[client] Suspend reconnection loops while the OS reports no network

On mobile the client kept dialing management, signal, relay and peer
connections while the device had no usable network at all (airplane
mode), burning battery for attempts that cannot succeed. Stopping the
engine is not an option: tearing it down destroys the TUN device, and
traffic can leak outside the tunnel until it is rebuilt.

Add client/netstate, a small gate the platform feeds from its own
connectivity callbacks. Every reconnection loop waits on it instead of
retrying blindly, and resets its backoff when the network returns so
recovery is immediate. The state is injected through functional options
and consumers hold a *State that may be nil, so every platform that does
not report availability behaves exactly as before.

The relay quick-reconnect rechecks availability after its 1.5s wait: the
disconnect that triggers it is usually the first symptom of the network
going away, so the flag typically arrives while it sleeps.

Report the suspension to the UI as well. peer.Listener grows
OnStateChanged with a typed ClientState, re-exported across the gomobile
boundary as integer constants, and the notifier maps Connecting to a new
NoNetwork state while the OS reports no network, so mobile clients can
show "no network available" instead of a misleading "connecting".

Finally, exit the client retry loop cleanly when its context is
cancelled. backoff.WithContext surfaces the bare context error, which
callers could not distinguish from a real failure — on Android that
turned an engine restart into an unrecoverable error.
This commit is contained in:
Zoltan Papp
2026-08-11 00:58:50 +02:00
parent 2ce6323602
commit 902263ac96
19 changed files with 673 additions and 81 deletions

View File

@@ -38,6 +38,7 @@ import (
"github.com/netbirdio/netbird/client/internal/updater"
"github.com/netbirdio/netbird/client/internal/updater/installer"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netstate"
cProto "github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/ssh"
sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -70,18 +71,33 @@ type ConnectClient struct {
updateManager *updater.Manager
persistSyncResponse bool
// netState gates every reconnection loop on OS-reported network
// availability. Nil (the default) disables gating; mobile platforms
// inject it via WithNetworkState.
netState *netstate.State
}
// ConnectClientOption configures optional ConnectClient behavior.
type ConnectClientOption func(*ConnectClient)
// WithNetworkState injects the OS network availability state that gates every
// reconnection loop; without it gating is disabled.
func WithNetworkState(netState *netstate.State) ConnectClientOption {
return func(c *ConnectClient) { c.netState = netState }
}
func NewConnectClient(
ctx context.Context,
config *profilemanager.Config,
statusRecorder *peer.Status,
opts ...ConnectClientOption,
) *ConnectClient {
// Derive the run context here so Stop owns the cancel that unblocks the run
// loop. runCancel is set once at construction, so Stop can call it without
// racing the run loop's startup. Callers therefore need not cancel before Stop.
runCtx, runCancel := context.WithCancel(ctx)
return &ConnectClient{
c := &ConnectClient{
ctx: runCtx,
runCancel: runCancel,
runExited: make(chan struct{}),
@@ -89,6 +105,10 @@ func NewConnectClient(
statusRecorder: statusRecorder,
engineMutex: sync.Mutex{},
}
for _, opt := range opts {
opt(c)
}
return c
}
func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
@@ -274,6 +294,13 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
return nil
}
// suspend connection attempts while the OS reports no usable network
if waited, err := c.netState.Wait(c.ctx); err != nil {
return nil
} else if waited {
backOff.Reset()
}
state.Set(StatusConnecting)
engineCtx, cancel := context.WithCancel(c.ctx)
@@ -285,7 +312,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}()
log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host)
mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled, mgm.WithNetworkState(c.netState))
if err != nil {
// On daemon shutdown / Down() the parent context is cancelled
// and the dial fails with "context canceled". Wrapping that
@@ -360,7 +387,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}()
// with the global Netbird config in hand connect (just a connection, no stream yet) Signal
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey)
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netState)
if err != nil {
log.Error(err)
return wrapErr(err)
@@ -396,7 +423,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
engineConfig.StateDir = filepath.Dir(path)
}
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
relayClient.WithNetworkState(c.netState))
c.statusRecorder.SetRelayMgr(relayManager)
if len(relayURLs) > 0 {
if token != nil {
@@ -424,6 +452,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
UpdateManager: c.updateManager,
ClientMetrics: c.clientMetrics,
MetricsCtx: c.ctx,
NetState: c.netState,
}, mobileDependency)
engine.SetSyncResponsePersistence(c.persistSyncResponse)
c.engine = engine
@@ -480,6 +509,16 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
// status stream stuck at Connecting.
err = backoff.Retry(operation, backoff.WithContext(backOff, c.ctx))
if err != nil {
// Once the client context is cancelled backoff.WithContext surfaces the
// bare context error, and any attempt torn down mid-flight reports the
// same. That cancellation is the caller asking us to stop (Stop, Down or
// an engine restart), so exit cleanly instead of handing back a failure
// the caller would have to distinguish from a real one.
if c.ctx.Err() != nil && errors.Is(err, context.Canceled) {
log.Info("exiting client retry loop, context cancelled")
return nil
}
log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
state.Set(StatusNeedsLogin)
@@ -673,7 +712,7 @@ func selectMTU(localMTU uint16, peerMTU int32) uint16 {
}
// connectToSignal creates Signal Service client and established a connection
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key) (*signal.GrpcClient, error) {
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netState *netstate.State) (*signal.GrpcClient, error) {
var sigTLSEnabled bool
if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
sigTLSEnabled = true
@@ -681,7 +720,7 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
sigTLSEnabled = false
}
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled)
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled, signal.WithNetworkState(netState))
if err != nil {
log.Errorf("error while connecting to the Signal Exchange Service %s: %s", wtConfig.Signal.Uri, err)
return nil, gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Signal Service : %s", err)

