mesh-controller/cmd/mesh-controller/network_test.go

package main

import (
	"context"
	"os"
	"strings"
	"testing"

	"github.com/novox/mesh-controller/internal/catalogue"
	"github.com/novox/mesh-controller/internal/inventory"
	"github.com/novox/mesh-controller/internal/overlay"
)

// placementOf is what the mesh holds about where one node is.
func placementOf(t *testing.T, ctx context.Context, inv *inventory.Inventory, name string) inventory.Overlay {
	t.Helper()
	placed, err := inv.Overlays(ctx)
	if err != nil {
		t.Fatal(err)
	}
	for _, one := range placed {
		if one.Name == name {
			return one
		}
	}
	t.Fatalf("%s is not placed at all", name)
	return inventory.Overlay{}
}

// The sibling of `node public-domain`, and the worse one: a placement is three facts declared
// together, so an invocation that said none of them took all three away — the endpoint every other
// machine dials, the site, and the hub. A mesh whose hub was placed that way has no paths left.
func TestPlacingANodeWithNothingSaidDoesNotUnplaceIt(t *testing.T) {
	open := aMesh(t)
	ctx := t.Context()
	if err := overlayPlace(ctx, open.inventory,
		[]string{"anchor", "--endpoint", "198.51.100.10:51820", "--site", "hosting", "--hub"}); err != nil {
		t.Fatal(err)
	}

	err := overlayPlace(ctx, open.inventory, []string{"anchor"})
	if err == nil {
		t.Fatal("saying nothing unplaced the node instead of being refused")
	}
	if !strings.Contains(err.Error(), "--nothing") {
		t.Errorf("the refusal does not say how to mean it: %v", err)
	}

	held := placementOf(t, ctx, open.inventory, "anchor")
	if held.Endpoint != "198.51.100.10:51820" || held.Site != "hosting" || !held.Hub {
		t.Fatalf("the placement was taken away by an invocation that was refused: %+v", held)
	}
}

// Placing a machine with nothing set is a real thing to want — one that roams and opens every path
// itself is exactly that — so it keeps a way to be said, by name.
func TestPlacingANodeWithNothingIsAskedForByName(t *testing.T) {
	open := aMesh(t)
	ctx := t.Context()
	if err := overlayPlace(ctx, open.inventory,
		[]string{"anchor", "--endpoint", "198.51.100.10:51820", "--site", "hosting"}); err != nil {
		t.Fatal(err)
	}
	if err := overlayPlace(ctx, open.inventory, []string{"anchor", "--nothing"}); err != nil {
		t.Fatal(err)
	}
	held := placementOf(t, ctx, open.inventory, "anchor")
	if held.Endpoint != "" || held.Site != "" || held.Hub {
		t.Fatalf("--nothing did not place it with nothing: %+v", held)
	}
}

// Both at once cannot be meant, so neither silently wins.
func TestAPlacementAndNothingTogetherIsRefused(t *testing.T) {
	open := aMesh(t)
	ctx := t.Context()
	if err := overlayPlace(ctx, open.inventory,
		[]string{"anchor", "--site", "hosting", "--nothing"}); err == nil {
		t.Fatal("a placement and --nothing together was accepted")
	}
}

// A machine is named for the others only while it is on the private network — placed AND running
// what puts it there — the same set the resolver means by "on the private network". A machine
// that has an address and no networking is not named: a name resolving to an address that does
// not answer hangs where an unknown name fails at once (novox/hq issue 079).
func TestOnlyAMachineOnThePrivateNetworkIsNamed(t *testing.T) {
	open := aMesh(t) // two placed machines, both assigned what puts them on the private network
	ctx := t.Context()
	shelf, err := open.inventory.Catalogue(ctx)
	if err != nil {
		t.Fatal(err)
	}
	names, err := namesInTheMesh(ctx, open.inventory, shelf)
	if err != nil {
		t.Fatal(err)
	}
	if names["anchor.internal"] != "10.77.0.1" || names["laptop.internal"] != "10.77.0.2" {
		t.Fatalf("two machines on the network are not both named: %v", names)
	}
	// The laptop keeps its place and its address, and stops running the network.
	if err := open.inventory.Unassign(ctx, "laptop", overlay.Name); err != nil {
		t.Fatal(err)
	}
	names, err = namesInTheMesh(ctx, open.inventory, shelf)
	if err != nil {
		t.Fatal(err)
	}
	if _, still := names["laptop.internal"]; still || names["anchor.internal"] != "10.77.0.1" {
		t.Fatalf("a machine that left the network is still named, or the one that stayed is not: %v", names)
	}
}

