Compare commits

..

3 Commits

Author SHA1 Message Date
Zoltan Papp
bc73e6bd71 [client] Debug: create GUI windows on demand and destroy them on close
Experiment on top of the memory profiler: the main and Settings windows are no
longer created at startup or kept alive hidden, so an idle tray holds no webview
process. The WindowManager owns creation, rebuilds the main window on the next
show, and defers every show until the frontend reports it has rendered, which
keeps an empty webview off screen.

Measured on macOS: idle footprint drops from ~160 MB to ~74 MB, at the cost of
~150-250 ms per window open.
2026-08-07 14:43:52 +02:00
Zoltan Papp
04ca92d42b [client] Debug: add process tree and window inventory to GUI memory dumps
The webview runs in child processes whose memory the Go runtime profiles
cannot see, so each snapshot now also records the whole process tree with
RSS/VMS plus PSS and Private_Dirty from smaps_rollup on Linux, and the live
Wails window inventory. Snapshots now run at startup, 2 and 5 minutes.
2026-08-07 14:43:29 +02:00
Zoltan Papp
079aee8d63 [client] Debug: dump GUI memory profiles to /tmp/nbgui
Temporary debug patch for the GUI memory consumption investigation. Writes
two snapshots - one at startup, one after 5 minutes - each into its own
/tmp/nbgui/<timestamp>-<pid> directory containing the heap, goroutine and
threadcreate profiles plus a memstats.txt summary.
2026-08-07 14:43:29 +02:00
33 changed files with 737 additions and 1246 deletions

View File

@@ -25,8 +25,6 @@ import (
"github.com/netbirdio/netbird/client/internal/routemanager"
"github.com/netbirdio/netbird/client/internal/stdnet"
"github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/formatter"
"github.com/netbirdio/netbird/route"
@@ -34,6 +32,11 @@ import (
types "github.com/netbirdio/netbird/upload-server/types"
)
// ConnectionListener export internal Listener for mobile
type ConnectionListener interface {
peer.Listener
}
// TunAdapter export internal TunAdapter for mobile
type TunAdapter interface {
device.TunAdapter
@@ -74,13 +77,6 @@ type Client struct {
deviceName string
uiVersion string
networkChangeListener listener.NetworkChangeListener
// netState outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run and RunWithoutLogin inject it into each new
// ConnectClient, which distributes it to every reconnection loop.
netState *netstate.State
// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
sweeper *netsweep.Sweeper
stateMu sync.RWMutex
connectClient *internal.ConnectClient
@@ -152,28 +148,9 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
recorder: peer.NewRecorder(""),
ctxCancelLock: &sync.Mutex{},
networkChangeListener: networkChangeListener,
netState: netstate.New(),
sweeper: netsweep.New(),
}
}
// SetNetworkAvailable feeds OS-reported network availability into the client.
// While unavailable, the internal reconnect loops suspend their attempts and
// the connection listener reports NoNetwork instead of Connecting; when
// availability returns, the loops resume immediately with a fresh backoff.
func (c *Client) SetNetworkAvailable(available bool) {
c.netState.Set(available)
c.recorder.SetNetworkAvailable(available)
}
// NotifyNetworkChange cuts the management, signal and relay connections
// after the OS switched networks, so the reconnect loops redial immediately
// on the new one. The engine and the TUN device stay untouched.
func (c *Client) NotifyNetworkChange() {
n := c.sweeper.Sweep()
log.Infof("network change: swept %d connections", n)
}
// Run start the internal client. It is a blocker function
func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroidTV bool, dns *DNSList, dnsReadyListener DnsReadyListener, envList *EnvList) error {
exportEnvList(envList)
@@ -211,8 +188,7 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
}
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, cacheDir, cfgFile, connectClient)
// This path runs the interactive SSO flow, so reaching here means the peer
// is authenticated again — release the latch Status() reports from. Clear
@@ -253,8 +229,7 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
// todo do not throw error in case of cancelled context
ctx = internal.CtxInitState(ctx)
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, cacheDir, cfgFile, connectClient)
return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
}
@@ -538,7 +513,7 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error {
// SetConnectionListener set the network connection listener
func (c *Client) SetConnectionListener(listener ConnectionListener) {
c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
c.recorder.SetConnectionListener(listener)
}
// RemoveConnectionListener remove connection listener

View File

@@ -1,41 +0,0 @@
//go:build android
package android
import (
"github.com/netbirdio/netbird/client/internal/peer"
)
// Client state values delivered via ConnectionListener.OnStateChanged,
// re-exported as basic constants so gomobile emits them into the generated
// Java bindings. They mirror peer.ClientState*: append-only, never reorder.
const (
ClientStateDisconnected = int(peer.ClientStateDisconnected)
ClientStateConnected = int(peer.ClientStateConnected)
ClientStateConnecting = int(peer.ClientStateConnecting)
ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
ClientStateNoNetwork = int(peer.ClientStateNoNetwork)
)
// ConnectionListener export internal Listener for mobile. It mirrors
// peer.Listener with OnStateChanged taking a plain int (one of the
// ClientState* constants), because gomobile cannot bind named types.
type ConnectionListener interface {
OnStateChanged(state int)
OnConnected()
OnDisconnected()
OnConnecting()
OnDisconnecting()
OnAddressChanged(string, string)
OnPeersListChanged(int)
}
// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
// peer.Listener, converting the typed state to the int the binding carries.
type connectionListenerAdapter struct {
ConnectionListener
}
func (a connectionListenerAdapter) OnStateChanged(state peer.ClientState) {
a.ConnectionListener.OnStateChanged(int(state))
}

View File

@@ -16,47 +16,28 @@ import (
"google.golang.org/grpc"
nbnet "github.com/netbirdio/netbird/client/net"
"github.com/netbirdio/netbird/client/netsweep"
)
func WithCustomDialer(_ bool, _ string) grpc.DialOption {
return grpc.WithContextDialer(dialContext)
}
// WithSweeper dials like WithCustomDialer but registers connections and
// dials with the sweeper. Append it after WithCustomDialer: gRPC applies
// dial options in order, so the later context dialer wins.
func WithSweeper(sweeper *netsweep.Sweeper) grpc.DialOption {
return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
dial := sweeper.StartDial(ctx)
defer dial.Release()
if runtime.GOOS == "linux" {
currentUser, err := user.Current()
if err != nil {
return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
}
conn, err := dialContext(dial.Ctx(), addr)
if err != nil {
return nil, err
// the custom dialer requires root permissions which are not required for use cases run as non-root
if currentUser.Uid != "0" {
log.Debug("Not running as root, using standard dialer")
dialer := &net.Dialer{}
return dialer.DialContext(ctx, "tcp", addr)
}
}
return dial.WrapConn(conn)
conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
if err != nil {
return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
}
return conn, nil
})
}
func dialContext(ctx context.Context, addr string) (net.Conn, error) {
if runtime.GOOS == "linux" {
currentUser, err := user.Current()
if err != nil {
return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
}
// the custom dialer requires root permissions which are not required for use cases run as non-root
if currentUser.Uid != "0" {
log.Debug("Not running as root, using standard dialer")
dialer := &net.Dialer{}
return dialer.DialContext(ctx, "tcp", addr)
}
}
conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
if err != nil {
return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
}
return conn, nil
}

