Files
netbird/client/internal/peer/guard/sr_watcher.go
Zoltan Papp 5a89e6621b [client] Supress ICE signaling (#5820)
* [client] Suppress ICE signaling and periodic offers in force-relay mode

When NB_FORCE_RELAY is enabled, skip WorkerICE creation entirely,
suppress ICE credentials in offer/answer messages, disable the
periodic ICE candidate monitor, and fix isConnectedOnAllWay to
only check relay status so the guard stops sending unnecessary offers.

* [client] Dynamically suppress ICE based on remote peer's offer credentials

Track whether the remote peer includes ICE credentials in its
offers/answers. When remote stops sending ICE credentials, skip
ICE listener dispatch, suppress ICE credentials in responses, and
exclude ICE from the guard connectivity check. When remote resumes
sending ICE credentials, re-enable all ICE behavior.

* [client] Fix nil SessionID panic and force ICE teardown on relay-only transition

Fix nil pointer dereference in signalOfferAnswer when SessionID is nil
(relay-only offers). Close stale ICE agent immediately when remote peer
stops sending ICE credentials to avoid traffic black-hole during the
ICE disconnect timeout.

* [client] Add relay-only fallback check when ICE is unavailable

Ensure the relay connection is supported with the peer when ICE is disabled to prevent connectivity issues.

* [client] Add tri-state connection status to guard for smarter ICE retry (#5828)

* [client] Add tri-state connection status to guard for smarter ICE retry

Refactor isConnectedOnAllWay to return a ConnStatus enum (Connected,
Disconnected, PartiallyConnected) instead of a boolean. When relay is
up but ICE is not (PartiallyConnected), limit ICE offers to 3 retries
with exponential backoff then fall back to hourly attempts, reducing
unnecessary signaling traffic. Fully disconnected peers continue to
retry aggressively. External events (relay/ICE disconnect, signal/relay
reconnect) reset retry state to give ICE a fresh chance.

* [client] Clarify guard ICE retry state and trace log trigger

Split iceRetryState.attempt into shouldRetry (pure predicate) and
enterHourlyMode (explicit state transition) so the caller in
reconnectLoopWithRetry reads top-to-bottom. Restore the original
trace-log behavior in isConnectedOnAllWay so it only logs on full
disconnection, not on the new PartiallyConnected state.

* [client] Extract pure evalConnStatus and add unit tests

Split isConnectedOnAllWay into a thin method that snapshots state and
a pure evalConnStatus helper that takes a connStatusInputs struct, so
the tri-state decision logic can be exercised without constructing
full Worker or Handshaker objects. Add table-driven tests covering
force-relay, ICE-unavailable and fully-available code paths, plus
unit tests for iceRetryState budget/hourly transitions and reset.

* [client] Improve grammar in logs and refactor ICE credential checks
2026-04-21 15:52:08 +02:00

121 lines
2.6 KiB
Go

package guard
import (
"context"
"sync"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/internal/peer/ice"
"github.com/netbirdio/netbird/client/internal/stdnet"
)
type chNotifier interface {
SetOnReconnectedListener(func())
Ready() bool
}
type SRWatcher struct {
signalClient chNotifier
relayManager chNotifier
listeners map[chan struct{}]struct{}
mu sync.Mutex
iFaceDiscover stdnet.ExternalIFaceDiscover
iceConfig ice.Config
cancelIceMonitor context.CancelFunc
}
// NewSRWatcher creates a new SRWatcher. This watcher will notify the listeners when the ICE candidates change or the
// Relay connection is reconnected or the Signal client reconnected.
func NewSRWatcher(signalClient chNotifier, relayManager chNotifier, iFaceDiscover stdnet.ExternalIFaceDiscover, iceConfig ice.Config) *SRWatcher {
srw := &SRWatcher{
signalClient: signalClient,
relayManager: relayManager,
iFaceDiscover: iFaceDiscover,
iceConfig: iceConfig,
listeners: make(map[chan struct{}]struct{}),
}
return srw
}
func (w *SRWatcher) Start(disableICEMonitor bool) {
w.mu.Lock()
defer w.mu.Unlock()
if w.cancelIceMonitor != nil {
return
}
ctx, cancel := context.WithCancel(context.Background())
w.cancelIceMonitor = cancel
if !disableICEMonitor {
iceMonitor := NewICEMonitor(w.iFaceDiscover, w.iceConfig, GetICEMonitorPeriod())
go iceMonitor.Start(ctx, w.onICEChanged)
}
w.signalClient.SetOnReconnectedListener(w.onReconnected)
w.relayManager.SetOnReconnectedListener(w.onReconnected)
}
func (w *SRWatcher) Close() {
w.mu.Lock()
defer w.mu.Unlock()
if w.cancelIceMonitor == nil {
return
}
w.cancelIceMonitor()
w.signalClient.SetOnReconnectedListener(nil)
w.relayManager.SetOnReconnectedListener(nil)
}
func (w *SRWatcher) NewListener() chan struct{} {
w.mu.Lock()
defer w.mu.Unlock()
listenerChan := make(chan struct{}, 1)
w.listeners[listenerChan] = struct{}{}
return listenerChan
}
func (w *SRWatcher) RemoveListener(listenerChan chan struct{}) {
w.mu.Lock()
defer w.mu.Unlock()
delete(w.listeners, listenerChan)
close(listenerChan)
}
func (w *SRWatcher) onICEChanged() {
if !w.signalClient.Ready() {
return
}
log.Infof("network changes detected by ICE agent")
w.notify()
}
func (w *SRWatcher) onReconnected() {
if !w.signalClient.Ready() {
return
}
if !w.relayManager.Ready() {
return
}
log.Infof("reconnected to Signal or Relay server")
w.notify()
}
func (w *SRWatcher) notify() {
w.mu.Lock()
defer w.mu.Unlock()
for listener := range w.listeners {
select {
case listener <- struct{}{}:
default:
}
}
}