rebuild-replica-with-existing-data.md

@@ -47,7 +47,7 @@ No API change is required.
         3. replica eviction happens (volume.Status.Robustness is Healthy)
         4. there is no potential reusable replica
         5. there is a potential reusable replica but the replica replenishment wait interval is passed.
-    3. Reuse the failed replica by cleaning up `ReplicaSpec.HealthyAt` and `ReplicaSpec.FailedAt`. And `Replica.Spec.RebuildRetryCount` will be increasd by 1. 
+    3. Reuse the failed replica by cleaning up `ReplicaSpec.HealthyAt` and `ReplicaSpec.FailedAt`. And `Replica.Spec.RebuildRetryCount` will be increased by 1. 
     4. Clean up the related record in `Replica.Spec.RebuildRetryCount` when the rebuilding replica becomes mode `RW`.
     5. Guarantee the reused failed replica will be stopped before re-launching it.
 

enhancements/20200909-prometheus-support.md

@@ -72,7 +72,7 @@ For example, there are many times users ask us for supporting and the problems w
 If there is a CPU monitoring dashboard for instance managers, those problems can be quickly detected.
 
 #### Story 2
-User want to be notified about abnomal event such as disk space limit approaching. 
+User want to be notified about abnormal event such as disk space limit approaching. 
 We can expose metrics provide information about it and user can scrape the metrics and setup alert system.
 
 ### User Experience In Detail
@@ -82,7 +82,7 @@ Users can use Prometheus or other monitoring systems to collect those metrics by
 Then, user can display the collected data using tools such as Grafana.
 User can also setup alert by using tools such as Prometheus Alertmanager.
 
-Below are the desciptions of metrics which Longhorn exposes and how users can use them:
+Below are the descriptions of metrics which Longhorn exposes and how users can use them:
 
 1. longhorn_volume_capacity_bytes
 
@@ -347,7 +347,7 @@ We add a new end point `/metrics` to exposes all longhorn Prometheus metrics.
 
 ### Implementation Overview
 We follow the [Prometheus best practice](https://prometheus.io/docs/instrumenting/writing_exporters/#deployment), each Longhorn manager reports information about the components it manages.
-Prometheus can use service discovery mechanisim to find all longhorn-manager pods in longhorn-backend service.
+Prometheus can use service discovery mechanism to find all longhorn-manager pods in longhorn-backend service.
 
 We create a new collector for each type (volumeCollector, backupCollector, nodeCollector, etc..) and have a common baseCollector. 
 This structure is similar to the controller package: we have volumeController, nodeController, etc.. which have a common baseController.

enhancements/20210111-upgrade-engine-automatically.md

@@ -45,7 +45,7 @@ For part 2, we upgrade engine image for a volume when the following conditions a
 ### User Stories
 
 Before this enhancement, users have to manually upgrade engine images for volume after upgrading Longhorn system to a newer version.
-If there are thoudsands of volumes in the system, this is a significant manual work.
+If there are thousands of volumes in the system, this is a significant manual work.
 
 After this enhancement users either have to do nothing (in case live upgrade is possible) 
 or they only have to scale down/up the workload (in case there is a new default IM image)

enhancements/20210216-volume-live-migration.md

@@ -70,7 +70,7 @@ spec:
   url: https://download.cirros-cloud.net/0.4.0/cirros-0.4.0-x86_64-disk.img
 ```
 
-Afterwards deploy the `cirros-rwx-blk.yaml` to create a live migratabale virtual machine.
+Afterwards deploy the `cirros-rwx-blk.yaml` to create a live migratable virtual machine.
 ```yaml
 apiVersion: kubevirt.io/v1alpha3
 kind: VirtualMachine

enhancements/20210510-automatic-rebalance-replica.md

@@ -155,14 +155,14 @@ With an example of cluster set for 2 zones and default of 2 replicas volume:
   - The default value is `ignored`.
 
 - In Volume Controller `syncVolume` -> `ReconcileEngineReplicaState` -> `replenishReplicas`, calculate and add number of replicas to be rebalanced to `replenishCount`.
-  > The logic ignores all `soft-anti-affinity` settings. This will always try to achieve zone balance then node balance. And creating for replicas will leave for ReplicaScheduler to determine for the canidates.
+  > The logic ignores all `soft-anti-affinity` settings. This will always try to achieve zone balance then node balance. And creating for replicas will leave for ReplicaScheduler to determine for the candidates.
   1. Skip volume replica rebalance when volume spec `replicaAutoBalance` is `disabled`.
   2. Skip if volume `Robustness` is not `healthy`.
   3. For `least-effort`, try to get the replica rebalance count.
       1. For `zone` duplicates, get the replenish number.
             1. List all the occupied node zones with volume replicas running.
                   - The zone is balanced when this is equal to volume spec `NumberOfReplicas`.
-            2. List all available and schedulabled nodes in non-occupied zones.
+            2. List all available and schedulable nodes in non-occupied zones.
                   - The zone is balanced when no available nodes are found.
             3. Get the number of replicas off-balanced:
                   - number of replicas in volume spec - number of occupied node zones.

