Merge pull request rook#16922 from subhamkrai/remove-fencing-obsolete-code

csi: remove automated node fencing code

Author: subhamkrai

Documentation/Storage-Configuration/Block-Storage-RBD/block-storage.md

@@ -196,7 +196,7 @@ The erasure coded pool must be set as the `dataPool` parameter in
 
 ## Node Loss
 
-If a node goes down where a pod is running where a RBD RWO volume is mounted, the volume cannot automatically be mounted on another node. The node must be guaranteed to be offline before the volume can be mounted on another node.
+If a node goes down where a pod is running where a volume is mounted, the volume cannot automatically be mounted on another node. The node must be guaranteed to be offline before the volume can be mounted on another node.
 
 
 ### Handling Node Loss
@@ -209,7 +209,7 @@ kubectl taint nodes <node-name> node.kubernetes.io/out-of-service=nodeshutdown:N
 kubectl taint nodes <node-name> node.kubernetes.io/out-of-service=nodeshutdown:NoSchedule
 ```
 
-After the taint is added to the node, the CephCSI driver will automatically handle the network fencing to prevent connections to Ceph from the RBD volume on that node.
+After the taint is added to the node, the CephCSI driver will automatically handle the network fencing to prevent connections to Ceph from the volume on that node.
 
 ### Node Recovery
 

deploy/examples/operator-openshift.yaml

@@ -567,8 +567,6 @@ data:
   ROOK_CEPH_COMMANDS_TIMEOUT_SECONDS: "15"
   # Enable the csi addons sidecar.
   CSI_ENABLE_CSIADDONS: "false"
-  # Enable watch for faster recovery from rbd rwo node loss
-  ROOK_WATCH_FOR_NODE_FAILURE: "true"
   # ROOK_CSIADDONS_IMAGE: "quay.io/csiaddons/k8s-sidecar:v0.14.0"
   # The GCSI RPC timeout value (in seconds). It should be >= 120. If this variable is not set or is an invalid value, it's default to 150.
   CSI_GRPC_TIMEOUT_SECONDS: "150"

deploy/examples/operator.yaml

@@ -509,8 +509,6 @@ data:
   ROOK_CEPH_COMMANDS_TIMEOUT_SECONDS: "15"
   # Enable the csi addons sidecar.
   CSI_ENABLE_CSIADDONS: "false"
-  # Enable watch for faster recovery from rbd rwo node loss
-  ROOK_WATCH_FOR_NODE_FAILURE: "true"
   # ROOK_CSIADDONS_IMAGE: "quay.io/csiaddons/k8s-sidecar:v0.14.0"
   # The CSI GRPC timeout value (in seconds). It should be >= 120. If this variable is not set or is an invalid value, it's default to 150.
   CSI_GRPC_TIMEOUT_SECONDS: "150"

design/ceph/node-loss-rbd-cephfs.md

@@ -43,7 +43,6 @@ import (
 	corev1 "k8s.io/api/core/v1"
 	kerrors "k8s.io/apimachinery/pkg/api/errors"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-	"k8s.io/apimachinery/pkg/labels"
 	apituntime "k8s.io/apimachinery/pkg/runtime"
 	"k8s.io/apimachinery/pkg/types"
 	"k8s.io/client-go/tools/record"
@@ -501,38 +500,6 @@ func (c *ClusterController) requestClusterDelete(clusterObj *cephv1.CephCluster)
 			return reconcile.Result{}, nil // do not requeue the delete
 		}
 	}
-	_, err := c.context.ApiExtensionsClient.ApiextensionsV1().CustomResourceDefinitions().Get(c.OpManagerCtx, "networkfences.csiaddons.openshift.io", metav1.GetOptions{})
-	if err == nil {
-		log.NamespacedInfo(clusterObj.Namespace, logger, "removing networkFence if matching cephCluster UID found")
-		networkFenceList := &addonsv1alpha1.NetworkFenceList{}
-		labelSelector := labels.SelectorFromSet(map[string]string{
-			networkFenceLabel: string(clusterObj.GetUID()),
-		})
-
-		opts := []client.DeleteAllOfOption{
-			client.MatchingLabels{
-				networkFenceLabel: string(clusterObj.GetUID()),
-			},
-			client.GracePeriodSeconds(0),
-		}
-		err = c.client.DeleteAllOf(c.OpManagerCtx, &addonsv1alpha1.NetworkFence{}, opts...)
-		if err != nil && !kerrors.IsNotFound(err) {
-			return reconcile.Result{}, errors.Wrapf(err, "failed to delete networkFence with label %s", networkFenceLabel)
-		}
-
-		err = c.client.List(c.OpManagerCtx, networkFenceList, &client.MatchingLabelsSelector{Selector: labelSelector})
-		if err != nil && !kerrors.IsNotFound(err) {
-			return reconcile.Result{}, errors.Wrap(err, "failed to list networkFence")
-		}
-		if len(networkFenceList.Items) > 0 {
-			for i := range networkFenceList.Items {
-				err = opcontroller.RemoveFinalizerWithName(c.OpManagerCtx, c.client, &networkFenceList.Items[i], "csiaddons.openshift.io/network-fence")
-				if err != nil {
-					return reconcile.Result{}, errors.Wrap(err, "failed to remove finalizer")
-				}
-			}
-		}
-	}
 
 	log.NamespacedInfo(clusterObj.Namespace, logger, "cleaning up CephCluster %q", nsName)
 	if existingCluster != nil {