feat(cluster): bidirektionaler Peer-Heartbeat (Primary→Secondary Push) — v1.2.97

Bisher pushte nur der Secondary seine Liveness an den Primary (runPrimaryPush). Der Primary pushte nichts → in der lokalen ha_nodes des Secondary fror die Primary-Row nach dem Boot ein → die vom Secondary ausgelieferte UI zeigte den Primary als offline.
Neu: runPeerPush auf dem Primary/Founder pusht alle 30s self (role=primary) an jeden Peer via mTLS (/agent/cluster/peers). PushSelfToPeer(role) generalisiert PushSelfToPrimary; registerPeerRequest+AgentRegisterPeer akzeptieren ein role-Feld (default 'peer' → joining-Peer-Verhalten unverändert). Peer-Register-Log bei Routine-Pushes auf Debug (Info nur bei neuem Peer/IP-Wechsel) gegen 30s-Spam.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Debian
2026-06-06 13:24:13 +02:00
parent b20ace8763
commit b3dda81b49
4 changed files with 86 additions and 6 deletions

View File

@@ -128,7 +128,7 @@ func Join(req Request) error {
// synchronous on the primary side.
var autoRegErr error
for i := 0; i < 3; i++ {
if err := autoRegister(primary, tlsDir, req.CommonName, req.Version, req.NodeID, ""); err == nil {
if err := autoRegister(primary, tlsDir, req.CommonName, req.Version, req.NodeID, "", "peer"); err == nil {
autoRegErr = nil
break
} else {
@@ -222,13 +222,21 @@ func issueCert(primary, token, csr string, insecure bool) (caCert, peerCert stri
// goroutine so the primary's ha_nodes always reflects the secondary's actual
// config_hash (not the stale join-time value).
func PushSelfToPrimary(primaryURL, tlsDir, nodeID, fqdn, version, configHash string) error {
return PushSelfToPeer(primaryURL, tlsDir, nodeID, fqdn, version, configHash, "peer")
}
// PushSelfToPeer sendet die eigene Identität an einen beliebigen Peer (mTLS,
// /agent/cluster/peers). role bestimmt, mit welcher Rolle sich dieser Node
// beim Empfänger einträgt: ein Secondary pusht "peer" an den Primary, der
// Primary pusht "primary" an jeden Secondary (bidirektionaler Heartbeat).
func PushSelfToPeer(peerURL, tlsDir, nodeID, fqdn, version, configHash, role string) error {
if tlsDir == "" {
tlsDir = clustertls.DefaultDir
}
return autoRegister(primaryURL, tlsDir, fqdn, version, nodeID, configHash)
return autoRegister(peerURL, tlsDir, fqdn, version, nodeID, configHash, role)
}
func autoRegister(primary, tlsDir, commonName, version, nodeID, configHash string) error {
func autoRegister(primary, tlsDir, commonName, version, nodeID, configHash, role string) error {
u, err := url.Parse(primary)
if err != nil {
return err
@@ -241,6 +249,9 @@ func autoRegister(primary, tlsDir, commonName, version, nodeID, configHash strin
nodeID = strings.TrimSpace(string(raw))
}
hostname, _ := os.Hostname()
if role == "" {
role = "peer"
}
body, _ := json.Marshal(map[string]string{
"id": nodeID,
"name": hostname,
@@ -248,6 +259,7 @@ func autoRegister(primary, tlsDir, commonName, version, nodeID, configHash strin
"api_url": "https://" + commonName + ":3443",
"version": version,
"config_hash": configHash,
"role": role,
})
pair, err := tls.LoadX509KeyPair(tlsDir+"/peer.crt", tlsDir+"/peer.key")