View File

@@ -3,7 +3,6 @@ package grpc
import (
"google.golang.org/grpc"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/util/wsproxy/client"
)
@@ -12,8 +11,3 @@ import (
func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
return client.WithWebSocketDialer(tlsEnabled, component)
}
// WithSweeper is a no-op on WASM/JS: there is no network change signal.
func WithSweeper(_ *netsweep.Sweeper) grpc.DialOption {
return grpc.EmptyDialOption{}
}

View File

@@ -38,8 +38,6 @@ 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"
"github.com/netbirdio/netbird/client/netsweep"
cProto "github.com/netbirdio/netbird/client/proto"
"github.com/netbirdio/netbird/client/ssh"
sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -72,42 +70,18 @@ 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
// sweeper cuts the management, signal and relay connections on network
// change; nil disables it.
sweeper *netsweep.Sweeper
}
// 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 }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) ConnectClientOption {
return func(c *ConnectClient) { c.sweeper = sweeper }
}
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)
c := &ConnectClient{
return &ConnectClient{
ctx: runCtx,
runCancel: runCancel,
runExited: make(chan struct{}),
@@ -115,10 +89,6 @@ func NewConnectClient(
statusRecorder: statusRecorder,
engineMutex: sync.Mutex{},
}
for _, opt := range opts {
opt(c)
}
return c
}
func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
@@ -304,13 +274,6 @@ 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)
@@ -322,8 +285,7 @@ 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,
mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper))
mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
if err != nil {
// On daemon shutdown / Down() the parent context is cancelled
// and the dial fails with "context canceled". Wrapping that
@@ -398,7 +360,7 @@ 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, c.netState, c.sweeper)
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey)
if err != nil {
log.Error(err)
return wrapErr(err)
@@ -434,8 +396,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
engineConfig.StateDir = filepath.Dir(path)
}
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
c.statusRecorder.SetRelayMgr(relayManager)
if len(relayURLs) > 0 {
if token != nil {
@@ -463,7 +424,6 @@ 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
@@ -520,16 +480,6 @@ 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)
@@ -723,7 +673,7 @@ 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, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) {
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key) (*signal.GrpcClient, error) {
var sigTLSEnabled bool
if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
sigTLSEnabled = true
@@ -731,8 +681,7 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
sigTLSEnabled = false
}
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled)
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

@@ -58,7 +58,6 @@ 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"
@@ -181,9 +180,6 @@ 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.
@@ -207,10 +203,6 @@ 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
@@ -344,7 +336,6 @@ func NewEngine(
syncMsgMux: &sync.Mutex{},
config: config,
mobileDep: mobileDep,
netState: services.NetState,
STUNs: []*stun.URI{},
TURNs: []*stun.URI{},
networkSerial: 0,
@@ -1900,8 +1891,7 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
Addr: e.getRosenpassAddr(),
PermissiveMode: e.config.RosenpassPermissive,
},
ICEConfig: e.createICEConfig(),
NetworkState: e.netState,
ICEConfig: e.createICEConfig(),
}
serviceDependencies := peer.ServiceDependencies{

View File

@@ -26,7 +26,6 @@ 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"
)
@@ -94,10 +93,6 @@ 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 {
@@ -259,7 +254,7 @@ 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.config.NetworkState)
conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher)
conn.wg.Add(1)
go func() {

View File

@@ -6,8 +6,6 @@ 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.
@@ -33,26 +31,20 @@ type connStatusFunc func() ConnStatus
// - Relayed connection disconnected
// - ICE candidate changes
type Guard struct {
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
log *log.Entry
isConnectedOnAllWay connStatusFunc
timeout time.Duration
srWatcher *SRWatcher
relayedConnDisconnected chan struct{}
iCEConnDisconnected chan struct{}
}
// 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 {
func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher) *Guard {
return &Guard{
log: log,
isConnectedOnAllWay: isConnectedFn,
timeout: timeout,
srWatcher: srWatcher,
netState: netState,
relayedConnDisconnected: make(chan struct{}, 1),
iCEConnDisconnected: make(chan struct{}, 1),
}
@@ -107,12 +99,6 @@ 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, nil)
return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw)
}
// countBackoffTickerGoroutines returns how many goroutines are currently sitting

View File

@@ -1,40 +1,11 @@
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

@@ -4,57 +4,31 @@ import (
"sync"
)
const (
stateDisconnected = iota
stateConnected
stateConnecting
stateDisconnecting
)
type notifier struct {
serverStateLock sync.Mutex
listenersLock sync.Mutex
listener Listener
currentClientState bool
lastNotification ClientState
lastNotification int
lastNumberOfPeers int
lastFqdnAddress string
lastIPAddress string
networkAvailable bool
}
func newNotifier() *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)
}
return &notifier{}
}
func (n *notifier) setListener(listener Listener) {
n.serverStateLock.Lock()
lastNotification := n.effectiveState(n.lastNotification)
lastNotification := n.lastNotification
numOfPeers := n.lastNumberOfPeers
fqdnAddress := n.lastFqdnAddress
address := n.lastIPAddress
@@ -87,45 +61,43 @@ func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
}
n.lastNotification = calculatedState
effective := n.effectiveState(calculatedState)
n.serverStateLock.Unlock()
n.notify(effective)
n.notify(calculatedState)
}
func (n *notifier) clientStart() {
n.serverStateLock.Lock()
n.currentClientState = true
n.lastNotification = ClientStateConnecting
effective := n.effectiveState(ClientStateConnecting)
n.lastNotification = stateConnecting
n.serverStateLock.Unlock()
n.notify(effective)
n.notify(stateConnecting)
}
func (n *notifier) clientStop() {
n.serverStateLock.Lock()
n.currentClientState = false
n.lastNotification = ClientStateDisconnected
n.lastNotification = stateDisconnected
n.serverStateLock.Unlock()
n.notify(ClientStateDisconnected)
n.notify(stateDisconnected)
}
func (n *notifier) clientTearDown() {
n.serverStateLock.Lock()
n.currentClientState = false
n.lastNotification = ClientStateDisconnecting
n.lastNotification = stateDisconnecting
n.serverStateLock.Unlock()
n.notify(ClientStateDisconnecting)
n.notify(stateDisconnecting)
}
func (n *notifier) isServerStateChanged(newState ClientState) bool {
func (n *notifier) isServerStateChanged(newState int) bool {
return n.lastNotification != newState
}
func (n *notifier) notify(state ClientState) {
func (n *notifier) notify(state int) {
n.listenersLock.Lock()
listener := n.listener
n.listenersLock.Unlock()
@@ -137,20 +109,20 @@ func (n *notifier) notify(state ClientState) {
notifyListener(listener, state)
}
func (n *notifier) calculateState(managementConn, signalConn bool) ClientState {
func (n *notifier) calculateState(managementConn, signalConn bool) int {
if managementConn && signalConn {
return ClientStateConnected
return stateConnected
}
if !managementConn && !signalConn && !n.currentClientState {
return ClientStateDisconnected
return stateDisconnected
}
if n.lastNotification == ClientStateDisconnecting {
return ClientStateDisconnecting
if n.lastNotification == stateDisconnecting {
return stateDisconnecting
}
return ClientStateConnecting
return stateConnecting
}
func (n *notifier) peerListChanged(numOfPeers int) {
@@ -187,19 +159,15 @@ func (n *notifier) localAddressChanged(fqdn, address string) {
listener.OnAddressChanged(fqdn, address)
}
func notifyListener(l Listener, state ClientState) {
// legacy per-state callbacks; NoNetwork is delivered only via
// OnStateChanged below
func notifyListener(l Listener, state int) {
switch state {
case ClientStateDisconnected:
case stateDisconnected:
l.OnDisconnected()
case ClientStateConnected:
case stateConnected:
l.OnConnected()
case ClientStateConnecting:
case stateConnecting:
l.OnConnecting()
case ClientStateDisconnecting:
case stateDisconnecting:
l.OnDisconnecting()
}
l.OnStateChanged(state)
}

