dbus: hold node-message-bus, and never restart the bus live (hq ADR 0215)

A live restart of the system bus during an upgrade hung every login on a workstation until a reboot. The module owns the bus's packages, declares the bus running with no restart or reload trigger, publishes only curated events (health, services, denials; never traffic) and serves tools to look at both buses.
2026-10-05 11:50:52 +02:00
parent 4224ac7252
commit 7b5e1d3362
19 changed files with 3106 additions and 0 deletions
@@ -0,0 +1,67 @@
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+)
+
+// Run on a real machine with MESH_LIVE=1: every tool reads this machine's buses, and the watcher's
+// connection answers. Nothing is changed.
+func TestLiveTools(t *testing.T) {
+	if os.Getenv("MESH_LIVE") == "" {
+		t.Skip("set MESH_LIVE=1 on a machine with a system bus")
+	}
+	ctx := context.Background()
+	m := Here()
+	b, err := DialSystemBus()
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer b.Close()
+	if err := b.Ping(ctx); err != nil {
+		t.Fatal(err)
+	}
+	id, _ := b.ID(ctx)
+	pid, _ := b.PID(ctx, busName)
+	t.Logf("bus %s, driver pid %d in %s", id, pid, m.UnitOf(pid))
+	show := func(name string, v any, err error) {
+		raw, _ := json.Marshal(v)
+		if len(raw) > 1500 {
+			raw = append(raw[:1500], "…"...)
+		}
+		t.Logf("%s: %v\n%s", name, err, raw)
+	}
+	n, err := m.Names(ctx, "system")
+	show("names system", n, err)
+	n, err = m.Names(ctx, "session")
+	show("names session", n, err)
+	o, err := m.Introspect(ctx, "system", "org.freedesktop.login1", "/org/freedesktop/login1")
+	show("introspect", o, err)
+	w, err := m.Monitor(ctx, "system", 2, "", nil)
+	show("monitor", w, err)
+	show("health", m.Health(ctx, nil), nil)
+	show("check", m.Check(ctx, nil), nil)
+}
+
+// Run with MESH_LIVE=1: the watcher connects, pings and baselines the names, and says nothing.
+func TestLiveWatcher(t *testing.T) {
+	if os.Getenv("MESH_LIVE") == "" {
+		t.Skip("set MESH_LIVE=1 on a machine with a system bus")
+	}
+	m := Here()
+	var said []string
+	w := NewWatcher(m, func(e string, b any) error { said = append(said, e); return nil }, DialSystemBus, m.Denials)
+	w.state = filepath.Join(t.TempDir(), "bus")
+	ctx, cancel := context.WithTimeout(context.Background(), PingEvery+2*time.Second)
+	defer cancel()
+	w.Run(ctx)
+	s := w.Snapshot()
+	t.Logf("%+v said %v", s, said)
+	if s.BusID == "" || s.LastPingAt == "" || s.Stalled || s.Services == 0 {
+		t.Fatalf("%+v", s)
+	}
+}