Compare commits
5
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1cfe6be9c4 | ||
|
|
4e4481b6f2 | ||
|
|
63ca073938 | ||
|
|
b244a768a3 | ||
|
|
f6a93fe74c |
@@ -25,11 +25,11 @@ import (
|
||||
// against a mesh that is serving. It answers from records: what is missing, and what would happen.
|
||||
// `rollout` itself refuses unless the check is clean.
|
||||
//
|
||||
// **The old broker is not switched off by this.** It stays an ordinary provider of `amqp` for whatever
|
||||
// else uses it — on this installation, a whole automation layer that has nothing to do with the mesh
|
||||
// ([ADR 0119](../../02-DECISIONS/0119-amqp-is-a-provision-not-the-bus.md)). Only the mesh's own
|
||||
// traffic moves, which is why this is survivable at all: what breaks if it goes wrong is the mesh's
|
||||
// ability to change things, not the services its modules are serving.
|
||||
// **The old broker goes with the move, and goes last** (novox/hq ADR 0131): AMQP is not a provision,
|
||||
// so once every machine reports on the new bus its module is unassigned. Only the mesh's own traffic
|
||||
// is what moves, which is why this is survivable at all: what breaks if it goes wrong is the mesh's
|
||||
// ability to change things, not the services its modules are serving — measured on 2026-09-27, when
|
||||
// a seat emptied mid-change and the control plane looped for two hours while every service stayed up.
|
||||
|
||||
const rolloutUsage = "rollout check | rollout --confirm"
|
||||
|
||||
@@ -105,7 +105,6 @@ func readinessOf(ctx context.Context, inv *inventory.Inventory) (broker.Readines
|
||||
ModuleCredentialled: map[string]bool{},
|
||||
// The old broker keeps its other clients on this installation, and saying so is how the plan
|
||||
// stops reading as a retirement.
|
||||
OldBusHasOtherClients: true,
|
||||
}
|
||||
|
||||
address, _, err := broker.OnNATS()
|
||||
|
||||
@@ -35,10 +35,6 @@ type Readiness struct {
|
||||
Modules []string
|
||||
// ModuleCredentialled is which of those has one.
|
||||
ModuleCredentialled map[string]bool
|
||||
// StillOnTheOldBus is whether anything of the mesh's own still needs the bus it is leaving —
|
||||
// which is not a reason to stop, because that broker stays as an ordinary provider of `amqp`
|
||||
// (ADR 0119). Recorded so nobody reads the move as a retirement.
|
||||
OldBusHasOtherClients bool
|
||||
}
|
||||
|
||||
// NotReady is every reason this mesh cannot move its bus yet, in the order somebody would fix them.
|
||||
@@ -120,10 +116,11 @@ func WhatMoves(r Readiness) []string {
|
||||
out = append(out, fmt.Sprintf("move %d module runtime(s), and confirm each answers",
|
||||
len(r.Modules)))
|
||||
}
|
||||
if r.OldBusHasOtherClients {
|
||||
out = append(out, "leave the old broker running: it stays an ordinary provider of `amqp` for "+
|
||||
"whatever else uses it (ADR 0119), and this move is not its retirement")
|
||||
}
|
||||
// **The old broker goes, and it goes last** (novox/hq ADR 0131). AMQP is not a provision, so once
|
||||
// every machine reports on the new bus nothing of the mesh is left speaking to it, and its module
|
||||
// is unassigned. Said as a step so nobody reads the move as leaving a second bus behind.
|
||||
out = append(out, "then unassign the old broker's module: AMQP is not a provision (ADR 0131), and "+
|
||||
"once every machine reports on the new bus nothing of the mesh speaks to it")
|
||||
return out
|
||||
}
|
||||
|
||||
|
||||
@@ -79,9 +79,8 @@ func TestEachThingMissingNamesItsOwnRemedy(t *testing.T) {
|
||||
|
||||
// What the move would do is written out rather than summarised, because this is the one step with
|
||||
// nothing to inspect afterwards — so reading it is the last chance to disagree.
|
||||
func TestWhatMovesNamesEveryMachineAndSaysTheOldBrokerStays(t *testing.T) {
|
||||
func TestWhatMovesNamesEveryMachineAndEndsWithTheOldBrokerGoing(t *testing.T) {
|
||||
r := aMeshReadyToMove()
|
||||
r.OldBusHasOtherClients = true
|
||||
steps := strings.Join(WhatMoves(r), "\n")
|
||||
|
||||
for _, want := range []string{"anchor", "laptop", "user list", "module runtime"} {
|
||||
@@ -89,9 +88,11 @@ func TestWhatMovesNamesEveryMachineAndSaysTheOldBrokerStays(t *testing.T) {
|
||||
t.Errorf("the plan does not mention %q:\n%s", want, steps)
|
||||
}
|
||||
}
|
||||
// Said explicitly, so nobody reads the move as switching the old broker off — it stays serving
|
||||
// whatever else uses it, and that is a decision already taken.
