mesh-controller/internal/catalogue/two_resolvers_test.go

package catalogue

import (
	"strings"
	"testing"
)

// The mesh has two resolvers (novox/hq ADR 0223): `mesh-dns-resolver` is replicated, held on the
// anchor and on the home server, each answering the same names; every machine's resolver file lists
// every holder — its own first when it is one — and no public resolver. ADR 0196 listed the mesh's
// resolver then a public one, and musl asks both at once and takes the first reply: from the home
// server the public "no such name" for the anchor's mesh name won, every time, in every Alpine build.
// The file is written by the module holding the machine's uplink (ADR 0223 part 2).

// resolverMachines is the anchor and the home server holding the resolver, and a laptop holding nothing.
var resolverMachines = map[string]string{
	"anchor.internal": "10.42.0.1", "laptop.internal": "10.42.0.2", "home.internal": "10.42.0.3"}

// bothResolvers is the two holders on record, as `seat mesh-dns-resolver --add` leaves them.
var bothResolvers = []Held{
	{Claim: "mesh-dns-resolver", Scope: ScopeMesh, Node: "anchor", Module: "dnsmasq"},
	{Claim: "mesh-dns-resolver", Scope: ScopeMesh, Node: "home", Module: "dnsmasq"},
}

// uplinks is every module in the catalogue holding node-uplink, and so writing the machine's resolver
// file (novox/hq ADR 0223 part 2): the program that would otherwise rewrite it is the one that writes it.
var uplinks = []string{"dhcpcd", "networkmanager", "systemd-networkd"}

// managing is a machine as each uplink module needs it: able to install, run a service and run the
// manager that module is for.
func managing(node string) Node {
	caps := map[string]bool{"package-manager": true, "service-manager": true}
	for _, u := range uplinks {
		caps["uplink-"+u] = true
	}
	return Node{Name: node, At: node + ".internal", Capabilities: caps}
}

// twoResolverShelf is the resolver, the uplink modules that write what a machine asks, and a stand-in
// answering `mesh-addressing`.
func twoResolverShelf(t *testing.T) map[string]Manifest {
	t.Helper()
	out := map[string]Manifest{
		"net":     {Module: "net", Version: "1", Provides: []Offer{{Name: "mesh-addressing"}}},
		"dnsmasq": catalogueManifest(t, "dnsmasq"),
	}
	for _, u := range uplinks {
		out[u] = catalogueManifest(t, u)
	}
	return out
}

// worldWithout is the rest of the mesh as a plan for one machine sees it: every other holder's claim
// and offer, and both holders on record.
func worldWithout(node string) World {
	w := World{Holdings: bothResolvers, Offered: map[string][]Provider{}}
	for _, h := range bothResolvers {
		if h.Node == node {
			continue
		}
		w.Held = append(w.Held, h)
		w.Offered["wildcard-resolution"] = append(w.Offered["wildcard-resolution"],
			Provider{Node: h.Node, At: h.Node + ".internal", Module: h.Module})
	}
	return w
}

// resolvConfOn resolves and composes one machine and answers with the nameservers its resolver file
// lists, in order, and the file. The file is the uplink's — `uplink` is one of the assigned modules —
// and nothing else on the machine declares that path.
func resolvConfOn(t *testing.T, node, uplink string, assigned []string) ([]string, string) {
	t.Helper()
	got, err := Resolve(twoResolverShelf(t), assigned, managing(node), worldWithout(node))
	if err != nil {
		t.Fatalf("%s with %s does not resolve with two resolvers on record: %v", node, uplink, err)
	}
	out, err := got.Declaration(Rendering{
		Names: resolverMachines, Machines: resolverMachines, Suffix: "internal",
		Holders: map[string]map[string]string{"mesh-dns-resolver": {
			"anchor.internal": "10.42.0.1", "home.internal": "10.42.0.3"}},
		Needed: map[string]map[string]string{"dnsmasq": {"broker": "sealed"}},
	})
	if err != nil {
		t.Fatalf("%s with %s does not compose: %v", node, uplink, err)
	}
	var file map[string]any
	for _, r := range out {
		if r["path"] != "/etc/resolv.conf" {
			continue
		}
		if file != nil {
			t.Fatalf("%s declares /etc/resolv.conf twice: %v and %v", node, file["id"], r["id"])
		}
		file = r
	}
	if file == nil || file["id"] != uplink+".fact-resolvers" {
		t.Fatalf("%s's resolver file is not %s's: %v", node, uplink, file)
	}
	content, _ := file["content"].(string)
	var servers []string
	for _, line := range strings.Split(content, "\n") {
		if strings.HasPrefix(line, "nameserver ") {
			servers = append(servers, strings.TrimPrefix(line, "nameserver "))
		}
	}
	return servers, content
}

