A service may omit its state, so unassigning an uplink module never stops the machine's network manager (hq ADR 0117)

2026-09-27 00:11:58 +02:00
parent fdc768c476
commit 06aaac0820
7 changed files with 374 additions and 24 deletions
@@ -0,0 +1,191 @@
+package apply
+
+import (
+	"context"
+	"fmt"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/novox/mesh-host/internal/store"
+)
+
+// Defends novox/hq ADR 0117: a service that omits its state leaves the unit's lifecycle to the
+// machine. The mesh reflects its triggers on a unit already running and does nothing else to it —
+// never starts, stops, enables or disables it, and forgets it when undeclared.
+
+// unitIn is a service manager whose one unit is active or not, recording what it is asked.
+func unitIn(active bool, commands *[]string) Runner {
+	return func(_ context.Context, name string, args ...string) (string, error) {
+		line := name + " " + strings.Join(args, " ")
+		*commands = append(*commands, line)
+		switch {
+		case strings.Contains(line, "is-enabled"):
+			return "enabled", nil
+		case strings.Contains(line, "show") && strings.Contains(line, "ActiveState"):
+			if active {
+				return "LoadState=loaded\nActiveState=active\nSubState=running", nil
+			}
+			return "LoadState=loaded\nActiveState=inactive\nSubState=dead", nil
+		}
+		return "", nil
+	}
+}
+
+func statelessDecl(path, content, triggers string) string {
+	return fmt.Sprintf(`{"declaration":1,"resources":[
+	  {"id":"uplink.conf","type":"file","path":%q,"into":"block","content":%q},
+	  {"id":"uplink.manager","type":"service","unit":"NetworkManager.service",%s}
+	]}`, path, content, triggers)
+}
+
+// touched is whether any command would change the unit's lifecycle.
+func touched(commands []string) []string {
+	var changing []string
+	for _, c := range commands {
+		for _, verb := range []string{" start ", " stop ", " restart ", " enable ", " disable ", " reload "} {
+			if strings.Contains(c+" ", verb) {
+				changing = append(changing, c)
+			}
+		}
+	}
+	return changing
+}
+
+func TestAStatelessServiceRunningIsReloadedForItsTrigger(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "mesh.conf")
+	var commands []string
+	report, _, err := Apply(context.Background(), archHost(t),
+		parse(t, statelessDecl(path, "[main]\ndns=none\n", `"reload-on":["uplink.conf"]`)),
+		store.State{}, store.OriginDeclared, unitIn(true, &commands), nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	joined := strings.Join(commands, "\n")
+	if !strings.Contains(joined, "systemctl reload NetworkManager.service") {
+		t.Errorf("the running manager was not reloaded; commands were %v", commands)
+	}
+	for _, c := range touched(commands) {
+		if !strings.Contains(c, "reload") {
+			t.Errorf("the manager's lifecycle was touched: %s", c)
+		}
+	}
+	if o := outcomeOf(report, "uplink.manager"); o.Action != "updated" || !strings.Contains(o.Detail, "reloaded for uplink.conf") {
+		t.Errorf("reported as %q: %s", o.Action, o.Detail)
+	}
+}
+
+func TestAStatelessServiceNotRunningIsLeftSo(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "mesh.conf")
+	for _, triggers := range []string{`"reload-on":["uplink.conf"]`, `"restart-on":["uplink.conf"]`} {
+		var commands []string
+		report, _, err := Apply(context.Background(), archHost(t),
+			parse(t, statelessDecl(path, fmt.Sprintf("# %s\n", triggers), triggers)),
+			store.State{}, store.OriginDeclared, unitIn(false, &commands), nil, nil)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if changing := touched(commands); len(changing) > 0 {
+			t.Errorf("%s: an inactive unit was acted on: %v", triggers, changing)
+		}
+		if o := outcomeOf(report, "uplink.manager"); o.Action != "unchanged" ||
+			o.Detail != "not running; the change applies at its next start" {
+			t.Errorf("%s: reported as %q: %s", triggers, o.Action, o.Detail)
+		}
+	}
+}
+
+func TestAStatelessServiceIsRestartedOnlyForItsRestartTrigger(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "mesh.conf")
+	var commands []string
+	d := parse(t, statelessDecl(path, "x\n", `"restart-on":["uplink.conf"]`))
+	_, state, err := Apply(context.Background(), archHost(t), d, store.State{}, store.OriginDeclared,
+		unitIn(true, &commands), nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !strings.Contains(strings.Join(commands, "\n"), "stop NetworkManager.service") {
+		t.Errorf("not restarted for its restart trigger; commands were %v", commands)
+	}
+	// Nothing it reflects changed: nothing is asked of the unit at all.