|
||||
if !strings.Contains(steps, "not its retirement") {
|
||||
t.Errorf("the plan does not say the old broker stays:\n%s", steps)
|
||||
// Said explicitly, and last: AMQP is not a provision (novox/hq ADR 0131), so the move ends with
|
||||
// the old broker's module unassigned, not left behind as a second bus. An earlier version of this
|
||||
// test pinned the opposite, under a record 0131 superseded.
|
||||
lines := WhatMoves(r)
|
||||
if last := lines[len(lines)-1]; !strings.Contains(last, "unassign the old broker") {
|
||||
t.Errorf("the plan does not end with the old broker going:\n%s", steps)
|
||||
}
|
||||
}
|
||||
|
||||
+11
-11
@@ -184,17 +184,17 @@ func claimProblems(m Manifest) []string {
|
||||
}
|
||||
|
||||
for _, c := range m.Claims {
|
||||
if seat, known := SeatNamed(c.Name); known {
|
||||
if c.At() != seat.Scope {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s claims %s at scope %q, and %s is a %s seat",
|
||||
m.Module, c.Name, c.At(), c.Name, seat.Scope))
|
||||
}
|
||||
if seat.Delivers != "" && !providesAt(m, seat.Delivers, seat.Scope) {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s claims %s, whose holder answers for %q, and %s does not provide %q at %s scope",
|
||||
m.Module, c.Name, seat.Delivers, m.Module, seat.Delivers, seat.Scope))
|
||||
}
|
||||
if _, known := SeatNamed(c.Name); known {
|
||||
// **A seat's scope and what it delivers are not judged here** (novox/hq ADR 0122).
|
||||
// This function runs wherever a manifest is parsed, and one of those places is the
|
||||
// build machine, which has no store: there, `SeatNamed` answers from the set the
|
||||
// binary shipped with, so a build would be refused for disagreeing with a compiled
|
||||
// copy of data the control plane owns. Exactly that happened — a holder of the bus
|
||||
// seat was refused for not providing what a stale compiled row said the seat
|
||||
// delivered, while the store's own row said otherwise.
|
||||
//
|
||||
// Both checks moved to CatalogueProblems, which only ever runs in the control plane,
|
||||
// after UseSeats has replaced the set with the store's.
|
||||
continue
|
||||
}
|
||||
if isSystemSeatName(c.Name) {
|
||||
|
||||
@@ -190,7 +190,22 @@ func CatalogueProblems(shelf Shelf) []string {
|
||||
}
|
||||
s, isModuleSeat := declared[c.Name]
|
||||
if !isModuleSeat {
|
||||
continue // a mesh seat: already judged by claimProblems
|
||||
// **A mesh seat is judged here and nowhere else** (novox/hq ADR 0122): the set is
|
||||
// the store's, and this is the only place that runs with the store's set loaded.
|
||||
// The parser cannot do it — it also runs on the build machine, against whatever
|
||||
// set that binary was compiled with.
|
||||
seat, _ := SeatNamed(c.Name)
|
||||
if c.At() != seat.Scope {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s claims %s at scope %q, and %s is a %s seat",
|
||||
module, c.Name, c.At(), c.Name, seat.Scope))
|
||||
}
|
||||
if seat.Delivers != "" && !providesAt(m, seat.Delivers, seat.Scope) {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
"%s claims %s, whose holder answers for %q, and %s does not provide %q at %s scope",
|
||||
module, c.Name, seat.Delivers, module, seat.Delivers, seat.Scope))
|
||||
}
|
||||
continue
|
||||
}
|
||||
if c.At() != s.At() {
|
||||
problems = append(problems, fmt.Sprintf(
|
||||
|
||||
@@ -91,7 +91,10 @@ func TestAClaimMustMatchTheDeclaredScope(t *testing.T) {
|
||||
|
||||
// The mesh's own seats still work, and are not shadowed by the derived half.
|
||||
func TestTheMeshsOwnSeatsAreStillClaimable(t *testing.T) {
|
||||
m := Manifest{Module: "nats", Claims: []Claim{{Name: "mesh-broker", Scope: ScopeMesh}}}
|
||||
// It delivers the bus, so its holder provides the bus — the rule this check now enforces.
|
||||
m := Manifest{Module: "nats",
|
||||
Provides: []Offer{{Name: "mesh-bus", Scope: ScopeMesh}},
|
||||
Claims: []Claim{{Name: "mesh-broker", Scope: ScopeMesh}}}
|
||||
if got := problemsFor(t, Shelf{"nats": m}); got != "" {
|
||||
t.Fatalf("a mesh seat was refused by the derived check: %s", got)
|
||||
}
|
||||
@@ -106,3 +109,38 @@ func TestTheProblemsAreStable(t *testing.T) {
|
||||
t.Fatalf("unstable:\n%s\n%s", first, second)
|
||||
}
|
||||
}
|
||||
|
||||
// **A build machine has no store, so it may not judge a seat.** The set is data the control plane
|
||||
// owns (novox/hq ADR 0122), and `ParseManifest` runs on the build machine too, against whatever set
|
||||
// that binary was compiled with. When the two disagreed, a valid holder of the bus seat was refused
|
||||
// mid-rollout — the compiled row said the seat delivered one provision, the store's row said
|
||||
// another, and the build failed on the copy rather than the truth. The parser judges the manifest;
|
||||
// the seat set judges the claim, where it is loaded.
