Merge pull request #1740 from dankova22/release-2.1.15

Release 2.1.15

Author: k8s-ci-robot

Dockerfile

@@ -38,7 +38,7 @@ RUN mkdir -p /tmp/rpms && \
     then echo "Installing efs-utils from Amazon Linux 2 yum repo" && \
          yum -y install --downloadonly --downloaddir=/tmp/rpms amazon-efs-utils-1.35.0-1.amzn2.noarch; \
     else echo "Installing efs-utils from github using the latest git tag" && \
-         yum -y install systemd git rpm-build make openssl-devel curl && \
+         yum -y install systemd git rpm-build make openssl-devel curl golang cmake && \
          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && \
          source $HOME/.cargo/env && \
          rustup update && \

OWNERS

@@ -11,3 +11,5 @@ approvers:
 - Ashley-wenyizha
 - mskanth972
 - seanzatzdev-amazon
+- dankova22
+- DavidXU12345

charts/aws-efs-csi-driver/templates/controller-serviceaccount.yaml

@@ -85,4 +85,33 @@ subjects:
 roleRef:
   kind: ClusterRole
   name: efs-csi-external-provisioner-role-describe-secrets
-  apiGroup: rbac.authorization.k8s.io
+  apiGroup: rbac.authorization.k8s.io
+{{- if .Values.controller.fileSystemIdRefs.enabled }}
+---
+# Permissions needed for pulling file system id
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: efs-csi-filesystem-id-reader-role
+  labels:
+    app.kubernetes.io/name: {{ include "aws-efs-csi-driver.name" . }}
+rules:
+  - apiGroups: [""]
+    resources: ["configmaps", "secrets"]
+    verbs: ["get"]
+---
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: efs-csi-filesystem-id-reader-role-binding
+  labels:
+    app.kubernetes.io/name: {{ include "aws-efs-csi-driver.name" . }}
+subjects:
+  - kind: ServiceAccount
+    name: {{ .Values.controller.serviceAccount.name }}
+    namespace: {{ .Release.Namespace }}
+roleRef:
+  kind: ClusterRole
+  name: efs-csi-filesystem-id-reader-role
+  apiGroup: rbac.authorization.k8s.io
+{{- end }}

charts/aws-efs-csi-driver/templates/storageclass.yaml

@@ -5,7 +5,7 @@ metadata:
   name: {{ .name }}
   {{- with .annotations }}
   annotations:
-  {{ toYaml . | indent 4 }}
+  {{- toYaml . | nindent 4 }}
   {{- end }}
 provisioner: efs.csi.aws.com
 {{- with .mountOptions }}

charts/aws-efs-csi-driver/values.yaml

@@ -136,6 +136,9 @@ controller:
   #    topologyKey: kubernetes.io/hostname
   #    whenUnsatisfiable: ScheduleAnyway
   topologySpreadConstraints: []
+  # Enable reading filesystem IDs from configmap/secret
+  fileSystemIdRefs:
+    enabled: false
 
 ## Node daemonset variables
 
@@ -219,8 +222,6 @@ storageClasses: []
 #   annotations:
 #     # Use that annotation if you want this to your default storageclass
 #     storageclass.kubernetes.io/is-default-class: "true"
-#   mountOptions:
-#   - tls
 #   parameters:
 #     provisioningMode: efs-ap
 #     fileSystemId: fs-1122aabb

