Optimize the docs and filename for blacklist function

Author: yansun1996

api/v1alpha1/deviceconfig_types.go

@@ -94,7 +94,9 @@ type DriverSpec struct {
 	// +kubebuilder:default=true
 	Enable *bool `json:"enable,omitempty"`
 
-	// blacklist amdgpu drivers on the host
+	// blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+	// Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+	// Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
 	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="BlacklistDrivers",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:blacklistDrivers"}
 	Blacklist *bool `json:"blacklist,omitempty"`
 

bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml

@@ -30,7 +30,7 @@ metadata:
         }
       ]
     capabilities: Basic Install
-    createdAt: "2025-03-25T06:19:27Z"
+    createdAt: "2025-03-26T20:10:59Z"
     operatorframework.io/suggested-namespace: openshift-amd-gpu
     operators.operatorframework.io/builder: operator-sdk-v1.32.0
     operators.operatorframework.io/project_layout: go.kubebuilder.io/v3
@@ -229,7 +229,10 @@ spec:
         path: driver.amdgpuInstallerRepoURL
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:amdgpuInstallerRepoURL
-      - description: blacklist amdgpu drivers on the host
+      - description: blacklist amdgpu drivers on the host. Node reboot is required
+          to apply the baclklist on the worker nodes. Not working for OpenShift cluster.
+          OpenShift users please use the Machine Config Operator (MCO) resource to
+          configure amdgpu blacklist. Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
         displayName: BlacklistDrivers
         path: driver.blacklist
         x-descriptors:

bundle/manifests/amd.com_deviceconfigs.yaml

@@ -342,7 +342,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true

config/crd/bases/amd.com_deviceconfigs.yaml

@@ -338,7 +338,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true

config/manifests/bases/amd-gpu-operator.clusterserviceversion.yaml

@@ -200,7 +200,10 @@ spec:
         path: driver.amdgpuInstallerRepoURL
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:amdgpuInstallerRepoURL
-      - description: blacklist amdgpu drivers on the host
+      - description: blacklist amdgpu drivers on the host. Node reboot is required
+          to apply the baclklist on the worker nodes. Not working for OpenShift cluster.
+          OpenShift users please use the Machine Config Operator (MCO) resource to
+          configure amdgpu blacklist. Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
         displayName: BlacklistDrivers
         path: driver.blacklist
         x-descriptors:

helm-charts-k8s/Chart.lock

@@ -6,4 +6,4 @@ dependencies:
   repository: file://./charts/kmm
   version: v1.0.0
 digest: sha256:f9a315dd2ce3d515ebf28c8e9a6a82158b493ca2686439ec381487761261b597
-generated: "2025-03-25T06:19:17.248998622Z"
+generated: "2025-03-26T20:10:45.247725094Z"

helm-charts-k8s/crds/deviceconfig-crd.yaml

@@ -346,7 +346,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true

helm-charts-openshift/Chart.lock

@@ -6,4 +6,4 @@ dependencies:
   repository: file://./charts/kmm
   version: v1.0.0
 digest: sha256:25200c34a5cc846a1275e5bf3fc637b19e909dc68de938189c5278d77d03f5ac
-generated: "2025-03-25T06:19:26.060856628Z"
+generated: "2025-03-26T20:10:56.781691243Z"

helm-charts-openshift/crds/deviceconfig-crd.yaml

@@ -346,7 +346,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true

internal/nodelabeller/nodelabeller.go

@@ -52,6 +52,8 @@ const (
 	defaultNodeLabellerImage    = "rocm/k8s-device-plugin:labeller-latest"
 	defaultUbiNodeLabellerImage = "rocm/k8s-node-labeller:rhubi-latest"
 	defaultInitContainerImage   = "busybox:1.36"
+	defaultBlacklistFileName    = "blacklist-amdgpu.conf"
+	openShiftBlacklistFileName  = "blacklist-amdgpu-by-operator.conf"
 )
 
 //go:generate mockgen -source=nodelabeller.go -package=nodelabeller -destination=mock_nodelabeller.go NodeLabeller
@@ -129,15 +131,19 @@ func (nl *nodeLabeller) SetNodeLabellerAsDesired(ds *appsv1.DaemonSet, devConfig
 		},
 	}
 
-	var initContainerCommand []string
+	blackListFileName := defaultBlacklistFileName
+	if nl.isOpenShift {
+		blackListFileName = openShiftBlacklistFileName
+	}
 
+	var initContainerCommand []string
 	if devConfig.Spec.Driver.Blacklist != nil && *devConfig.Spec.Driver.Blacklist {
 		// if users want to apply the blacklist, init container will add the amdgpu to the blacklist
-		initContainerCommand = []string{"sh", "-c", "echo \"# added by gpu operator \nblacklist amdgpu\" > /host-etc/modprobe.d/blacklist-amdgpu.conf; while [ ! -d /host-sys/class/kfd ] || [ ! -d /host-sys/module/amdgpu/drivers/ ]; do echo \"amdgpu driver is not loaded \"; sleep 2 ;done"}
+		initContainerCommand = []string{"sh", "-c", fmt.Sprintf("echo \"# added by gpu operator \nblacklist amdgpu\" > /host-etc/modprobe.d/%v; while [ ! -d /host-sys/class/kfd ] || [ ! -d /host-sys/module/amdgpu/drivers/ ]; do echo \"amdgpu driver is not loaded \"; sleep 2 ;done", blackListFileName)}
 	} else {
 		// if users disabled the KMM driver, or disabled the blacklist
 		// init container will remove any hanging amdgpu blacklist entry from the list
-		initContainerCommand = []string{"sh", "-c", "rm -f /host-etc/modprobe.d/blacklist-amdgpu.conf; while [ ! -d /host-sys/class/kfd ] || [ ! -d /host-sys/module/amdgpu/drivers/ ]; do echo \"amdgpu driver is not loaded \"; sleep 2 ;done"}
+		initContainerCommand = []string{"sh", "-c", fmt.Sprintf("rm -f /host-etc/modprobe.d/%v; while [ ! -d /host-sys/class/kfd ] || [ ! -d /host-sys/module/amdgpu/drivers/ ]; do echo \"amdgpu driver is not loaded \"; sleep 2 ;done", blackListFileName)}
 	}
 
 	initContainerImage := defaultInitContainerImage