fix: pause VM before MMDS injection, resume after to ensure config is applied

- Load snapshot with ResumeVM: false so MMDS data can be written while VM is paused
- Call ResumeVM explicitly after configureMmds succeeds
- Skip PUT /mmds/config on restored VMs (Firecracker rejects it with 400)
- Strip JSON quotes from MMDS values with tr -d '"' in net-init script
- Add 169.254.169.2/32 link-local addr and flush eth0 before applying new IP

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

orchestrator/console.go

@@ -118,7 +118,7 @@ func RunConsoleProxy(cfg Config, id int, tapName string) error {
 		})
 	}
 
-	// --- Start VM (blocks until snapshot is loaded and VM is running) ---
+	// --- Start VM (blocks until snapshot is loaded and VM is PAUSED) ---
 	start := time.Now()
 	logger.Infof("restoring clone %d from snapshot ...", id)
 	if err := m.Start(ctx); err != nil {
@@ -126,10 +126,10 @@ func RunConsoleProxy(cfg Config, id int, tapName string) error {
 		ptm.Close()
 		return fmt.Errorf("restore clone %d: %w", id, err)
 	}
-	elapsed := time.Since(start)
 
 	// Inject per-clone IP config via MMDS so the fc-net-init guest daemon
 	// can configure eth0 without any manual steps inside the VM.
+	// This must happen while the VM is PAUSED (ResumeVM: false in snapshot load).
 	if cfg.AutoNetConfig && cfg.Bridge != "none" {
 		guestIP := fmt.Sprintf("%s.%d/24", cfg.GuestPrefix, 10+id)
 		if err := configureMmds(ctx, sockPath, guestIP, cfg.GuestGW, "1.1.1.1"); err != nil {
@@ -139,6 +139,14 @@ func RunConsoleProxy(cfg Config, id int, tapName string) error {
 		}
 	}
 
+	// Now RESUME the VM to start execution!
+	if err := m.ResumeVM(ctx); err != nil {
+		pts.Close()
+		ptm.Close()
+		return fmt.Errorf("resume clone %d: %w", id, err)
+	}
+	elapsed := time.Since(start)
+
 	// Release our copy of the slave — firecracker holds its own fd now.
 	// Closing here ensures we get EOF on ptm when firecracker exits.
 	pts.Close()

orchestrator/network.go

@@ -110,9 +110,12 @@ func configureMmds(ctx context.Context, sockPath, ip, gw, dns string) error {
 		return nil
 	}
 
-	// Store the network config the guest daemon will poll for.
+	// 1. MMDS configuration (version, network_interfaces binding, etc.) is
-	// PUT /mmds/config (interface association) was already handled by the SDK
+	// persisted in the golden snapshot, so we don't need to configure it here.
-	// via AllowMMDS: true on the NetworkInterface before the VM started.
+	// In fact, Firecracker will reject PUT /mmds/config with a 400 error
+	// on a restored VM, which previously caused this function to abort early.
+
+	// 2. Store the network config the guest daemon will poll for.
 	return doJSON(http.MethodPut, "/mmds", map[string]string{
 		"ip":  ip,
 		"gw":  gw,

orchestrator/orchestrator.go

@@ -121,11 +121,13 @@ func (o *Orchestrator) buildRootfs() error {
 	netInitScript := `#!/bin/sh
 # Poll Firecracker MMDS for network config, apply it, then exit.
 # Runs in background; loops until MMDS responds (survives snapshot resume).
+ip addr add 169.254.169.2/32 dev eth0 2>/dev/null
 while true; do
-  ip=$(wget -q -T1 -O- http://169.254.169.254/ip 2>/dev/null)
+  ip=$(wget -q -T1 -O- http://169.254.169.254/ip 2>/dev/null | tr -d '"')
   [ -n "$ip" ] || { sleep 1; continue; }
-  gw=$(wget -q -T1 -O- http://169.254.169.254/gw 2>/dev/null)
+  gw=$(wget -q -T1 -O- http://169.254.169.254/gw 2>/dev/null | tr -d '"')
-  dns=$(wget -q -T1 -O- http://169.254.169.254/dns 2>/dev/null)
+  dns=$(wget -q -T1 -O- http://169.254.169.254/dns 2>/dev/null | tr -d '"')
+  ip addr flush dev eth0 2>/dev/null
   ip addr add "$ip" dev eth0 2>/dev/null
   ip route add default via "$gw" dev eth0 2>/dev/null
   printf "nameserver %s\n" "$dns" > /etc/resolv.conf

orchestrator/snapshot.go

@@ -30,7 +30,7 @@ func loadSnapshotWithNetworkOverride(ctx context.Context, sockPath, memPath, vms
 	payload := snapshotLoadRequest{
 		MemFilePath:  memPath,
 		SnapshotPath: vmstatePath,
-		ResumeVM:     true,
+		ResumeVM:     false, // Changed: We pause here so MMDS can be configured BEFORE Resume.
 		NetworkOverrides: []networkOverride{
 			{IfaceID: "1", HostDevName: tapName},
 		},