enhancements/20210624-label-driven-recurring-job.md

@@ -354,7 +354,7 @@ Labels
 [labels/2]: [b]
 ```
 - `Name` field should be immutable.
-- `Task` field should be imuutable.
+- `Task` field should be immutable.
 
 *And* user edit the fields in the form.
 

enhancements/20210701-backing-image.md

@@ -337,7 +337,7 @@ After the enhancement, users can directly specify the BackingImage during volume
             - BackingImageDataSource has not been created. Add retry would solve this case.
             - BackingImageDataSource is gone but BackingImage has not been cleaned up. Longhorn can ignore BackingImageDataSource when BackingImage deletion timestamp is set.
     - BackingImage disk cleanup:
-        - This cannot break the HA besides affacting replicas. The main idea is similar to the cleanup in BackingImage Controller.
+        - This cannot break the HA besides attaching replicas. The main idea is similar to the cleanup in BackingImage Controller.
 9. In CSI:
     - Check the backing image during the volume creation.
     - The missing BackingImage will be created when both BackingImage name and data source info are provided.
@@ -370,7 +370,7 @@ After the enhancement, users can directly specify the BackingImage during volume
         - Similar to `Fetch`, the image will try to reuse existing files.
         - The manager is responsible for managing all port. The image will use the functions provided by the manager to get then release ports.
     - API `Send`: Send a backing image file to a receiver. This should be similar to replica rebuilding.
-    - API `Delete`: Unregister the image then delete the imge work directory. Make sure syncing or pulling will be cancelled if exists.
+    - API `Delete`: Unregister the image then delete the image work directory. Make sure syncing or pulling will be cancelled if exists.
     - API `Get`/`List`: Collect the status of one backing image file/all backing image files.
     - API `Watch`: establish a streaming connection to report BackingImage file info.
 - As I mentioned above, we will use BackingImage UUID to generate work directories for each BackingImage. The work directory is like:

enhancements/20210810-volume-clone.md

@@ -190,7 +190,7 @@ Using those methods, the Sparse-tools know where is a data/hole interval to tran
 
 ### Longhorn CSI plugin
 * Advertise that Longhorn CSI driver has ability to clone a volume, `csi.ControllerServiceCapability_RPC_CLONE_VOLUME`
-* When receiving a volume creat request, inspect `req.GetVolumeContentSource()` to see if it is from anther volume.
+* When receiving a volume creat request, inspect `req.GetVolumeContentSource()` to see if it is from another volume.
   If so, create a new Longhorn volume with appropriate `DataSource` set so Longhorn volume controller can start cloning later on.
 
 ### Test plan

enhancements/20220324-orphaned-data-cleanup.md

@@ -66,7 +66,7 @@ After the enhancement, Longhorn automatically finds out the orphaned replica dir
     - Users can enable the global auto-deletion on setting page. By default, the auto-deletion is disabled.
 
 - Via `kubectl`
-    - Users can list the orphaned replica directoris by `kubectl -n longhorn-system get orphans`.
+    - Users can list the orphaned replica directories by `kubectl -n longhorn-system get orphans`.
     - Users can delete the orphaned replica directories by `kubectl -n longhorn-system delete orphan <name>`.
     - Users can enable the global auto-deletion by `kubectl -n longhorn-system edit settings orphan-auto-deletion`
 

enhancements/20220801-failed-backups-cleanup.md

@@ -0,0 +1,110 @@
+# Failed Backup Clean Up
+
+## Summary
+
+Longhorn will leave the failed backups behind and will not delete the backups automatically either until the backup target is removed. Failed backup cleanup will be occurred when making a backup to remote backup target failed. This LEP will trigger the deletion of failed backups automatically.
+
+### Related Issues
+
+[[IMPROVEMENT] Support failed/obsolete orphaned backup cleanup](https://github.com/longhorn/longhorn/issues/3898)
+
+## Motivation
+
+### Goals
+
+- Support the auto-deletion of failed backups that exceeded the TTL.
+- Support the global auto-deletion option of failed backups cleanup for users.
+- The process should not be stuck in the reconciliation of the controllers.
+
+### Non-goals [optional]
+
+- Clean up unknown files or directories on the remote backup target.
+
+## Proposal
+
+1. The `backup_volume_controller` will be responsible for deleting Backup CR when there is a backup which state is in `Error` or `Unknown`.
+