View File

@@ -6,32 +6,29 @@ import (
)
type mocListener struct {
lastState ClientState
lastState int
wg sync.WaitGroup
peersWg sync.WaitGroup
peers int
}
func (l *mocListener) OnConnected() {
l.lastState = ClientStateConnected
l.lastState = stateConnected
l.wg.Done()
}
func (l *mocListener) OnDisconnected() {
l.lastState = ClientStateDisconnected
l.lastState = stateDisconnected
l.wg.Done()
}
func (l *mocListener) OnConnecting() {
l.lastState = ClientStateConnecting
l.lastState = stateConnecting
l.wg.Done()
}
func (l *mocListener) OnDisconnecting() {
l.lastState = ClientStateDisconnecting
l.lastState = stateDisconnecting
l.wg.Done()
}
func (l *mocListener) OnStateChanged(state ClientState) {
}
func (l *mocListener) OnAddressChanged(host, addr string) {
}
@@ -60,15 +57,15 @@ func Test_notifier_serverState(t *testing.T) {
type scenario struct {
name string
expected ClientState
expected int
mgmState bool
signalState bool
}
scenarios := []scenario{
{"connected", ClientStateConnected, true, true},
{"mgm down", ClientStateConnecting, false, true},
{"signal down", ClientStateConnecting, true, false},
{"disconnected", ClientStateDisconnected, false, false},
{"connected", stateConnected, true, true},
{"mgm down", stateConnecting, false, true},
{"signal down", stateConnecting, true, false},
{"disconnected", stateDisconnected, false, false},
}
for _, tt := range scenarios {
@@ -88,7 +85,7 @@ func Test_notifier_SetListener(t *testing.T) {
listener.setPeersWaiter()
n := newNotifier()
n.lastNotification = ClientStateConnecting
n.lastNotification = stateConnecting
n.setListener(listener)
listener.wait()
listener.waitPeers()
@@ -102,7 +99,7 @@ func Test_notifier_RemoveListener(t *testing.T) {
listener.setWaiter()
listener.setPeersWaiter()
n := newNotifier()
n.lastNotification = ClientStateConnecting
n.lastNotification = stateConnecting
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

@@ -1211,12 +1211,6 @@ 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)

View File

@@ -21,8 +21,6 @@ import (
"github.com/netbirdio/netbird/client/internal/listener"
"github.com/netbirdio/netbird/client/internal/peer"
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/formatter"
"github.com/netbirdio/netbird/route"
@@ -30,6 +28,11 @@ import (
types "github.com/netbirdio/netbird/upload-server/types"
)
// ConnectionListener export internal Listener for mobile
type ConnectionListener interface {
peer.Listener
}
// RouteListener export internal RouteListener for mobile
type NetworkChangeListener interface {
listener.NetworkChangeListener
@@ -76,12 +79,6 @@ type Client struct {
onHostDnsFn func([]string)
dnsManager dns.IosDnsManager
loginComplete bool
// netState outlives engine restarts: it mirrors the OS connectivity, not
// the engine lifecycle. Run injects it into each new ConnectClient, which
// distributes it to every reconnection loop.
netState *netstate.State
// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
sweeper *netsweep.Sweeper
// preloadedConfig holds config loaded from JSON (used on tvOS where file writes are blocked)
preloadedConfig *profilemanager.Config
@@ -104,8 +101,6 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
ctxCancelLock: &sync.Mutex{},
networkChangeListener: networkChangeListener,
dnsManager: dnsManager,
netState: netstate.New(),
sweeper: netsweep.New(),
}
}
@@ -181,8 +176,7 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
c.onHostDnsFn = func([]string) {}
cfg.WgIface = interfaceName
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
c.setState(cfg, connectClient)
// Persist the latest sync response so DebugBundle can include the network
// map. On iOS this is backed by disk to keep it out of the constrained
@@ -191,24 +185,6 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
return connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile, c.cacheDir, c.logFilePath)
}
// SetNetworkAvailable feeds OS-reported network availability into the client
// (e.g. from NWPathMonitor). While unavailable, the internal reconnect loops
// suspend their attempts and the connection listener reports NoNetwork
// instead of Connecting; when availability returns, the loops resume
// immediately with a fresh backoff.
func (c *Client) SetNetworkAvailable(available bool) {
c.netState.Set(available)
c.recorder.SetNetworkAvailable(available)
}
// NotifyNetworkChange cuts the management, signal and relay connections
// after the OS switched networks, so the reconnect loops redial immediately
// on the new one. The engine and the TUN device stay untouched.
func (c *Client) NotifyNetworkChange() {
n := c.sweeper.Sweep()
log.Infof("network change: swept %d connections", n)
}
// Stop the internal client and free the resources
func (c *Client) Stop() {
c.ctxCancelLock.Lock()
@@ -344,7 +320,7 @@ func (c *Client) GetStatusDetails() *StatusDetails {
// SetConnectionListener set the network connection listener
func (c *Client) SetConnectionListener(listener ConnectionListener) {
c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
c.recorder.SetConnectionListener(listener)
}
// RemoveConnectionListener remove connection listener

View File

@@ -1,43 +0,0 @@
//go:build ios
package NetBirdSDK
import (
"github.com/netbirdio/netbird/client/internal/peer"
)
// Client state values, re-exported as basic constants so gomobile emits them
// into the generated bindings. They mirror peer.ClientState*: append-only,
// never reorder.
const (
ClientStateDisconnected = int(peer.ClientStateDisconnected)
ClientStateConnected = int(peer.ClientStateConnected)
ClientStateConnecting = int(peer.ClientStateConnecting)
ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
ClientStateNoNetwork = int(peer.ClientStateNoNetwork)
)
// ConnectionListener export internal Listener for mobile.
//
// It intentionally lacks OnStateChanged for now: adding a method to a gomobile
// interface breaks every Swift implementation, so the iOS app keeps building
// against the legacy per-state callbacks. A follow-up will extend it together
// with the app.
type ConnectionListener interface {
OnConnected()
OnDisconnected()
OnConnecting()
OnDisconnecting()
OnAddressChanged(string, string)
OnPeersListChanged(int)
}
// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
// peer.Listener.
type connectionListenerAdapter struct {
ConnectionListener
}
// OnStateChanged is dropped on iOS until the app adopts the state callback;
// the legacy per-state callbacks continue to fire.
func (a connectionListenerAdapter) OnStateChanged(peer.ClientState) {}