// Per uplink module: each writes a resolver file listing both holders, the machine's own first on a
// holder, and only the holders on a machine that is none.
func TestEveryUplinkListsBothResolversItsOwnFirst(t *testing.T) {
	for _, uplink := range uplinks {
		for node, want := range map[string][]string{
			"anchor": {"10.42.0.1", "10.42.0.3"},
			"home":   {"10.42.0.3", "10.42.0.1"},
			"laptop": {"10.42.0.1", "10.42.0.3"},
		} {
			assigned := []string{uplink}
			if node != "laptop" {
				assigned = append(assigned, "dnsmasq")
			}
			servers, content := resolvConfOn(t, node, uplink, assigned)
			if strings.Join(servers, " ") != strings.Join(want, " ") {
				t.Errorf("%s on %s lists %v; want %v\n%s", uplink, node, servers, want, content)
			}
			for _, public := range []string{"1.1.1.1", "8.8.8.8", "9.9.9.9"} {
				if strings.Contains(content, public) {
					t.Errorf("%s on %s lists a public resolver beside the mesh's (ADR 0223):\n%s", uplink, node, content)
				}
			}
			if !strings.HasSuffix(content, "\noptions timeout:1 attempts:2 edns0\n") {
				t.Errorf("%s on %s does not end with two short attempts:\n%s", uplink, node, content)
			}
		}
	}
}

// One file, whichever manager the machine runs: the three modules carry the same template, so a
// machine changing its manager changes nothing in what it asks, and a fix made to one is made to all.
func TestEveryUplinkWritesTheSameResolverFile(t *testing.T) {
	var first, firstOf string
	for _, uplink := range uplinks {
		fact, ok := catalogueManifest(t, uplink).Facts["resolvers"]
		if !ok || fact.Path != "/etc/resolv.conf" || fact.Shared || fact.Home {
			t.Fatalf("%s does not write the machine's resolver file whole: %+v", uplink, fact)
		}
		if first == "" {
			first, firstOf = fact.Template, uplink
			continue
		}
		if fact.Template != first {
			t.Errorf("%s's resolver file differs from %s's; the three are kept identical", uplink, firstOf)
		}
	}
}

// The requirement stays with what writes the file (ADR 0223 part 1): a machine is refused when nothing
// in the mesh resolves, rather than given a file listing nothing.
func TestEveryUplinkRequiresTheMeshsResolver(t *testing.T) {
	for _, uplink := range uplinks {
		found := false
		for _, r := range catalogueManifest(t, uplink).Requires {
			found = found || r == "wildcard-resolution"
		}
		if !found {
			t.Errorf("%s writes the resolver file and does not require wildcard-resolution", uplink)
		}
	}
	_, err := Resolve(twoResolverShelf(t), []string{"networkmanager"}, managing("laptop"), World{})
	if err == nil || !strings.Contains(err.Error(), "wildcard-resolution") {
		t.Errorf("an uplink was composed on a mesh with no resolver: %v", err)
	}
}

// A holder answers its own requirement, even though the other holder sorts first (issue 258 kept).
func TestAHolderAnswersItsOwnRequirement(t *testing.T) {
	got, err := Resolve(twoResolverShelf(t), []string{"dnsmasq", "networkmanager"},
		managing("home"), worldWithout("home"))
	if err != nil {
		t.Fatal(err)
	}
	for _, n := range got.Needs {
		if n.Name == "wildcard-resolution" && n.From != "home" {
			t.Errorf("the home server's uplink is bound to %s; it holds the seat itself", n.From)
		}
	}
}

