Apply only the node's own compositions, never the controller's
mesh/delivery merged: source.main moved to novox/mesh-host@84737f4cb26d
mesh/check being carried to 38d666f22390 on 84737f4cb26d | from 14a12cc7b6f9
mesh/delivery merged: source.main moved to novox/mesh-host@84737f4cb26d
mesh/check being carried to 38d666f22390 on 84737f4cb26d | from 14a12cc7b6f9
The controller ended by its unassignment, so a node that falls back to the compositions in its bucket follows what nobody writes (issue 1126, A7). The node agent now always runs its own composer: without a placement key it composes nothing and keeps what runs, a placement it cannot watch stops the agent and is said, and a candidate taking its placement away is refused instead of answered as a return to the controller. The start-time placement read, the end-when-placed watchers and the returning answer go, with their tests and the three integration tests of the controller-composed path. Claude-Session: https://claude.ai/code/session_01NcbgfJ9Gum47zkFKWRaovL
This commit is contained in:
@@ -21,7 +21,6 @@ import (
|
||||
"github.com/novox/mesh-host/internal/agent"
|
||||
"github.com/novox/mesh-host/internal/link"
|
||||
"github.com/novox/mesh-host/internal/selfcompose"
|
||||
"github.com/novox/mesh-host/internal/store"
|
||||
)
|
||||
|
||||
// The node agent whole, against a real bus with JetStream started in the test: the wants bucket, the node's composition
|
||||
@@ -237,126 +236,6 @@ func within(t *testing.T, d time.Duration, what string, ok func() bool) {
|
||||
}
|
||||
}
|
||||
|
||||
// R6-A AC1: given a running agent on a bus, when a want naming a digest and that composition are written, the module is
|
||||
// applied within one second and its have names the fingerprint and the digest; a composition whose digest no want names
|
||||
// is not applied.
|
||||
func TestNatsAWantAndItsCompositionAreAppliedWithinASecond(t *testing.T) {
|
||||
t.Run("1957: an engine start starts a declared-running unit", testNatsAnEngineStartStartsADeclaredRunningUnitTheHaveSaysRuns)
|
||||
b := newItBed(t)
|
||||
stop := b.start(false)
|
||||
defer stop()
|
||||
time.Sleep(300 * time.Millisecond) // the watches are up
|
||||
|
||||
fp := fpIt("a")
|
||||
dig := b.compose("web", fp, "one\n", false, b.controll)
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
if b.file("web") != "" {
|
||||
t.Fatal("a composition no want names was applied")
|
||||
}
|
||||
began := time.Now()
|
||||
b.want("web", fp, dig, "")
|
||||
within(t, time.Second, "the module was not applied within one second of its want", func() bool { return b.file("web") == "one\n" })
|
||||
t.Logf("applied %s after the want", time.Since(began))
|
||||
within(t, 2*time.Second, "the have does not name the fingerprint and the digest", func() bool {
|
||||
h := b.have("web")
|
||||
return h.FP == fp && h.Composed == dig && h.Phase == delivery.PhaseRunning
|
||||
})
|
||||
|
||||
// A want naming a digest the composition at its fingerprint does not have applies nothing.
|
||||
fp2 := fpIt("b")
|
||||
b.compose("web", fp2, "two\n", false, b.controll)
|
||||
b.want("web", fp2, "sha256:"+strings.Repeat("0", 64), "")
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
if b.file("web") != "one\n" {
|
||||
t.Fatalf("a want naming another digest changed the module: %q", b.file("web"))
|
||||
}
|
||||
}
|
||||
|
||||
// R6-A AC5: a data module that ran before asks its backup before any resource changes; a backup that fails holds the
|
||||
// module (nothing applied, the have says held with the backup's words); when its want then says skip, it is applied.
|
||||
func TestNatsADataModuleAsksItsBackupFirstAndIsHeldWhenItFails(t *testing.T) {
|
||||
b := newItBed(t)
|
||||
var mu sync.Mutex
|
||||
var asked []string
|
||||
var onDiskWhenAsked string
|
||||
if _, err := b.conn.Subscribe("mesh.seat.node-backup.tool.now."+itNode, func(m *nats.Msg) {
|
||||
mu.Lock()
|
||||
asked = append(asked, "now")
|
||||
onDiskWhenAsked = b.file("db")
|
||||
mu.Unlock()
|
||||
_ = m.Respond([]byte(`{"result":{"started":"db"}}`))
|
||||
// The holder says the backup ended on its event.