cmd/main.go

@@ -47,6 +47,8 @@ func main() {
 		maxInflightMountCalls      = flag.Int64("max-inflight-mount-calls", driver.UnsetMaxInflightMountCounts, "New NodePublishVolume operation will be blocked if maximum number of inflight calls is reached. If maxInflightMountCallsOptIn is true, it has to be set to a positive value.")
 		volumeAttachLimitOptIn     = flag.Bool("volume-attach-limit-opt-in", false, "Opt in to use volume attach limit.")
 		volumeAttachLimit          = flag.Int64("volume-attach-limit", driver.UnsetVolumeAttachLimit, "Maximum number of volumes that can be attached to a node. If volumeAttachLimitOptIn is true, it has to be set to a positive value.")
+		forceUnmountAfterTimeout   = flag.Bool("force-unmount-after-timeout", false, "Enable force unmount if normal unmount times out during NodeUnpublishVolume.")
+		unmountTimeout             = flag.Duration("unmount-timeout", driver.DefaultUnmountTimeout, "Timeout for unmounting a volume during NodePublishVolume when forceUnmountAfterTimeout is true. If the timeout is reached, the volume will be forcibly unmounted. The default value is 30 seconds.")
 	)
 	klog.InitFlags(nil)
 	flag.Parse()
@@ -65,7 +67,7 @@ func main() {
 	if err != nil {
 		klog.Fatalln(err)
 	}
-	drv := driver.NewDriver(*endpoint, etcAmazonEfs, *efsUtilsStaticFilesPath, *tags, *volMetricsOptIn, *volMetricsRefreshPeriod, *volMetricsFsRateLimit, *deleteAccessPointRootDir, *adaptiveRetryMode, *maxInflightMountCallsOptIn, *maxInflightMountCalls, *volumeAttachLimitOptIn, *volumeAttachLimit)
+	drv := driver.NewDriver(*endpoint, etcAmazonEfs, *efsUtilsStaticFilesPath, *tags, *volMetricsOptIn, *volMetricsRefreshPeriod, *volMetricsFsRateLimit, *deleteAccessPointRootDir, *adaptiveRetryMode, *maxInflightMountCallsOptIn, *maxInflightMountCalls, *volumeAttachLimitOptIn, *volumeAttachLimit, *forceUnmountAfterTimeout, *unmountTimeout)
 	if err := drv.Run(); err != nil {
 		klog.Fatalln(err)
 	}

deploy/kubernetes/base/node-daemonset.yaml

@@ -61,6 +61,8 @@ spec:
             - --max-inflight-mount-calls=10
             - --volume-attach-limit-opt-in=false
             - --volume-attach-limit=20
+            - --force-unmount-after-timeout=false
+            - --unmount-timeout=30s
           env:
             - name: CSI_ENDPOINT
               value: unix:/csi/csi.sock

docs/README.md

@@ -28,7 +28,9 @@ The following CSI interfaces are implemented:
 | Parameters            | Values | Default         | Optional | Description                                                                                                                                                                                                                                                                                                                                                                                   |
 |-----------------------|--------|-----------------|----------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | provisioningMode      | efs-ap |                 | false    | Type of volume provisioned by efs. Currently, Access Points are supported.                                                                                                                                                                                                                                                                                                                    |
-| fileSystemId          |        |                 | false    | File System under which access points are created.                                                                                                                                                                                                                                                                                                                                            | 
+| fileSystemId          |        |                 | true*    | File System under which access points are created. See footnote for usage details.                                                                                                                                                                                                                                             |
+| fileSystemIdConfigRef |        |                 | true*    | Reference to a ConfigMap containing the filesystem ID in format `namespace/name/key`. See footnote for usage details.                                                                                                                                                                                                           |
+| fileSystemIdSecretRef |        |                 | true*    | Reference to a Secret containing the filesystem ID in format `namespace/name/key`. See footnote for usage details.                                                                                                                                                                                                                |
 | directoryPerms        |        |                 | false    | Directory permissions for [Access Point root directory](https://docs.aws.amazon.com/efs/latest/ug/efs-access-points.html#enforce-root-directory-access-point) creation.                                                                                                                                                                                                                       |
 | uid                   |        |                 | true     | POSIX user Id to be applied for [Access Point root directory](https://docs.aws.amazon.com/efs/latest/ug/efs-access-points.html#enforce-root-directory-access-point) creation.                                                                                                                                                                                                                 |
 | gid                   |        |                 | true     | POSIX group Id to be applied for [Access Point root directory](https://docs.aws.amazon.com/efs/latest/ug/efs-access-points.html#enforce-root-directory-access-point) creation.                                                                                                                                                                                                                |
@@ -38,9 +40,10 @@ The following CSI interfaces are implemented:
 | subPathPattern        |        | `/${.PV.name}`  | true     | The template used to construct the subPath under which each of the access points created under Dynamic Provisioning. Can be made up of fixed strings and limited variables, is akin to the 'subPathPattern' variable on the [nfs-subdir-external-provisioner](https://github.com/kubernetes-sigs/nfs-subdir-external-provisioner) chart. Supports `.PVC.name`,`.PVC.namespace` and `.PV.name` |
 | ensureUniqueDirectory |        | true            | true     | **NOTE: Only set this to false if you're sure this is the behaviour you want**.<br/> Used when dynamic provisioning is enabled, if set to true, appends the a UID to the pattern specified in `subPathPattern` to ensure that access points will not accidentally point at the same directory.                                                                                                |
 | az                    |        | ""              | true     | Used for cross-account mount. `az` under storage class parameter is optional. If specified, mount target associated with the az will be used for cross-account mount. If not specified, a random mount target will be picked for cross account mount                                                                                                                                          |
-| reuseAccessPoint      |        | false           | true     | When set to true, it creates the Access Point client-token from the provided PVC name. So that the AccessPoint can be replicated from a different cluster if same PVC name and storageclass configuration are used.                                                                                                                                                                                    |
+| reuseAccessPoint      |        | false           | true     | When set to true, it creates the Access Point client-token from the provided PVC name. So that the AccessPoint can be replicated from a different cluster if same PVC name and storageclass configuration are used. This feature is currently only supported for a single filesystem per account/region. If attempting to reuse access points across multiple clusters and filesystems within the same region, volume provisioning will fail. If you wish to use the same EFS accesspoint across different clusters for multiple filesystems in a single region, we recommend manually creating the access points and [statically provisioning](https://github.com/kubernetes-sigs/aws-efs-csi-driver/tree/master/examples/kubernetes/access_points) those volumes.                                                                                                                                                                            |
 