+    The reconciliation procedure of the `backup_volume_controller` gets the latest failed backups from the datastore and delete the failed backups.
+
+    ```text
+
+          queue           ┌───────────────┐
+         ┌┐ ┌┐ ┌┐         │               │
+     ... ││ ││ ││ ──────► │ syncHandler() |
+         └┘ └┘ └┘         │               │
+                          └───────┬───────┘
+                                  │
+                       ┌──────────▼───────────┐
+                       │                      │
+                       │     reconcile()      |
+                       │                      │
+                       └──────────┬───────────┘
+                                  │
+                       ┌──────────▼───────────┐
+                       │                      │
+                       │  get failed backups  │
+                       │                      |
+                       |  then delete them    │
+                       │                      │
+                       └──────────────────────┘
+
+
+
+    ```
+
+### User Stories
+
+When a user or recurring job tries to make a backup and store it in the remote backup target, many situations will cause the backup procedure failed. In some cases, there will be some failed backups still staying in the Longhorn system and this kind of backups are not handled by the Longhorn system until user removes the backup target. Or users can manage the failed backups via Longhorn GUI or command line tools manually.
+
+After the enhancement, Longhorn can delete the failed backups automatically after enabling auto-deletion.
+
+### User Experience In Detail
+
+- Via Longhorn GUI
+  - Users can be aware of that backup was failed if auto-deletion is disabled.
+  - Users can check the event log to understand why the backup failed and deleted.
+
+- Via `kubectl`
+  - Users can list the failed backups by `kubectl -n longhorn-system get backups` if auto-deletion is disabled.
+
+## Design
+
+### Implementation Overview
+
+**Settings**
+
+- Add setting `failed-backup-ttl`. Default value is `1440` minutes and set to `0` to disable the auto-deletion.
+
+**Failed Backup**
+
+- Backups in the state `longhorn.BackupStateError` or `longhorn.BackupStateUnknown`.
+
+**Backup Controller**
+
+- Start the monitor and sync the backup status with the monitor in each reconcile loop.
+- Update the backup status.
+- Trigger `backup_volume_controller` to delete the failed backups.
+
+**Backup Volume controller**
+
+- Reconcile loop usually is triggered after backupstore polling which is controlled by **Backupstore Poll Interval** setting.
+- Start to get all backups in each reconcile loop
+- Tell failed backups from all backups and try to delete failed backups by default.
+- Update the backup volume CR status.
+
+### Test plan
+
+**Integration tests**
+
+- `backups` CRs with `Error` or `Unknown` state will be removed by `backup_volume_controller` triggered by backupstore polling when the `backup_monitor` detects the backup failed.
+- `backups` CRs with `Error` or `Unknown` state will not be handled if the auto-deletion is disabled.
+
+## Note [optional]
+
+### Why not leverage the current orphan framework
+
+1. We already have the backup CR to handle the backup resources and failed backup is not like orphaned replica which is not owned by any volume at the beginning.
+
+2. Cascading deletion of orphaned CR and backup CR would be more complicated than we just handle the failed backups immediately when backup procedure failed. Both in this LEP or orphan framework we would delete the failed backups by `backup_volume_controller`.
+
+3. Listing orphaned backups and failed backups on both two UI pages `Orphaned Data` and `Backup` might be a bit confusing for users. Deleting items manually on either of two pages would be involved in what it mentioned at statement 2.

enhancements/YYYYMMDD-template.md

@@ -29,7 +29,7 @@ What is out of scope for this enhancement? Listing non-goals helps to focus disc
 This is where we get down to the nitty gritty of what the proposal actually is.
 
 ### User Stories
-Detail the things that people will be able to do if this enhancement is implemented. A good practise is including a comparsion of what user cannot do before the enhancement implemented, why user would want an enhancement and what user need to do after, to make it clear why the enhancement beneficial to the user.
+Detail the things that people will be able to do if this enhancement is implemented. A good practise is including a comparison of what user cannot do before the enhancement implemented, why user would want an enhancement and what user need to do after, to make it clear why the enhancement beneficial to the user.
 
