fix(nodeadm): add retry to net.LookupHost (#2585)

* fix(nodeadm): Add retry to net.LookupHost()


---------

Co-authored-by: Nikolay Kvetsinski <kvetsins@amazon.com>

Author: nkvetsinski

nodeadm/go.mod

@@ -27,6 +27,7 @@ require (
 	cel.dev/expr v0.24.0 // indirect
 	github.com/Masterminds/semver/v3 v3.4.0 // indirect
 	github.com/antlr4-go/antlr/v4 v4.13.0 // indirect
+	github.com/avast/retry-go/v5 v5.0.0 // indirect
 	github.com/aws/aws-sdk-go-v2/credentials v1.19.7 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.17 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.17 // indirect

nodeadm/go.sum

@@ -6,6 +6,12 @@ github.com/Masterminds/semver/v3 v3.4.0 h1:Zog+i5UMtVoCU8oKka5P7i9q9HgrJeGzI9SA1
 github.com/Masterminds/semver/v3 v3.4.0/go.mod h1:4V+yj/TJE1HU9XfppCwVMZq3I84lprf4nC11bSS5beM=
 github.com/antlr4-go/antlr/v4 v4.13.0 h1:lxCg3LAv+EUK6t1i0y1V6/SLeUi0eKEKdhQAlS8TVTI=
 github.com/antlr4-go/antlr/v4 v4.13.0/go.mod h1:pfChB/xh/Unjila75QW7+VU4TSnWnnk9UTnmpPaOR2g=
+github.com/avast/retry-go v2.7.0+incompatible h1:XaGnzl7gESAideSjr+I8Hki/JBi+Yb9baHlMRPeSC84=
+github.com/avast/retry-go v2.7.0+incompatible/go.mod h1:XtSnn+n/sHqQIpZ10K1qAevBhOOCWBLXXy3hyiqqBrY=
+github.com/avast/retry-go v3.0.0+incompatible h1:4SOWQ7Qs+oroOTQOYnAHqelpCO0biHSxpiH9JdtuBj0=
+github.com/avast/retry-go v3.0.0+incompatible/go.mod h1:XtSnn+n/sHqQIpZ10K1qAevBhOOCWBLXXy3hyiqqBrY=
+github.com/avast/retry-go/v5 v5.0.0 h1:kf1Qc2UsTZ4qq8elDymqfbISvkyMuhgRxuJqX2NHP7k=
+github.com/avast/retry-go/v5 v5.0.0/go.mod h1://d+usmKWio1agtZfS1H/ltTqwtIfBnRq9zEwjc3eH8=
 github.com/aws/aws-sdk-go-v2 v1.41.1 h1:ABlyEARCDLN034NhxlRUSZr4l71mh+T5KAeGh6cerhU=
 github.com/aws/aws-sdk-go-v2 v1.41.1/go.mod h1:MayyLB8y+buD9hZqkCW3kX1AKq07Y5pXxtgB+rRFhz0=
 github.com/aws/aws-sdk-go-v2/config v1.32.7 h1:vxUyWGUwmkQ2g19n7JY/9YL8MfAIl7bTesIUykECXmY=

nodeadm/internal/kubelet/config.go

@@ -19,8 +19,8 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	k8skubelet "k8s.io/kubelet/config/v1beta1"
 
+	"github.com/avast/retry-go/v5"
 	"github.com/aws/smithy-go/ptr"
-
 	"github.com/awslabs/amazon-eks-ami/nodeadm/internal/api"
 	"github.com/awslabs/amazon-eks-ami/nodeadm/internal/aws/imds"
 	"github.com/awslabs/amazon-eks-ami/nodeadm/internal/containerd"
@@ -178,7 +178,20 @@ func (ksc *kubeletConfig) withOutpostSetup(cfg *api.NodeConfig) error {
 		}
 
 		// TODO: cleanup
-		ipAddresses, err := net.LookupHost(apiUrl.Host)
+		var ipAddresses []string
+		err = retry.New(
+			retry.Attempts(6),
+			retry.Delay(200*time.Millisecond),
+			retry.OnRetry(func(n uint, err error) {
+				zap.L().Info("Retrying DNS lookup after error", zap.Error(err))
+			}),
+		).Do(
+			func() error {
+				var err error
+				ipAddresses, err = net.LookupHost(apiUrl.Host)
+				return err
+			},
+		)
 		if err != nil {
 			return err
 		}