Updates Alternat to use Amazon Linux 2023 (#116)

* Updates Alternat to use Amazon Linux 2023

* remove out of date comment and now unused workflow

* install terraform

* fix test

* retries

* use assert

* sudo make me

* newline

* whitespace

.github/workflows/test.yaml

@@ -31,6 +31,9 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
+      - name: Install Terraform
+        uses: hashicorp/setup-terraform@v3
+
       - name: Install Go
         uses: actions/setup-go@v5
         with:

README.md

@@ -34,7 +34,7 @@ Features:
 
 * Self-provisioned NAT instances in Auto Scaling Groups
 * Standby NAT Gateways with health checks and automated failover, facilitated by a Lambda function
-* Vanilla Amazon Linux 2 AMI (no AMI management requirement)
+* Vanilla Amazon Linux 2023 AMI (no AMI management requirement)
 * Optional use of SSM for connecting to the NAT instances
 * Max instance lifetimes (no long-lived instances!) with automated failover
 * A Terraform module to set everything up

main.tf

@@ -135,7 +135,7 @@ resource "aws_iam_role_policy" "alternat_lifecycle_hook" {
 }
 
 
-data "aws_ami" "amazon_linux_2" {
+data "aws_ami" "amazon_linux_2023" {
   most_recent = true
   owners      = ["amazon"]
 
@@ -151,7 +151,7 @@ data "aws_ami" "amazon_linux_2" {
 
   filter {
     name   = "name"
-    values = ["amzn2-ami-hvm*"]
+    values = ["al2023-ami-2023*"]
   }
 }
 
@@ -218,7 +218,7 @@ resource "aws_launch_template" "nat_instance_template" {
     name = aws_iam_instance_profile.nat_instance.name
   }
 
-  image_id = var.nat_ami == "" ? data.aws_ami.amazon_linux_2.id : var.nat_ami
+  image_id = var.nat_ami == "" ? data.aws_ami.amazon_linux_2023.id : var.nat_ami
 
   instance_type = var.nat_instance_type
 

scripts/alternat.sh

@@ -35,13 +35,16 @@ validate_var() {
 # configure_nat() sets up Linux to act as a NAT device.
 # See https://docs.aws.amazon.com/vpc/latest/userguide/VPC_NAT_Instance.html#NATInstance
 configure_nat() {
-   echo "Beginning NAT configuration"
+   dnf -y install nftables
 
-   echo "Determining the MAC address on eth0"
-   local eth0_mac="$(cat /sys/class/net/eth0/address)" || panic "Unable to determine MAC address on eth0."
-   echo "Found MAC $eth0_mac for eth0."
+   local nic_name="$(ip route show | grep default | sed -n 's/.*dev \([^\ ]*\).*/\1/p')"
+   echo "Found interface name ${nic_name}"
 
-   local vpc_cidr_uri="http://169.254.169.254/latest/meta-data/network/interfaces/macs/$eth0_mac/vpc-ipv4-cidr-blocks"
+   echo "Determining the MAC address on ${nic_name}"
+   local nic_mac="$(cat /sys/class/net/${nic_name}/address)" || panic "Unable to determine MAC address on ${nic_name}."
+   echo "Found MAC ${nic_mac} for ${nic_name}."
+
+   local vpc_cidr_uri="http://169.254.169.254/latest/meta-data/network/interfaces/macs/${nic_mac}/vpc-ipv4-cidr-blocks"
    echo "Metadata location for vpc ipv4 ranges: $vpc_cidr_uri"
 
    local vpc_cidr_ranges=$(CURL_WITH_TOKEN "$vpc_cidr_uri")
@@ -56,18 +59,19 @@ configure_nat() {
    echo "Enabling NAT..."
    # Read more about these settings here: https://www.kernel.org/doc/Documentation/networking/ip-sysctl.txt
 
-   sysctl -q -w net.ipv4.ip_forward=1 net.ipv4.conf.eth0.send_redirects=0 net.ipv4.ip_local_port_range="1024 65535" ||
+   sysctl -q -w "net.ipv4.ip_forward"=1 "net.ipv4.conf.$nic_name.send_redirects"=0 "net.ipv4.ip_local_port_range"="1024 65535" ||
       panic
 
+   nft add table ip nat
+   nft add chain ip nat postrouting { type nat hook postrouting priority 100 \; }
+
    for cidr in "${vpc_cidrs[@]}";
    do
-      (iptables -t nat -C POSTROUTING -o eth0 -s "$cidr" -j MASQUERADE 2> /dev/null ||
-      iptables -t nat -A POSTROUTING -o eth0 -s "$cidr" -j MASQUERADE) ||
-      panic
+      nft add rule ip nat postrouting ip saddr "$cidr" oif "$nic_name" masquerade
    done
 
-   sysctl net.ipv4.ip_forward net.ipv4.conf.eth0.send_redirects net.ipv4.ip_local_port_range
-   iptables -n -t nat -L POSTROUTING
+   sysctl "net.ipv4.ip_forward" "net.ipv4.conf.${nic_name}.send_redirects" "net.ipv4.ip_local_port_range"
+   nft list ruleset
 
    echo "NAT configuration complete"
 }
@@ -172,8 +176,6 @@ export AWS_DEFAULT_OUTPUT="text"
 
 # Disable pager output
 # https://docs.aws.amazon.com/cli/latest/userguide/cli-usage-pagination.html#cli-usage-pagination-clientside
-# This is not needed in aws cli v1 which is installed on the current version of Amazon Linux 2.
-# However, it may be needed to prevent breakage if they update to cli v2 in the future.
 export AWS_PAGER=""
 
 # Set Instance Identity URI

test/alternat_test.go

@@ -137,18 +137,22 @@ func TestAlternat(t *testing.T) {
 		retry.DoWithRetry(t, fmt.Sprintf("Check SSH connection to %s", ip), maxRetries, waitTime, func() (string, error) {
 			return "", ssh.CheckSshConnectionE(t, natInstance)
 		})
-		command := "/usr/sbin/sysctl net.ipv4.ip_forward net.ipv4.conf.eth0.send_redirects net.ipv4.ip_local_port_range"
 
-		expectedText := `net.ipv4.ip_forward = 1
-net.ipv4.conf.eth0.send_redirects = 0
-net.ipv4.ip_local_port_range = 1024	65535
+		command := "sudo /usr/sbin/nft list ruleset"
+
+		expectedText := `table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority srcnat; policy accept;
+		ip saddr 10.10.0.0/16 oif "ens5" masquerade
+	}
+}
 `
 
-		maxRetries = 1
+		maxRetries = 5
 		waitTime = 10 * time.Second
 		retry.DoWithRetry(t, fmt.Sprintf("SSH to NAT instance at IP %s", ip), maxRetries, waitTime, func() (string, error) {
 			actualText, err := ssh.CheckSshCommandE(t, natInstance, command)
-			require.NoError(t, err)
+			assert.NoError(t, err)
 			if actualText != expectedText {
 				return "", fmt.Errorf("Expected SSH command to return '%s' but got '%s'", expectedText, actualText)
 			}
@@ -188,7 +192,7 @@ net.ipv4.ip_local_port_range = 1024	65535
 			return "All private route tables route through NAT Gateway", nil
 		})
 		logger := logger.Logger{}
-		logger.Logf(t, output)	
+		logger.Logf(t, output)
 		updateEgress(t, ec2Client, sgId, false)
 	})
 }