// novox/hq ADR 0105: the range every address is composed from is the adopted tunnel's, read from
// the tunnel the hub holds — never stored anywhere else.
func TestTheOverlaysRangeIsTheAdoptedTunnels(t *testing.T) {
	open := aMesh(t)
	ctx := t.Context()
	inv := open.inventory
	t.Setenv(OverlayCIDRVar, "10.99.0.0/16")

	before, err := overlayRange(ctx, inv)
	if err != nil || before != "10.99.0.0/16" {
		t.Fatalf("without an adopted tunnel the range is not what genesis said: %q %v", before, err)
	}

	// The hub becomes what genesis makes of a machine in use: adopted, enrolled with the found
	// tunnel's key, and presenting the tunnel.
	if err := inv.SetAdopted(ctx, "anchor", true); err != nil {
		t.Fatal(err)
	}
	hub, err := inv.NodeByName(ctx, "anchor")
	if err != nil {
		t.Fatal(err)
	}
	const key = "THE-TUNNELS-KEY========================="
	if err := inv.RecordOverlayKey(ctx, hub.ID, key); err != nil {
		t.Fatal(err)
	}
	if err := inv.RecordTunnel(ctx, hub.ID, inventory.Tunnel{
		Interface: "wg0", Unit: "wg-quick@wg0", Config: "/etc/wireguard/wg0.conf", Port: 51900,
		Address: "192.0.2.1/24", Range: "192.0.2.0/24", PublicKey: key,
		Peers: []inventory.TunnelPeer{{PublicKey: "PEER-TWO", Address: "192.0.2.2"}},
	}); err != nil {
		t.Fatal(err)
	}

	after, err := overlayRange(ctx, inv)
	if err != nil || after != "192.0.2.0/24" {
		t.Fatalf("with an adopted tunnel the range is %q (%v), not the tunnel's", after, err)
	}

	// A placement whose endpoint is on another port than the tunnel's is refused: the peers dial
	// the tunnel's port.
	err = overlayPlace(ctx, inv, []string{"anchor", "--endpoint", "198.51.100.10:51820", "--site", "hosting", "--hub"})
	if err == nil || !strings.Contains(err.Error(), "51900") {
		t.Fatalf("an endpoint off the tunnel's port was accepted: %v", err)
	}
	// On the tunnel's port, the hub is placed at the tunnel's address — whatever it had before.
	if err := inv.SetPlace(ctx, "anchor", "", "", false, ""); err != nil {
		t.Fatal(err)
	}
	if err := overlayPlace(ctx, inv, []string{"anchor", "--endpoint", "198.51.100.10:51900", "--site", "hosting", "--hub"}); err != nil {
		t.Fatal(err)
	}
	if placed := placementOf(t, ctx, inv, "anchor"); placed.Address != "192.0.2.1" {
		t.Fatalf("the hub was placed at %s, not the tunnel's own address", placed.Address)
	}

	// And the hub's declaration carries the peer and the takeover.
	nodes, computed, err := graph(ctx, open)
	if err != nil {
		t.Fatal(err)
	}
	var hubNode overlay.Node
	for _, n := range nodes {
		if n.Name == "anchor" {
			hubNode = n
		}
	}
	if hubNode.TakesOver == nil || hubNode.TakesOver.Unit != "wg-quick@wg0" {
		t.Errorf("the hub is not told to take over the found tunnel: %+v", hubNode)
	}
	carried := false
	for _, p := range computed["anchor"] {
		if p.Key == "PEER-TWO" && p.Allowed == "192.0.2.2/32" {
			carried = true
		}
	}
	if !carried {
		t.Errorf("the hub's peer list does not carry the tunnel's peer: %+v", computed["anchor"])
	}
}

