Issue 8032: make node agent configMap name configurable

changelogs/unreleased/8097-Lyndon-Li

@@ -0,0 +1 @@
+Fix issue #8032, make node-agent configMap name configurable

pkg/cmd/cli/nodeagent/server.go

@@ -84,6 +84,7 @@
 	metricsAddress          string
 	resourceTimeout         time.Duration
 	dataMoverPrepareTimeout time.Duration
+	nodeAgentConfig         string
 }
 
 func NewServerCommand(f client.Factory) *cobra.Command {
@@ -120,6 +121,7 @@
 	command.Flags().DurationVar(&config.resourceTimeout, "resource-timeout", config.resourceTimeout, "How long to wait for resource processes which are not covered by other specific timeout parameters. Default is 10 minutes.")
 	command.Flags().DurationVar(&config.dataMoverPrepareTimeout, "data-mover-prepare-timeout", config.dataMoverPrepareTimeout, "How long to wait for preparing a DataUpload/DataDownload. Default is 30 minutes.")
 	command.Flags().StringVar(&config.metricsAddress, "metrics-address", config.metricsAddress, "The address to expose prometheus metrics")
+	command.Flags().StringVar(&config.nodeAgentConfig, "node-agent-config", config.nodeAgentConfig, "The name of configMap containing node-agent configurations.")
 
 	return command
 }
@@ -463,14 +465,14 @@
 var getConfigsFunc = nodeagent.GetConfigs
 
 func (s *nodeAgentServer) getDataPathConfigs() {
-	configs, err := getConfigsFunc(s.ctx, s.namespace, s.kubeClient)
-	if err != nil {
-		s.logger.WithError(err).Warn("Failed to get node agent configs")
+	if s.config.nodeAgentConfig == "" {
+		s.logger.Info("No node-agent configMap is specified")
 		return
 	}
 
-	if configs == nil {
-		s.logger.Infof("Node agent configs are not found")
+	configs, err := getConfigsFunc(s.ctx, s.namespace, s.kubeClient, s.config.nodeAgentConfig)
+	if err != nil {
+		s.logger.WithError(err).Warnf("Failed to get node agent configs from configMap %s, ignore it", s.config.nodeAgentConfig)
 		return
 	}
 

pkg/cmd/cli/nodeagent/server_test.go

@@ -17,12 +17,12 @@ package nodeagent
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"os"
 	"path/filepath"
 	"testing"
 
-	"github.com/pkg/errors"
 	"github.com/stretchr/testify/assert"
 	corev1 "k8s.io/api/core/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
@@ -122,28 +122,36 @@ func Test_getDataPathConfigs(t *testing.T) {
 
 	tests := []struct {
 		name          string
-		getFunc       func(context.Context, string, kubernetes.Interface) (*nodeagent.Configs, error)
+		getFunc       func(context.Context, string, kubernetes.Interface, string) (*nodeagent.Configs, error)
+		configMapName string
 		expectConfigs *nodeagent.Configs
 		expectLog     string
 	}{
 		{
-			name: "failed to get configs",
-			getFunc: func(context.Context, string, kubernetes.Interface) (*nodeagent.Configs, error) {
+			name:      "no config specified",
+			expectLog: "No node-agent configMap is specified",
+		},
+		{
+			name:          "failed to get configs",
+			configMapName: "node-agent-config",
+			getFunc: func(context.Context, string, kubernetes.Interface, string) (*nodeagent.Configs, error) {
 				return nil, errors.New("fake-get-error")
 			},
-			expectLog: "Failed to get node agent configs",
+			expectLog: "Failed to get node agent configs from configMap node-agent-config, ignore it",
 		},
 		{
-			name: "configs cm not found",
-			getFunc: func(context.Context, string, kubernetes.Interface) (*nodeagent.Configs, error) {
-				return nil, nil
+			name:          "configs cm not found",
+			configMapName: "node-agent-config",
+			getFunc: func(context.Context, string, kubernetes.Interface, string) (*nodeagent.Configs, error) {
+				return nil, errors.New("fake-not-found-error")
 			},
-			expectLog: "Node agent configs are not found",
+			expectLog: "Failed to get node agent configs from configMap node-agent-config, ignore it",
 		},
 
