mesh-host/internal/bootstrap/preflight_test.go

package bootstrap

import (
	"context"
	"errors"
	"strings"
	"testing"
	"time"

	"github.com/novox/mesh-host/internal/declaration"
)

// An installed package is not a capability (novox/hq 04-ISSUES/007). The daemon is asked, and a
// machine where it does not answer is refused before anything is loaded, written or applied.
//
// The refusal has to be plain, because the person reading it is standing in front of a machine
// that will not work: it says what was asked, what came back, that re-running is safe, and names
// the record that explains why an installed docker is not enough.
func TestPreflightRefusesPlainlyWhenTheRuntimeDoesNotAnswer(t *testing.T) {
	silent := func(context.Context, string, ...string) (string, error) {
		return "", errors.New("Cannot connect to the Docker daemon at unix:///var/run/docker.sock")
	}

	// No wait, so this is one attempt: what is being tested is the refusal, not the patience.
	err := waitForRuntime(context.Background(), silent, time.Second, 0, func(string) {})
	if err == nil {
		t.Fatal("a machine whose container runtime does not answer was accepted")
	}
	for _, wanted := range []string{
		"no container runtime that answers",
		"Cannot connect to the Docker daemon",
		"04-ISSUES/007",
		"idempotent",
	} {
		if !strings.Contains(err.Error(), wanted) {
			t.Errorf("the refusal does not mention %q:\n%v", wanted, err)
		}
	}
}

// And a runtime that is merely slow to start is waited for rather than refused.
//
// A socket-activated daemon queued behind the network is not absent, it is a few seconds away.
// Refusing on the first attempt would make a correct bootstrap fail for being observed too early —
// and `docker load` against such a daemon blocks silently rather than failing, which is how one
// became a 35-minute silence (04-ISSUES/024).
func TestARuntimeThatIsStillStartingIsWaitedFor(t *testing.T) {
	previous := runtimeAskEvery
	runtimeAskEvery = time.Millisecond
	defer func() { runtimeAskEvery = previous }()

	attempts := 0
	slow := func(context.Context, string, ...string) (string, error) {
		attempts++
		if attempts < 3 {
			return "", errors.New("Cannot connect to the Docker daemon")
		}
		return "27.0.3\n", nil
	}

	var said []string
	if err := waitForRuntime(context.Background(), slow, time.Second, time.Second,
		func(line string) { said = append(said, line) }); err != nil {
		t.Fatalf("a runtime that answered on the third ask was refused: %v", err)
	}
	if attempts != 3 {
		t.Errorf("the runtime was asked %d time(s)", attempts)
	}
	if !strings.Contains(strings.Join(said, "\n"), "27.0.3") {
		t.Errorf("the version the daemon reported was not said back: %v", said)
	}
}

// What has to be reachable is what the bundle actually names, not "the internet".
//
// The mesh's own image is carried and nothing serves it, so asking a registry about it would be
// asking a question with no answer — which is the whole point of naming an image by the digest of
// its own configuration.
func TestOnlyTheRegistriesTheBundleNamesAreAskedAbout(t *testing.T) {
	parsed, err := declaration.ParseFileTrusted([]byte(`{"declaration":1,"resources":[
	  {"id":"store","type":"container","name":"mesh-store","image":"postgres@sha256:` +
		strings.Repeat("7", 64) + `"},
	  {"id":"broker","type":"container","name":"mesh-broker","image":"192.0.2.250:5000/lavinmq@sha256:` +
		strings.Repeat("8", 64) + `"},
	  {"id":"control-plane","type":"container","name":"mesh-controller","image":"` + held + `"}
	]}`))
	if err != nil {
		t.Fatal(err)
	}

	got := registriesIn(parsed)
	want := []string{DefaultRegistry, "192.0.2.250:5000"}
	if len(got) != len(want) {
		t.Fatalf("asked about %v, want %v", got, want)
	}
	for i := range want {
		if got[i] != want[i] {
			t.Errorf("asked about %v, want %v", got, want)
		}
	}
}

// And the control plane's slot is excluded whatever is in it.
//
// Found on the first real run of this installer. A template names the control plane by SOMETHING
// and step 3 replaces it with the id of the carried image, so whatever was there is never pulled —
// but preflight was reading that slot like any other and dialling it. The lab's template still
// carried the address of a registry the lab no longer raises, so a correct install timed out in
// preflight against a machine with a perfectly good network.
func TestTheControlPlanesOwnRegistryIsNeverAskedAbout(t *testing.T) {
	parsed, err := declaration.ParseFileTrusted([]byte(`{"declaration":1,"resources":[
	  {"id":"store","type":"container","name":"mesh-store","image":"postgres@sha256:` +
		strings.Repeat("7", 64) + `"},
	  {"id":"control-plane","type":"container","name":"mesh-controller","image":"192.0.2.250:5000/mesh-controller@sha256:` +
		strings.Repeat("8", 64) + `"}
	]}`))
	if err != nil {
		t.Fatal(err)
	}

	got := registriesIn(parsed)
	if len(got) != 1 || got[0] != DefaultRegistry {
		t.Fatalf("asked about %v; the control plane's own reference is about to be replaced and "+
			"must not be reached for", got)
	}
}

func TestWhereAnImageWouldBeFetchedFrom(t *testing.T) {
	// The container runtime's own rule: the part before the first slash is a registry host if it
	// has a dot, a port, or is localhost. Getting this wrong means dialling a hostname that is
	// really the first half of a repository name, and refusing a machine that is fine.
	for _, c := range []struct {
		reference string
		host      string
		served    bool
	}{
		{"postgres@sha256:" + strings.Repeat("a", 64), DefaultRegistry, true},
		{"cloudamqp/lavinmq@sha256:" + strings.Repeat("a", 64), DefaultRegistry, true},
		{"192.0.2.250:5000/postgres@sha256:" + strings.Repeat("a", 64), "192.0.2.250:5000", true},
		{"localhost/mesh-controller@sha256:" + strings.Repeat("a", 64), "localhost:443", true},
		{"registry.example.com/a/b@sha256:" + strings.Repeat("a", 64), "registry.example.com:443", true},
		// Held by this machine. Nothing serves it, and nothing can.
		{"sha256:" + strings.Repeat("a", 64), "", false},
		{"", "", false},
	} {
		host, served := registryOf(c.reference)
		if host != c.host || served != c.served {
			t.Errorf("%q → (%q, %v), want (%q, %v)", c.reference, host, served, c.host, c.served)
		}
	}
}

// A template whose temporary control plane is given no bus is refused at preflight, before anything
// is changed, rather than raised and waited on at the verify step until its timeout (novox/hq issue
// 146, ADR 0331 §4): that control plane says it has no MESH_BUS_NATS every few seconds, for ever.
func TestATemplateWhoseControlPlaneHasNoBusIsRefusedBeforeAnythingIsRaised(t *testing.T) {
	template := string(theRealBundle(t))
	if _, err := CheckTemplate([]byte(template)); err != nil {
		t.Fatalf("the shipped bundle is refused at preflight: %v", err)
	}
	const bus = `"MESH_BUS_NATS": "nats://controller:bootstrap@127.0.0.1:5671",`
	if !strings.Contains(template, bus) {
		t.Fatalf("the shipped bundle does not give its control plane %s", bus)
	}
	_, err := CheckTemplate([]byte(strings.Replace(template, bus, "", 1)))
	if err == nil || !strings.Contains(err.Error(), BusVar) {
		t.Fatalf("a control plane with no bus was let through preflight: %v", err)
	}
}