Add tests

# Conflicts:
#	shared/relay/client/manager.go

client/internal/peer/worker_relay.go

@@ -54,19 +54,15 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 	w.relaySupportedOnRemotePeer.Store(true)
 
 	// the relayManager will return with error in case if the connection has lost with relay server
-	currentRelayAddress, _, err := w.relayManager.RelayInstanceAddress()
+	_, _, err := w.relayManager.RelayInstanceAddress()
 	if err != nil {
 		w.log.Errorf("failed to handle new offer: %s", err)
 		return
 	}
 
-	srv := w.preferredRelayServer(currentRelayAddress, remoteOfferAnswer.RelaySrvAddress)
-	var serverIP netip.Addr
-	if srv == remoteOfferAnswer.RelaySrvAddress {
-		serverIP = remoteOfferAnswer.RelaySrvIP
-	}
-
-	relayedConn, err := w.relayManager.OpenConn(w.peerCtx, srv, w.config.Key, serverIP)
+	preferForeign := !w.isController
+	remoteRelayServer := relayClient.RelayServer{Addr: remoteOfferAnswer.RelaySrvAddress, IP: remoteOfferAnswer.RelaySrvIP}
+	relayedConn, err := w.relayManager.OpenConn(w.peerCtx, remoteRelayServer, w.config.Key, preferForeign)
 	if err != nil {
 		if errors.Is(err, relayClient.ErrConnAlreadyExists) {
 			w.log.Debugf("handled offer by reusing existing relay connection")
@@ -80,14 +76,13 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 	w.relayedConn = relayedConn
 	w.relayLock.Unlock()
 
-	err = w.relayManager.AddCloseListener(srv, w.onRelayClientDisconnected)
-	if err != nil {
-		log.Errorf("failed to add close listener: %s", err)
+	if err := w.relayManager.AddCloseListener(relayedConn.RemoteAddr().String(), w.onRelayClientDisconnected); err != nil {
+		w.log.Errorf("failed to add close listener: %s", err)
 		_ = relayedConn.Close()
 		return
 	}
 
-	w.log.Debugf("peer conn opened via Relay: %s", srv)
+	w.log.Debugf("peer conn opened via Relay: %s", relayedConn.RemoteAddr())
 	go w.conn.onRelayConnectionIsReady(RelayConnInfo{
 		relayedConn:     relayedConn,
 		rosenpassPubKey: remoteOfferAnswer.RosenpassPubKey,
@@ -126,13 +121,6 @@ func (w *WorkerRelay) isRelaySupported(answer *OfferAnswer) bool {
 	return answer.RelaySrvAddress != ""
 }
 
-func (w *WorkerRelay) preferredRelayServer(myRelayAddress, remoteRelayAddress string) string {
-	if w.isController {
-		return myRelayAddress
-	}
-	return remoteRelayAddress
-}
-
 func (w *WorkerRelay) onRelayClientDisconnected() {
 	go w.conn.onRelayDisconnected()
 }

shared/relay/client/fallback_opener.go

@@ -0,0 +1,176 @@
+package client
+
+import (
+	"context"
+	"errors"
+	"net"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+)
+
+const (
+	raceTotalTimeout  = 40 * time.Second
+	raceFallbackDelay = 10 * time.Second
+)
+
+type raceAttempt struct {
+	conn net.Conn
+	err  error
+}
+
+type raceOutcome struct {
+	conn net.Conn
+	err  error
+	done bool
+}
+
+type connRace struct {
+	opener            *FallbackOpener
+	peerKey           string
+	remoteRelayServer RelayServer
+	preferForeign     bool
+
+	raceCtx         context.Context
+	otherCtx        context.Context
+	cancelPreferred context.CancelFunc
+	cancelOther     context.CancelFunc
+	results         chan raceAttempt
+	fallbackTimer   *time.Timer
+
+	otherStarted bool
+	settled      int
+	lastErr      error
+}
+
+type FallbackOpener struct {
+	home         *Client
+	foreignStore *ForeignRelaysStore
+
+	fallbackDelay time.Duration
+	totalTimeout  time.Duration
+	// openFn performs a single attempt. It is overridable in tests; when nil the
+	// real home/foreign dispatch in open is used.
+	openFn func(ctx context.Context, peerKey string, remoteRelayServer RelayServer, foreign bool) raceAttempt
+}
+
+func NewFallbackOpener(home *Client, foreignStore *ForeignRelaysStore) *FallbackOpener {
+	return &FallbackOpener{
+		home:          home,
+		foreignStore:  foreignStore,
+		fallbackDelay: raceFallbackDelay,
+		totalTimeout:  raceTotalTimeout,
+	}
+}
+
+func (r *FallbackOpener) Run(ctx context.Context, peerKey string, remoteRelayServer RelayServer, preferForeign bool) (net.Conn, error) {
+	raceCtx, cancel := context.WithTimeout(ctx, r.totalTimeout)
+	defer cancel()
+
+	preferredCtx, cancelPreferred := context.WithCancel(raceCtx)
+	otherCtx, cancelOther := context.WithCancel(raceCtx)
+
+	race := &connRace{
+		opener:            r,
+		peerKey:           peerKey,
+		remoteRelayServer: remoteRelayServer,
+		preferForeign:     preferForeign,
+		raceCtx:           raceCtx,
+		otherCtx:          otherCtx,
+		cancelPreferred:   cancelPreferred,
+		cancelOther:       cancelOther,
+		results:           make(chan raceAttempt, 2),
+		fallbackTimer:     time.NewTimer(r.fallbackDelay),
+	}
+	defer race.fallbackTimer.Stop()
+
+	go func() {
+		race.results <- r.open(preferredCtx, peerKey, remoteRelayServer, preferForeign)
+	}()
+
+	for {
+		select {
+		case <-race.fallbackTimer.C:
+			race.startOther()
+		case res := <-race.results:
+			if o := race.handleResult(res); o.done {
+				return o.conn, o.err
+			}
+		case <-raceCtx.Done():
+			return race.onTimeout()
+		}
+	}
+}
+
+func (c *connRace) startOther() {
+	if c.otherStarted {
+		return
+	}
+	c.otherStarted = true
+	c.fallbackTimer.Stop()
+	go func() {
+		c.results <- c.opener.open(c.otherCtx, c.peerKey, c.remoteRelayServer, !c.preferForeign)
+	}()
+}
+
+func (c *connRace) handleResult(res raceAttempt) raceOutcome {
+	if (res.err == nil && res.conn != nil) || errors.Is(res.err, ErrConnAlreadyExists) {
+		c.settled++
+		c.stop()
+		return raceOutcome{conn: res.conn, err: res.err, done: true}
+	}
+
+	c.lastErr = res.err
+	c.settled++
+	if !c.otherStarted {
+		c.startOther()
+		return raceOutcome{}
+	}
+	if c.settled == 2 {
+		c.cancelPreferred()
+		c.cancelOther()
+		return raceOutcome{err: c.lastErr, done: true}
+	}
+	return raceOutcome{}
+}
+
+func (c *connRace) onTimeout() (net.Conn, error) {
+	c.stop()
+	if c.lastErr != nil {
+		return nil, c.lastErr
+	}
+	return nil, c.raceCtx.Err()
+}
+
+func (c *connRace) stop() {
+	c.cancelPreferred()
+	c.cancelOther()
+	go c.opener.drainLoser(c.results, c.settled, c.otherStarted)
+}
+
+func (r *FallbackOpener) open(ctx context.Context, peerKey string, remoteRelayServer RelayServer, foreign bool) raceAttempt {
+	if r.openFn != nil {
+		return r.openFn(ctx, peerKey, remoteRelayServer, foreign)
+	}
+	if foreign {
+		conn, err := r.foreignStore.OpenConn(ctx, peerKey, remoteRelayServer)
+		return raceAttempt{conn: conn, err: err}
+	}
+	conn, err := r.home.OpenConn(ctx, peerKey)
+	return raceAttempt{conn: conn, err: err}
+}
+
+func (r *FallbackOpener) drainLoser(results chan raceAttempt, settled int, otherStarted bool) {
+	started := 1
+	if otherStarted {
+		started = 2
+	}
+	for i := settled; i < started; i++ {
+		res := <-results
+		if res.conn != nil {
+			if err := res.conn.Close(); err != nil {
+				log.Debugf("failed to close losing relay connection: %v", err)
+			}
+		}
+	}
+}

