Merge the qemu-guest-agent bootstrap into each Proxy's cloud-config instead of vendor-data

In the kind cluster two KVM Proxies with real cloud-configs booted fine but never left Provisioning: the guest agent was not installed, so the provider could not learn the IP. cloud-init merges vendor-data under user-data with its default mergers, which keep the user-data's value for any key both define and never append lists, so a cloud-config with its own `packages:` silently dropped the vendor-data's packages and runcmd. The integration test passed only because its user-data was empty. withGuestAgent now appends qemu-guest-agent to `packages` and the enable command to `runcmd` of the Proxy's own cloud-config (skipping entries already present) and re-renders it. Vendor-data is no longer defaulted; `vendorData` is plain extra data. User-data that is not a cloud-config document (script, #include, MIME) still gets the bootstrap as vendor-data. A cloud-config that is not a YAML mapping, or whose packages/runcmd is not a list, fails the Proxy as ErrPermanent. Validated in-cluster: both Proxies Ready and healthy in two minutes, 204 through squid from the LAN. Docs, sample comment, CHANGELOG and the plan execution log (Run 7) updated. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-10 21:06:54 +00:00
parent 220967660d
commit 366736f53f
9 changed files with 382 additions and 30 deletions
@@ -4,10 +4,12 @@ import (
 	"bytes"
 	"io"
 	"maps"
+	"reflect"
 	"strings"
 	"testing"

 	"github.com/kdomanski/iso9660"
+	"sigs.k8s.io/yaml"
 )

 func readSeed(t *testing.T, iso []byte) (label string, files map[string]string) {
@@ -42,7 +44,7 @@ func readSeed(t *testing.T, iso []byte) (label string, files map[string]string)
 func TestBuildSeedISO_contents(t *testing.T) {
 	t.Parallel()
 	userData := "#cloud-config\npackages: [squid]\n"
-	iso, err := buildSeedISO("proxy-abc123def456ghij", userData, defaultVendorData)
+	iso, err := buildSeedISO("proxy-abc123def456ghij", userData, guestAgentVendorData)
 	if err != nil {
 		t.Fatalf("buildSeedISO() error = %v", err)
 	}
@@ -56,7 +58,7 @@ func TestBuildSeedISO_contents(t *testing.T) {
 	if files["user-data"] != userData {
 		t.Errorf("user-data = %q, want verbatim cloud-init", files["user-data"])
 	}
-	if files["vendor-data"] != defaultVendorData {
+	if files["vendor-data"] != guestAgentVendorData {
 		t.Errorf("vendor-data = %q", files["vendor-data"])
 	}
 	if got, want := files["meta-data"], "instance-id: proxy-abc123def456ghij\nlocal-hostname: proxy-abc123def456ghij\n"; got != want {
@@ -89,7 +91,7 @@ func TestBuildSeedISO_deterministicContent(t *testing.T) {