View File

@@ -58,6 +58,7 @@ import (
"github.com/netbirdio/netbird/client/internal/syncstore"
"github.com/netbirdio/netbird/client/internal/updater"
"github.com/netbirdio/netbird/client/jobexec"
"github.com/netbirdio/netbird/client/netstate"
cProto "github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/system"
nbdns "github.com/netbirdio/netbird/dns"
@@ -180,6 +181,9 @@ type EngineServices struct {
UpdateManager *updater.Manager
ClientMetrics *metrics.ClientMetrics
MetricsCtx context.Context
// NetState gates the reconnection loops on OS-reported network
// availability; nil disables gating.
NetState *netstate.State
}
// Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -203,6 +207,10 @@ type Engine struct {
config *EngineConfig
mobileDep MobileDependency
// netState gates the peer reconnection guards on OS-reported network
// availability; nil disables gating.
netState *netstate.State
// STUNs is a list of STUN servers used by ICE
STUNs []*stun.URI
// TURNs is a list of STUN servers used by ICE
@@ -336,6 +344,7 @@ func NewEngine(
syncMsgMux: &sync.Mutex{},
config: config,
mobileDep: mobileDep,
netState: services.NetState,
STUNs: []*stun.URI{},
TURNs: []*stun.URI{},
networkSerial: 0,
@@ -1891,7 +1900,8 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
Addr: e.getRosenpassAddr(),
PermissiveMode: e.config.RosenpassPermissive,
},
ICEConfig: e.createICEConfig(),
ICEConfig: e.createICEConfig(),
NetworkState: e.netState,
}
serviceDependencies := peer.ServiceDependencies{

View File

@@ -26,6 +26,7 @@ import (
"github.com/netbirdio/netbird/client/internal/portforward"
"github.com/netbirdio/netbird/client/internal/rosenpass"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/route"
relayClient "github.com/netbirdio/netbird/shared/relay/client"
)
@@ -93,6 +94,10 @@ type ConnConfig struct {
// ICEConfig ICE protocol configuration
ICEConfig icemaker.Config
// NetworkState gates the reconnection guard on OS-reported network
// availability; nil disables gating.
NetworkState *netstate.State
}
type Conn struct {
@@ -254,7 +259,7 @@ func (conn *Conn) open(engineCtx context.Context, firstPacket []byte) error {
conn.handshaker.AddICEListener(conn.workerICE.OnNewOffer)
}
conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher)
conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher, conn.config.NetworkState)
conn.wg.Add(1)
go func() {

View File

@@ -6,6 +6,8 @@ import (
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
)
// ConnStatus represents the connection state as seen by the guard.
@@ -31,20 +33,26 @@ 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
// netState gates reconnect attempts on OS-reported network availability;
// nil disables gating.
netState *netstate.State
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 netState
// disables network availability gating.
func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState *netstate.State) *Guard {
return &Guard{
log: log,
isConnectedOnAllWay: isConnectedFn,
timeout: timeout,
srWatcher: srWatcher,
netState: netState,
relayedConnDisconnected: make(chan struct{}, 1),
iCEConnDisconnected: make(chan struct{}, 1),
}
@@ -99,6 +107,12 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
for {
select {
case <-tickerChannel:
// skip attempts while the OS reports no usable network; the ticker
// keeps running so other events remain responsive, and the guard
// resumes via the signal/relay reconnect events once network returns
if !g.netState.IsOnline() {
continue
}
switch g.isConnectedOnAllWay() {
case ConnStatusConnected:
// all good, nothing to do