shared/relay/client/fallback_opener_test.go

@@ -0,0 +1,450 @@
+package client
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// The FallbackOpener race is driven by a single goroutine (Run's select loop)
+// with worker goroutines that communicate only through the buffered results
+// channel and the two cancel contexts. These tests exercise that state machine
+// in isolation via an injected openFn, so no relay server or network is needed.
+// Timing is scaled down through the fallbackDelay/totalTimeout fields.
+
+// raceFakeConn tracks whether Close was called. Only Close is exercised by the
+// race logic (drainLoser closes losers; Run returns the winner untouched).
+type raceFakeConn struct {
+	net.Conn
+	label  string
+	closed atomic.Bool
+}
+
+func (c *raceFakeConn) Close() error {
+	c.closed.Store(true)
+	return nil
+}
+
+// raceAttemptScript describes how a single scripted attempt behaves.
+type raceAttemptScript struct {
+	delay time.Duration
+	conn  *raceFakeConn // non-nil => the attempt succeeds and returns this conn
+	err   error         // returned when conn is nil
+	// ignoreCtx makes the attempt complete after delay even if its context is
+	// cancelled. It models an OpenConn that produced a real connection right as
+	// the race cancelled it - exactly the case drainLoser must clean up.
+	ignoreCtx bool
+}
+
+// fakeOpener replaces FallbackOpener.open. Scripts are keyed by the foreign
+// flag, so which script is "preferred" depends on the preferForeign argument
+// passed to Run.
+type fakeOpener struct {
+	mu      sync.Mutex
+	scripts map[bool]raceAttemptScript
+	calls   []bool // foreign flag of each open() invocation, in order
+}
+
+func (f *fakeOpener) open(ctx context.Context, _ string, _ RelayServer, foreign bool) raceAttempt {
+	f.mu.Lock()
+	f.calls = append(f.calls, foreign)
+	s, ok := f.scripts[foreign]
+	f.mu.Unlock()
+	if !ok {
+		return raceAttempt{err: fmt.Errorf("no script for foreign=%v", foreign)}
+	}
+
+	if s.delay > 0 {
+		timer := time.NewTimer(s.delay)
+		defer timer.Stop()
+		if s.ignoreCtx {
+			<-timer.C
+		} else {
+			select {
+			case <-timer.C:
+			case <-ctx.Done():
+				return raceAttempt{err: ctx.Err()}
+			}
+		}
+	}
+
+	if s.conn != nil {
+		return raceAttempt{conn: s.conn}
+	}
+	return raceAttempt{err: s.err}
+}
+
+func (f *fakeOpener) callCount() int {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return len(f.calls)
+}
+
+func (f *fakeOpener) firstCallForeign(t *testing.T) bool {
+	t.Helper()
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	require.NotEmpty(t, f.calls, "expected at least one open attempt")
+	return f.calls[0]
+}
+
+func newTestOpener(f *fakeOpener, fallbackDelay, totalTimeout time.Duration) *FallbackOpener {
+	o := NewFallbackOpener(nil, nil)
+	o.openFn = f.open
+	o.fallbackDelay = fallbackDelay
+	o.totalTimeout = totalTimeout
+	return o
+}
+
+const (
+	// controller prefers the home relay, i.e. preferForeign == false.
+	preferHome    = false
+	preferForeign = true
+)
+
+var errAttempt = errors.New("attempt failed")
+
+// The preferred attempt wins before the fallback timer fires, so the other
+// attempt is never started.
+func TestFallbackOpener_PreferredWinsImmediately(t *testing.T) {
+	homeConn := &raceFakeConn{label: "home"}
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {conn: homeConn},                            // preferred (home): instant success
+		true:  {delay: 5 * time.Second, conn: foreignConn}, // would never finish in time
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.NoError(t, err)
+	require.Same(t, homeConn, conn)
+	assert.Equal(t, 1, f.callCount(), "other attempt must not start when preferred wins first")
+	assert.False(t, f.firstCallForeign(t), "home must be tried first when preferring home")
+	assert.False(t, foreignConn.closed.Load())
+}
+
+// preferForeign flips which relay is tried first.
+func TestFallbackOpener_PreferForeignRoutesForeignFirst(t *testing.T) {
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		true:  {conn: foreignConn}, // preferred (foreign): instant success
+		false: {delay: 5 * time.Second, conn: &raceFakeConn{}},
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferForeign)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn)
+	assert.Equal(t, 1, f.callCount())
+	assert.True(t, f.firstCallForeign(t), "foreign must be tried first when preferring foreign")
+}
+
+// ErrConnAlreadyExists counts as success: Run returns it and does not start the
+// other attempt.
+func TestFallbackOpener_ErrConnAlreadyExistsIsSuccess(t *testing.T) {
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {err: ErrConnAlreadyExists},
+		true:  {delay: 5 * time.Second, conn: &raceFakeConn{}},
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.ErrorIs(t, err, ErrConnAlreadyExists)
+	assert.Nil(t, conn)
+	assert.Equal(t, 1, f.callCount(), "other attempt must not start on ErrConnAlreadyExists")
+}
+
+// A preferred failure starts the other attempt immediately, without waiting for
+// the fallback timer.
+func TestFallbackOpener_PreferredFailsStartsOtherBeforeTimer(t *testing.T) {