|
||||
ev, _ := json.Marshal(map[string]any{"node": itNode, "module": "db", "ok": false, "at": time.Now().UTC(),
|
||||
"error": "restic: the repository is locked"})
|
||||
_ = b.conn.Publish(backedUpEvent, ev)
|
||||
}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
stop := b.start(false)
|
||||
defer stop()
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
|
||||
fp1, fp2 := fpIt("a"), fpIt("b")
|
||||
b.want("db", fp1, b.compose("db", fp1, "v1\n", true, b.controll), "")
|
||||
within(t, 3*time.Second, "the first composition was not applied", func() bool { return b.file("db") == "v1\n" })
|
||||
mu.Lock()
|
||||
if len(asked) != 0 {
|
||||
t.Fatalf("a module that never ran was backed up: %v", asked)
|
||||
}
|
||||
mu.Unlock()
|
||||
|
||||
dig2 := b.compose("db", fp2, "v2\n", true, b.controll)
|
||||
b.want("db", fp2, dig2, "")
|
||||
within(t, 3*time.Second, "the module was not held behind the failed backup", func() bool {
|
||||
h := b.have("db")
|
||||
return h.Phase == delivery.PhaseHeld && strings.Contains(h.Detail, "repository is locked")
|
||||
})
|
||||
mu.Lock()
|
||||
if len(asked) != 1 || onDiskWhenAsked != "v1\n" {
|
||||
t.Fatalf("the backup was asked %v, with %q on disk: it is asked before any resource changes", asked, onDiskWhenAsked)
|
||||
}
|
||||
mu.Unlock()
|
||||
if b.file("db") != "v1\n" {
|
||||
t.Fatalf("something was applied behind a failed backup: %q", b.file("db"))
|
||||
}
|
||||
if h := b.have("db"); h.FP != fp1 {
|
||||
t.Fatalf("a held module should still name what it runs: %+v", h)
|
||||
}
|
||||
|
||||
b.want("db", fp2, dig2, delivery.BackupSkip)
|
||||
within(t, 3*time.Second, "the module was not applied once its want said skip", func() bool { return b.file("db") == "v2\n" })
|
||||
within(t, 2*time.Second, "the have does not say running at the new fingerprint", func() bool {
|
||||
h := b.have("db")
|
||||
return h.Phase == delivery.PhaseRunning && h.FP == fp2 && h.Composed == dig2
|
||||
})
|
||||
}
|
||||
|
||||
// R6-A AC9, the hand path end to end: with no controller running, a composition signed by the operator's key and a want
|
||||
// naming it are applied and the have written; the same signed by a key nobody trusts is not.
|
||||
func TestNatsTheHandPathAppliesACompositionTheOperatorSigned(t *testing.T) {
|
||||
b := newItBed(t)
|
||||
stop := b.start(true)
|
||||
defer stop()
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
|
||||
_, stranger, _ := ed25519.GenerateKey(nil)
|
||||
fpS := fpIt("c")
|
||||
b.want("evil", fpS, b.compose("evil", fpS, "no\n", false, stranger), "")
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
if b.file("evil") != "" {
|
||||
t.Fatal("a composition signed by a key nobody trusts was applied")
|
||||
}
|
||||
|
||||
fp := fpIt("d")
|
||||
dig := b.compose("rescue", fp, "back\n", false, b.operator)
|
||||
b.want("rescue", fp, dig, "")
|
||||
within(t, 2*time.Second, "the operator's composition was not applied", func() bool { return b.file("rescue") == "back\n" })
|
||||
within(t, 2*time.Second, "the have was not written", func() bool {
|
||||
h := b.have("rescue")
|
||||
return h.FP == fp && h.Composed == dig && h.Phase == delivery.PhaseRunning
|
||||
})
|
||||
}
|
||||
|
||||
// Issue 1126 (ADR 0547 §2, the milestone's H8): the node agent started whole against a real bus, once the catalogue
|
||||
// places its node (the placement written after it started), composes a module from its want, the indexer's manifest, its record and its mesh-config value, and applies it,
|
||||
// with no key in the controller's compositions; a changed config value is composed again on its event and applied as a
|
||||
@@ -478,9 +357,10 @@ func h8once(t *testing.T, b *itBed, resolved, candidates nats.KeyValue, place []
|
||||
}
|
||||
}
|
||||
|
||||
// h8back is the way back (issue 1126, the seed's revert): a candidate deleting the node's placement is compared with
|
||||
// the controller's compositions at its wants (here none: refused, naming web), and the placement key deleted returns the agent to them without a
|
||||
// restart, said in the journal and the node's have, keeping what runs.
