The mesh says what it applied, and the replay has an address it may use

The pipeline was observable from a merge to an artifact and went dark where it touched a machine: a
node's report is control traffic only the control plane reads, so nothing said which version a
machine runs, or that it refused to (novox/hq ADR 0134). The control plane now states both under the
seat it holds — a role's events belong to the role and keep their address when the holder is
replaced — and only when the report is news, because a machine reconciles every minute and a fact per
report would be a fact per minute per machine.

Whether a report is news is the store's answer: it holds the previous one, so the listener returns it
and the server states the fact. That also gives the catch-up replay a subject the controller may
publish: it was published as a module's event from a module called "control-plane", which does not
exist, so the controller's own account refused it and every catalogue that asked what it missed was
answered with nothing.
This commit is contained in:
2026-09-28 16:07:18 +02:00
parent cec792ce9d
commit 1ebad3786c
16 changed files with 366 additions and 70 deletions
+111 -6
View File
@@ -86,14 +86,15 @@ type counted struct {
heard []Report
}
func (c *counted) Heard(_ context.Context, r Report) error {
func (c *counted) Heard(_ context.Context, r Report) (bool, error) {
c.mu.Lock()
defer c.mu.Unlock()
if c.err != nil {
return c.err
return false, c.err
}
c.heard = append(c.heard, r)
return nil
// News, so what the mesh states about a report is exercised wherever a report is.
return true, nil
}
func (c *counted) refusing(err error) {
@@ -207,11 +208,11 @@ type sentAndHeardSafely struct {
heard []Report
}
func (s *sentAndHeardSafely) Heard(_ context.Context, r Report) error {
func (s *sentAndHeardSafely) Heard(_ context.Context, r Report) (bool, error) {
s.mu.Lock()
defer s.mu.Unlock()
s.heard = append(s.heard, r)
return nil
return true, nil
}
func (s *sentAndHeardSafely) Outstanding(context.Context, string) (string, error) {
@@ -451,4 +452,108 @@ func TestNatsWorkSlowerThanTheWindowIsNotHandedOverAgain(t *testing.T) {
// slowly is a listener that runs whatever it was given.
type slowly struct{ work func() }
func (s slowly) Heard(context.Context, Report) error { s.work(); return nil }
func (s slowly) Heard(context.Context, Report) (bool, error) { s.work(); return true, nil }
// **The mesh says what it applied** (novox/hq ADR 0134), under the seat the control plane holds — and
// says nothing when a report is the same state said again, which is what a machine reconciling every
// minute sends.
func TestNatsTheMeshSaysWhatAMachineApplied(t *testing.T) {
js := aBus(t)
heard := make(chan *nats.Msg, 4)
sub, err := js.Conn().Subscribe(SeatEventSubject(MeshControllerSeat, ">"), func(m *nats.Msg) {
heard <- m
})
if err != nil {
t.Fatal(err)
}
defer sub.Unsubscribe() //nolint:errcheck // the subscription dies with the connection
_, stop := servingOn(t, js, &counted{})
defer stop()
// A report that changed something: the store says it was news.
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store", "broker"}})
if err != nil {
t.Fatal(err)
}
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
t.Fatal(err)
}
select {
case m := <-heard:
if m.Subject != SeatEventSubject(MeshControllerSeat, KeyApplied) {
t.Fatalf("the mesh stated %q", m.Subject)
}
var said Applied
if err := json.Unmarshal(m.Data, &said); err != nil {
t.Fatal(err)
}
if said.Node != "anchor" || said.Declared != "d1" || said.Resources != 2 {
t.Fatalf("it said %+v", said)
}
case <-time.After(10 * time.Second):
t.Fatal("the mesh said nothing about a machine that now runs something else")
}
// A refusal is its own fact, with the reason in it rather than only in a log.
refusal, err := json.Marshal(Report{Node: "anchor", Declared: "d2",
Failed: map[string]string{"gitea.server": "no such image"}})
if err != nil {
t.Fatal(err)
}
if _, err := js.Context().Publish(ReportSubject("anchor"), refusal); err != nil {
t.Fatal(err)
}
select {
case m := <-heard:
if m.Subject != SeatEventSubject(MeshControllerSeat, KeyRefused) {
t.Fatalf("a refusal was stated as %q", m.Subject)
}
var said Refused
if err := json.Unmarshal(m.Data, &said); err != nil {
t.Fatal(err)
}
if said.Failed["gitea.server"] == "" {
t.Fatalf("the refusal does not say which resource or why: %+v", said)
}
case <-time.After(10 * time.Second):
t.Fatal("the mesh said nothing about a machine that refused what it was sent")
}
}
// And a report that is not news is not a fact. A machine reconciles every minute; a fact per report
// would be a fact per minute per machine, which is a stream nobody reads.
func TestNatsAReportThatIsNotNewsIsNotStated(t *testing.T) {
js := aBus(t)
heard := make(chan *nats.Msg, 4)
sub, err := js.Conn().Subscribe(SeatEventSubject(MeshControllerSeat, ">"), func(m *nats.Msg) {
heard <- m
})
if err != nil {
t.Fatal(err)
}
defer sub.Unsubscribe() //nolint:errcheck // the subscription dies with the connection
// A store that records the report and says it was nothing new — which is what the mesh's own
// store says about a machine repeating itself.
_, stop := servingOn(t, js, sameAgain{})
defer stop()
body, err := json.Marshal(Report{Node: "anchor", Declared: "d1", Applied: []string{"store"}})
if err != nil {
t.Fatal(err)
}
if _, err := js.Context().Publish(ReportSubject("anchor"), body); err != nil {
t.Fatal(err)
}
select {
case m := <-heard:
t.Fatalf("the mesh stated %q about a machine that changed nothing", m.Subject)
case <-time.After(3 * time.Second):
}
}
// sameAgain records a report and says it was the same state said again.
type sameAgain struct{}
func (sameAgain) Heard(context.Context, Report) (bool, error) { return false, nil }