View File

@@ -1,93 +0,0 @@
// Package netstate tracks OS-reported network availability for the client.
//
// A State instance is owned by the platform integration (e.g. the Android or
// iOS bindings, fed from ConnectivityManager callbacks or NWPathMonitor) and
// is injected into the connection retry loops (management, signal, relay,
// peer guards and the top-level connect loop), which consult it to avoid
// burning CPU and battery on reconnect attempts while the device has no
// network at all (e.g. airplane mode), and to reset their backoff as soon as
// the network returns.
//
// Consumers hold a *State that may be nil — every non-mobile platform leaves
// it unset. The read methods are safe on a nil receiver: they report online
// and never block, so consumers behave as if this package did not exist.
package netstate
import (
"context"
"sync"
log "github.com/sirupsen/logrus"
)
// State holds the OS-reported network availability. The zero value is not
// usable; create instances with New.
type State struct {
mu sync.Mutex
online bool
changed chan struct{}
}
// New creates a State that starts online.
func New() *State {
return &State{
online: true,
changed: make(chan struct{}),
}
}
// Set records whether the OS reports any usable network. Transitions wake up
// all Wait callers immediately.
func (s *State) Set(online bool) {
s.mu.Lock()
defer s.mu.Unlock()
if s.online == online {
return
}
s.online = online
close(s.changed)
s.changed = make(chan struct{})
log.Infof("OS network availability changed: online=%t", online)
}
// IsOnline reports whether the OS reports at least one usable network. On a
// nil receiver — no State injected — it reports online.
func (s *State) IsOnline() bool {
if s == nil {
return true
}
s.mu.Lock()
defer s.mu.Unlock()
return s.online
}
// Wait blocks while the network is offline. It reports whether it had to
// wait, so callers can reset their backoff after an outage. It returns early
// with the context error when ctx is done. On a nil receiver — no State
// injected — it returns immediately.
func (s *State) Wait(ctx context.Context) (bool, error) {
if s == nil {
return false, nil
}
waited := false
for {
s.mu.Lock()
if s.online {
s.mu.Unlock()
return waited, nil
}
ch := s.changed
s.mu.Unlock()
if !waited {
waited = true
log.Debugf("network is offline, pausing connection attempts")
}
select {
case <-ctx.Done():
return waited, ctx.Err()
case <-ch:
}
}
}

View File

@@ -1,170 +0,0 @@
package netstate
import (
"context"
"sync"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestNewStateIsOnline(t *testing.T) {
assert.True(t, New().IsOnline(), "a fresh State should start online")
}
func TestSetTogglesOnlineState(t *testing.T) {
s := New()
s.Set(false)
assert.False(t, s.IsOnline(), "state should be offline after Set(false)")
s.Set(true)
assert.True(t, s.IsOnline(), "state should be online after Set(true)")
}
func TestWaitReturnsImmediatelyWhenOnline(t *testing.T) {
s := New()
ctx, cancel := context.WithTimeout(context.Background(), time.Second)
defer cancel()
waited, err := s.Wait(ctx)
require.NoError(t, err)
assert.False(t, waited, "Wait should not block when the network is online")
}
func TestWaitBlocksUntilOnline(t *testing.T) {
s := New()
s.Set(false)
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
result := make(chan bool, 1)
go func() {
waited, err := s.Wait(ctx)
if err != nil {
result <- false
return
}
result <- waited
}()
// Verify Wait is actually blocking while offline
select {
case <-result:
t.Fatal("Wait should block while the network is offline")
case <-time.After(100 * time.Millisecond):
}
s.Set(true)
select {
case waited := <-result:
assert.True(t, waited, "Wait should report that it had to wait for the network")
case <-time.After(2 * time.Second):
t.Fatal("Wait should return promptly after the network becomes available")
}
}
func TestWaitReturnsOnContextCancel(t *testing.T) {
s := New()
s.Set(false)
ctx, cancel := context.WithCancel(context.Background())
result := make(chan error, 1)
go func() {
_, err := s.Wait(ctx)
result <- err
}()
cancel()
select {
case err := <-result:
assert.ErrorIs(t, err, context.Canceled)
case <-time.After(2 * time.Second):
t.Fatal("Wait should return promptly after context cancellation")
}
}
func TestWaitWakesAllWaiters(t *testing.T) {
s := New()
s.Set(false)
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
const waiters = 10
var wg sync.WaitGroup
results := make(chan bool, waiters)
for i := 0; i < waiters; i++ {
wg.Add(1)
go func() {
defer wg.Done()
waited, err := s.Wait(ctx)
if err != nil {
results <- false
return
}
results <- waited
}()
}
time.Sleep(100 * time.Millisecond)
s.Set(true)
wg.Wait()
close(results)
count := 0
for waited := range results {
assert.True(t, waited, "every waiter should report that it waited")
count++
}
assert.Equal(t, waiters, count, "all waiters should have returned")
}
func TestNilStateReadsAreNoops(t *testing.T) {
var s *State
assert.True(t, s.IsOnline(), "nil State should report online")
waited, err := s.Wait(context.Background())
require.NoError(t, err)
assert.False(t, waited, "nil State's Wait should not block")
}
func TestConcurrentSetAndWait(t *testing.T) {
s := New()
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
var wg sync.WaitGroup
for i := 0; i < 4; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := 0; j < 100; j++ {
s.Set(j%2 == 0)
s.IsOnline()
}
}()
}
for i := 0; i < 4; i++ {
wg.Add(1)
go func() {
defer wg.Done()
for j := 0; j < 100; j++ {
if _, err := s.Wait(ctx); err != nil {
return
}
}
}()
}
wg.Wait()
}

