From 19f81bf1f0062f6f17acb303bea9f726c3361699 Mon Sep 17 00:00:00 2001 From: subhamkrai Date: Fri, 10 Jan 2025 15:54:32 +0530 Subject: [PATCH] Revert "csi: disable fencing in Rook" This reverts commit 4d38c60a1f7e44ec3706c917d1317db0a7d8d6f1. --- .../Block-Storage-RBD/block-storage.md | 7 ++----- Documentation/Troubleshooting/ceph-csi-common-issues.md | 3 +++ pkg/operator/ceph/cluster/watcher.go | 6 +++--- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/Documentation/Storage-Configuration/Block-Storage-RBD/block-storage.md b/Documentation/Storage-Configuration/Block-Storage-RBD/block-storage.md index 54a1fb89b219..5ce95ead3c4d 100644 --- a/Documentation/Storage-Configuration/Block-Storage-RBD/block-storage.md +++ b/Documentation/Storage-Configuration/Block-Storage-RBD/block-storage.md @@ -196,6 +196,8 @@ The erasure coded pool must be set as the `dataPool` parameter in 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. +!!! Note + These instructions are for clusters with Kubernetes version 1.26 or greater. For K8s 1.25 or older, see the [manual steps in the CSI troubleshooting guide](../../Troubleshooting/ceph-csi-common-issues.md#node-loss) to recover from the node loss. ### Configure CSI-Addons @@ -215,11 +217,6 @@ kubectl patch cm rook-ceph-operator-config -n -p $'data:\n "CSI_ENABL ### Handling Node Loss -!!! warning - Automated node loss handling is currently disabled, please refer to the [manual steps](../../Troubleshooting/ceph-csi-common-issues.md#node-loss) to recover from the node loss. - We are actively working on a new design for this feature. - For more details see the [tracking issue](https://github.com/rook/rook/issues/14832). - When a node is confirmed to be down, add the following taints to the node: ```console diff --git a/Documentation/Troubleshooting/ceph-csi-common-issues.md b/Documentation/Troubleshooting/ceph-csi-common-issues.md index 11ab1765b688..fa8ce8af5c07 100644 --- a/Documentation/Troubleshooting/ceph-csi-common-issues.md +++ b/Documentation/Troubleshooting/ceph-csi-common-issues.md @@ -413,6 +413,9 @@ Where `-m` is one of the mon endpoints and the `--key` is the key used by the CS When a node is lost, you will see application pods on the node stuck in the `Terminating` state while another pod is rescheduled and is in the `ContainerCreating` state. +!!! important + For clusters with Kubernetes version 1.26 or greater, see the [improved automation](../Storage-Configuration/Block-Storage-RBD/block-storage.md#recover-rbd-rwo-volume-in-case-of-node-loss) to recover from the node loss. If using K8s 1.25 or older, continue with these instructions. + ### Force deleting the pod To force delete the pod stuck in the `Terminating` state: diff --git a/pkg/operator/ceph/cluster/watcher.go b/pkg/operator/ceph/cluster/watcher.go index b117994ccbee..4f899450e61e 100644 --- a/pkg/operator/ceph/cluster/watcher.go +++ b/pkg/operator/ceph/cluster/watcher.go @@ -90,9 +90,9 @@ func (c *clientCluster) onK8sNode(ctx context.Context, object runtime.Object) bo cluster := c.getCephCluster() // Continue reconcile in case of failure too since we don't want to block other node reconcile - // if err := c.handleNodeFailure(ctx, cluster, node, opNamespace); err != nil { - // logger.Errorf("failed to handle node failure. %v", err) - // } + if err := c.handleNodeFailure(ctx, cluster, node); err != nil { + logger.Errorf("failed to handle node failure. %v", err) + } // skip reconcile if node is already checked in a previous reconcile if nodesCheckedForReconcile.Has(node.Name) {