[client] Merge main into peer event bus refactor

client/internal/peer/guard/guard.go

@@ -22,6 +22,12 @@ const (
 
 type connStatusFunc func() ConnStatus
 
+// NetworkWatcher is the availability view the guard gates reconnects on.
+type NetworkWatcher interface {
+	IsOnline() bool
+	Changed() <-chan struct{}
+}
+
 // Guard is responsible for the reconnection logic.
 // It will trigger to send an offer to the peer then has connection issues.
 // Watch these events:
@@ -31,20 +37,26 @@ type connStatusFunc func() ConnStatus
 // - Relayed connection disconnected
 // - ICE candidate changes
 type Guard struct {
-	log                     *log.Entry
-	isConnectedOnAllWay     connStatusFunc
-	timeout                 time.Duration
-	srWatcher               *SRWatcher
+	log                 *log.Entry
+	isConnectedOnAllWay connStatusFunc
+	timeout             time.Duration
+	srWatcher           *SRWatcher
+	// netWatcher gates reconnect attempts on OS-reported network availability;
+	// nil disables gating.
+	netWatcher              NetworkWatcher
 	relayedConnDisconnected chan struct{}
 	iCEConnDisconnected     chan struct{}
 }
 
-func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher) *Guard {
+// NewGuard creates a reconnection guard for a peer connection. A nil netWatcher
+// disables network availability gating.
+func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netWatcher NetworkWatcher) *Guard {
 	return &Guard{
 		log:                     log,
 		isConnectedOnAllWay:     isConnectedFn,
 		timeout:                 timeout,
 		srWatcher:               srWatcher,
+		netWatcher:              netWatcher,
 		relayedConnDisconnected: make(chan struct{}, 1),
 		iCEConnDisconnected:     make(chan struct{}, 1),
 	}
@@ -96,9 +108,19 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 	iceState := &iceRetryState{log: g.log}
 	defer iceState.reset()
 
+	var netChanged <-chan struct{}
+	if g.netWatcher != nil {
+		netChanged = g.netWatcher.Changed()
+	}
+
 	for {
 		select {
 		case <-tickerChannel:
+			// skip attempts while the OS reports no usable network; the
+			// netChanged case below resumes the loop once it returns
+			if g.netWatcher != nil && !g.netWatcher.IsOnline() {
+				continue
+			}
 			switch g.isConnectedOnAllWay() {
 			case ConnStatusConnected:
 				// all good, nothing to do
@@ -135,6 +157,23 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 			tickerChannel = ticker.C
 			iceState.reset()
 
+		case <-netChanged:
+			// Re-arm for the next transition before acting on this one.
+			netChanged = g.netWatcher.Changed()
+			if !g.netWatcher.IsOnline() {
+				continue
+			}
+			// Ticks skipped while offline drove the backoff towards its
+			// maximum without ever attempting, and left the ICE budget
+			// frozen — possibly in hourly mode. Recover on our own so the
+			// peer does not depend on a signal or relay event that never
+			// comes when both stayed up across the outage.
+			g.log.Debugf("network is back, reset reconnection ticker")
+			ticker.Stop()
+			ticker = g.newReconnectTicker(ctx)
+			tickerChannel = ticker.C
+			iceState.reset()
+
 		case <-ctx.Done():
 			g.log.Debugf("context is done, stop reconnect loop")
 			return

client/internal/peer/guard/guard_leak_test.go

@@ -15,7 +15,7 @@ import (
 
 func newTestGuard(status connStatusFunc) *Guard {
 	srw := NewSRWatcher(nil, nil, nil, ice.Config{})
-	return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw)
+	return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw, nil)
 }
 
 // countBackoffTickerGoroutines returns how many goroutines are currently sitting

client/internal/peer/guard/guard_netstate_test.go

@@ -0,0 +1,107 @@
+package guard
+
+import (
+	"context"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/netevents/netstate"
+)
+
+// newTestGuardWithNetState builds a guard with a realistic MaxInterval: the
+// backoff must be able to grow well past the outage, as it does in production
+// where the timeout is seconds to minutes.
+func newTestGuardWithNetState(status connStatusFunc, netState *netstate.State) *Guard {
+	srw := NewSRWatcher(nil, nil, nil, ice.Config{})
+	return NewGuard(log.WithField("test", "guard"), status, 30*time.Second, srw, netState)
+}
+
+// TestGuard_RecoversAfterOfflineToOnline covers a peer that stays disconnected
+// across a network outage while neither signal nor relay reports an event —
+// both stayed up, as on a short airplane mode toggle over Wi-Fi.
+//
+// Every tick taken while offline is skipped, but it still advances the
+// exponential backoff, so by the time the network returns the next tick can be
+// tens of seconds away. Without an explicit reaction to the transition the
+// peer waits out that interval for a recovery that could start immediately.
+func TestGuard_RecoversAfterOfflineToOnline(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	// Start from the reconnect ticker (800ms initial interval), the state a
+	// peer is in after it loses its connection.
+	go g.Start(ctx, func() { attempts.Add(1) })
+	g.SetRelayedConnDisconnected()
+
+	// Let the backoff climb: 0.8s, 1.6s, 3.2s, 6.4s ... every tick is skipped
+	// while offline, but each one doubles the wait for the next.
+	netState.Set(false)
+	time.Sleep(8 * time.Second)
+
+	offlineAttempts := attempts.Load()
+	if offlineAttempts != 0 {
+		t.Fatalf("callback ran %d times while offline, want 0", offlineAttempts)
+	}
+
+	netState.Set(true)
+
+	// The next organic tick is now several seconds out, so anything within
+	// this window can only come from reacting to the transition itself.
+	pollCtx, stopPolling := context.WithTimeout(ctx, 2*time.Second)
+	defer stopPolling()
+
+	select {
+	case <-pollCtx.Done():
+		t.Fatal("peer was not retried within 2s of the network coming back, " +
+			"with neither a signal nor a relay event to fall back on")
+	case <-pollUntil(pollCtx, func() bool { return attempts.Load() > 0 }):
+	}
+}
+
+// TestGuard_OfflineTransitionDoesNotRetry checks the other direction: going
+// offline must not itself trigger an attempt.
+func TestGuard_OfflineTransitionDoesNotRetry(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go g.Start(ctx, func() { attempts.Add(1) })
+
+	netState.Set(false)
+	time.Sleep(5 * time.Second)
+
+	if got := attempts.Load(); got != 0 {
+		t.Fatalf("callback ran %d times after going offline, want 0", got)
+	}
+}
+
+// pollUntil closes the returned channel once cond holds. It gives up when ctx
+// is done, so the polling goroutine never outlives the test that started it.
+func pollUntil(ctx context.Context, cond func() bool) <-chan struct{} {
+	done := make(chan struct{})
+	go func() {
+		for {
+			if cond() {
+				close(done)
+				return
+			}
+			select {
+			case <-ctx.Done():
+				return
+			case <-time.After(10 * time.Millisecond):
+			}
+		}
+	}()
+	return done
+}