 **Note**
+* **Filesystem ID Source (marked with \*)**: Exactly one of `fileSystemId`, `fileSystemIdConfigRef`, or `fileSystemIdSecretRef` must be specified to provide the EFS filesystem ID. For detailed usage guide, see the [ConfigMap and Secret Resolution Guide](./filesystem-id-resolution.md).
 * Custom Posix group Id range for Access Point root directory must include both `gidRangeStart` and `gidRangeEnd` parameters. These parameters are optional only if both are omitted. If you specify one, the other becomes mandatory.
 * When using a custom Posix group ID range, there is a possibility for the driver to run out of available POSIX group Ids. We suggest ensuring custom group ID range is large enough or create a new storage class with a new file system to provision additional volumes. 
 * `az` under storage class parameter is not be confused with efs-utils mount option `az`. The `az` mount option is used for cross-az mount or efs one zone file system mount within the same aws account as the cluster.
@@ -49,6 +52,7 @@ The following CSI interfaces are implemented:
  * The uid/gid configured on the access point is either the uid/gid specified in the storage class, a value in the gidRangeStart-gidRangeEnd (used as both uid/gid) specified in the storage class, or is a value selected by the driver is no uid/gid or gidRange is specified.
  * We suggest using [static provisioning](https://github.com/kubernetes-sigs/aws-efs-csi-driver/blob/master/examples/kubernetes/static_provisioning/README.md) if you do not wish to use user identity enforcement.
 
+---
 If you want to pass any other mountOptions to Amazon EFS CSI driver while mounting, they can be passed in through the Persistent Volume or the Storage Class objects, depending on whether static or dynamic provisioning is used. The following are examples of some mountOptions that can be passed:
 * **lookupcache**: Specifies how the kernel manages its cache of directory entries for a given mount point. Mode can be one of all, none, pos, or positive. Each mode has different functions and for more information you can refer to this [link](https://linux.die.net/man/5/nfs).
 * **iam**: Use the CSI Node Pod's IAM identity to authenticate with Amazon EFS.
@@ -171,7 +175,7 @@ You can find previous efs-csi-driver versions' images from [here](https://galler
 