View File

@@ -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

View File

@@ -1,11 +1,40 @@
package peer
// ClientState identifies the client connection state delivered via
// Listener.OnStateChanged.
type ClientState int
// Client states. The numeric values cross the gomobile boundary (the mobile
// bindings re-export them as integer constants), so they are a wire format:
// append new states at the end, never reorder or insert.
const (
ClientStateDisconnected ClientState = iota
ClientStateConnected
ClientStateConnecting
ClientStateDisconnecting
// ClientStateNoNetwork is an overlay state: it is never stored as the
// last notification, only derived from ClientStateConnecting while the
// OS reports no usable network (see notifier.effectiveState).
ClientStateNoNetwork
)
// Listener is a callback type about the NetBird network connection state
type Listener interface {
// OnStateChanged reports every client state transition. New states are
// delivered only through this callback; the per-state callbacks below
// are kept for compatibility and will be removed once all consumers
// have migrated.
OnStateChanged(state ClientState)
// Deprecated: consume OnStateChanged instead.
OnConnected()
// Deprecated: consume OnStateChanged instead.
OnDisconnected()
// Deprecated: consume OnStateChanged instead.
OnConnecting()
// Deprecated: consume OnStateChanged instead.
OnDisconnecting()
OnAddressChanged(string, string)
OnPeersListChanged(int)
}

View File

@@ -4,31 +4,57 @@ import (
"sync"
)
const (
stateDisconnected = iota
stateConnected
stateConnecting
stateDisconnecting
)
type notifier struct {
serverStateLock sync.Mutex
listenersLock sync.Mutex
listener Listener
currentClientState bool
lastNotification int
lastNotification ClientState
lastNumberOfPeers int
lastFqdnAddress string
lastIPAddress string
networkAvailable bool
}
func newNotifier() *notifier {
return &notifier{}
return &notifier{
networkAvailable: true,
}
}
// effectiveState maps the computed state to what listeners should see:
// while the OS reports no usable network, "Connecting" would be a lie —
// connection attempts are suspended — so it is reported as NoNetwork.
// Caller must hold serverStateLock.
func (n *notifier) effectiveState(state ClientState) ClientState {
if !n.networkAvailable && state == ClientStateConnecting {
return ClientStateNoNetwork
}
return state
}
// setNetworkAvailable records the OS network availability and re-notifies
// the listener when the flag flips the effective state (Connecting <->
// NoNetwork).
func (n *notifier) setNetworkAvailable(available bool) {
n.serverStateLock.Lock()
if n.networkAvailable == available {
n.serverStateLock.Unlock()
return
}
previous := n.effectiveState(n.lastNotification)
n.networkAvailable = available
current := n.effectiveState(n.lastNotification)
n.serverStateLock.Unlock()
if previous != current {
n.notify(current)
}
}
func (n *notifier) setListener(listener Listener) {
n.serverStateLock.Lock()
lastNotification := n.lastNotification
lastNotification := n.effectiveState(n.lastNotification)
numOfPeers := n.lastNumberOfPeers
fqdnAddress := n.lastFqdnAddress
address := n.lastIPAddress
@@ -61,43 +87,45 @@ func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
}
n.lastNotification = calculatedState
effective := n.effectiveState(calculatedState)
n.serverStateLock.Unlock()
n.notify(calculatedState)
n.notify(effective)
}
func (n *notifier) clientStart() {
n.serverStateLock.Lock()
n.currentClientState = true
n.lastNotification = stateConnecting
n.lastNotification = ClientStateConnecting
effective := n.effectiveState(ClientStateConnecting)
n.serverStateLock.Unlock()
n.notify(stateConnecting)
n.notify(effective)
}
func (n *notifier) clientStop() {
n.serverStateLock.Lock()
n.currentClientState = false
n.lastNotification = stateDisconnected
n.lastNotification = ClientStateDisconnected
n.serverStateLock.Unlock()
n.notify(stateDisconnected)
n.notify(ClientStateDisconnected)
}
func (n *notifier) clientTearDown() {
n.serverStateLock.Lock()
n.currentClientState = false
n.lastNotification = stateDisconnecting
n.lastNotification = ClientStateDisconnecting
n.serverStateLock.Unlock()
n.notify(stateDisconnecting)
n.notify(ClientStateDisconnecting)
}
func (n *notifier) isServerStateChanged(newState int) bool {
func (n *notifier) isServerStateChanged(newState ClientState) bool {
return n.lastNotification != newState
}
func (n *notifier) notify(state int) {
func (n *notifier) notify(state ClientState) {
n.listenersLock.Lock()
listener := n.listener
n.listenersLock.Unlock()
@@ -109,20 +137,20 @@ func (n *notifier) notify(state int) {
notifyListener(listener, state)
}
func (n *notifier) calculateState(managementConn, signalConn bool) int {
func (n *notifier) calculateState(managementConn, signalConn bool) ClientState {
if managementConn && signalConn {
return stateConnected
return ClientStateConnected
}
if !managementConn && !signalConn && !n.currentClientState {
return stateDisconnected
return ClientStateDisconnected
}
if n.lastNotification == stateDisconnecting {
return stateDisconnecting
if n.lastNotification == ClientStateDisconnecting {
return ClientStateDisconnecting
}
return stateConnecting
return ClientStateConnecting
}
func (n *notifier) peerListChanged(numOfPeers int) {
@@ -159,15 +187,19 @@ func (n *notifier) localAddressChanged(fqdn, address string) {
listener.OnAddressChanged(fqdn, address)
}
func notifyListener(l Listener, state int) {
func notifyListener(l Listener, state ClientState) {
// legacy per-state callbacks; NoNetwork is delivered only via
// OnStateChanged below
switch state {
case stateDisconnected:
case ClientStateDisconnected:
l.OnDisconnected()
case stateConnected:
case ClientStateConnected:
l.OnConnected()
case stateConnecting:
case ClientStateConnecting:
l.OnConnecting()
case stateDisconnecting:
case ClientStateDisconnecting:
l.OnDisconnecting()
}
l.OnStateChanged(state)
}

