fix: add self-healing for forward service name migration

When upgrading from older versions, service names changed from
placeholder IDs (forward_user_0) to real user_tunnel IDs, causing
service not found errors during control operations.

- Add fallback cleanup+rebuild logic on UpdateService when service
  not found during the upgrade transition period.
- Add self-healing retry on Pause/Resume when all variants are missing.
- Refactor controlForwardServicesOnNode to support unit testing.
- Add tests for shouldSelfHealForwardServiceControl and
  controlForwardServiceCommand helper functions.

Entire-Checkpoint: a7f0c3175d06
This commit is contained in:
sagitchu
2026-03-05 12:40:20 +08:00
parent 32474bec20
commit f496f58a4d
3 changed files with 160 additions and 26 deletions
@@ -290,6 +290,11 @@ func (h *Handler) syncForwardServicesWithWarnings(forward *forwardRecord, method
services := buildForwardServiceConfigs(serviceBase, forward, tunnel, node, fp.Port, strings.TrimSpace(fp.InIP), limiterID, tunnelTLSProtocol)
_, err = h.sendNodeCommand(node.ID, method, services, true, false)
if err != nil && allowFallbackAdd && method == "UpdateService" {
if isNotFoundError(err) {
if delErr := h.deleteForwardServicesOnNode(forward, node.ID); delErr != nil && !isNotFoundError(delErr) {
return warnings, fmt.Errorf("节点 %s 清理旧服务失败: %w", node.Name, delErr)
}
}
_, err = h.sendNodeCommand(node.ID, "AddService", services, true, false)
}
if err != nil && strings.EqualFold(strings.TrimSpace(method), "UpdateService") && isAddressAlreadyInUseError(err) {
@@ -437,40 +442,26 @@ func (h *Handler) controlForwardServices(forward *forwardRecord, commandType str
candidateTunnelIDs = append(candidateTunnelIDs, allUserTunnelIDs...)
bases := buildForwardServiceBaseCandidates(forward.ID, forward.UserID, userTunnelID, candidateTunnelIDs)
seen := map[int64]struct{}{}
healed := false
for _, fp := range ports {
if _, ok := seen[fp.NodeID]; ok {
continue
}
seen[fp.NodeID] = struct{}{}
var lastNotFoundErr error
nodeHandled := false
nodeHandled, lastNotFoundErr, err := h.controlForwardServicesOnNode(fp.NodeID, bases, commandType)
if err != nil {
return err
}
for _, base := range bases {
variants := []string{base + "_tcp", base + "_udp"}
if shouldTryLegacySingleService(commandType) || strings.EqualFold(strings.TrimSpace(commandType), "DeleteService") {
variants = append(variants, base)
if !nodeHandled && lastNotFoundErr != nil && !healed && shouldSelfHealForwardServiceControl(commandType) {
if healErr := h.syncForwardServices(forward, "UpdateService", true); healErr != nil {
return healErr
}
candidateHandled := false
for _, name := range variants {
payload := map[string]interface{}{
"services": []string{name},
}
_, err := h.sendNodeCommand(fp.NodeID, commandType, payload, false, false)
if err == nil {
candidateHandled = true
continue
}
if !isNotFoundError(err) {
return err
}
lastNotFoundErr = err
}
if candidateHandled {
nodeHandled = true
break
healed = true
nodeHandled, lastNotFoundErr, err = h.controlForwardServicesOnNode(fp.NodeID, bases, commandType)
if err != nil {
return err
}
}
@@ -488,6 +479,49 @@ func (h *Handler) controlForwardServices(forward *forwardRecord, commandType str
return nil
}
func (h *Handler) controlForwardServicesOnNode(nodeID int64, bases []string, commandType string) (bool, error, error) {
return controlForwardServiceCommand(bases, commandType, func(name string) error {
payload := map[string]interface{}{
"services": []string{name},
}
_, err := h.sendNodeCommand(nodeID, commandType, payload, false, false)
return err
})
}
func controlForwardServiceCommand(bases []string, commandType string, send func(name string) error) (bool, error, error) {
var lastNotFoundErr error
for _, base := range bases {
variants := []string{base + "_tcp", base + "_udp"}
if shouldTryLegacySingleService(commandType) || strings.EqualFold(strings.TrimSpace(commandType), "DeleteService") {
variants = append(variants, base)
}
candidateHandled := false
for _, name := range variants {
err := send(name)
if err == nil {
candidateHandled = true
continue
}
if !isNotFoundError(err) {
return false, lastNotFoundErr, err
}
lastNotFoundErr = err
}
if candidateHandled {
return true, nil, nil
}
}
return false, lastNotFoundErr, nil
}
func shouldSelfHealForwardServiceControl(commandType string) bool {
cmd := strings.ToLower(strings.TrimSpace(commandType))
return cmd == "pauseservice" || cmd == "resumeservice"
}
func (h *Handler) applyNodeProtocolChange(nodeID int64, httpVal, tlsVal, socksVal int) error {
_, err := h.sendNodeCommand(nodeID, "SetProtocol", map[string]interface{}{
"http": httpVal,
@@ -69,6 +69,78 @@ func TestShouldTryLegacySingleService(t *testing.T) {
}
}
func TestShouldSelfHealForwardServiceControl(t *testing.T) {
if !shouldSelfHealForwardServiceControl("PauseService") {
t.Fatalf("PauseService should trigger self-heal")
}
if !shouldSelfHealForwardServiceControl(" resumeService ") {
t.Fatalf("ResumeService should trigger self-heal")
}
if shouldSelfHealForwardServiceControl("DeleteService") {
t.Fatalf("DeleteService should not trigger self-heal")
}
}
func TestControlForwardServiceCommandHandledOnKnownVariant(t *testing.T) {
bases := []string{"12_34_56"}
called := make([]string, 0)
handled, lastNotFoundErr, err := controlForwardServiceCommand(bases, "PauseService", func(name string) error {
called = append(called, name)
if name == "12_34_56_udp" {
return nil
}
return errors.New("service " + name + " not found")
})
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if !handled {
t.Fatalf("expected handled=true")
}
if lastNotFoundErr != nil {
t.Fatalf("expected lastNotFoundErr=nil when handled")
}
wantCalls := []string{"12_34_56_tcp", "12_34_56_udp", "12_34_56"}
if !reflect.DeepEqual(called, wantCalls) {
t.Fatalf("expected calls %v, got %v", wantCalls, called)
}
}
func TestControlForwardServiceCommandReturnsLastNotFoundWhenAllMissing(t *testing.T) {
bases := []string{"12_34_56"}
handled, lastNotFoundErr, err := controlForwardServiceCommand(bases, "PauseService", func(name string) error {
return errors.New("service " + name + " not found")
})
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if handled {
t.Fatalf("expected handled=false")
}
if lastNotFoundErr == nil {
t.Fatalf("expected lastNotFoundErr when all variants are missing")
}
}
func TestControlForwardServiceCommandReturnsHardError(t *testing.T) {
bases := []string{"12_34_56"}
handled, lastNotFoundErr, err := controlForwardServiceCommand(bases, "PauseService", func(name string) error {
if name == "12_34_56_tcp" {
return errors.New("network timeout")
}
return nil
})
if err == nil {
t.Fatalf("expected hard error")
}
if handled {
t.Fatalf("expected handled=false on hard error")
}
if lastNotFoundErr != nil {
t.Fatalf("did not expect not-found error alongside hard error")
}
}
func TestIsAlreadyExistsMessage(t *testing.T) {
if !isAlreadyExistsMessage("service demo already exists") {
t.Fatalf("expected already exists message to be tolerated")