 		{
-			name: "succeed",
-			getFunc: func(context.Context, string, kubernetes.Interface) (*nodeagent.Configs, error) {
+			name:          "succeed",
+			configMapName: "node-agent-config",
+			getFunc: func(context.Context, string, kubernetes.Interface, string) (*nodeagent.Configs, error) {
 				return configs, nil
 			},
 			expectConfigs: configs,
@@ -155,6 +163,9 @@ func Test_getDataPathConfigs(t *testing.T) {
 			logBuffer := ""
 
 			s := &nodeAgentServer{
+				config: nodeAgentServerConfig{
+					nodeAgentConfig: test.configMapName,
+				},
 				logger: testutil.NewSingleLogger(&logBuffer),
 			}
 

pkg/nodeagent/node_agent.go

@@ -34,8 +34,7 @@ import (
 
 const (
 	// daemonSet is the name of the Velero node agent daemonset.
-	daemonSet  = "node-agent"
-	configName = "node-agent-config"
+	daemonSet = "node-agent"
 )
 
 var (
@@ -121,14 +120,10 @@ func GetPodSpec(ctx context.Context, kubeClient kubernetes.Interface, namespace
 	return &ds.Spec.Template.Spec, nil
 }
 
-func GetConfigs(ctx context.Context, namespace string, kubeClient kubernetes.Interface) (*Configs, error) {
+func GetConfigs(ctx context.Context, namespace string, kubeClient kubernetes.Interface, configName string) (*Configs, error) {
 	cm, err := kubeClient.CoreV1().ConfigMaps(namespace).Get(ctx, configName, metav1.GetOptions{})
 	if err != nil {
-		if apierrors.IsNotFound(err) {
-			return nil, nil
-		} else {
-			return nil, errors.Wrapf(err, "error to get node agent configs %s", configName)
-		}
+		return nil, errors.Wrapf(err, "error to get node agent configs %s", configName)
 	}
 
 	if cm.Data == nil {

pkg/nodeagent/node_agent_test.go

@@ -254,10 +254,6 @@ func TestGetConfigs(t *testing.T) {
 		expectResult  *Configs
 		expectErr     string
 	}{
-		{
-			name:      "cm is not found",
-			namespace: "fake-ns",
-		},
 		{
 			name:      "cm get error",
 			namespace: "fake-ns",
@@ -318,7 +314,7 @@ func TestGetConfigs(t *testing.T) {
 				fakeKubeClient.Fake.PrependReactor(reactor.verb, reactor.resource, reactor.reactorFunc)
 			}
 
-			result, err := GetConfigs(context.TODO(), test.namespace, fakeKubeClient)
+			result, err := GetConfigs(context.TODO(), test.namespace, fakeKubeClient, "node-agent-config")
 			if test.expectErr == "" {
 				assert.NoError(t, err)
 

site/content/docs/main/data-movement-backup-node-selection.md

@@ -11,12 +11,12 @@ Velero data movement backup supports to constrain the nodes where it runs. This
 - Constrain the data movement backup to run in specific nodes because these nodes have more resources than others  
 - Constrain the data movement backup to run in specific nodes because the storage allows volume/snapshot provisions in these nodes only  
 
-Velero introduces a new section in ```node-agent-config``` configMap, called ```loadAffinity```, through which you can specify the nodes to/not to run data movement backups, in the affinity and anti-affinity flavors.  
-If it is not there, ```node-agent-config``` should be created manually. The configMap should be in the same namespace where Velero is installed. If multiple Velero instances are installed in different namespaces, there should be one configMap in each namespace which applies to node-agent in that namespace only.  
+Velero introduces a new section in the node-agent configMap, called ```loadAffinity```, through which you can specify the nodes to/not to run data movement backups, in the affinity and anti-affinity flavors.  
+If it is not there, a configMap should be created manually. The configMap should be in the same namespace where Velero is installed. If multiple Velero instances are installed in different namespaces, there should be one configMap in each namespace which applies to node-agent in that namespace only. The name of the configMap should be specified in the node-agent server parameter ```--node-agent-config```.  
 Node-agent server checks these configurations at startup time. Therefore, you could edit this configMap any time, but in order to make the changes effective, node-agent server needs to be restarted.  
 