View File

@@ -1,171 +0,0 @@
// Package netsweep cuts network-bound activity when the OS switches networks:
// a sweep closes the registered connections and aborts the in-flight dials, so
// their owners redial immediately instead of waiting for the old sockets to
// time out.
//
// A nil *Sweeper disables everything: all methods are nil-safe no-ops.
package netsweep
import (
"context"
"errors"
"net"
"sync"
log "github.com/sirupsen/logrus"
)
// ErrSwept reports that a dial finished after a network change swept its
// registration. The connection is already closed; the caller must treat it
// as a failed dial and redial on the new network.
var ErrSwept = errors.New("netsweep: connection swept by network change")
// sweptConn deregisters itself from the sweeper when closed.
type sweptConn struct {
net.Conn
sweeper *Sweeper
id uint64
}
func (c *sweptConn) Close() error {
c.sweeper.deregister(c.id)
return c.Conn.Close()
}
// Sweeper registers live connections and in-flight dials so Sweep can cut
// everything that started before the network changed.
type Sweeper struct {
mu sync.Mutex
conns map[uint64]net.Conn
dials map[uint64]*Dial
nextID uint64
}
// New creates an empty sweeper.
func New() *Sweeper {
return &Sweeper{
conns: make(map[uint64]net.Conn),
dials: make(map[uint64]*Dial),
}
}
// Dial tracks one dial from start to connection registration. It hands the
// dialed connection to the sweeper atomically, so a sweep can never fall
// between the dial finishing and the connection being registered.
type Dial struct {
sweeper *Sweeper
ctx context.Context
cancel context.CancelFunc
id uint64
done bool // set by Sweep, WrapConn or Release; guarded by sweeper.mu
}
// StartDial registers an in-flight dial. Dial with Ctx, hand the result to
// WrapConn, and Release the dial when the attempt is over, typically deferred.
func (s *Sweeper) StartDial(ctx context.Context) *Dial {
if s == nil {
return &Dial{ctx: ctx}
}
ctx, cancel := context.WithCancel(ctx)
d := &Dial{sweeper: s, ctx: ctx, cancel: cancel}
s.mu.Lock()
d.id = s.nextID
s.nextID++
s.dials[d.id] = d
s.mu.Unlock()
return d
}
// Ctx returns the dial's context. Sweep cancels it, so a dial started on the
// old network aborts instead of waiting out its handshake timeout.
func (d *Dial) Ctx() context.Context {
return d.ctx
}
// WrapConn hands conn over to the sweeper. If a sweep ran since StartDial,
// the connection belongs to the old network: it is closed and ErrSwept is
// returned. Otherwise conn is registered against the next sweep and returned
// wrapped, deregistering itself on Close. Call it once, before Release.
func (d *Dial) WrapConn(conn net.Conn) (net.Conn, error) {
s := d.sweeper
if s == nil {
return conn, nil
}
s.mu.Lock()
if d.done {
s.mu.Unlock()
if err := conn.Close(); err != nil {
log.Debugf("swept dial close error: %v", err)
}
return nil, ErrSwept
}
d.done = true
delete(s.dials, d.id)
id := s.nextID
s.nextID++
s.conns[id] = conn
s.mu.Unlock()
return &sweptConn{Conn: conn, sweeper: s, id: id}, nil
}
// Release ends the dial's registration and cancels its context. It is
// idempotent and safe after WrapConn, so callers can defer it.
func (d *Dial) Release() {
s := d.sweeper
if s == nil {
return
}
s.mu.Lock()
d.done = true
delete(s.dials, d.id)
s.mu.Unlock()
d.cancel()
}
// Sweep closes every registered connection, aborts every in-flight dial, and
// returns how many connections it closed. A dial whose connection was not
// yet handed to WrapConn is marked, so the late WrapConn closes it instead
// of registering it.
func (s *Sweeper) Sweep() int {
if s == nil {
return 0
}
s.mu.Lock()
conns := s.conns
dials := s.dials
s.conns = make(map[uint64]net.Conn)
s.dials = make(map[uint64]*Dial)
for _, d := range dials {
d.done = true
}
s.mu.Unlock()
if len(dials) > 0 {
log.Debugf("aborting %d in-flight dials", len(dials))
for _, d := range dials {
d.cancel()
}
}
for _, conn := range conns {
log.Debugf("sweeping connection %s -> %s", conn.LocalAddr(), conn.RemoteAddr())
if err := conn.Close(); err != nil {
log.Debugf("swept connection close error: %v", err)
}
}
return len(conns)
}
func (s *Sweeper) deregister(id uint64) {
s.mu.Lock()
delete(s.conns, id)
s.mu.Unlock()
}

View File

@@ -1,168 +0,0 @@
package netsweep
import (
"context"
"net"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestSweepClosesRegisteredConns(t *testing.T) {
sweeper := New()
c1 := wrap(t, sweeper, connPair(t))
c2 := wrap(t, sweeper, connPair(t))
assert.Equal(t, 2, sweeper.Sweep(), "both live connections should be closed")
// The wrappers must report closed now.
buf := make([]byte, 1)
_, err := c1.Read(buf)
assert.Error(t, err, "first connection should be unusable after the sweep")
_, err = c2.Read(buf)
assert.Error(t, err, "second connection should be unusable after the sweep")
assert.Equal(t, 0, sweeper.Sweep(), "second sweep should find nothing")
}
func TestCloseDeregisters(t *testing.T) {
sweeper := New()
conn := wrap(t, sweeper, connPair(t))
require.NoError(t, conn.Close())
assert.Equal(t, 0, sweeper.Sweep(), "closed connection must leave the registry")
}
func TestCloseIsIdempotent(t *testing.T) {
sweeper := New()
conn := wrap(t, sweeper, connPair(t))
require.NoError(t, conn.Close())
assert.Error(t, conn.Close(), "double close surfaces the underlying error but must not panic")
}
func TestSweepOnlyAffectsOlderConns(t *testing.T) {
sweeper := New()
_ = wrap(t, sweeper, connPair(t))
assert.Equal(t, 1, sweeper.Sweep())
// A connection dialed after the sweep must survive until the next one.
_ = wrap(t, sweeper, connPair(t))
assert.Equal(t, 1, sweeper.Sweep(), "post-sweep connection belongs to the next sweep")
}
func TestSweepAbortsInFlightDials(t *testing.T) {
sweeper := New()
dial := sweeper.StartDial(context.Background())
defer dial.Release()
sweeper.Sweep()
assert.ErrorIs(t, dial.Ctx().Err(), context.Canceled, "sweep must cancel the in-flight dial context")
}
func TestReleasedDialIsNotAborted(t *testing.T) {
sweeper := New()
// Simulate a dial that finished before the sweep.
released := sweeper.StartDial(context.Background())
released.Release()
// A dial still in flight during the sweep.
pending := sweeper.StartDial(context.Background())
defer pending.Release()
sweeper.Sweep()
assert.ErrorIs(t, pending.Ctx().Err(), context.Canceled, "pending dial must be aborted")
}
func TestSweepBetweenDialAndHandoffClosesConn(t *testing.T) {
sweeper := New()
dial := sweeper.StartDial(context.Background())
defer dial.Release()
// The dial succeeds on the old network, then the sweep lands before the
// connection is handed over.
conn := connPair(t)
assert.Equal(t, 0, sweeper.Sweep(), "the connection is not registered yet")
wrapped, err := dial.WrapConn(conn)
require.ErrorIs(t, err, ErrSwept)
require.Nil(t, wrapped)
buf := make([]byte, 1)
_, err = conn.Read(buf)
assert.Error(t, err, "the old-network connection must be closed, not leaked")
assert.Equal(t, 0, sweeper.Sweep(), "nothing may leak into the next sweep")
}
func TestNilSweeperIsNoop(t *testing.T) {
var sweeper *Sweeper
conn := connPair(t)
dial := sweeper.StartDial(context.Background())
defer dial.Release()
wrapped, err := dial.WrapConn(conn)
require.NoError(t, err)
assert.Equal(t, conn, wrapped, "nil sweeper must return the conn unchanged")
assert.NoError(t, dial.Ctx().Err(), "nil sweeper must not cancel the dial context")
assert.Equal(t, 0, sweeper.Sweep(), "nil sweeper closes nothing")
}
// wrap registers conn with the sweeper through a completed dial.
func wrap(t *testing.T, sweeper *Sweeper, conn net.Conn) net.Conn {
t.Helper()
dial := sweeper.StartDial(context.Background())
defer dial.Release()
wrapped, err := dial.WrapConn(conn)
require.NoError(t, err)
return wrapped
}
// connPair dials a loopback TCP connection and keeps the accepted peer open
// until the test ends: a peer that closed early would make the connection
// unreadable on its own, so a read error after the sweep would prove nothing.
func connPair(t *testing.T) net.Conn {
t.Helper()
l, err := net.Listen("tcp", "127.0.0.1:0")
require.NoError(t, err)
t.Cleanup(func() {
if err := l.Close(); err != nil {
t.Logf("listener close error: %v", err)
}
})
accepted := make(chan net.Conn, 1)
go func() {
conn, err := l.Accept()
if err != nil {
close(accepted)
return
}
accepted <- conn
}()
conn, err := net.Dial("tcp", l.Addr().String())
require.NoError(t, err)
peer, ok := <-accepted
require.True(t, ok, "listener must accept the dialed connection")
t.Cleanup(func() {
if err := peer.Close(); err != nil {
t.Logf("peer close error: %v", err)
}
})
return conn
}