 ### Features
 * Static provisioning - Amazon EFS file system needs to be created manually first, then it could be mounted inside container as a persistent volume (PV) using the driver.
-* Dynamic provisioning - Uses a persistent volume claim (PVC) to dynamically provision a persistent volume (PV). On Creating a PVC, kuberenetes requests Amazon EFS to create an Access Point in a file system which will be used to mount the PV.
+* Dynamic provisioning - Uses a persistent volume claim (PVC) to dynamically provision a persistent volume (PV). On Creating a PVC, Kubernetes requests Amazon EFS to create an Access Point in a file system which will be used to mount the PV.
 * Mount Options - Mount options can be specified in the persistent volume (PV) or storage class for dynamic provisioning to define how the volume should be mounted.
 * Encryption of data in transit - Amazon EFS file systems are mounted with encryption in transit enabled by default in the master branch version of the driver.
 * Cross account mount - Amazon EFS file systems from different aws accounts can be mounted from an Amazon EKS cluster.
@@ -359,6 +363,11 @@ After deploying the driver, you can continue to these sections:
 | max-inflight-mount-calls   |        | -1       | true     | New NodePublishVolume operation will be blocked if maximum number of inflight calls is reached. If maxInflightMountCallsOptIn is true, it has to be set to a positive value.                                                                                                                                                                                  |
 | volume-attach-limit-opt-in   |        | false       | true     | Opt in to use volume attach limit.                                                                                                                                                                                   |
 | volume-attach-limit   |        |  -1      | true     | Maximum number of volumes that can be attached to a node. If volumeAttachLimitOptIn is true, it has to be set to a positive value.                                                                                                                                                                 |
+| force-unmount-after-timeout   |        |  false      | true     | Enable force unmount if normal unmount times out during NodeUnpublishVolume                                                                                                                                                                 |
+| unmount-timeout   |        |  30s      | true     | Timeout for unmounting a volume during NodePublishVolume when forceUnmountAfterTimeout is true. If the timeout is reached, the volume will be forcibly unmounted. The default value is 30 seconds.                                                                                                                                                                 |
+
+#### Force Unmount After Timeout
+The `force-unmount-after-timeout` feature addresses issues when `NodeUnpublishVolume` gets called infinite times and hangs indefinitely due to broken NFS connections. When enabled, if a normal unmount operation exceeds the configured timeout, the driver will forcibly unmount the volume to prevent indefinite hanging and allow the operation to complete.
 
 #### Suggestion for setting max-inflight-mount-calls and volume-attach-limit
 

docs/filesystem-id-resolution.md

@@ -0,0 +1,40 @@
+# Dynamic Filesystem ID Resolution
+
+The EFS CSI driver supports dynamic filesystem ID resolution from Kubernetes ConfigMaps and Secrets. This enables workflows where tools provision EFS filesystems and write the filesystem ID to Kubernetes resources, which the CSI driver reads automatically during volume provisioning.
+
+**Reference Format:** `namespace/name/key`
+
+**Parameter Requirements:** Exactly one of `fileSystemId`, `fileSystemIdConfigRef`, or `fileSystemIdSecretRef` must be specified in StorageClass parameters.
+
+**Example with ConfigMap:**
+```yaml
+# ConfigMap created
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: efs-config
+  namespace: kube-system
+data:
+  fileSystemId: fs-02604354c13d0316d
+---
+# StorageClass references the ConfigMap
+kind: StorageClass
+apiVersion: storage.k8s.io/v1
+metadata:
+  name: efs-sc
+provisioner: efs.csi.aws.com
+parameters:
+  provisioningMode: efs-ap
+  fileSystemIdConfigRef: "kube-system/efs-config/fileSystemId"
+  directoryPerms: "700"
+```
+
+**Enabling RBAC Permissions (Required):**
+
+This feature requires additional RBAC permissions for the controller service account to read ConfigMaps and Secrets. When installing via Helm, enable with:
+```bash
+helm install aws-efs-csi-driver ./charts/aws-efs-csi-driver \
+  --set controller.fileSystemIdRefs.enabled=true
+```
+
+For static manifest installations, manually apply the RBAC resources from the Helm chart templates. 

examples/kubernetes/access_points/README.md

@@ -84,7 +84,6 @@ Also you can verify that data is written into the EFS filesystems:
 ```
 spec:
   mountOptions:
-    - tls
     - accesspoint=fsap-068c22f0246419f75
 ```
 as this could subject you to