 ### Sample
-Here is a sample of the ```node-agent-config``` configMap with ```loadAffinity```:
+Here is a sample of the configMap with ```loadAffinity```:
 ```json
 {
     "loadAffinity": [
@@ -50,6 +50,21 @@ To create the configMap, save something like the above sample to a json file and
 kubectl create cm node-agent-config -n velero --from-file=<json file name>
 ```
 
+To provide the configMap to node-agent, edit the node-agent daemonset and add the ```- --node-agent-config``` argument to the spec:
+1. Open the node-agent daemonset spec  
+```
+kubectl edit ds node-agent -n velero
+```
+2. Add ```- --node-agent-config``` to ```spec.template.spec.containers```  
+```
+spec:
+  template:
+    spec:
+      containers:
+      - args:
+        - --node-agent-config=<configMap name>
+```
+
 ### Affinity
 Affinity configuration means allowing the data movement backup to run in the nodes specified. There are two ways to define it:
 -  It could be defined by `MatchLabels`. The labels defined in `MatchLabels` means a `LabelSelectorOpIn` operation by default, so in the current context, they will be treated as affinity rules. In the above sample, it defines to run data movement backups in nodes with label `beta.kubernetes.io/instance-type` of value `Standard_B4ms` (Run data movement backups in `Standard_B4ms` nodes only).    

site/content/docs/main/node-agent-concurrency.md

@@ -8,7 +8,7 @@ Varying from the data size, data complexity, resource availability, the tasks ma
 
 Node-agent concurrency configurations allow you to configure the concurrent number of node-agent loads per node. When the resources are sufficient in nodes, you can set a large concurrent number, so as to reduce the backup/restore time; otherwise, the concurrency should be reduced, otherwise, the backup/restore may encounter problems, i.e., time lagging, hang or OOM kill.  
 
-To set Node-agent concurrency configurations, a configMap named ```node-agent-config``` should be created manually. The configMap should be in the same namespace where Velero is installed. If multiple Velero instances are installed in different namespaces, there should be one configMap in each namespace which applies to node-agent in that namespace only.  
+To set Node-agent concurrency configurations, a configMap should be created manually. The configMap should be in the same namespace where Velero is installed. If multiple Velero instances are installed in different namespaces, there should be one configMap in each namespace which applies to node-agent in that namespace only. The name of the configMap should be specified in the node-agent server parameter ```--node-agent-config```.  
 Node-agent server checks these configurations at startup time. Therefore, you could edit this configMap any time, but in order to make the changes effective, node-agent server needs to be restarted.  
 
 ### Global concurrent number
@@ -32,7 +32,7 @@ At least one node is expected to have a label with the specified ```RuledConfigs
 If one node falls into more than one rules, e.g., if node1 also has the label ```beta.kubernetes.io/instance-type=Standard_B4ms```, the smallest number (3) will be used.  
 
 ### Sample
-A sample of the complete ```node-agent-config``` configMap is as below:
+A sample of the complete configMap is as below:
 ```json
 {
     "loadConcurrency": {
@@ -62,5 +62,19 @@ To create the configMap, save something like the above sample to a json file and
 ```
 kubectl create cm node-agent-config -n velero --from-file=<json file name>
 ```
+To provide the configMap to node-agent, edit the node-agent daemonset and add the ```- --node-agent-config``` argument to the spec:
+1. Open the node-agent daemonset spec  
+```
+kubectl edit ds node-agent -n velero
+```
+2. Add ```- --node-agent-config``` to ```spec.template.spec.containers```  
+```
+spec:
+  template:
+    spec:
+      containers:
+      - args:
+        - --node-agent-config=<configMap name>
+```