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {err: errAttempt}, // preferred fails instantly
+		true:  {delay: 5 * time.Millisecond, conn: foreignConn},
+	}}
+	fallbackDelay := 500 * time.Millisecond
+	o := newTestOpener(f, fallbackDelay, 2*time.Second)
+
+	start := time.Now()
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+	elapsed := time.Since(start)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn)
+	assert.Equal(t, 2, f.callCount())
+	assert.Less(t, elapsed, fallbackDelay/2, "fallback must not wait for the timer after a preferred failure")
+}
+
+// When the preferred attempt is slow, the fallback timer starts the other
+// attempt and its success wins.
+func TestFallbackOpener_TimerStartsOtherWhenPreferredSlow(t *testing.T) {
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 5 * time.Second}, // preferred hangs until cancelled
+		true:  {delay: 5 * time.Millisecond, conn: foreignConn},
+	}}
+	fallbackDelay := 40 * time.Millisecond
+	o := newTestOpener(f, fallbackDelay, 2*time.Second)
+
+	start := time.Now()
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+	elapsed := time.Since(start)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn)
+	assert.Equal(t, 2, f.callCount())
+	assert.GreaterOrEqual(t, elapsed, fallbackDelay, "other must not start before the fallback timer fires")
+}
+
+// Both attempts fail: Run returns the last error and tries both relays.
+func TestFallbackOpener_BothFail(t *testing.T) {
+	errOther := errors.New("other failed")
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {err: errAttempt},
+		true:  {err: errOther},
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.Error(t, err)
+	assert.Nil(t, conn)
+	assert.ErrorIs(t, err, errOther, "the most recent error should be surfaced")
+	assert.Equal(t, 2, f.callCount())
+}
+
+// When both attempts succeed, drainLoser must close the losing connection so it
+// is not leaked. Here the preferred attempt wins and the foreign loser - which
+// produced a real conn despite being cancelled - is closed.
+func TestFallbackOpener_DoubleSuccessClosesLoser(t *testing.T) {
+	homeConn := &raceFakeConn{label: "home"}
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 30 * time.Millisecond, conn: homeConn},                     // preferred wins
+		true:  {delay: 80 * time.Millisecond, conn: foreignConn, ignoreCtx: true}, // loser yields a conn after cancel
+	}}
+	o := newTestOpener(f, 15*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.NoError(t, err)
+	require.Same(t, homeConn, conn)
+	assert.Equal(t, 2, f.callCount())
+	assert.False(t, homeConn.closed.Load(), "the winning connection must not be closed")
+	require.Eventually(t, foreignConn.closed.Load, time.Second, 5*time.Millisecond,
+		"the losing connection must be closed by drainLoser")
+}
+
+// Winner selection is purely by result arrival order, not by preference: when
+// the non-preferred attempt returns first it wins even though home was
+// preferred. This is the mechanism behind the split-relay concern - two peers
+// racing independently have no shared tie-break, so under adversarial timing
+// they can settle on different relays. Documented here as current behavior.
+func TestFallbackOpener_FasterOtherWinsDespitePreference(t *testing.T) {
+	homeConn := &raceFakeConn{label: "home"}
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 60 * time.Millisecond, conn: homeConn, ignoreCtx: true}, // preferred but slower
+		true:  {delay: 5 * time.Millisecond, conn: foreignConn},                // other is faster
+	}}
+	o := newTestOpener(f, 15*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn, "the first successful attempt wins regardless of preference")
+	require.Eventually(t, homeConn.closed.Load, time.Second, 5*time.Millisecond,
+		"the slower preferred attempt becomes the loser and is closed")
+}
+
+// The whole race is bounded by totalTimeout. With no attempt succeeding or
+// failing, Run returns the deadline error.
+func TestFallbackOpener_TotalTimeout(t *testing.T) {
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 5 * time.Second},
+		true:  {delay: 5 * time.Second},
+	}}
+	o := newTestOpener(f, 20*time.Millisecond, 80*time.Millisecond)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.Error(t, err)
+	assert.Nil(t, conn)
+	assert.ErrorIs(t, err, context.DeadlineExceeded)
+}
+
+// Cancelling the caller's context aborts the race promptly with the cancel
+// error, even before the fallback timer would fire.
+func TestFallbackOpener_ParentContextCanceled(t *testing.T) {
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 5 * time.Second},
+		true:  {delay: 5 * time.Second},
+	}}
+	// fallbackDelay large so the timer never fires; only the parent cancel ends the race.
+	o := newTestOpener(f, 5*time.Second, 5*time.Second)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	go func() {
+		time.Sleep(20 * time.Millisecond)
+		cancel()
+	}()
+
+	start := time.Now()
+	conn, err := o.Run(ctx, "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.Error(t, err)
+	assert.Nil(t, conn)
+	assert.ErrorIs(t, err, context.Canceled)