View File

@@ -6,29 +6,32 @@ import (
)
type mocListener struct {
lastState int
lastState ClientState
wg sync.WaitGroup
peersWg sync.WaitGroup
peers int
}
func (l *mocListener) OnConnected() {
l.lastState = stateConnected
l.lastState = ClientStateConnected
l.wg.Done()
}
func (l *mocListener) OnDisconnected() {
l.lastState = stateDisconnected
l.lastState = ClientStateDisconnected
l.wg.Done()
}
func (l *mocListener) OnConnecting() {
l.lastState = stateConnecting
l.lastState = ClientStateConnecting
l.wg.Done()
}
func (l *mocListener) OnDisconnecting() {
l.lastState = stateDisconnecting
l.lastState = ClientStateDisconnecting
l.wg.Done()
}
func (l *mocListener) OnStateChanged(state ClientState) {
}
func (l *mocListener) OnAddressChanged(host, addr string) {
}
@@ -57,15 +60,15 @@ func Test_notifier_serverState(t *testing.T) {
type scenario struct {
name string
expected int
expected ClientState
mgmState bool
signalState bool
}
scenarios := []scenario{
{"connected", stateConnected, true, true},
{"mgm down", stateConnecting, false, true},
{"signal down", stateConnecting, true, false},
{"disconnected", stateDisconnected, false, false},
{"connected", ClientStateConnected, true, true},
{"mgm down", ClientStateConnecting, false, true},
{"signal down", ClientStateConnecting, true, false},
{"disconnected", ClientStateDisconnected, false, false},
}
for _, tt := range scenarios {
@@ -85,7 +88,7 @@ func Test_notifier_SetListener(t *testing.T) {
listener.setPeersWaiter()
n := newNotifier()
n.lastNotification = stateConnecting
n.lastNotification = ClientStateConnecting
n.setListener(listener)
listener.wait()
listener.waitPeers()
@@ -99,7 +102,7 @@ func Test_notifier_RemoveListener(t *testing.T) {
listener.setWaiter()
listener.setPeersWaiter()
n := newNotifier()
n.lastNotification = stateConnecting
n.lastNotification = ClientStateConnecting
n.setListener(listener)
// setListener replays cached state on a goroutine; wait for both the state
// and peers callbacks to finish so we don't race on listener.peers.

View File

@@ -1211,6 +1211,12 @@ func (d *Status) ClientTeardown() {
d.notifyStateChange()
}
// SetNetworkAvailable records the OS-reported network availability; while
// unavailable, listeners see NoNetwork instead of Connecting.
func (d *Status) SetNetworkAvailable(available bool) {
d.notifier.setNetworkAvailable(available)
}
// SetConnectionListener set a listener to the notifier
func (d *Status) SetConnectionListener(listener Listener) {
d.notifier.setListener(listener)