 The experience details should be in the `User Experience In Detail` later.
 

examples/data_migration.yaml

@@ -19,7 +19,7 @@ spec:
           image: ubuntu:xenial
           tty: true
           command: [ "/bin/sh" ]
-          args: [ "-c", "cp -r -v /mnt/old/* /mnt/new" ]
+          args: [ "-c", "cp -r -v /mnt/old/. /mnt/new" ]
           volumeMounts:
             - name: old-vol
               mountPath: /mnt/old

examples/restore_to_file.yaml.template

@@ -16,7 +16,7 @@ spec:
       --output-file '/tmp/restore/<OUTPUT_FILE>'
       --output-format <OUTPUT_FORMAT>
     # the version of longhorn engine should be v0.4.1 or higher
-    image: rancher/longhorn-engine:v0.4.1
+    image: longhornio/longhorn-engine:<LONGHORN_VERSION>
     imagePullPolicy: IfNotPresent
     securityContext:
       privileged: true

examples/statefulset.yaml

@@ -32,7 +32,7 @@ spec:
       terminationGracePeriodSeconds: 10
       containers:
       - name: nginx
-        image: k8s.gcr.io/nginx-slim:0.8
+        image: registry.k8s.io/nginx-slim:0.8
         livenessProbe:
           exec:
             command:

scripts/environment_check.sh

@@ -1,5 +1,8 @@
 #!/bin/bash
 
+######################################################
+# Log
+######################################################
 export RED='\x1b[0;31m'
 export GREEN='\x1b[38;5;22m'
 export CYAN='\x1b[36m'
@@ -67,17 +70,9 @@ error() {
   fi
 }
 
-detect_node_os()
-{
-  local pod="$1"
-
-  OS=`kubectl exec -it $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c 'grep -E "^ID_LIKE=" /etc/os-release | cut -d= -f2'`
-  if [[ -z "${OS}" ]]; then
-    OS=`kubectl exec -it $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c 'grep -E "^ID=" /etc/os-release | cut -d= -f2'`
-  fi
-  echo "$OS"
-}
-
+######################################################
+# Check logics
+######################################################
 set_packages_and_check_cmd()
 {
   case $OS in
@@ -97,6 +92,10 @@ set_packages_and_check_cmd()
     CHECK_CMD='pacman -Q'
     PACKAGES=(nfs-utils open-iscsi)
     ;;
+  *"gentoo"* )
+    CHECK_CMD='qlist -I'
+    PACKAGES=(net-fs/nfs-utils sys-block/open-iscsi)
+    ;;
   *)
     CHECK_CMD=''
     PACKAGES=()
@@ -106,23 +105,45 @@ set_packages_and_check_cmd()
    esac
 }
 
-check_dependencies() {
+detect_node_kernel_release()
+{
+  local pod="$1"
+
+  KERNEL_RELEASE=$(kubectl exec -i $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c 'uname -r')
+  echo "$KERNEL_RELEASE"
+}
+
+detect_node_os()
+{
+  local pod="$1"
+
+  OS=$(kubectl exec -i $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c 'grep -E "^ID_LIKE=" /etc/os-release | cut -d= -f2')
+  if [[ -z "${OS}" ]]; then
+    OS=$(kubectl exec -i $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c 'grep -E "^ID=" /etc/os-release | cut -d= -f2')
+  fi
+  echo "$OS"
+}
+
+check_local_dependencies() {
   local targets=($@)
 
-  local allFound=true
+  local all_found=true
   for ((i=0; i<${#targets[@]}; i++)); do
     local target=${targets[$i]}
     if [ "$(which $target)" == "" ]; then
-      allFound=false
+      all_found=false
       error "Not found: $target"
     fi
   done
-  if [ "$allFound" == "false" ]; then
-    error "Please install missing dependencies."
+
+  if [ "$all_found" == "false" ]; then
+    msg="Please install missing dependencies: ${targets[@]}."
+    info "$msg"
     exit 2
-  else
-    info "Required dependencies are installed."
   fi
+
+  msg="Required dependencies '${targets[@]}' are installed."
+  info "$msg"
 }
 
 create_ds() {
@@ -211,12 +232,12 @@ check_mount_propagation() {
 }
 
 check_package_installed() {
-  local pods=$(kubectl get pods -o name | grep longhorn-environment-check)
+  local pods=$(kubectl get pods -o name -l app=longhorn-environment-check)
 
-  local allFound=true
+  local all_found=true
 
   for pod in ${pods}; do
-    OS=`detect_node_os $pod`
+    OS=$(detect_node_os $pod)
     if [ x"$OS" == x"" ]; then
       error "Unable to detect OS on node $node."
       exit 2
@@ -227,72 +248,137 @@ check_package_installed() {
     for ((i=0; i<${#PACKAGES[@]}; i++)); do
       local package=${PACKAGES[$i]}
 
-      kubectl exec -it $pod -- nsenter --mount=/proc/1/ns/mnt -- timeout 30 bash -c "$CHECK_CMD $package" > /dev/null 2>&1
+      kubectl exec -i $pod -- nsenter --mount=/proc/1/ns/mnt -- timeout 30 bash -c "$CHECK_CMD $package" > /dev/null 2>&1
       if [ $? != 0 ]; then
-        allFound=false
-        node=`kubectl get ${pod} --no-headers -o=custom-columns=:.spec.nodeName`
+        all_found=false