+	commands = nil
+	report, _, err := Apply(context.Background(), archHost(t), d, state, store.OriginDeclared,
+		unitIn(true, &commands), nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if changing := touched(commands); len(changing) > 0 {
+		t.Errorf("with nothing changed the unit was acted on: %v", changing)
+	}
+	if got := outcomeOf(report, "uplink.manager").Action; got != "unchanged" {
+		t.Errorf("with nothing changed it was %q", got)
+	}
+}
+
+func TestAStatelessServiceUndeclaredIsForgottenNotStopped(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "mesh.conf")
+	var commands []string
+	_, state, err := Apply(context.Background(), archHost(t),
+		parse(t, statelessDecl(path, "x\n", `"reload-on":["uplink.conf"]`)),
+		store.State{}, store.OriginDeclared, unitIn(true, &commands), nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if rec, _ := state.Find("uplink.manager"); !rec.Stateless {
+		t.Fatal("the record does not say the service was stateless")
+	}
+	if steps := Plan(somethingElse(t), state, store.OriginDeclared); !hasStep(steps, "forget", "uplink.manager") {
+		t.Errorf("the preview does not forget it: %v", steps)
+	}
+	commands = nil
+	report, _, err := Apply(context.Background(), archHost(t), somethingElse(t), state, store.OriginDeclared,
+		unitIn(true, &commands), nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if changing := touched(commands); len(changing) > 0 {
+		t.Errorf("undeclaring acted on the unit: %v", changing)
+	}
+	o := outcomeOf(report, "uplink.manager")
+	if o.Action != "forgotten" || o.Detail != "its state was never the mesh's" {
+		t.Errorf("undeclaring was %q: %s", o.Action, o.Detail)
+	}
+}
+
+func TestAStatelessServiceIsNeverHeldOnAnAdoptedNode(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "mesh.conf")
+	resources := fmt.Sprintf(`{"id":"uplink.conf","type":"file","path":%q,"into":"block","content":"x\n"},
+	  {"id":"uplink.manager","type":"service","unit":"NetworkManager.service","reload-on":["uplink.conf"]}`, path)
+	d := adopted(t, `{"taken":[],"untaken":{"uplink":["uplink.conf","uplink.manager"]}}`, resources)
+	for _, s := range Plan(d, store.State{}, store.OriginDeclared) {
+		if s.ID == "uplink.manager" && (s.Verb == "hold" || s.Verb == "create" || strings.Contains(s.Why, "replaces")) {
+			t.Errorf("the preview holds or replaces a stateless service: %+v", s)
+		}
+	}
+	var commands []string
+	report, state, err := ApplyKeeping(context.Background(), archHost(t), d, store.State{},
+		store.OriginDeclared, unitIn(true, &commands), nil, nil, KeepIn(t.TempDir()))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := outcomeOf(report, "uplink.manager").Action; got == "held" {
+		t.Fatal("a stateless service was held, though it replaces nothing that was found")
+	}
+	if len(state.Held) != 0 {
+		t.Errorf("something was held: %+v", state.Held)
+	}
+	for _, c := range touched(commands) {
+		if !strings.Contains(c, "reload") {
+			t.Errorf("the adopted node's manager lifecycle was touched: %s", c)
+		}
+	}
+}
+
+func hasStep(steps []Step, verb, id string) bool {
+	for _, s := range steps {
+		if s.Verb == verb && s.ID == id {
+			return true
+		}
+	}
+	return false
+}