+	assert.Less(t, time.Since(start), time.Second, "must return shortly after the parent context is cancelled")
+	assert.Equal(t, 1, f.callCount(), "the other attempt must not start")
+}
+
+// rendezvous models the relay-level requirement that a relayed connection is
+// established only once BOTH peers subscribe to the same relay server. arrive
+// records a peer's presence on a relay and returns a channel that closes when
+// the second peer arrives, so an attempt can only complete after a real
+// rendezvous - the same coupling the production code depends on.
+type rendezvous struct {
+	mu       sync.Mutex
+	arrivals map[string]int
+	gates    map[string]chan struct{}
+}
+
+func newRendezvous() *rendezvous {
+	return &rendezvous{arrivals: map[string]int{}, gates: map[string]chan struct{}{}}
+}
+
+func (r *rendezvous) arrive(relay string) <-chan struct{} {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	g, ok := r.gates[relay]
+	if !ok {
+		g = make(chan struct{})
+		r.gates[relay] = g
+	}
+	r.arrivals[relay]++
+	if r.arrivals[relay] == 2 {
+		close(g)
+	}
+	return g
+}
+
+// splitPeer is one peer's view of the two relays. relayFor maps the foreign
+// flag to a relay name; postDelay is how long after the rendezvous that peer's
+// OpenConn takes to return (its per-relay subscribe latency). Different values
+// per peer model the asymmetric timing that triggers finding #1.
+type splitPeer struct {
+	rv        *rendezvous
+	relayFor  map[bool]string
+	postDelay map[string]time.Duration
+}
+
+func (p *splitPeer) open(ctx context.Context, _ string, _ RelayServer, foreign bool) raceAttempt {
+	relay := p.relayFor[foreign]
+
+	select {
+	case <-p.rv.arrive(relay):
+	case <-ctx.Done():
+		return raceAttempt{err: ctx.Err()}
+	}
+
+	timer := time.NewTimer(p.postDelay[relay])
+	defer timer.Stop()
+	select {
+	case <-timer.C:
+	case <-ctx.Done():
+		return raceAttempt{err: ctx.Err()}
+	}
+	return raceAttempt{conn: &raceFakeConn{label: relay}}
+}
+
+// TestFallbackOpener_SplitRelaySelection reproduces finding #1: the two peers
+// run FallbackOpener.Run independently with no shared tie-break, so the winner
+// is chosen purely by local result-arrival order. Under an adversarial - but
+// self-consistent - timing profile they settle on DIFFERENT relays.
+//
+// Both peers prefer relayA (the controller's home). The split needs each peer's
+// preferred relayA to be slow enough that both start their fallback (so both
+// relays actually rendezvous), and then each peer's fast path to be a different
+// relay:
+//   - peerA: relayA slow (abandoned), relayB fast  -> peerA wins relayB
+//   - peerB: relayA fast (wins),      relayB slow  -> peerB wins relayA
+//
+// Each winner then cancels its attempt on the relay the OTHER peer actually
+// kept, leaving two half-open relayed connections that were both reported as
+// successful. When a deterministic cross-peer tie-break is added to fix this,
+// invert the assertion below to require convergence.
+func TestFallbackOpener_SplitRelaySelection(t *testing.T) {
+	const (
+		relayA = "relayA" // controller's home relay; both peers prefer it
+		relayB = "relayB" // non-controller's home relay
+	)
+	rv := newRendezvous()
+
+	peerA := &splitPeer{
+		rv:       rv,
+		relayFor: map[bool]string{false: relayA, true: relayB}, // home=relayA
+		postDelay: map[string]time.Duration{
+			relayA: 500 * time.Millisecond, // preferred but slow -> abandoned
+			relayB: 10 * time.Millisecond,  // fallback is fast -> peerA wins relayB
+		},
+	}
+	peerB := &splitPeer{
+		rv:       rv,
+		relayFor: map[bool]string{false: relayB, true: relayA}, // home=relayB
+		postDelay: map[string]time.Duration{
+			relayA: 80 * time.Millisecond,  // preferred, wins - but only after starting fallback
+			relayB: 500 * time.Millisecond, // fallback (home) is slow -> abandoned
+		},
+	}
+
+	fallbackDelay := 30 * time.Millisecond
+	newPeerOpener := func(p *splitPeer) *FallbackOpener {
+		o := NewFallbackOpener(nil, nil)
+		o.openFn = p.open
+		o.fallbackDelay = fallbackDelay
+		o.totalTimeout = 5 * time.Second
+		return o
+	}
+	oA := newPeerOpener(peerA)
+	oB := newPeerOpener(peerB)
+
+	type result struct {
+		conn net.Conn
+		err  error
+	}
+	var ra, rb result
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go func() {
+		defer wg.Done()
+		ra.conn, ra.err = oA.Run(context.Background(), "peerB", RelayServer{Addr: relayB}, preferHome)
+	}()
+	go func() {
+		defer wg.Done()
+		rb.conn, rb.err = oB.Run(context.Background(), "peerA", RelayServer{Addr: relayA}, preferForeign)
+	}()
+	wg.Wait()
+
+	require.NoError(t, ra.err)
+	require.NoError(t, rb.err)
+	aRelay := ra.conn.(*raceFakeConn).label
+	bRelay := rb.conn.(*raceFakeConn).label
+	t.Logf("peerA settled on %s, peerB settled on %s", aRelay, bRelay)
+
+	assert.Equal(t, aRelay, bRelay,
+		"peers selected different relays with no cross-peer tie-break")
+	assert.Equal(t, relayB, aRelay, "peerA abandoned its slow preferred relay and won the fallback")
+	assert.Equal(t, relayA, bRelay, "peerB won its preferred relay after starting the fallback")
+}