+        node=$(kubectl get ${pod} --no-headers -o=custom-columns=:.spec.nodeName)
         error "$package is not found in $node."
       fi
     done
   done
 
-  if [ "$allFound" == "false" ]; then
+  if [ "$all_found" == "false" ]; then
     error "Please install missing packages."
     exit 2
-  else
-    info "Required packages are installed."
   fi
+
+  info "Required packages are installed."
+}
+
+check_hostname_uniqueness() {
+  hostnames=$(kubectl get nodes -o jsonpath='{.items[*].status.addresses[?(@.type=="Hostname")].address}')
+
+  declare -A deduplicate_hostnames
+  num_nodes=0
+  for hostname in ${hostnames}; do
+    num_nodes=$((num_nodes+1))
+    deduplicate_hostnames["${hostname}"]="${hostname}"
+  done
+
+  if [ "${#deduplicate_hostnames[@]}" != "${num_nodes}" ]; then
+    error "Nodes do not have unique hostnames."
+    exit 2
+  fi
+
+  info "Hostname uniqueness check is passed."
 }
 
 check_multipathd() {
-  local pods=$(kubectl get pods -o name | grep longhorn-environment-check)
-  local allNotFound=true
+  local pods=$(kubectl get pods -o name -l app=longhorn-environment-check)
+  local all_not_found=true
 
   for pod in ${pods}; do
     kubectl exec -t $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c "systemctl status --no-pager multipathd.service" > /dev/null 2>&1
     if [ $? = 0 ]; then
-      allNotFound=false
-      node=`kubectl get ${pod} --no-headers -o=custom-columns=:.spec.nodeName`
+      all_not_found=false
+      node=$(kubectl get ${pod} --no-headers -o=custom-columns=:.spec.nodeName)
       warn "multipathd is running on $node."
     fi
   done
 
-  if [ "$allNotFound" == "false" ]; then
+  if [ "$all_not_found" == "false" ]; then
     warn "multipathd would probably result in the Longhorn volume mount failure. Please refer to https://longhorn.io/kb/troubleshooting-volume-with-multipath for more information."
   fi
 }
 
 check_iscsid() {
-  local pods=$(kubectl get pods -o name | grep longhorn-environment-check)
-  local allFound=true
+  local pods=$(kubectl get pods -o name -l app=longhorn-environment-check)
+  local all_found=true
 
   for pod in ${pods}; do
     kubectl exec -t $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c "systemctl status --no-pager iscsid.service" > /dev/null 2>&1
 
     if [ $? != 0 ]; then
-      allFound=false
-      node=`kubectl get ${pod} --no-headers -o=custom-columns=:.spec.nodeName`
+      all_found=false
+      node=$(kubectl get ${pod} --no-headers -o=custom-columns=:.spec.nodeName)
       error "iscsid is not running on $node."
     fi
   done
 
-  if [ "$allFound" == "false" ]; then
+  if [ "$all_found" == "false" ]; then
     exit 2
   fi
 }
 
-DEPENDENCIES=(kubectl jq mktemp)
-check_dependencies ${DEPENDENCIES[@]}
+check_nfs_client_kernel_support() {
+  local pods=$(kubectl get pods -o name -l app=longhorn-environment-check)
+  local all_found=true
+  local nfs_client_kernel_configs=("CONFIG_NFS_V4_1" "CONFIG_NFS_V4_2")
 
+  for config in "${nfs_client_kernel_configs[@]}"; do
+    declare -A nodes=()
+
+    for pod in ${pods}; do
+      local kernel_release=$(detect_node_kernel_release $pod)
+      if [ x"$kernel_release" == x"" ]; then
+        error "Unable to detect kernel release on node $node."
+        exit 2
+      fi
+
+      node=$(kubectl get ${pod} --no-headers -o=custom-columns=:.spec.nodeName)
+      res=$(kubectl exec -t $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c "grep -E \"^# ${config} is not set\" /boot/config-${kernel_release}" > /dev/null 2>&1)
+      if [[ $? == 0 ]]; then
+        all_found=false
+        nodes["${node}"]="${node}"
+      else
+        res=$(kubectl exec -t $pod -- nsenter --mount=/proc/1/ns/mnt -- bash -c "grep -E \"^${config}=\" /boot/config-${kernel_release}" > /dev/null 2>&1)
+        if [[ $? != 0 ]]; then
+          all_found=false
+          warn "Unable to check kernel config ${config} on node ${node}"
+        fi
+      fi
+    done
+
+    if [ ${#nodes[@]} != 0 ]; then
+      warn ""${config}" kernel config is not enabled on nodes ${nodes[*]}."
+    fi
+  done
+
+  if [[ ${all_found} == false ]]; then
+    warn "NFS client kernel support, ${nfs_client_kernel_configs[*]}, is not enabled on Longhorn nodes. Please refer to https://longhorn.io/docs/1.4.0/deploy/install/#installing-nfsv4-client for more information."
+  fi
+}
+
+######################################################
+# Main logics
+######################################################
+DEPENDENCIES=("kubectl" "jq" "mktemp")
+check_local_dependencies "${DEPENDENCIES[@]}"
+
+# Check the each host has a unique hostname (for RWX volume)
+check_hostname_uniqueness
+