|
||||
// h8back is A7 of issue 1126: no composition made elsewhere is applied. A candidate deleting the node's placement is
|
||||
// refused, never answered as a return to the controller's compositions; the placement key deleted leaves the agent on
|
||||
// its own composer, composing nothing and keeping what runs, said in the journal, the node's have still saying it
|
||||
// composes its own.
|
||||
func h8back(t *testing.T, b *itBed, placement, resolved, candidates nats.KeyValue, hkey string) {
|
||||
t.Helper()
|
||||
node := func() delivery.HaveNode {
|
||||
@@ -502,65 +382,38 @@ func h8back(t *testing.T, b *itBed, placement, resolved, candidates nats.KeyValu
|
||||
if _, err := candidates.Put(ckey, craw); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// The controller holds no composition at web's want (the node composed its own): returning would leave web with
|
||||
// nothing to apply, and the answer says so rather than "same" (review of the shadow, round 1).
|
||||
within(t, 10*time.Second, "the node did not refuse returning to compositions the controller does not hold", func() bool {
|
||||
within(t, 10*time.Second, "the node did not refuse a candidate taking its placement away", func() bool {
|
||||
a := node().Candidates["revert-x"]
|
||||
return a.Proposal == "revert-x" && a.Returns == "" && a.Verdict == delivery.CandidateRefused &&
|
||||
strings.Contains(a.Refused, "web: the controller holds no composition")
|
||||
strings.Contains(a.Refused, "composes nothing")
|
||||
})
|
||||
ran := b.have("web").Composed
|
||||
pkey, _ := delivery.PlacementNodeKey(itNode)
|
||||
// A pass in flight at the switch (issue 1126, 2026-10-28: the last pass of the own run, failing on its run's end,
|
||||
// marked the next agent's modules failed): a config value changed starts one, and the key goes at once.
|
||||
// A pass in flight when the key goes (issue 1126, 2026-10-28): a config value changed starts one, and the key goes at once.
|
||||
if _, err := resolved.Put(itNode+".web.greeting", []byte(`{"value":"salut","source":"module"}`)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := placement.Delete(pkey); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
stopWatch := make(chan struct{})
|
||||
marked := make(chan Have1126, 1)
|
||||
go func() {
|
||||
for {
|
||||
select {
|
||||
case <-stopWatch:
|
||||
return
|
||||
case <-time.After(20 * time.Millisecond):
|
||||
}
|
||||
if h := b.have("web"); h.Phase == delivery.PhaseFailed {
|
||||
select {
|
||||
case marked <- Have1126{h.Phase, h.Detail}:
|
||||
default:
|
||||
}
|
||||
return
|
||||
}
|
||||
}
|
||||
}()
|
||||
defer close(stopWatch)
|
||||
within(t, 15*time.Second, "the node did not return to the controller's compositions when its placement went", func() bool {
|
||||
within(t, 15*time.Second, "the node did not say it composes nothing once its placement went", func() bool {
|
||||
b.mu.Lock()
|
||||
said := strings.Join(b.said, "\n")
|
||||
b.mu.Unlock()
|
||||
return strings.Contains(said, "key in the seat's placement state is gone") && node().Composes == delivery.ComposesController
|
||||
return strings.Contains(said, "key in the seat's placement state is gone: it composes nothing of its own")
|
||||
})
|
||||
time.Sleep(3 * time.Second) // what a pass in flight would mark lands within it
|
||||
select {
|
||||
case h := <-marked:
|
||||
t.Errorf("a pass in flight at the switch marked web failed: %+v", h)
|
||||
default:
|
||||
b.mu.Lock()
|
||||
said := strings.Join(b.said, "\n")
|
||||
b.mu.Unlock()
|
||||
if n := node(); n.Composes != delivery.ComposesOwn || strings.Contains(said, "applying the controller's compositions") {
|
||||
t.Errorf("without its placement the node turned to the controller's compositions: %q", n.Composes)
|
||||
}
|
||||
if h := b.have("web"); h.Composed != ran || h.Phase == delivery.PhaseFailed || b.file("web") != "greeting=salut\n" {
|
||||
t.Errorf("returning to the controller's compositions moved what runs: %+v, %q", h, b.file("web"))
|
||||
t.Errorf("without its placement what runs moved: %+v, %q", h, b.file("web"))
|
||||
}
|
||||
}
|
||||
|
||||
// Have1126 is what H8's way back watches of web's have.
