Files
bind-operator/internal/controller/bindzone_notify_test.go
T
unkinben aab11457af
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
Make intra-cluster NOTIFY loop-free (TSIG-keyed, no pod IPs in restart config)
v0.2.5 (PR #14) added an options-scope allow-notify enumerating the primary
pod IP on secondaries. Options-scope config feeds the config-hash annotation
that rolls the StatefulSet, so any config change rolled the pods, the primary
came back on a new pod IP, the operator re-rendered with the new IP, the hash
changed, the pods rolled again — an infinite roll loop across every
BindCluster. The prod deployment was reverted to v0.2.4.

Replace the pod-IP allow-notify with TSIG-authenticated NOTIFY:

- Secondaries render `allow-notify { key "<name>"; };` — a static key element
  with NO IPs. It depends only on the key name, so pod-IP churn can never
  change the render, the config-hash, or trigger a restart.
- The primary signs its outgoing NOTIFYs: the zone-scope also-notify entries
  (already enumerating replica pod IPs, applied via rndc addzone/modzone with
  NO restart) now carry `key "<name>"`.
- Key choice: reuse the cluster's catalog transfer TSIG key (TransferKeyRef).
  Secondaries already present it for AXFR and it is in keys.conf on every pod,
  so no new key plumbing is needed.

Add a permanent regression guard for the loop class:
- controller: reconcile the ConfigMap with the primary pod on two different
  IPs and assert the config-hash is byte-identical.
- render: render restart-scoped input and assert no pod IP appears in
  allow-notify; RenderInput no longer has any pod-IP field.

Zone-scope also-notify (rndc, no restart) legitimately still lists pod IPs;
only restart-scoped config must be pod-IP-independent.
2026-07-25 23:31:20 +10:00

66 lines
2.3 KiB
Go

package controller
import (
"context"
"strings"
"testing"
bindv1alpha1 "git.unkin.net/unkin/bind-operator/api/v1alpha1"
)
// A primary zone with known secondaries renders notify explicit + also-notify
// so a dynamic update NOTIFYs the secondaries immediately.
func TestBuildZoneConfigPrimaryAlsoNotify(t *testing.T) {
r := &BindZoneReconciler{}
zone := &bindv1alpha1.BindZone{
Spec: bindv1alpha1.BindZoneSpec{
ZoneName: "main.unkin.net",
Type: bindv1alpha1.ZonePrimary,
},
}
cfg, err := r.buildZoneConfig(context.Background(), zone, "transfer-key", []string{"10.42.2.6", "10.42.1.5"}, "externaldns-key")
if err != nil {
t.Fatalf("buildZoneConfig: %v", err)
}
if !strings.Contains(cfg, "notify explicit") {
t.Errorf("expected notify explicit in %q", cfg)
}
// also-notify entries are keyed so secondaries can admit the NOTIFY by TSIG
// key (allow-notify { key ... }) instead of by (churning) pod IP.
if !strings.Contains(cfg, `also-notify { 10.42.2.6 key "externaldns-key"; 10.42.1.5 key "externaldns-key"; }`) {
t.Errorf("expected keyed also-notify with the secondary IPs in %q", cfg)
}
}
// also-notify entries carry no key when none is configured (unkeyed NOTIFY).
func TestBuildZoneConfigPrimaryAlsoNotifyUnkeyed(t *testing.T) {
r := &BindZoneReconciler{}
zone := &bindv1alpha1.BindZone{
Spec: bindv1alpha1.BindZoneSpec{ZoneName: "main.unkin.net", Type: bindv1alpha1.ZonePrimary},
}
cfg, err := r.buildZoneConfig(context.Background(), zone, "transfer-key", []string{"10.42.2.6"}, "")
if err != nil {
t.Fatalf("buildZoneConfig: %v", err)
}
if !strings.Contains(cfg, "also-notify { 10.42.2.6; }") {
t.Errorf("expected unkeyed also-notify in %q", cfg)
}
}
// With no secondaries, no also-notify is emitted (single-replica cluster).
func TestBuildZoneConfigPrimaryNoNotifyTargets(t *testing.T) {
r := &BindZoneReconciler{}
zone := &bindv1alpha1.BindZone{
Spec: bindv1alpha1.BindZoneSpec{ZoneName: "main.unkin.net", Type: bindv1alpha1.ZonePrimary},
}
cfg, err := r.buildZoneConfig(context.Background(), zone, "transfer-key", nil, "externaldns-key")
if err != nil {
t.Fatalf("buildZoneConfig: %v", err)
}
if strings.Contains(cfg, "also-notify") || strings.Contains(cfg, "notify explicit") {
t.Errorf("did not expect notify clauses with no targets: %q", cfg)
}
}