shared/relay/client/foreign_relays_store.go

@@ -0,0 +1,155 @@
+package client
+
+import (
+	"context"
+	"net"
+	"sync"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/sync/singleflight"
+
+	relayAuth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
+)
+
+type foreignRelay struct {
+	client  *Client
+	created time.Time
+	inUse   int
+}
+
+type ForeignRelaysStore struct {
+	mu      sync.RWMutex
+	clients map[string]*foreignRelay
+
+	group singleflight.Group
+
+	ctx                  context.Context
+	tokenStore           *relayAuth.TokenStore
+	peerID               string
+	mtu                  uint16
+	transportFallback    *transportFallback
+	onDisconnect         func(string)
+	keepUnusedServerTime time.Duration
+}
+
+func NewForeignRelaysStore(ctx context.Context, tokenStore *relayAuth.TokenStore, peerID string, mtu uint16, transportFallback *transportFallback, onDisconnect func(string), keepUnusedServerTime time.Duration) *ForeignRelaysStore {
+	return &ForeignRelaysStore{
+		clients:              make(map[string]*foreignRelay),
+		ctx:                  ctx,
+		tokenStore:           tokenStore,
+		peerID:               peerID,
+		mtu:                  mtu,
+		transportFallback:    transportFallback,
+		onDisconnect:         onDisconnect,
+		keepUnusedServerTime: keepUnusedServerTime,
+	}
+}
+
+func (f *ForeignRelaysStore) OpenConn(ctx context.Context, peerKey string, remoteRelayServer RelayServer) (net.Conn, error) {
+	fr, err := f.acquire(remoteRelayServer)
+	if err != nil {
+		return nil, err
+	}
+	defer f.release(fr)
+
+	return fr.client.OpenConn(ctx, peerKey)
+}
+
+func (f *ForeignRelaysStore) acquire(remoteRelayServer RelayServer) (*foreignRelay, error) {
+	f.mu.Lock()
+	if fr, ok := f.clients[remoteRelayServer.Addr]; ok {
+		fr.inUse++
+		f.mu.Unlock()
+		return fr, nil
+	}
+	f.mu.Unlock()
+
+	v, err, _ := f.group.Do(remoteRelayServer.Addr, func() (any, error) {
+		f.mu.RLock()
+		fr, ok := f.clients[remoteRelayServer.Addr]
+		f.mu.RUnlock()
+		if ok {
+			return fr, nil
+		}
+
+		relayClient := NewClientWithServerIP(remoteRelayServer.Addr, remoteRelayServer.IP, f.tokenStore, f.peerID, f.mtu)
+		relayClient.SetTransportFallback(f.transportFallback)
+		if err := relayClient.Connect(f.ctx); err != nil {
+			return nil, err
+		}
+		relayClient.SetOnDisconnectListener(f.onDisconnect)
+
+		f.mu.Lock()
+		fr = &foreignRelay{client: relayClient, created: time.Now()}
+		f.clients[remoteRelayServer.Addr] = fr
+		f.mu.Unlock()
+		return fr, nil
+	})
+	if err != nil {
+		return nil, err
+	}
+
+	fr := v.(*foreignRelay)
+	f.mu.Lock()
+	if cur, ok := f.clients[remoteRelayServer.Addr]; !ok || cur != fr {
+		f.mu.Unlock()
+		return f.acquire(remoteRelayServer)
+	}
+	fr.inUse++
+	f.mu.Unlock()
+	return fr, nil
+}
+
+func (f *ForeignRelaysStore) release(fr *foreignRelay) {
+	f.mu.Lock()
+	fr.inUse--
+	f.mu.Unlock()
+}
+
+func (f *ForeignRelaysStore) evict(serverAddress string) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	if _, ok := f.clients[serverAddress]; ok {
+		delete(f.clients, serverAddress)
+		log.Debugf("evicted disconnected foreign relay client: %s", serverAddress)
+	}
+}
+
+func (f *ForeignRelaysStore) cleanupUnused() {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+
+	for addr, fr := range f.clients {
+		if time.Since(fr.created) <= f.keepUnusedServerTime {
+			continue
+		}
+		if fr.inUse > 0 {
+			continue
+		}
+		if fr.client.HasConns() {
+			continue
+		}
+		fr.client.SetOnDisconnectListener(nil)
+		go func() {
+			_ = fr.client.Close()
+		}()
+		log.Debugf("clean up unused relay server connection: %s", addr)
+		delete(f.clients, addr)
+	}
+}
+
+func (f *ForeignRelaysStore) states() []RelayConnState {
+	f.mu.RLock()
+	clients := make([]*Client, 0, len(f.clients))
+	for _, fr := range f.clients {
+		clients = append(clients, fr.client)
+	}
+	f.mu.RUnlock()
+
+	states := make([]RelayConnState, 0, len(clients))
+	for _, c := range clients {
+		states = append(states, relayConnState(c))
+	}
+	return states
+}

shared/relay/client/manager.go

@@ -22,27 +22,6 @@ var (
 	ErrRelayClientNotConnected = fmt.Errorf("relay client not connected")
 )
 
-// RelayTrack hold the relay clients for the foreign relay servers.
-// With the mutex can ensure we can open new connection in case the relay connection has been established with
-// the relay server.
-type RelayTrack struct {
-	sync.RWMutex
-	relayClient *Client
-	err         error
-	created     time.Time
-	// ready is closed once the dial started by openConnVia finishes (relayClient
-	// or err is set). Callers reusing a track wait on this instead of the track
-	// lock, so the dial never runs under rt.Lock.
-	ready chan struct{}
-}
-
-func NewRelayTrack() *RelayTrack {
-	return &RelayTrack{
-		created: time.Now(),
-		ready:   make(chan struct{}),
-	}
-}
-
 type OnServerCloseListener func()
 
 // ManagerOption configures a Manager at construction time.
@@ -59,6 +38,11 @@ type RelayConnState struct {
 	Err error
 }
 
+type RelayServer struct {
+	Addr string
+	IP   netip.Addr
+}
+
 // WithMaxBackoffInterval caps the exponential backoff between reconnect
 // attempts to the home relay. A non-positive value keeps the default.
 func WithMaxBackoffInterval(d time.Duration) ManagerOption {
@@ -83,8 +67,7 @@ type Manager struct {
 	relayClientMu  sync.RWMutex
 	reconnectGuard *Guard
 
-	relayClients      map[string]*RelayTrack
-	relayClientsMutex sync.RWMutex
+	foreign *ForeignRelaysStore
 
 	onDisconnectedListeners map[string]*list.List
 	onReconnectedListenerFn func()
@@ -120,7 +103,6 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
 			ConnectionTimeout: defaultConnectionTimeout,
 			TransportFallback: tf,
 		},
-		relayClients:            make(map[string]*RelayTrack),
 		onDisconnectedListeners: make(map[string]*list.List),
 		cleanupInterval:         relayCleanupInterval,
 		keepUnusedServerTime:    keepUnusedServerTime,
@@ -128,6 +110,7 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
 	for _, opt := range opts {
 		opt(m)
 	}
+	m.foreign = NewForeignRelaysStore(ctx, tokenStore, peerID, mtu, tf, m.onServerDisconnected, m.keepUnusedServerTime)
 	m.serverPicker.ServerURLs.Store(serverURLs)
 	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval)
 	return m
@@ -159,40 +142,26 @@ func (m *Manager) Serve() error {
 	return err
 }
 
-// OpenConn opens a connection to the given peer key. If the peer is on the same relay server, the connection will be
-// established via the relay server. If the peer is on a different relay server, the manager will establish a new
-// connection to the relay server. It returns back with a net.Conn what represent the remote peer connection.
-//
-// serverIP, when valid and serverAddress is foreign, is used as a dial target if the FQDN-based dial fails.
-// Ignored for the local home-server path. TLS verification still uses the FQDN via SNI.
-func (m *Manager) OpenConn(ctx context.Context, serverAddress, peerKey string, serverIP netip.Addr) (net.Conn, error) {
+func (m *Manager) OpenConn(ctx context.Context, remoteRelayServer RelayServer, peerKey string, preferForeign bool) (net.Conn, error) {
 	m.relayClientMu.RLock()
-	defer m.relayClientMu.RUnlock()
+	relayClient := m.relayClient
+	m.relayClientMu.RUnlock()
 
-	if m.relayClient == nil {
+	if relayClient == nil {
 		return nil, ErrRelayClientNotConnected
 	}
 