+# Create a daemonset for checking the requirements in each node
 TEMP_DIR=$(mktemp -d)
 
 trap cleanup EXIT
 create_ds
 wait_ds_ready
+
+check_nfs_client_kernel_support
 check_package_installed
 check_iscsid
 check_multipathd
 check_mount_propagation
 
 exit 0
-

scripts/longhorn_rancher_chart_migration.sh

@@ -0,0 +1,201 @@
+#!/bin/bash
+#set -x
+
+kubectl get-all version &> /dev/null
+if [ $? -ne 0 ]; then
+  echo "ERROR: command (kubectl get-all) is not found. Please install it here: https://github.com/corneliusweig/ketall#installation"
+  exit 1
+fi
+
+set -e
+
+usage() {
+  echo ""
+  echo "The migration includes:"
+  echo "1. Running the script with --type=migrate to migrate the labels and annotations for Longhorn resources"
+  echo "2. Manually installing Longhorn chart in app&marketplace UI"
+  echo "3. Running script with --type=cleanup to remove the old Longhorn chart from old catalog UI"
+  echo ""
+  echo "usage:"
+  echo "$0 [options]"
+  echo "  -u | --upstream-kubeconfig:      upstream rancher cluster kubeconfig path"
+  echo "  -d | --downstream-kubeconfig:    downstream cluster kubeconfig path"
+  echo "  -t | --type:                     specify the type you want to run (migrate or cleanup)"
+  echo "  --dry-run:                       do not run migriation"
+  echo ""
+  echo "example:"
+  echo "  $0 -u /path/to/upstream/rancher/cluster/kubeconfig -d /path/to/downstream/cluster/kubeconfig"
+}
+
+SCRIPT_DIR="$(dirname "$0")"
+UPSTREAM_KUBECONFIG=""
+DOWNSTREAM_KUBECONFIG=""
+KUBECTL_DRY_RUN=""
+
+while [ "$1" != "" ]; do
+  case $1 in
+  -u | --upstream-kubeconfig)
+    shift
+    UPSTREAM_KUBECONFIG="$1"
+    ;;
+  -d | --downstream-kubeconfig)
+    shift
+    DOWNSTREAM_KUBECONFIG="$1"
+    ;;
+  -t | --type)
+    shift
+    TYPE="$1"
+    ;;
+  --dry-run)
+    KUBECTL_DRY_RUN="--dry-run=client"
+    ;;
+  *)
+    usage
+    exit 1
+    ;;
+  esac
+  shift
+done
+
+if [ -z "$UPSTREAM_KUBECONFIG" ]; then
+  echo "--upstream-kubeconfig is mandatory"
+  usage
+  exit 1
+fi
+if [ -z "$DOWNSTREAM_KUBECONFIG" ]; then
+  echo "--downstream-kubeconfig is mandatory"
+  usage
+  exit 1
+fi
+if [ "$TYPE" != "migrate" ] &&  [ "$TYPE" != "cleanup" ] ; then
+  echo "--type must be set to migrate or cleanup"
+  usage
+  exit 1
+fi
+
+
+# Longhorn Namespace
+RELEASE_NAMESPACE=longhorn-system
+# Longhorn Release Name
+RELEASE_NAME=longhorn-system
+
+
+echo "Looking up Rancher Project App '${RELEASE_NAME}' ..."
+DOWNSTREAMCLUSTERID=$(cat  ${DOWNSTREAM_KUBECONFIG} | grep "server:.*https://.*/k8s/clusters/.*"  | awk -F'/' '{print $(NF)}' | awk -F'"' '{print $1}')
+RANCHERAPP=$(kubectl --kubeconfig ${UPSTREAM_KUBECONFIG} get --all-namespaces apps.project.cattle.io -o jsonpath='{range.items[*]}{.metadata.namespace} {.metadata.name} {.spec.targetNamespace} {.spec.projectName} {.spec.externalId}{"\n"}{end}' | grep -s "${RELEASE_NAME} ${RELEASE_NAMESPACE} ${DOWNSTREAMCLUSTERID}")
+RANCHERAPPNS=$(echo "${RANCHERAPP}" | awk '{print $1}')
+RANCHERAPPEXTERNALID=$(echo "${RANCHERAPP}" | awk '{print $5}')
+RANCHERAPPCATALOG=$(echo "${RANCHERAPPEXTERNALID}" | sed -n 's/.*catalog=\(.*\)/\1/p' | awk -F '&' '{print $1}' | sed 's/migrated-//')
+RANCHERAPPTEMPLATE=$(echo "${RANCHERAPPEXTERNALID}" | sed -n 's/.*template=\(.*\)/\1/p' | awk -F '&' '{print $1}')
+RANCHERAPPTEMPLATEVERSION=$(echo "${RANCHERAPPEXTERNALID}" | sed -n 's/.*version=\(.*\)/\1/p' | awk -F '&' '{print $1}')
+RANCHERAPPVALUES=""
+RANCHERAPPANSWERS=""
+
+if [ -z "$DOWNSTREAMCLUSTERID" ] || [ -z "$RANCHERAPP" ] || [ -z "$RANCHERAPPNS" ] || [ -z "$RANCHERAPPCATALOG" ] || [ -z "$RANCHERAPPTEMPLATE" ] || [ -z "$RANCHERAPPTEMPLATEVERSION" ]; then
+  echo "Rancher Project App '${RELEASE_NAME}' not found!"
+  exit 1
+fi
+
+RANCHERAPPVALUES=$(kubectl --kubeconfig ${UPSTREAM_KUBECONFIG} -n ${RANCHERAPPNS} get apps.project.cattle.io ${RELEASE_NAME} -o go-template='{{if .spec.valuesYaml}}{{.spec.valuesYaml}}{{end}}')
+if [ -z "${RANCHERAPPVALUES}" ]; then
+  RANCHERAPPANSWERS=$(kubectl --kubeconfig ${UPSTREAM_KUBECONFIG} -n ${RANCHERAPPNS} get apps.project.cattle.io ${RELEASE_NAME} -o go-template='{{if .spec.answers}}{{range $key,$value := .spec.answers}}{{$key}}: {{$value}}{{"\n"}}{{end}}{{end}}' | sed 's/: /=/' | sed 's/$/,/' | sed '$ s/.$//' | tr -d '\n')
+fi
+if [ -z "${RANCHERAPPVALUES:-$RANCHERAPPANSWERS}" ]; then
+  echo "No valid answers found!"
+  exit 1
+fi
+
+echo ""
+echo "Rancher Project App '${RELEASE_NAME}' found:"
+echo "  Project-Namespace: ${RANCHERAPPNS}"
+echo "  Downstream-Cluster: ${DOWNSTREAMCLUSTERID}"
+echo "  Catalog: ${RANCHERAPPCATALOG}"
+echo "  Template: ${RANCHERAPPTEMPLATE} (${RANCHERAPPTEMPLATEVERSION})"
+echo "  Answers:"