|
||||
func TestTheParserDoesNotJudgeWhatOnlyTheStoreKnows(t *testing.T) {
|
||||
was := Seats()
|
||||
t.Cleanup(func() { UseSeats(was) })
|
||||
|
||||
// A store whose bus seat delivers something this module does provide.
|
||||
UseSeats([]Seat{{Name: "mesh-broker", Scope: ScopeMesh, Delivers: "amqp", Decision: "test"}})
|
||||
raw := []byte(`{"module":"lavinmq","version":"1",` +
|
||||
`"provides":[{"name":"amqp","scope":"mesh"}],` +
|
||||
`"claims":[{"name":"mesh-broker","scope":"mesh"}]}`)
|
||||
|
||||
m, err := ParseManifest(raw)
|
||||
if err != nil {
|
||||
t.Fatalf("the parser refused a claim only the seat set can judge: %v", err)
|
||||
}
|
||||
if got := CatalogueProblems(Shelf{m.Module: m}); len(got) != 0 {
|
||||
t.Fatalf("a holder that provides what the store says the seat delivers was refused: %v", got)
|
||||
}
|
||||
|
||||
// And with the store saying the seat delivers something else, registration is what refuses it.
|
||||
UseSeats([]Seat{{Name: "mesh-broker", Scope: ScopeMesh, Delivers: "mesh-bus", Decision: "test"}})
|
||||
if _, err := ParseManifest(raw); err != nil {
|
||||
t.Fatalf("the parser judged it the second time: %v", err)
|
||||
}
|
||||
got := strings.Join(CatalogueProblems(Shelf{m.Module: m}), "; ")
|
||||
if !strings.Contains(got, `does not provide "mesh-bus"`) {
|
||||
t.Fatalf("registration did not refuse a holder that cannot answer for the seat: %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -138,26 +138,32 @@ func TestAModuleDefinesAndClaimsItsOwnSeat(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// **At registration, not in the parser** (novox/hq ADR 0122): a seat's scope is a property of the
|
||||
// set, the set is the store's, and the parser also runs on a build machine that has no store.
|
||||
func TestASeatClaimedAtAnotherScopeIsRefused(t *testing.T) {
|
||||
_, err := ParseManifest(claimed(`[{"name":"npm-package-registry","scope":"node"}]`))
|
||||
if err == nil {
|
||||
t.Fatal("a mesh seat was held per node")
|
||||
m, err := ParseManifest(claimed(`[{"name":"npm-package-registry","scope":"node"}]`))
|
||||
if err != nil {
|
||||
t.Fatalf("the parser judged a scope it reads from data it may not have: %v", err)
|
||||
}
|
||||
if !strings.Contains(err.Error(), "mesh seat") {
|
||||
t.Fatalf("the refusal does not say which scope the seat is: %v", err)
|
||||
got := strings.Join(CatalogueProblems(Shelf{m.Module: m}), "; ")
|
||||
if !strings.Contains(got, "mesh seat") {
|
||||
t.Fatalf("the refusal does not say which scope the seat is: %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestADeliveringSeatIsOnlyHeldByAModuleThatProvides(t *testing.T) {
|
||||
// Holding it makes the module the mesh's answer for the provision. A module that cannot answer
|
||||
// would be the answer anyway, and every consumer would be sent to it.
|
||||
// And refused at registration, where the seat set is the store's: what a seat delivers is
|
||||
// data, so a compiled copy of it may not be what refuses a build (novox/hq ADR 0122).
|
||||
raw := []byte(`{"module":"thing","version":"1","claims":[{"name":"git","scope":"mesh"}]}`)
|
||||
_, err := ParseManifest(raw)
|
||||
if err == nil {
|
||||
t.Fatal("a module holding the git seat need not provide git")
|
||||
m, err := ParseManifest(raw)
|
||||
if err != nil {
|
||||
t.Fatalf("the parser judged what a seat delivers: %v", err)
|
||||
}
|
||||
if !strings.Contains(err.Error(), `does not provide "git"`) {
|
||||
t.Fatalf("the refusal does not say what is missing: %v", err)
|
||||
got := strings.Join(CatalogueProblems(Shelf{m.Module: m}), "; ")
|
||||
if !strings.Contains(got, `does not provide "git"`) {
|
||||
t.Fatalf("the refusal does not say what is missing: %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user