-	foreign, err := m.isForeignServer(serverAddress)
+	foreign, err := m.isForeignServer(relayClient, remoteRelayServer.Addr)
 	if err != nil {
 		return nil, err
 	}
 
-	var (
-		netConn net.Conn
-	)
 	if !foreign {
-		log.Debugf("open peer connection via permanent server: %s", peerKey)
-		netConn, err = m.relayClient.OpenConn(ctx, peerKey)
-	} else {
-		log.Debugf("open peer connection via foreign server: %s", serverAddress)
-		netConn, err = m.openConnVia(ctx, serverAddress, peerKey, serverIP)
-	}
-	if err != nil {
-		return nil, err
+		return relayClient.OpenConn(ctx, peerKey)
 	}
 
-	return netConn, err
+	opener := NewFallbackOpener(relayClient, m.foreign)
+	return opener.Run(ctx, peerKey, remoteRelayServer, preferForeign)
 }
 
 // Ready returns true if the home Relay client is connected to the relay server.
@@ -223,7 +192,7 @@ func (m *Manager) AddCloseListener(serverAddress string, onClosedListener OnServ
 		return ErrRelayClientNotConnected
 	}
 
-	foreign, err := m.isForeignServer(serverAddress)
+	foreign, err := m.isForeignServer(m.relayClient, serverAddress)
 	if err != nil {
 		return err
 	}
@@ -287,26 +256,7 @@ func (m *Manager) RelayStates() []RelayConnState {
 		states = append(states, st)
 	}
 
-	// Snapshot the tracks, then query each outside the map lock: a track can be
-	// held by an in-progress Connect, and blocking on it must not stall other
-	// relay operations.
-	m.relayClientsMutex.RLock()
-	tracks := make([]*RelayTrack, 0, len(m.relayClients))
-	for _, rt := range m.relayClients {
-		tracks = append(tracks, rt)
-	}
-	m.relayClientsMutex.RUnlock()
-
-	// Only connected foreign relays carry state; a failed connect is evicted
-	// immediately (openConnVia), so there is no error state to surface.
-	for _, rt := range tracks {
-		rt.RLock()
-		rc := rt.relayClient
-		rt.RUnlock()
-		if rc != nil {
-			states = append(states, relayConnState(rc))
-		}
-	}
+	states = append(states, m.foreign.states()...)
 
 	return states
 }
@@ -327,76 +277,6 @@ func (m *Manager) UpdateToken(token *relayAuth.Token) error {
 	return m.tokenStore.UpdateToken(token)
 }
 
-func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string, serverIP netip.Addr) (net.Conn, error) {
-	// check if already has a connection to the desired relay server
-	m.relayClientsMutex.RLock()
-	rt, ok := m.relayClients[serverAddress]
-	m.relayClientsMutex.RUnlock()
-	if ok {
-		return m.openConnOnTrack(ctx, rt, peerKey)
-	}
-
-	// if not, establish a new connection but check it again (because changed the lock type) before starting the
-	// connection
-	m.relayClientsMutex.Lock()
-	rt, ok = m.relayClients[serverAddress]
-	if ok {
-		m.relayClientsMutex.Unlock()
-		return m.openConnOnTrack(ctx, rt, peerKey)
-	}
-
-	// Publish the track and release the map lock BEFORE dialing, so the dial does
-	// not run under rt.Lock (which would block RelayStates and the cleanup loop
-	// for the full dial). Concurrent callers find this track and wait on rt.ready.
-	rt = NewRelayTrack()
-	m.relayClients[serverAddress] = rt
-	m.relayClientsMutex.Unlock()
-
-	relayClient := NewClientWithServerIP(serverAddress, serverIP, m.tokenStore, m.peerID, m.mtu)
-	relayClient.SetTransportFallback(m.transportFallback)
-	err := relayClient.Connect(m.ctx)
-	if err != nil {
-		rt.Lock()
-		rt.err = err
-		rt.Unlock()
-		close(rt.ready)
-		m.relayClientsMutex.Lock()
-		delete(m.relayClients, serverAddress)
-		m.relayClientsMutex.Unlock()
-		return nil, err
-	}
-	// if connection closed then delete the relay client from the list
-	relayClient.SetOnDisconnectListener(m.onServerDisconnected)
-	rt.Lock()
-	rt.relayClient = relayClient
-	rt.Unlock()
-	close(rt.ready)
-
-	return relayClient.OpenConn(ctx, peerKey)
-}
-
-// openConnOnTrack opens a peer connection through an existing relay track,
-// waiting for the dial started by another openConnVia call to finish. It waits
-// on rt.ready rather than the track lock, so it neither holds nor contends the
-// track lock across the dial.
-func (m *Manager) openConnOnTrack(ctx context.Context, rt *RelayTrack, peerKey string) (net.Conn, error) {
-	select {
-	case <-rt.ready:
-	case <-ctx.Done():
-		return nil, ctx.Err()
-	}
-
-	rt.RLock()
-	defer rt.RUnlock()
-	if rt.err != nil {
-		return nil, rt.err
-	}
-	if rt.relayClient == nil {
-		return nil, ErrRelayClientNotConnected
-	}
-	return rt.relayClient.OpenConn(ctx, peerKey)
-}
-
 func (m *Manager) onServerConnected() {
 	m.listenerLock.Lock()
 	defer m.listenerLock.Unlock()
@@ -422,21 +302,12 @@ func (m *Manager) onServerDisconnected(serverAddress string) {
 	m.relayClientMu.Unlock()
 
 	if !isHome {
-		m.evictForeignRelay(serverAddress)
+		m.foreign.evict(serverAddress)
 	}
 
 	m.notifyOnDisconnectListeners(serverAddress)
 }
 
-func (m *Manager) evictForeignRelay(serverAddress string) {
-	m.relayClientsMutex.Lock()
-	defer m.relayClientsMutex.Unlock()
-	if _, ok := m.relayClients[serverAddress]; ok {
-		delete(m.relayClients, serverAddress)
-		log.Debugf("evicted disconnected foreign relay client: %s", serverAddress)
-	}
-}
-
 func (m *Manager) listenGuardEvent(ctx context.Context) {
 	for {
 		select {
@@ -459,8 +330,8 @@ func (m *Manager) storeClient(client *Client) {
 	m.relayClient.SetOnDisconnectListener(m.onServerDisconnected)
 }
 