View File

@@ -0,0 +1,18 @@
import { useEffect, useRef } from "react";
import { Events } from "@wailsio/runtime";
import { useStatus } from "@/contexts/StatusContext.tsx";
const EVENT_WINDOW_PAINTED = "netbird:window-painted";
export const ReadySignal = () => {
const { isReady } = useStatus();
const sent = useRef(false);
useEffect(() => {
if (!isReady || sent.current) return;
sent.current = true;
void Events.Emit(EVENT_WINDOW_PAINTED);
}, [isReady]);
return null;
};

View File

@@ -5,6 +5,7 @@ import { DebugBundleProvider } from "@/contexts/DebugBundleContext.tsx";
import { ProfileProvider } from "@/contexts/ProfileContext.tsx";
import { DialogProvider } from "@/contexts/DialogContext.tsx";
import { RestrictionsProvider } from "@/contexts/RestrictionsContext.tsx";
import { ReadySignal } from "@/components/ReadySignal.tsx";
export const AppLayout = () => {
return (
@@ -16,6 +17,7 @@ export const AppLayout = () => {
<DebugBundleProvider>
<ClientVersionProvider>
<Outlet />
<ReadySignal />
</ClientVersionProvider>
</DebugBundleProvider>
</RestrictionsProvider>

View File

@@ -95,6 +95,10 @@ func main() {
}
})
// Debug patch, not for release: dumps heap/goroutine profiles and the
// process tree to /tmp/nbgui for the memory consumption investigation.
startMemProfiler(app)
profiles := services.NewProfiles(conn)
// updater.Holder owns the typed update State; DaemonFeed feeds it and the
// Update service is a thin Wails-bound facade over it plus the install RPCs.
@@ -139,13 +143,11 @@ func main() {
prefStore: prefStore,
})
window := newMainWindow(app, prefStore)
// Settings is created eagerly (hidden) so the first gear click paints
// instantly and React keeps per-tab state across reopens. The other
// auxiliary windows stay lazy + destroy-on-close so Wails's macOS
// dock-reopen handler can't resurrect them.
windowManager := services.NewWindowManager(app, window, bundle, prefStore, iconWindow)
windowManager := services.NewWindowManager(app, nil, bundle, prefStore, iconWindow)
windowManager.SetMainFactory(func() *application.WebviewWindow {
return newMainWindow(app, prefStore, windowManager)
})
registerDockReopenHook(app, windowManager)
// Minimal WMs (XEmbed-tray path) neither center small windows nor restore
// position across hide -> show, dropping them top-left. Gate Go-side
// re-centering on that environment; nil leaves placement to the WM on full
@@ -168,7 +170,7 @@ func main() {
// RegisterStatusNotifierItem hits a watcher we control.
startStatusNotifierWatcher()
tray = NewTray(app, window, TrayServices{
tray = NewTray(app, nil, TrayServices{
Connection: connection,
Settings: settings,
Profiles: profiles,
@@ -338,9 +340,7 @@ func registerServices(app *application.App, conn *Conn, s registeredServices) {
app.RegisterService(application.NewService(s.compat))
}
// newMainWindow creates the hidden main window, sized to the user's last view
// mode, and installs the hide-on-close and macOS dock-reopen hooks.
func newMainWindow(app *application.App, prefStore *preferences.Store) *application.WebviewWindow {
func newMainWindow(app *application.App, prefStore *preferences.Store, wm *services.WindowManager) *application.WebviewWindow {
// Width matches the last view mode so Advanced-mode users don't see the
// window pop from 380px to 900px on launch. Height is mode-agnostic.
initialWidth := 380
@@ -368,29 +368,25 @@ func newMainWindow(app *application.App, prefStore *preferences.Store) *applicat
},
})
// Hide instead of quit on close; "really quit" is reached via tray -> Quit.
window.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) {
window.RegisterHook(events.Common.WindowClosing, func(_ *application.WindowEvent) {
if services.ShuttingDown() {
return
}
e.Cancel()
window.Hide()
wm.ForgetMain()
})
// On macOS, Wails' default applicationShouldHandleReopen handler Show()s
// every hidden window on dock-icon click, resurrecting hide-on-close
// surfaces like Settings. Cancel it in a hook (hooks run before listeners)
// and show only the main window. No-op elsewhere — the event never fires.
if runtime.GOOS == "darwin" {
app.Event.RegisterApplicationEventHook(events.Mac.ApplicationShouldHandleReopen, func(e *application.ApplicationEvent) {
e.Cancel()
if e.Context().HasVisibleWindows() {
return
}
window.Show()
window.Focus()
})
}
return window
}
func registerDockReopenHook(app *application.App, wm *services.WindowManager) {
if runtime.GOOS != "darwin" {
return
}
app.Event.RegisterApplicationEventHook(events.Mac.ApplicationShouldHandleReopen, func(e *application.ApplicationEvent) {
e.Cancel()
if e.Context().HasVisibleWindows() {
return
}
wm.ShowMain()
})
}