// A seat held once is still held once: a second claimant on another machine is refused while
// nothing is on record, and a store recording two holders of it is refused, naming the seat.
func TestASingleHolderMeshSeatStillRefusesASecondHolder(t *testing.T) {
	store := shelf(mod("postgres", nil, nil, nil, Claim{Name: "mesh-store", Scope: ScopeMesh}))
	other := Held{Claim: "mesh-store", Scope: ScopeMesh, Node: "anchor", Module: "postgres"}
	if _, err := Resolve(store, []string{"postgres"}, workstation(), World{Held: []Held{other}}); err == nil ||
		!strings.Contains(err.Error(), "one per mesh") {
		t.Errorf("a second claimant of a seat held once was not refused: %v", err)
	}
	here := Held{Claim: "mesh-store", Scope: ScopeMesh, Node: workstation().Name, Module: "postgres"}
	_, err := Resolve(store, []string{"postgres"}, workstation(),
		World{Held: []Held{other}, Holdings: []Held{other, here}})
	if err == nil || !strings.Contains(err.Error(), "on record as held by 2") {
		t.Errorf("two holders on record for a seat held once were not refused: %v", err)
	}
}

// Replicated is not "whoever is assigned": two claimants with nothing on record are refused, as for
// any mesh seat, and each holder is added by an act.
func TestTwoUnrecordedClaimantsOfTheReplicatedSeatAreRefused(t *testing.T) {
	w := worldWithout("home")
	w.Holdings = nil
	_, err := Resolve(twoResolverShelf(t), []string{"dnsmasq"}, Node{Name: "home", At: "home.internal"}, w)
	if err == nil || !strings.Contains(err.Error(), "seat mesh-dns-resolver --to") {
		t.Errorf("a second resolver with nothing on record was not refused, naming the handover: %v", err)
	}
}

// Only the mesh's resolver is replicated: a seat being replicated is a decision, recorded.
func TestOnlyTheResolverIsReplicated(t *testing.T) {
	for _, s := range Seats() {
		if s.Replicated != (s.Name == "mesh-dns-resolver") {
			t.Errorf("%s replicated = %v; only mesh-dns-resolver is (ADR 0223)", s.Name, s.Replicated)
		}
	}
	UseSeats([]Seat{{Name: "mesh-dns-resolver", Scope: ScopeMesh, Delivers: "wildcard-resolution"}})
	defer UseSeats(DefaultSeats())
	if s, _ := SeatNamed("mesh-dns-resolver"); !s.Replicated {
		t.Error("loading the set from the store, which has no column for it, lost the resolver's replication")
	}
}

// Every consumer is bound to the same holder whatever order the mesh resolved its machines in.
func TestTheFirstHolderIsTheFirstProvider(t *testing.T) {
	providers := []Provider{{Node: "anchor", Module: "dnsmasq"}, {Node: "home", Module: "dnsmasq"}}
	for _, held := range [][]Held{bothResolvers, {bothResolvers[1], bothResolvers[0]}} {
		if p, ok := HolderAmong("wildcard-resolution", providers, held); !ok || p.Node != "anchor" {
			t.Errorf("held in order %v answered %v", held, p)
		}
	}
}

// One host record per machine, beside its wildcard (novox/hq issue 262): a name with a host record
// says it exists and has no IPv6 address, where the wildcard alone said there is no such name, and
// musl reads that as final.
func TestTheResolverHasOneHostRecordPerMachine(t *testing.T) {
	got, err := Resolve(twoResolverShelf(t), []string{"dnsmasq"}, Node{Name: "anchor", At: "anchor.internal"},
		World{})
	if err != nil {
		t.Fatal(err)
	}
	out, err := got.Declaration(Rendering{Names: resolverMachines, Machines: resolverMachines, Suffix: "internal",
		Needed: map[string]map[string]string{"dnsmasq": {"broker": "sealed"}}})
	if err != nil {
		t.Fatal(err)
	}
	content, _ := byID(out)["dnsmasq.fact-node-zones"]["content"].(string)
	records := map[string]int{}
	for _, line := range strings.Split(content, "\n") {
		if strings.HasPrefix(line, "host-record=") {
			records[strings.TrimPrefix(line, "host-record=")]++
		}
	}
	for name, at := range resolverMachines {
		if records[name+","+at] != 1 {
			t.Errorf("%s has %d host records at %s, and has one:\n%s", name, records[name+","+at], at, content)
		}
	}
	if len(records) != len(resolverMachines) {
		t.Errorf("%d host records for %d machines:\n%s", len(records), len(resolverMachines), content)
	}
}