The node answers a placement candidate revision once: a module's have whose health words alone moved, or a key written again with its value, no longer composes every group's answer again (issue 1126)

On shanks probe/1126-seed-7 was answered at revision 84 every 13-17 s: each look rewrote the haves of its unhealthy modules with new words, and the shadow took any write of its own module haves, placement, modules or config values as a change. Each answer loaded the bus, the health tools timed out, the words moved again. Now only what an answer is composed from wakes it (what runs, folded modules, a changed value), and each group is answered again only when its keys' revisions or the node's inputs moved.
2026-10-28 12:02:57 +01:00
parent c3a2ffde67
commit 4182f8fbfb
3 changed files with 229 additions and 15 deletions
@@ -721,6 +721,65 @@ func TestTheNodeComposesItsWantsFromTheBus(t *testing.T) {
 		t.Errorf("answers handed again for nothing changed: %+v", a)
 	case <-time.After(100 * time.Millisecond):
 	}
+	// Issue 1126, 2026-10-28 (shanks answered probe/1126-seed-7 at revision 84 every 13-17 s): a candidate revision is
+	// answered once. A module's have whose health or words alone move (each look rewrites them), and a placement, a
+	// module or a config value written again with the value it held, answer nothing again; a new revision answers its
+	// group alone, and what runs moving answers every group once.
+	answering := func() int {
+		readOnly.mu.Lock()
+		defer readOnly.mu.Unlock()
+		n := 0
+		for _, l := range readOnly.said {
+			if strings.HasPrefix(l, "answering placement candidate ") {
+				n++
+			}
+		}
+		return n
+	}
+	drain := func() {
+		for {
+			select {
+			case answers = <-answered:
+			case <-time.After(150 * time.Millisecond):
+				return
+			}
+		}
+	}
+	lemursHave := func(detail string, rev uint64) {
+		raw, err := delivery.EncodeHave(delivery.Have{FP: fp, Composed: lemursDigest, Phase: delivery.PhaseRunning,
+			Health: delivery.HealthFailed, Detail: detail})
+		if err != nil {
+			t.Fatal(err)
+		}
+		hk, _ := delivery.HaveKey("n1", "lemurs")
+		sb.put(delivery.HaveBucket, hk, raw, rev)
+	}
+	lemursHave("its tool lemurs_health: no link to the bus is open", 10)
+	drain()
+	settled := answering()
+	lemursHave("its tool lemurs_health: no answer within 10s", 11)
+	lemursHave("its tool lemurs_health: no answer within 20s", 12)
+	sb.put(delivery.PlacementBucket, "placement.n1", tp, 2)
+	lraw, _ := delivery.EncodeModule(mods["lemurs"])
+	sb.put(delivery.ModulesBucket, "lemurs", lraw, 2)
+	drain()
+	if got := answering(); got != settled {
+		t.Errorf("answered %d more time(s) with no candidate revision and no input of the node changed", got-settled)
+	}
+	candidate("same", 8, "lemurs")
+	waitFor("the new revision answered", func(a map[string]delivery.CandidateAnswer) bool { return a["same"].Revision == 8 })
+	drain()
+	if got := answering(); got != settled+1 {
+		t.Errorf("a new revision of one group answered %d group(s), want 1", got-settled)
+	}
+	settled = answering()
+	hk, _ := delivery.HaveKey("n1", "lemurs")
+	moved, _ := delivery.EncodeHave(delivery.Have{FP: fp, Composed: "sha256:" + strings.Repeat("e", 64), Phase: delivery.PhaseRunning})
+	sb.put(delivery.HaveBucket, hk, moved, 13)
+	drain()
+	if got := answering(); got != settled+len(answers) {
+		t.Errorf("what runs moved, and %d answer(s) were composed again for %d group(s)", got-settled, len(answers))
+	}
 	k, _ := delivery.PlacementCandidateKey("same", "n1")
 	sb.del(delivery.PlacementCandidatesBucket, k)
 	waitFor("the deleted group's answer stays", func(a map[string]delivery.CandidateAnswer) bool { _, ok := a["same"]; return !ok && len(a) == 4 })