+printf '%s\n' "${RANCHERAPPVALUES:-$RANCHERAPPANSWERS}"
+echo ""
+
+if [ "$TYPE" == "cleanup" ] ; then
+
+  MANAGER=$(kubectl --kubeconfig ${DOWNSTREAM_KUBECONFIG} -n ${RELEASE_NAMESPACE} get ds longhorn-manager -ojsonpath="{.metadata.labels['app\.kubernetes\.io/managed-by']}")
+  if [ $MANAGER != "Helm" ] ; then
+    echo "Labels have not been migrated. Did you run the part 1 by specifying the flag --type=migrate ?"
+    exit 1
+  fi
+
+  echo ""
+  echo "Patching Project App Catalog ..."
+  kubectl --kubeconfig ${UPSTREAM_KUBECONFIG} -n ${RANCHERAPPNS} ${KUBECTL_DRY_RUN} patch apps.project.cattle.io ${RELEASE_NAME} --type=merge --patch-file=/dev/stdin <<-EOF
+  {
+    "metadata": {
+      "annotations": {
+        "cattle.io/skipUninstall": "true",
+        "catalog.cattle.io/ui-source-repo": "helm3-library",
+        "catalog.cattle.io/ui-source-repo-type": "cluster",
+        "apps.cattle.io/migrated": "true"
+      }
+    }
+  }
+EOF
+
+  if [ $? -ne 0 ]; then
+     echo "Failed Patching Project App Catalog"
+     exit 1
+  fi
+
+  echo ""
+  echo "Deleting Project App Catalog ..."
+  kubectl --kubeconfig ${UPSTREAM_KUBECONFIG} -n ${RANCHERAPPNS} ${KUBECTL_DRY_RUN} delete apps.project.cattle.io ${RELEASE_NAME}
+
+  exit 0
+fi
+
+echo ""
+echo ""
+echo "Checking concurrent-automatic-engine-upgrade-per-node-limit setting ..."
+SETTING=$(kubectl --kubeconfig ${DOWNSTREAM_KUBECONFIG} -n ${RELEASE_NAMESPACE} get settings.longhorn.io concurrent-automatic-engine-upgrade-per-node-limit -ojsonpath="{.value}")
+if [ "$SETTING" != "0" ]; then
+  echo "concurrent-automatic-engine-upgrade-per-node-limit must be set to 0 before the migration"
+  exit 1
+fi
+
+echo ""
+echo ""
+echo "Looking up existing Resources ..."
+RESOURCES=$(kubectl get-all --kubeconfig ${DOWNSTREAM_KUBECONFIG} --exclude AppRevision -o name -l io.cattle.field/appId=${RELEASE_NAME} 2>/dev/null | sort)
+if [[ "$RESOURCES" == "No resources"* ]]; then
+  RESOURCES=""
+fi
+
+echo ""
+echo "Patching CRD Resources ..."
+for resource in $RESOURCES; do
+  if [[ $resource == "customresourcedefinition.apiextensions.k8s.io/"* ]]; then
+    kubectl --kubeconfig ${DOWNSTREAM_KUBECONFIG} -n ${RELEASE_NAMESPACE} ${KUBECTL_DRY_RUN} annotate --overwrite ${resource} "meta.helm.sh/release-name"="longhorn-crd" "meta.helm.sh/release-namespace"="${RELEASE_NAMESPACE}" "helm.sh/resource-policy"="keep"
+    kubectl --kubeconfig ${DOWNSTREAM_KUBECONFIG} -n ${RELEASE_NAMESPACE} ${KUBECTL_DRY_RUN} label --overwrite ${resource} "app.kubernetes.io/managed-by"="Helm"
+  fi
+
+done
+
+echo ""
+echo "Patching Other Resources ..."
+for resource in $RESOURCES; do
+  if [[ $resource == "customresourcedefinition.apiextensions.k8s.io/"* ]]; then
+    continue
+  fi
+  kubectl --kubeconfig ${DOWNSTREAM_KUBECONFIG} -n ${RELEASE_NAMESPACE} ${KUBECTL_DRY_RUN} annotate --overwrite ${resource} "meta.helm.sh/release-name"="longhorn" "meta.helm.sh/release-namespace"="${RELEASE_NAMESPACE}"
+  kubectl --kubeconfig ${DOWNSTREAM_KUBECONFIG} -n ${RELEASE_NAMESPACE} ${KUBECTL_DRY_RUN} label --overwrite ${resource} "app.kubernetes.io/managed-by"="Helm"
+done
+
+
+echo ""
+echo "-----------------------------"
+echo "Successfully updated the annotations and labels for the resources!"
+echo "Next step:"
+echo "  1. Go to Rancher UI -> Go to the downstream cluster -> App&Marketplace -> Charts"
+echo "  2. Find and select the Longhorn chart"
+echo "  3. Select the chart version corresponding the Longhorn version ${RANCHERAPPTEMPLATEVERSION}"
+echo "  4. Install the chart with the correct helm values. Here are the helm values of your old charts: "
+printf '%s\n' "${RANCHERAPPVALUES:-$RANCHERAPPANSWERS}"
+echo "  5. Verify that the migrated charts are working ok"
+echo "  6. Run this script again with the flag --type=cleanup to remove the old chart from the legacy UI"

scripts/restore-backup-to-file.sh

@@ -0,0 +1,104 @@
+#!/bin/bash
+
+export RED='\x1b[0;31m'
+export NO_COLOR='\x1b[0m'
+
+usage () {
+   echo "USAGE: $0 --aws-access-key <your_aws_access_key>  \ "
+   echo "          --aws-secret-access-key <your_aws_secret_access_key> \ "
+   echo "          --backup-url s3://backupbucket@ap-northeast-1/backupstore?backup=<backup_name>&volume=<volume_name> \ "
+   echo "          --output-file volume.raw \ "
+   echo "          --output-format raw \ "
+   echo "          --version <longhorn_version>"
+   echo "          --backing-file <backing_file_path>"
+   echo "Restore a Longhorn backup to a raw image or a qcow2 image."
+   echo ""
+   echo "  -u, --backup-url             (Required) Backups S3/NFS URL. e.g., s3://backupbucket@us-east-1/backupstore?backup=backup-bd326da2c4414b02&volume=volumeexamplename"
