A node that runs a version alone-failed elsewhere still gets its want at it (ADR 0557 §2, issue 1496)
mesh/delivery merged: source.main moved to novox/mesh-delivery@bd107d20154c
mesh/delivery-group group fix/1496-start-health merged: every member is merged
mesh/check checking f007ca42279a on 4b36cc29a6ae | novox/mesh-delivery#81 in group fix/1496-start-health

Review of 50c4674: the bar on new wants naming F while a node fails it alone
also caught a node that runs F with no live want, the issue-1945 recovery path:
it went on neither list and its node-engine gave the module up. The bar now
holds only a node that neither wants nor runs F.
This commit is contained in:
2026-10-26 22:34:25 +01:00
parent 50c4674dfa
commit f007ca4227
2 changed files with 12 additions and 3 deletions
@@ -316,9 +316,11 @@ func Wants(m Module, n Nodes, wants map[string]delivery.Want, lastHealthy map[st
ok, target = true, have.FP
}
}
if ok && target == m.FP && len(out.NodeFailed) > 0 && !(had && !before.Removed && before.FP == m.FP) {
// While a node fails F alone, F reaches no further node: a node whose want does not name F yet gets no new want
// naming it, and wants already written stay (ADR 0557 §2).
if ok && target == m.FP && len(out.NodeFailed) > 0 && !(had && !before.Removed && before.FP == m.FP) &&
n.Haves[node][m.Name].FP != m.FP {
// While a node fails F alone, F reaches no further node: a node that neither wants nor runs F gets no new want
// naming it, and wants already written stay (ADR 0557 §2). A node that runs F with no live want gets its want at F, or
// it would be on neither list and its node-engine would give the module up (issue 1945).
ok, rule, words = false, delivery.RuleNotHeld, FailedAloneWords(m.Name, m.FP, slices.Sorted(maps.Keys(out.NodeFailed)))
}
switch {
@@ -183,6 +183,13 @@ func TestAFailedHealthHoldsAndSetsBack(t *testing.T) {
if _, written := out.Wants["g14"]; written {
t.Errorf("g14's want at F was rewritten: %+v", out.Wants["g14"])
}
// A node that runs F healthy with no want, while g14 fails it alone, gets its want at F and is on no neither list (issue 1945).
n.Haves["novox"]["mail"] = delivery.Have{FP: fNew, Phase: delivery.PhaseRunning, Health: delivery.HealthOK}
delete(before, "novox")
out = Wants(three, n, before, map[string]string{"ace": fOld, "g14": fOld, "novox": fOld})
if w := out.Wants["novox"]; w.FP != fNew || len(out.Neither) != 0 {
t.Errorf("novox running F with no want: want %+v, neither %+v; want its want at F and no neither", w, out.Neither)
}
n.Haves["ace"]["mail"], n.Haves["g14"]["mail"] = failedHave, n.Haves["ace"]["mail"]
// ADR 0557 §2: a witness that is offline keeps the have it last wrote and witnesses nothing (D1); F failing on a second node is