|
||||
type Have1126 struct {
|
||||
Phase delivery.Phase
|
||||
Detail string
|
||||
}
|
||||
|
||||
// h8state is what h8 set up that the rest of H8 writes to.
|
||||
type h8state struct {
|
||||
placement, resolved, candidates nats.KeyValue
|
||||
@@ -730,71 +583,3 @@ func h8rest(t *testing.T, b *itBed, resolved, candidates nats.KeyValue, hkey str
|
||||
t.Errorf("a candidate moved what runs: %+v, %q", h, b.file("web"))
|
||||
}
|
||||
}
|
||||
|
||||
// 1957/AC1 (integration; ADR 0568 §1): a node agent starting on a bus that holds a `running` have for a module at its want,
|
||||
// with a service manager (a systemctl on the PATH) that shows the module's unit inactive, starts the unit once and writes
|
||||
// the have running; the same start with the unit active applies nothing.
|
||||
func testNatsAnEngineStartStartsADeclaredRunningUnitTheHaveSaysRuns(t *testing.T) {
|
||||
for _, active := range []bool{false, true} {
|
||||
b := newItBed(t)
|
||||
bin := t.TempDir()
|
||||
stateFile, calls := filepath.Join(bin, "state"), filepath.Join(bin, "calls")
|
||||
if active {
|
||||
os.WriteFile(stateFile, []byte("active"), 0o644)
|
||||
} else {
|
||||
os.WriteFile(stateFile, []byte("inactive"), 0o644)
|
||||
}
|
||||
script := "#!/bin/sh\necho \"$@\" >> " + calls + "\ncase \"$1\" in\n" +
|
||||
"show) printf 'LoadState=loaded\\nActiveState=%s\\nType=simple\\n' \"$(cat " + stateFile + ")\" ;;\n" +
|
||||
"start) printf active > " + stateFile + " ;;\nis-enabled) echo enabled ;;\nesac\nexit 0\n"
|
||||
if err := os.WriteFile(filepath.Join(bin, "systemctl"), []byte(script), 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Setenv("PATH", bin+string(os.PathListSeparator)+os.Getenv("PATH"))
|
||||
|
||||
// The engine's own record of the unit, as a previous run left it, and the have it wrote then.
|
||||
res, _ := json.Marshal(map[string]any{"id": "web.unit", "type": "service", "unit": "web-it.service", "state": "running", "module": "web"})
|
||||
var known store.State
|
||||
known.Record(store.Applied{ID: "web.unit", Type: "service", Target: "web-it.service"})
|
||||
if err := store.Save(b.opts.state, known); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
fp := fpIt("a")
|
||||
c := delivery.Composed{Node: itNode, Module: "web", FP: fp, Resources: []json.RawMessage{res}}
|
||||
signed, _ := delivery.SignComposed(c, b.controll)
|
||||
raw, _ := delivery.EncodeComposed(signed)
|
||||
dig, _ := delivery.ComposedDigestOf(signed)
|
||||
key, _ := delivery.ComposedKey(itNode, "web", fp)
|
||||
if _, err := b.composed.Put(key, raw); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
b.want("web", fp, dig, "")
|
||||
hkey, _ := delivery.HaveKey(itNode, "web")
|
||||
have, err := delivery.EncodeHave(delivery.Have{FP: fp, Composed: dig, Phase: delivery.PhaseRunning, Health: delivery.HealthUnknown})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := b.haves.Put(hkey, have); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
stop := b.start(false)
|
||||
within(t, 5*time.Second, "the unit was not started and the have not running", func() bool {
|
||||
got, _ := os.ReadFile(stateFile)
|
||||
h := b.have("web")
|
||||
return string(got) == "active" && h.Phase == delivery.PhaseRunning && h.Composed == dig
|
||||
})
|
||||
time.Sleep(300 * time.Millisecond)
|
||||
stop()
|
||||
starts := 0
|
||||
log, _ := os.ReadFile(calls)
|
||||
for _, l := range strings.Split(string(log), "\n") {
|
||||
if strings.HasPrefix(l, "start") {
|
||||
starts++
|
||||
}
|
||||
}
|
||||
if want := map[bool]int{false: 1, true: 0}[active]; starts != want {
|
||||
t.Fatalf("unit active=%v: started %d times, want %d", active, starts, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user