+   echo "  -o, --output-file            (Required) Output file, e.g., /tmp/restore/volume.raw"
+   echo "  -f, --output-format          (Required) Output file format, e.g., raw or qcow2"
+   echo "  -v, --version                (Required) Longhorn version, e.g., v1.3.2"
+   echo "      --aws-access-key         (Optional) AWS credentials access key"
+   echo "      --aws-secret-access-key  (Optional) AWS credentials access secret key"
+   echo "  -b, --backing-file           (Optional) backing image. e.g., /tmp/backingfile.qcow2"
+   echo "  -h, --help                   Usage message"
+}
+
+error_invalid_params() {
+  echo -e "${RED}[ERROR]Invalid params. Check the required params.${NO_COLOR}"
+  usage
+  exit 1
+}
+
+while [[ "$#" -gt 0 ]]; do
+  key="$1"
+  case $key in
+    --aws-access-key)
+    aws_access_key="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    --aws-secret-access-key)
+    aws_secret_access_key="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    -u|--backup-url)
+    backup_url="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    -o|--output-file)
+    output_file="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    -f|--output-format)
+    output_format="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    -b|--backing-file)
+    backing_file="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    -v|--version)
+    version="$2"
+    shift # past argument
+    shift # past value
+    ;;
+    -h|--help)
+    usage
+    exit 0
+    shift
+    ;;
+    *)
+    error_invalid_params
+    ;;
+    esac
+done
+
+# Check the required parameters exits
+if [ -z "${backup_url}" ] || [ -z "${output_file}" ] || [ -z "${output_format}" ] || [ -z "${version}" ]; then
+      error_invalid_params
+fi
+if [[ "${backup_url}" =~ ^[Ss]3 ]]; then
+  if [ -z "${aws_access_key}" ] || [ -z "${aws_secret_access_key}" ]; then
+      error_invalid_params
+  fi
+fi
+
+# Compose the docker arguments
+if [[ "${backup_url}" =~ ^[Ss]3 ]]; then
+  CUSTOMIZED_ARGS="-e AWS_ACCESS_KEY_ID="${aws_access_key}" -e AWS_SECRET_ACCESS_KEY="${aws_secret_access_key}" "
+else
+  CUSTOMIZED_ARGS="--cap-add SYS_ADMIN --security-opt apparmor:unconfined"
+fi
+
+# Start restoring a backup to an image file. 
+docker run ${CUSTOMIZED_ARGS} -v /tmp/restore:/tmp/restore \
+            longhornio/longhorn-engine:"${version}" longhorn backup \
+            restore-to-file ""${backup_url}"" \
+            --output-file "/tmp/restore/${output_file}" \
+            --output-format "${output_format}" \
+            --backing-file "${backing_file}"

scripts/update-manifests-dev-version.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+
+# Example:
+#   ./scripts/update-manifests-dev-version.sh 1.3.0 1.4.0
+#
+# Result:
+#   Chart version will be updated to 1.4.0-dev
+#   Images (manager, engine, ui) will be updated to master-head
+#
+
+set -o errexit
+set -o nounset
+
+PRJ_DIR=$(readlink -f "$(dirname "${BASH_SOURCE[0]}")/.." 2>/dev/null || realpath "$(dirname "${BASH_SOURCE[0]}")/.." 2>/dev/null)
+CURRENT_VERSION=${CURRENT_VERSION:-$1}
+NEW_VERSION=${NEW_VERSION:-$2}-dev
+
+mapfile -t manifests < <(find "$PRJ_DIR" -type f -a \( -name '*.yaml' -o -name 'longhorn-images.txt' \))
+
+if [[ ${#manifests[@]} -le 0 ]]; then
+  echo "No manifests found to update from $PRJ_DIR" >/dev/stderr
+  exit 1
+fi
+
+echo "Updating $CURRENT_VERSION -> $NEW_VERSION-dev with master-head images in below manifests"
+for f in "${manifests[@]}"; do
+  f_name=$(basename "$f")
+
+  if [[ $f_name == "Chart.yaml" ]]; then
+    sed -i "s#\(version: \)${CURRENT_VERSION}#\1${NEW_VERSION}#g" "$f"
+    sed -i "s#\(appVersion: v\)${CURRENT_VERSION}#\1${NEW_VERSION}#g" "$f"
+  else
+    sed -i "s#\(:\s*\)v${CURRENT_VERSION}#\1master-head#g" "$f"
+  fi
+
+  echo "$f updated"
+done
+
+. "$PRJ_DIR"/scripts/generate-longhorn-yaml.sh

uninstall/uninstall.yaml

@@ -61,7 +61,7 @@ rules:
     resources: ["priorityclasses"]
     verbs: ["watch", "list"]
   - apiGroups: ["storage.k8s.io"]
-    resources: ["csidrivers", "storageclasses"]
+    resources: ["csidrivers", "storageclasses", "volumeattachments"]
     verbs: ["*"]
   - apiGroups: ["longhorn.io"]
     resources: ["volumes", "engines", "replicas", "settings", "engineimages", "nodes", "instancemanagers", "sharemanagers",
@@ -106,7 +106,7 @@ spec:
     spec:
       containers:
       - name: longhorn-uninstall
-        image: longhornio/longhorn-manager:v1.3.0
+        image: longhornio/longhorn-manager:v1.3.3-rc2
         imagePullPolicy: IfNotPresent
         securityContext:
           privileged: true