319
client/ui/memprof.go Normal file
View File

@@ -0,0 +1,319 @@
//go:build !android && !ios && !freebsd && !js
package main
import (
"bufio"
"fmt"
"os"
"path/filepath"
"runtime"
"runtime/pprof"
"strconv"
"strings"
"time"
"github.com/shirou/gopsutil/v4/process"
log "github.com/sirupsen/logrus"
"github.com/wailsapp/wails/v3/pkg/application"
"github.com/wailsapp/wails/v3/pkg/events"
)
// memProfOffsets are the snapshot times measured from application startup.
var memProfOffsets = []time.Duration{0, 2 * time.Minute, 5 * time.Minute}
// memProfMaxDepth bounds the child walk so a cycle in the reported parent links
// cannot spin forever.
const memProfMaxDepth = 4
type memProfileSpec struct {
profile string
file string
debug int
}
var memProfileSpecs = []memProfileSpec{
{profile: "heap", file: "heap.pprof", debug: 0},
{profile: "heap", file: "heap.txt", debug: 1},
{profile: "goroutine", file: "goroutine.txt", debug: 1},
{profile: "threadcreate", file: "threadcreate.txt", debug: 1},
}
var memProfStart = time.Now()
// startMemProfiler dumps a profile snapshot at every memProfOffsets mark, each
// into its own timestamped directory under memProfBaseDir. The first runs once
// the application is up so the window inventory sees the eagerly created
// windows. Every failure is logged and never stops the GUI.
func startMemProfiler(app *application.App) {
log.Infof("memory profiler enabled, writing to %s (snapshots at %v after startup)", memProfBaseDir(), memProfOffsets)
app.Event.OnApplicationEvent(events.Common.ApplicationStarted, func(*application.ApplicationEvent) {
go func() {
started := time.Now()
for _, offset := range memProfOffsets {
if wait := time.Until(started.Add(offset)); wait > 0 {
time.Sleep(wait)
}
writeMemProfile(app)
}
}()
})
}
// memProfBaseDir returns the directory holding the snapshot directories.
func memProfBaseDir() string {
if runtime.GOOS == "windows" {
return filepath.Join(os.TempDir(), "nbgui")
}
return "/tmp/nbgui"
}
// writeMemProfile creates a <timestamp>-<pid> directory and fills it with the
// runtime profiles, the memory statistics summary and the process tree.
func writeMemProfile(app *application.App) {
name := fmt.Sprintf("%s-%d", time.Now().Format("20060102-150405"), os.Getpid())
dir := filepath.Join(memProfBaseDir(), name)
if err := os.MkdirAll(dir, 0o755); err != nil {
log.Warnf("create memory profile dir %s: %v", dir, err)
return
}
// The heap profile reports live objects as of the last collection, so force
// one to keep inuse_space from counting garbage that is already unreachable.
runtime.GC()
if err := writeMemStats(filepath.Join(dir, "memstats.txt"), app); err != nil {
log.Warnf("write memory statistics: %v", err)
}
if err := writeProcTree(filepath.Join(dir, "proctree.txt")); err != nil {
log.Warnf("write process tree: %v", err)
}
for _, spec := range memProfileSpecs {
if err := writeMemProfileFile(spec, filepath.Join(dir, spec.file)); err != nil {
log.Warnf("write %s profile: %v", spec.profile, err)
}
}
log.Infof("memory profile written to %s", dir)
}
// writeMemProfileFile writes a single runtime profile to path.
func writeMemProfileFile(spec memProfileSpec, path string) error {
p := pprof.Lookup(spec.profile)
if p == nil {
return fmt.Errorf("unknown profile %q", spec.profile)
}
f, err := os.Create(path)
if err != nil {
return fmt.Errorf("create %s: %w", path, err)
}
defer func() {
if err := f.Close(); err != nil {
log.Debugf("close %s: %v", path, err)
}
}()
if err := p.WriteTo(f, spec.debug); err != nil {
return fmt.Errorf("write %s: %w", path, err)
}
return nil
}
// writeMemStats dumps the runtime memory statistics next to the process
// resident set size. A resident set much larger than Sys means the memory sits
// outside the Go heap (webview, GTK, other cgo allocations), where the pprof
// profiles cannot see it.
func writeMemStats(path string, app *application.App) error {
var m runtime.MemStats
runtime.ReadMemStats(&m)
var b strings.Builder
fmt.Fprintf(&b, "time: %s\n", time.Now().Format(time.RFC3339))
fmt.Fprintf(&b, "uptime: %s\n", time.Since(memProfStart).Round(time.Second))
fmt.Fprintf(&b, "pid: %d\n", os.Getpid())
fmt.Fprintf(&b, "\n")
rss, vms := processMemory()
fmt.Fprintf(&b, "process_rss: %s\n", rss)
fmt.Fprintf(&b, "process_vms: %s\n", vms)
fmt.Fprintf(&b, "\n")
fmt.Fprintf(&b, "sys: %s\n", formatMemBytes(m.Sys))
fmt.Fprintf(&b, "heap_alloc: %s\n", formatMemBytes(m.HeapAlloc))
fmt.Fprintf(&b, "heap_sys: %s\n", formatMemBytes(m.HeapSys))
fmt.Fprintf(&b, "heap_inuse: %s\n", formatMemBytes(m.HeapInuse))
fmt.Fprintf(&b, "heap_idle: %s\n", formatMemBytes(m.HeapIdle))
fmt.Fprintf(&b, "heap_released: %s\n", formatMemBytes(m.HeapReleased))
fmt.Fprintf(&b, "heap_objects: %d\n", m.HeapObjects)
fmt.Fprintf(&b, "stack_inuse: %s\n", formatMemBytes(m.StackInuse))
fmt.Fprintf(&b, "stack_sys: %s\n", formatMemBytes(m.StackSys))
fmt.Fprintf(&b, "mspan_sys: %s\n", formatMemBytes(m.MSpanSys))
fmt.Fprintf(&b, "mcache_sys: %s\n", formatMemBytes(m.MCacheSys))
fmt.Fprintf(&b, "gc_sys: %s\n", formatMemBytes(m.GCSys))
fmt.Fprintf(&b, "other_sys: %s\n", formatMemBytes(m.OtherSys))
fmt.Fprintf(&b, "next_gc: %s\n", formatMemBytes(m.NextGC))
fmt.Fprintf(&b, "num_gc: %d\n", m.NumGC)
fmt.Fprintf(&b, "\n")
fmt.Fprintf(&b, "goroutines: %d\n", runtime.NumGoroutine())
fmt.Fprintf(&b, "cgo_calls: %d\n", runtime.NumCgoCall())
fmt.Fprintf(&b, "gomaxprocs: %d\n", runtime.GOMAXPROCS(0))
fmt.Fprintf(&b, "\n")
writeWindowInventory(&b, app)
if err := os.WriteFile(path, []byte(b.String()), 0o644); err != nil {
return fmt.Errorf("write %s: %w", path, err)
}
return nil
}
// writeWindowInventory lists the live Wails windows. A window that exists holds
// a webview process even while hidden, so this tells apart a leaked window (the
// count grows) from windows whose content grew (the count stays put).
func writeWindowInventory(b *strings.Builder, app *application.App) {
windows := app.Window.GetAll()
fmt.Fprintf(b, "windows: %d\n", len(windows))
for _, w := range windows {
visible := "unknown"
if ww, ok := w.(*application.WebviewWindow); ok {
visible = strconv.FormatBool(ww.IsVisible())
}
fmt.Fprintf(b, " id=%-3d name=%-20q visible=%-7s minimised=%-5t focused=%t\n",
w.ID(), w.Name(), visible, w.IsMinimised(), w.IsFocused())
}
}
// writeProcTree dumps this process and its descendants with their memory
// footprint. The webview runs in child processes whose memory the Go runtime
// profiles cannot see, so this is what attributes a footprint to a component.
func writeProcTree(path string) error {
self, err := process.NewProcess(int32(os.Getpid()))
if err != nil {
return fmt.Errorf("open own process: %w", err)
}
var b strings.Builder
fmt.Fprintf(&b, "time: %s\n", time.Now().Format(time.RFC3339))
fmt.Fprintf(&b, "uptime: %s\n\n", time.Since(memProfStart).Round(time.Second))
fmt.Fprintf(&b, "%-8s %-8s %-28s %12s %12s %12s %12s\n", "PID", "PPID", "NAME", "RSS", "VMS", "PSS", "PRIV_DIRTY")
var totalRSS, totalPSS, totalPrivate uint64
walkProcTree(&b, self, 0, &totalRSS, &totalPSS, &totalPrivate)
fmt.Fprintf(&b, "\n%-8s %-8s %-28s %12s %12s %12s %12s\n", "", "", "TOTAL",
formatKB(totalRSS), "", formatKB(totalPSS), formatKB(totalPrivate))
fmt.Fprintf(&b, "\nPSS and PRIV_DIRTY come from /proc/<pid>/smaps_rollup and are Linux only.\n")
if err := os.WriteFile(path, []byte(b.String()), 0o644); err != nil {
return fmt.Errorf("write %s: %w", path, err)
}
return nil
}
// walkProcTree appends one line per process, depth-first, accumulating totals.
func walkProcTree(b *strings.Builder, p *process.Process, depth int, totalRSS, totalPSS, totalPrivate *uint64) {
name, err := p.Name()
if err != nil {
name = "unknown"
}
var rss, vms uint64
if info, err := p.MemoryInfo(); err == nil {
rss, vms = info.RSS, info.VMS
}
pss, private := smapsRollup(p.Pid)
*totalRSS += rss
*totalPSS += pss
*totalPrivate += private
ppid, err := p.Ppid()
if err != nil {
ppid = -1
}
fmt.Fprintf(b, "%-8d %-8d %-28s %12s %12s %12s %12s\n", p.Pid, ppid,
strings.Repeat(" ", depth)+name, formatKB(rss), formatKB(vms), formatKB(pss), formatKB(private))
if depth >= memProfMaxDepth {
return
}
children, err := p.Children()
if err != nil {
return
}
for _, child := range children {
walkProcTree(b, child, depth+1, totalRSS, totalPSS, totalPrivate)
}
}
// smapsRollup returns the proportional set size and private dirty bytes of pid,
// both zero on platforms without /proc.
func smapsRollup(pid int32) (uint64, uint64) {
f, err := os.Open(fmt.Sprintf("/proc/%d/smaps_rollup", pid))
if err != nil {
return 0, 0
}
defer func() {
if err := f.Close(); err != nil {
log.Debugf("close smaps_rollup for %d: %v", pid, err)
}
}()
var pss, private uint64
scanner := bufio.NewScanner(f)
for scanner.Scan() {
fields := strings.Fields(scanner.Text())
if len(fields) < 2 {
continue
}
kb, err := strconv.ParseUint(fields[1], 10, 64)
if err != nil {
continue
}
switch fields[0] {
case "Pss:":
pss = kb * 1024
case "Private_Dirty:":
private = kb * 1024
}
}
return pss, private
}
// processMemory returns the formatted resident and virtual size of this process.
func processMemory() (string, string) {
p, err := process.NewProcess(int32(os.Getpid()))
if err != nil {
unavailable := fmt.Sprintf("unavailable (%v)", err)
return unavailable, unavailable
}
info, err := p.MemoryInfo()
if err != nil {
unavailable := fmt.Sprintf("unavailable (%v)", err)
return unavailable, unavailable
}
return formatMemBytes(info.RSS), formatMemBytes(info.VMS)
}
// formatMemBytes renders a byte count as megabytes with the raw value kept.
func formatMemBytes(n uint64) string {
return fmt.Sprintf("%8.1f MB (%d bytes)", float64(n)/(1024*1024), n)
}
// formatKB renders a byte count as megabytes for the process tree columns, and
// a dash when the platform did not report the value.
func formatKB(n uint64) string {
if n == 0 {
return "-"
}
return fmt.Sprintf("%.1f MB", float64(n)/(1024*1024))
}

