Answer the review of hq issues 348 and 349: gaps, parts, the newest merge in any state
- A reopened fault keeps its gaps: it was there at a send unless the send fell in one, so a send that breaks a machine recovered before it still fails its gate (A2). - An undecided part holds only the conditions that name it (A4). - D2 holds a silent resolver for the next run again, refused or not: a burst of refusals is also a restart (A3). - A late merge is planned at the newest planned merge of its branch in any state, not only an open one (A1); merge times to the nanosecond (A5).
This commit is contained in:
@@ -98,9 +98,9 @@ func judgeNetworks(ctx context.Context, inv *inventory.Inventory, k *conditions.
|
||||
problems = append(problems, err.Error())
|
||||
}
|
||||
}
|
||||
undecided := undecidedMachines(f)
|
||||
undecided := undecidedParts(f)
|
||||
for _, c := range open {
|
||||
if !slices.Contains(networkKinds, c.Kind) || said[c.Key] || undecided[c.Subject.Machine] {
|
||||
if !slices.Contains(networkKinds, c.Kind) || said[c.Key] || heldUndecided(c, undecided) {
|
||||
continue
|
||||
}
|
||||
why := "no machine says it any more"
|
||||
@@ -117,36 +117,59 @@ func judgeNetworks(ctx context.Context, inv *inventory.Inventory, k *conditions.
|
||||
return nil
|
||||
}
|
||||
|
||||
// undecidedMachines is every machine whose newest statement has a part not yet judged: starting, or
|
||||
// unknown — one look failed and a second decides (novox/hq issue 348). Such a statement does not say a
|
||||
// fault is gone, so an open network condition about that machine is kept until a statement decides.
|
||||
// undecidedParts is, per machine, every part of its newest statement not yet judged: starting, or unknown
|
||||
// — one look failed and a second decides (novox/hq issue 348). Such a part does not say its fault is gone.
|
||||
// A statement whose parts are all decided but whose whole is unknown or starting holds every part. Pure.
|
||||
//
|
||||
// On 2026-10-09 the control node's resolver refused every question from 10:58 to 11:18 UTC. A build of
|
||||
// the node-engine sent at 10:59:34 restarted it; its first statement after the restart judged the names
|
||||
// once (unknown, "one look failed; a second decides"), and that statement cleared the control node's
|
||||
// network condition while its last evidence still said "connection refused". The second look raised it
|
||||
// again forty seconds later — after the send — and the gate failed the build for a fault from before it.
|
||||
// Pure.
|
||||
func undecidedMachines(f networkFacts) map[string]bool {
|
||||
out := map[string]bool{}
|
||||
// the node-engine sent at 10:59:34 restarted it; its first statement judged the names once (unknown, "one
|
||||
// look failed; a second decides"), and that statement cleared the control node's network condition while
|
||||
// its last evidence still said "connection refused". The second look raised it again forty seconds later —
|
||||
// after the send — and the gate failed the build for a fault from before it.
|
||||
func undecidedParts(f networkFacts) map[string]map[string]bool {
|
||||
out := map[string]map[string]bool{}
|
||||
for m, h := range f.healths {
|
||||
if h.Network == nil {
|
||||
continue
|
||||
}
|
||||
if h.Network.State == link.StateUnknown || h.Network.State == link.StateStarting {
|
||||
out[m] = true
|
||||
continue
|
||||
}
|
||||
parts := map[string]bool{}
|
||||
for _, p := range h.Network.Parts {
|
||||
if p.State == link.StateUnknown || p.State == link.StateStarting {
|
||||
out[m] = true
|
||||
break
|
||||
parts[p.Part] = true
|
||||
}
|
||||
}
|
||||
if len(parts) == 0 && (h.Network.State == link.StateUnknown || h.Network.State == link.StateStarting) {
|
||||
parts["*"] = true
|
||||
}
|
||||
if len(parts) > 0 {
|
||||
out[m] = parts
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// heldUndecided says an open network condition is kept rather than cleared: a part its newest evidence
|
||||
// names is undecided in the newest statement of a machine it is about. A condition about other parts
|
||||
// clears as before. Pure.
|
||||
func heldUndecided(c conditions.Condition, undecided map[string]map[string]bool) bool {
|
||||
said := ""
|
||||
if len(c.Evidence) > 0 {
|
||||
said = c.Evidence[0].Said
|
||||
}
|
||||
for _, m := range append([]string{c.Subject.Machine}, c.Subject.Also...) {
|
||||
parts := undecided[m]
|
||||
if parts["*"] {
|
||||
return true
|
||||
}
|
||||
for part := range parts {
|
||||
if strings.Contains(said, part+" since ") || strings.Contains(said, part+": ") {
|
||||
return true
|
||||
}
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// pointed is one machine's failing part that points at another machine.
|
||||
type pointed struct {
|
||||
from string
|
||||
|
||||
Reference in New Issue
Block a user