-func (m *Manager) isForeignServer(address string) (bool, error) {
-	rAddr, err := m.relayClient.ServerInstanceURL()
+func (m *Manager) isForeignServer(relayClient *Client, address string) (bool, error) {
+	rAddr, err := relayClient.ServerInstanceURL()
 	if err != nil {
 		return false, fmt.Errorf("relay client not connected")
 	}
@@ -475,50 +346,11 @@ func (m *Manager) startCleanupLoop() {
 		case <-m.ctx.Done():
 			return
 		case <-ticker.C:
-			m.cleanUpUnusedRelays()
+			m.foreign.cleanupUnused()
 		}
 	}
 }
 
-func (m *Manager) cleanUpUnusedRelays() {
-	m.relayClientsMutex.Lock()
-	defer m.relayClientsMutex.Unlock()
-
-	for addr, rt := range m.relayClients {
-		rt.Lock()
-		// if the connection failed to the server the relay client will be nil
-		// but the instance will be kept in the relayClients until the next locking
-		if rt.err != nil {
-			rt.Unlock()
-			continue
-		}
-
-		// dial still in progress (openConnVia publishes the track before Connect
-		// completes and no longer holds rt.Lock during it), nothing to clean up.
-		if rt.relayClient == nil {
-			rt.Unlock()
-			continue
-		}
-
-		if time.Since(rt.created) <= m.keepUnusedServerTime {
-			rt.Unlock()
-			continue
-		}
-
-		if rt.relayClient.HasConns() {
-			rt.Unlock()
-			continue
-		}
-		rt.relayClient.SetOnDisconnectListener(nil)
-		go func() {
-			_ = rt.relayClient.Close()
-		}()
-		log.Debugf("clean up unused relay server connection: %s", addr)
-		delete(m.relayClients, addr)
-		rt.Unlock()
-	}
-}
-
 func (m *Manager) addListener(serverAddress string, onClosedListener OnServerCloseListener) {
 	m.listenerLock.Lock()
 	defer m.listenerLock.Unlock()

shared/relay/client/manager_cleanup_test.go

@@ -2,17 +2,14 @@ package client
 
 import (
 	"context"
-	"net/netip"
 	"testing"
 	"time"
-
-	"github.com/stretchr/testify/require"
 )
 
 // TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial drives a real, hanging foreign
-// relay dial and asserts cleanUpUnusedRelays does not stall behind it.
+// relay dial and asserts the foreign store cleanup does not stall behind it.
 func TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial(t *testing.T) {
-	serverAddr := stallingRelayListener(t)
+	serverAddr, accepted := stallingRelayListener(t)
 
 	mCtx, mCancel := context.WithCancel(context.Background())
 	t.Cleanup(mCancel)
@@ -22,39 +19,32 @@ func TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial(t *testing.T) {
 	dialDone := make(chan struct{})
 	go func() {
 		defer close(dialDone)
-		_, _ = m.openConnVia(mCtx, serverAddr, "peerKey", netip.Addr{})
+		_, _ = m.foreign.OpenConn(mCtx, "peerKey", RelayServer{Addr: serverAddr})
 	}()
 
-	// The track appears in the map once the dial is in flight.
-	require.Eventually(t, func() bool {
-		m.relayClientsMutex.RLock()
-		defer m.relayClientsMutex.RUnlock()
-		_, ok := m.relayClients[serverAddr]
-		return ok
-	}, 5*time.Second, 5*time.Millisecond, "relay dial did not start")
+	select {
+	case <-accepted:
+	case <-time.After(5 * time.Second):
+		t.Fatal("relay dial did not reach the listener")
+	}
 
 	cleanupDone := make(chan struct{})
 	go func() {
 		defer close(cleanupDone)
-		m.cleanUpUnusedRelays()
+		m.foreign.cleanupUnused()
 	}()
 
 	select {
 	case <-cleanupDone:
 	case <-time.After(2 * time.Second):
-		t.Fatal("cleanUpUnusedRelays blocked on an in-progress relay dial while holding the relay map lock")
+		t.Fatal("cleanupUnused blocked on an in-progress relay dial")
 	}
 
-	m.relayClientsMutex.RLock()
-	_, stillTracked := m.relayClients[serverAddr]
-	m.relayClientsMutex.RUnlock()
-	require.True(t, stillTracked, "an in-progress relay dial must not be evicted by cleanup")
-
 	// Release the hanging dial so the goroutine can exit cleanly.
 	mCancel()
 	select {
 	case <-dialDone:
 	case <-time.After(5 * time.Second):
-		t.Fatal("openConnVia did not return after context cancellation")
+		t.Fatal("foreign OpenConn did not return after context cancellation")
 	}
 }

shared/relay/client/manager_relaystates_test.go

@@ -3,7 +3,6 @@ package client
 import (
 	"context"
 	"net"
-	"net/netip"
 	"sync"
 	"testing"
 	"time"
@@ -13,13 +12,16 @@ import (
 
 // stallingRelayListener accepts TCP connections and holds them open without ever
 // responding, so a relay handshake dialed against it blocks until its context is
-// cancelled. It returns the "rel://host:port" URL to dial.
-func stallingRelayListener(t *testing.T) string {
+// cancelled. accepted is signalled once per incoming connection so a caller can
+// wait until a dial has actually reached the listener. It returns the
+// "rel://host:port" URL to dial.
+func stallingRelayListener(t *testing.T) (string, <-chan struct{}) {
 	t.Helper()
 
 	ln, err := net.Listen("tcp", "127.0.0.1:0")
 	require.NoError(t, err)
 
+	accepted := make(chan struct{}, 1)
 	var mu sync.Mutex
 	var conns []net.Conn
 	go func() {
@@ -31,6 +33,10 @@ func stallingRelayListener(t *testing.T) string {
 			mu.Lock()
 			conns = append(conns, c)
 			mu.Unlock()
+			select {
+			case accepted <- struct{}{}:
+			default:
+			}
 		}
 	}()
 	t.Cleanup(func() {
@@ -42,14 +48,14 @@ func stallingRelayListener(t *testing.T) string {
 		mu.Unlock()
 	})
 
-	return "rel://" + ln.Addr().String()
+	return "rel://" + ln.Addr().String(), accepted
 }
 