// A takeover is composed only for a hub whose placement agrees with the tunnel: an address or an
// endpoint port that differs would have the host stop the found interface and raise the mesh's
// where no peer is listening.
func TestATakeoverIsNotComposedForAHubPlacedOffItsTunnel(t *testing.T) {
	open := aMesh(t)
	ctx := t.Context()
	inv := open.inventory
	if err := inv.SetAdopted(ctx, "anchor", true); err != nil {
		t.Fatal(err)
	}
	hub, err := inv.NodeByName(ctx, "anchor")
	if err != nil {
		t.Fatal(err)
	}
	const key = "THE-TUNNELS-KEY========================="
	if err := inv.RecordOverlayKey(ctx, hub.ID, key); err != nil {
		t.Fatal(err)
	}
	if err := inv.RecordTunnel(ctx, hub.ID, inventory.Tunnel{
		Interface: "wg0", Unit: "wg-quick@wg0", Config: "/etc/wireguard/wg0.conf", Port: 51900,
		Address: "192.0.2.1/24", Range: "192.0.2.0/24", PublicKey: key}); err != nil {
		t.Fatal(err)
	}
	// aMesh placed anchor at 10.77.0.1 on :51820 — the record of a hub placed before it took the
	// tunnel over.
	_, _, err = graph(ctx, open)
	if err == nil {
		t.Fatal("a takeover was composed for a hub whose address and port are not the tunnel's")
	}
	for _, want := range []string{"10.77.0.1", "192.0.2.1", "51820", "51900", "overlay place anchor"} {
		if !strings.Contains(err.Error(), want) {
			t.Errorf("the refusal does not say %q: %v", want, err)
		}
	}
	// Re-placed on the tunnel, it composes.
	if err := inv.SetPlace(ctx, "anchor", "", "", false, ""); err != nil {
		t.Fatal(err)
	}
	if err := overlayPlace(ctx, inv, []string{"anchor", "--endpoint", "198.51.100.10:51900", "--site", "here", "--hub"}); err != nil {
		t.Fatal(err)
	}
	if _, _, err := graph(ctx, open); err != nil {
		t.Fatalf("re-placed on the tunnel, the graph still refuses: %v", err)
	}
}

// theResolver is the catalogue's dnsmasq module as it is, or the test is skipped where the
// catalogue is not beside this checkout.
func theResolver(t *testing.T) catalogue.Manifest {
	t.Helper()
	raw, err := os.ReadFile("../../../mesh-catalog/modules/dnsmasq/module.json")
	if err != nil {
		t.Skipf("the catalogue is not beside this checkout: %v", err)
	}
	m, err := catalogue.ParseManifest(raw)
	if err != nil {
		t.Fatalf("dnsmasq does not parse:\n%v", err)
	}
	return m
}

// The resolver is handed every machine on the private network as a wildcard, the same set and the
// same source as the hosts file, and is handed it again when a machine leaves — through the
// module's own manifest asking for the fact, with no module of the mesh's own in between (hal
// dnsmasq-app conversion, novox/hq 08-connectivity). The runtime on that machine is pointed at the
// machine's own address, where the resolver answers for its containers.
func TestTheResolverIsToldEveryMachineOnTheNetworkAndToldAgainWhenOneLeaves(t *testing.T) {
	open := aMesh(t)
	ctx := t.Context()
	register(t, open, theResolver(t))
	if _, err := assign(ctx, open, "anchor", "dnsmasq"); err != nil {
		t.Fatal(err)
	}
	zones := func() string {
		t.Helper()
		for _, r := range composed(t, open, "anchor").Resources {
			if r["id"] == "dnsmasq.fact-node-zones" {
				if r["path"] != "/etc/mesh-resolver/nodes.conf" {
					t.Fatalf("the machines were written somewhere the resolver does not read: %v", r["path"])
				}
				return r["content"].(string)
			}
		}
		t.Fatal("the resolver was not handed the machines")
		return ""
	}
	first := zones()
	for _, want := range []string{
		"local=/internal/", "address=/anchor.internal/10.77.0.1\n", "address=/laptop.internal/10.77.0.2\n",
	} {
		if !strings.Contains(first, want) {
			t.Errorf("the resolver's machines lack %q:\n%s", want, first)
		}
	}
	for _, r := range composed(t, open, "anchor").Resources {
		if r["id"] == "dnsmasq.runtime-dns" {
			if !strings.Contains(r["content"].(string), `"10.77.0.1"`) || r["into"] != "json" {
				t.Errorf("the runtime is not pointed at this machine's own address, written into its file: %v", r)
			}
		}
	}

	// The laptop keeps its place and its address, and stops running the network.
	if err := open.inventory.Unassign(ctx, "laptop", overlay.Name); err != nil {
		t.Fatal(err)
	}
	after := zones()
	if strings.Contains(after, "laptop") || !strings.Contains(after, "address=/anchor.internal/10.77.0.1\n") {
		t.Fatalf("a machine that left the network is still a wildcard, or the one that stayed is not:\n%s", after)
	}
}