 func TestBuildSeedISO_emptyUserData(t *testing.T) {
 	t.Parallel()
-	iso, err := buildSeedISO("proxy-x", "", defaultVendorData)
+	iso, err := buildSeedISO("proxy-x", "", guestAgentVendorData)
 	if err != nil {
 		t.Fatalf("buildSeedISO() error = %v", err)
 	}
@@ -98,3 +100,150 @@ func TestBuildSeedISO_emptyUserData(t *testing.T) {
 		t.Errorf("user-data = %q (present=%v), want an empty file to still exist", body, ok)
 	}
 }
+
+// parseCloudConfig is what cloud-init sees: the document under the header.
+func parseCloudConfig(t *testing.T, doc string) map[string]any {
+	t.Helper()
+	if first, _, _ := strings.Cut(doc, "\n"); first != cloudConfigHeader {
+		t.Fatalf("first line = %q, want %q", first, cloudConfigHeader)
+	}
+	var cfg map[string]any
+	if err := yaml.Unmarshal([]byte(doc), &cfg); err != nil {
+		t.Fatalf("merged user-data is not YAML: %v\n%s", err, doc)
+	}
+	return cfg
+}
+
+func TestWithGuestAgent_mergesIntoCloudConfig(t *testing.T) {
+	t.Parallel()
+	agentCmd := []any{"systemctl", "enable", "--now", "qemu-guest-agent"}
+	tests := []struct {
+		name         string
+		userData     string
+		wantPackages []any
+		wantRuncmd   []any
+	}{
+		{
+			name:         "empty document",
+			userData:     "#cloud-config\n",
+			wantPackages: []any{"qemu-guest-agent"},
+			wantRuncmd:   []any{agentCmd},
+		},
+		{
+			name:         "no user-data at all",
+			userData:     "",
+			wantPackages: []any{"qemu-guest-agent"},
+			wantRuncmd:   []any{agentCmd},
+		},
+		{
+			// The case that motivated this: cloud-init's default merger keeps
+			// the user-data's lists and drops vendor-data's, so the agent must
+			// be appended to the user's own packages and runcmd.
+			name: "user packages and runcmd are kept and extended",
+			userData: "#cloud-config\npackages:\n  - squid\nruncmd:\n  - systemctl restart squid\n" +
+				"write_files:\n  - path: /etc/squid/conf.d/x.conf\n    content: |\n      http_port 3128\n      via off\n",
+			wantPackages: []any{"squid", "qemu-guest-agent"},
+			wantRuncmd:   []any{"systemctl restart squid", agentCmd},
+		},
+		{
+			name:         "agent already present is not duplicated",
+			userData:     "#cloud-config\npackages: [qemu-guest-agent]\nruncmd:\n  - [systemctl, enable, --now, qemu-guest-agent]\n",
+			wantPackages: []any{"qemu-guest-agent"},
+			wantRuncmd:   []any{agentCmd},
+		},
+		{
+			name:         "header with trailing whitespace",
+			userData:     "#cloud-config   \r\npackages: [curl]\n",
+			wantPackages: []any{"curl", "qemu-guest-agent"},
+			wantRuncmd:   []any{agentCmd},
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			user, vendor, err := withGuestAgent(tc.userData, "")
+			if err != nil {
+				t.Fatalf("withGuestAgent() error = %v", err)
+			}
+			if vendor != "" {
+				t.Errorf("vendor-data = %q, want none when the agent is merged into the user-data", vendor)
+			}
+			cfg := parseCloudConfig(t, user)
+			if !reflect.DeepEqual(cfg["packages"], tc.wantPackages) {
+				t.Errorf("packages = %#v, want %#v", cfg["packages"], tc.wantPackages)
+			}
+			if !reflect.DeepEqual(cfg["runcmd"], tc.wantRuncmd) {
+				t.Errorf("runcmd = %#v, want %#v", cfg["runcmd"], tc.wantRuncmd)
+			}
+		})
+	}
+}
+
+func TestWithGuestAgent_keepsOtherKeysAndVendorData(t *testing.T) {
+	t.Parallel()
+	userData := "#cloud-config\nhostname: px\nwrite_files:\n  - path: /etc/x\n    content: |\n      line one\n      line two\n    permissions: '0644'\nbootcmd: [echo hi]\n"
+	user, vendor, err := withGuestAgent(userData, "#cloud-config\nntp: {enabled: true}\n")
+	if err != nil {
+		t.Fatalf("withGuestAgent() error = %v", err)
+	}
+	if vendor != "#cloud-config\nntp: {enabled: true}\n" {
+		t.Errorf("vendor-data = %q, want the configured one verbatim", vendor)
+	}
+	got := parseCloudConfig(t, user)
+	delete(got, "packages")
+	delete(got, "runcmd")
+	want := parseCloudConfig(t, userData)
+	if !reflect.DeepEqual(got, want) {
+		t.Errorf("merged user-data changed the user's keys:\n got %#v\nwant %#v", got, want)
+	}
+}
+
+func TestWithGuestAgent_nonCloudConfigFallsBackToVendorData(t *testing.T) {
+	t.Parallel()
+	tests := []struct {
+		name       string
+		userData   string
+		vendorData string
+		wantVendor string
+	}{
+		{"shell script, no vendor-data", "#!/bin/sh\napt-get install -y squid\n", "", guestAgentVendorData},
+		{"include, no vendor-data", "#include\nhttps://example/x\n", "", guestAgentVendorData},
+		{"shell script, own vendor-data wins", "#!/bin/sh\n", "#cloud-config\nntp: {}\n", "#cloud-config\nntp: {}\n"},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			user, vendor, err := withGuestAgent(tc.userData, tc.vendorData)
+			if err != nil {
+				t.Fatalf("withGuestAgent() error = %v", err)
+			}
+			if user != tc.userData {
+				t.Errorf("user-data = %q, want it untouched", user)
+			}
+			if vendor != tc.wantVendor {
+				t.Errorf("vendor-data = %q, want %q", vendor, tc.wantVendor)
+			}
+		})
+	}
+}
+
+func TestWithGuestAgent_rejectsBrokenCloudConfig(t *testing.T) {
+	t.Parallel()
+	tests := []struct {
+		name     string
+		userData string
+	}{
+		{"not yaml", "#cloud-config\npackages: [squid\n"},
+		{"not a mapping", "#cloud-config\n- squid\n"},
+		{"packages is not a list", "#cloud-config\npackages: squid\n"},
+		{"runcmd is not a list", "#cloud-config\nruncmd:\n  a: b\n"},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if _, _, err := withGuestAgent(tc.userData, ""); err == nil {
+				t.Errorf("withGuestAgent() = nil error, want one for %q", tc.userData)
+			}
+		})
+	}
+}