 // TestRelayStates_DoesNotBlockOnRealHangingDial is a regression test for
 // RelayStates() called by a "status -d command" hanging behind an in-progress
-// relay dial.
+// foreign relay dial.
 func TestRelayStates_DoesNotBlockOnRealHangingDial(t *testing.T) {
-	serverAddr := stallingRelayListener(t)
+	serverAddr, accepted := stallingRelayListener(t)
 
 	mCtx, mCancel := context.WithCancel(context.Background())
 	t.Cleanup(mCancel)
@@ -59,15 +65,14 @@ func TestRelayStates_DoesNotBlockOnRealHangingDial(t *testing.T) {
 	dialDone := make(chan struct{})
 	go func() {
 		defer close(dialDone)
-		_, _ = m.openConnVia(mCtx, serverAddr, "peerKey", netip.Addr{})
+		_, _ = m.foreign.OpenConn(mCtx, "peerKey", RelayServer{Addr: serverAddr})
 	}()
 
-	require.Eventually(t, func() bool {
-		m.relayClientsMutex.RLock()
-		defer m.relayClientsMutex.RUnlock()
-		_, ok := m.relayClients[serverAddr]
-		return ok
-	}, 5*time.Second, 5*time.Millisecond, "relay dial did not start")
+	select {
+	case <-accepted:
+	case <-time.After(5 * time.Second):
+		t.Fatal("relay dial did not reach the listener")
+	}
 
 	done := make(chan []RelayConnState, 1)
 	go func() {
@@ -86,6 +91,6 @@ func TestRelayStates_DoesNotBlockOnRealHangingDial(t *testing.T) {
 	select {
 	case <-dialDone:
 	case <-time.After(5 * time.Second):
-		t.Fatal("openConnVia did not return after context cancellation")
+		t.Fatal("foreign OpenConn did not return after context cancellation")
 	}
 }

shared/relay/client/manager_serverip_test.go

@@ -3,7 +3,6 @@ package client
 import (
 	"context"
 	"io"
-	"net/netip"
 	"testing"
 	"time"
 
@@ -85,7 +84,7 @@ func TestManager_ForeignRelayServerIP(t *testing.T) {
 	t.Run("no server IP, dial fails", func(t *testing.T) {
 		dialCtx, dialCancel := context.WithTimeout(ctx, 5*time.Second)
 		defer dialCancel()
-		_, err := mgrAlice.OpenConn(dialCtx, brokenFQDN, "bob", netip.Addr{})
+		_, err := mgrAlice.OpenConn(dialCtx, RelayServer{Addr: brokenFQDN}, "bob", true)
 		if err == nil {
 			t.Fatalf("expected OpenConn to fail without server IP, got success")
 		}
@@ -95,7 +94,7 @@ func TestManager_ForeignRelayServerIP(t *testing.T) {
 		// Bob waits for Alice's incoming peer connection on his side.
 		bobSideCh := make(chan error, 1)
 		go func() {
-			conn, err := mgrBob.OpenConn(ctx, bobRealAddr, "alice", netip.Addr{})
+			conn, err := mgrBob.OpenConn(ctx, RelayServer{Addr: bobRealAddr}, "alice", false)
 			if err != nil {
 				bobSideCh <- err
 				return
@@ -113,7 +112,7 @@ func TestManager_ForeignRelayServerIP(t *testing.T) {
 			bobSideCh <- nil
 		}()
 
-		aliceConn, err := mgrAlice.OpenConn(ctx, brokenFQDN, "bob", bobAdvertisedIP)
+		aliceConn, err := mgrAlice.OpenConn(ctx, RelayServer{Addr: brokenFQDN, IP: bobAdvertisedIP}, "bob", true)
 		if err != nil {
 			t.Fatalf("alice OpenConn with server IP: %s", err)
 		}

shared/relay/client/manager_test.go

@@ -3,7 +3,6 @@ package client
 import (
 	"context"
 	"fmt"
-	"net/netip"
 	"testing"
 	"time"
 
@@ -106,11 +105,11 @@ func TestForeignConn(t *testing.T) {
 	if err != nil {
 		t.Fatalf("failed to get relay address: %s", err)
 	}
-	connAliceToBob, err := clientAlice.OpenConn(ctx, bobsSrvAddr, "bob", netip.Addr{})
+	connAliceToBob, err := clientAlice.OpenConn(ctx, RelayServer{Addr: bobsSrvAddr}, "bob", true)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}
-	connBobToAlice, err := clientBob.OpenConn(ctx, bobsSrvAddr, "alice", netip.Addr{})
+	connBobToAlice, err := clientBob.OpenConn(ctx, RelayServer{Addr: bobsSrvAddr}, "alice", false)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}
@@ -210,7 +209,7 @@ func TestForeginConnClose(t *testing.T) {
 	if err != nil {
 		t.Fatalf("failed to serve manager: %s", err)
 	}
-	conn, err := mgr.OpenConn(ctx, toURL(srvCfg2)[0], "bob", netip.Addr{})
+	conn, err := mgr.OpenConn(ctx, RelayServer{Addr: toURL(srvCfg2)[0]}, "bob", true)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}
@@ -302,7 +301,7 @@ func TestForeignAutoClose(t *testing.T) {
 	}
 
 	t.Log("open connection to another peer")
-	if _, err = mgr.OpenConn(ctx, foreignServerURL, "anotherpeer", netip.Addr{}); err == nil {
+	if _, err = mgr.OpenConn(ctx, RelayServer{Addr: foreignServerURL}, "anotherpeer", true); err == nil {
 		t.Fatalf("should have failed to open connection to another peer")
 	}
 
@@ -372,7 +371,7 @@ func TestAutoReconnect(t *testing.T) {
 	if err != nil {
 		t.Errorf("failed to get relay address: %s", err)
 	}
-	conn, err := clientAlice.OpenConn(ctx, ra, "bob", netip.Addr{})
+	conn, err := clientAlice.OpenConn(ctx, RelayServer{Addr: ra}, "bob", false)
 	if err != nil {
 		t.Errorf("failed to bind channel: %s", err)
 	}
@@ -392,7 +391,7 @@ func TestAutoReconnect(t *testing.T) {
 	}
 
 	log.Infof("reopent the connection")
-	_, err = clientAlice.OpenConn(ctx, ra, "bob", netip.Addr{})
+	_, err = clientAlice.OpenConn(ctx, RelayServer{Addr: ra}, "bob", false)
 	if err != nil {
 		t.Errorf("failed to open channel: %s", err)
 	}
@@ -454,7 +453,7 @@ func TestNotifierDoubleAdd(t *testing.T) {
 		t.Fatalf("failed to serve manager: %s", err)
 	}
 
-	conn1, err := clientAlice.OpenConn(ctx, clientAlice.ServerURLs()[0], "bob", netip.Addr{})
+	conn1, err := clientAlice.OpenConn(ctx, RelayServer{Addr: clientAlice.ServerURLs()[0]}, "bob", false)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}