View File

@@ -8,6 +8,7 @@ import (
"sync"
"time"
log "github.com/sirupsen/logrus"
"github.com/wailsapp/wails/v3/pkg/application"
"github.com/wailsapp/wails/v3/pkg/events"
@@ -29,6 +30,10 @@ const EventBrowserLoginCancel = "browser-login:cancel"
// EventSettingsOpen tells the mounted settings window which tab to show.
const EventSettingsOpen = "netbird:settings:open"
const EventWindowPainted = "netbird:window-painted"
const paintedFallback = 2 * time.Second
var WindowBackgroundColour = application.NewRGB(24, 26, 29) // bg-nb-gray-950
// WindowHeight is shared by the main and Settings windows.
@@ -94,9 +99,6 @@ func DialogWindowOptions(name, title, url string, linuxIcon []byte) application.
}
}
// WindowManager owns the auxiliary windows (main is created in main.go). Settings is created
// eagerly and hidden on close to keep React state; the rest are created on open, destroyed on
// close, so the macOS dock-reopen handler finds no hidden window to resurrect.
type WindowManager struct {
app *application.App
mainWindow *application.WebviewWindow
@@ -112,15 +114,31 @@ type WindowManager struct {
// hiddenForLogin holds windows hidden while the BrowserLogin popup is open, restored on close.
hiddenForLogin []application.Window
mu sync.Mutex
newMain func() *application.WebviewWindow
ready map[uint]bool
showPending map[uint]bool
showAsked map[uint]time.Time
pendingTab map[uint]string
fallbackTimers map[uint]*time.Timer
// recenterOnShow is set only on the minimal-WM/XEmbed path, where the WM neither centers nor
// restores position; nil on full desktops so re-centering can't fight a user-moved window.
recenterOnShow func() bool
}
// NewWindowManager wires the manager to the main app; translator/prefs may be nil (tests). The
// Settings window is created here (hidden) so the first OpenSettings is instant.
func NewWindowManager(app *application.App, mainWindow *application.WebviewWindow, translator ErrorTranslator, prefs LanguagePreference, linuxIcon []byte) *WindowManager {
s := &WindowManager{app: app, mainWindow: mainWindow, translator: translator, prefs: prefs, linuxIcon: linuxIcon}
s := &WindowManager{
app: app,
mainWindow: mainWindow,
translator: translator,
prefs: prefs,
linuxIcon: linuxIcon,
ready: map[uint]bool{},
showPending: map[uint]bool{},
showAsked: map[uint]time.Time{},
pendingTab: map[uint]string{},
fallbackTimers: map[uint]*time.Timer{},
}
s.watchPainted()
// Re-title live windows on language flip. Wired internally so the binding generator
// doesn't try to expose the interface param.
if sub, ok := prefs.(LanguageSubscriber); ok && sub != nil {
@@ -136,7 +154,11 @@ func NewWindowManager(app *application.App, mainWindow *application.WebviewWindo
}
}()
}
s.settings = app.Window.NewWithOptions(application.WebviewWindowOptions{
return s
}
func (s *WindowManager) newSettingsWindow() *application.WebviewWindow {
w := s.app.Window.NewWithOptions(application.WebviewWindowOptions{
Name: "settings",
Title: s.title("window.title.settings"),
Width: 900,
@@ -150,18 +172,15 @@ func NewWindowManager(app *application.App, mainWindow *application.WebviewWindo
URL: "/#/settings",
Mac: AppleMacOSAppearanceOptions(),
Windows: MicrosoftWindowsAppearanceOptions(),
Linux: LinuxAppearanceOptions(linuxIcon),
Linux: LinuxAppearanceOptions(s.linuxIcon),
})
// Hide (not destroy) on close to keep React state; reset to General for a flash-free reopen.
s.settings.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) {
if ShuttingDown() {
return
}
e.Cancel()
s.app.Event.Emit(EventSettingsOpen, "general")
s.settings.Hide()
w.RegisterHook(events.Common.WindowClosing, func(_ *application.WindowEvent) {
s.mu.Lock()
s.settings = nil
s.forgetWindowLocked(w)
s.mu.Unlock()
})
return s
return w
}
// OpenSettings shows the settings window on tab (empty → General), switching tab via
@@ -171,11 +190,23 @@ func (s *WindowManager) OpenSettings(tab string) {
if target == "" {
target = "general"
}
s.app.Event.Emit(EventSettingsOpen, target)
s.settings.Show()
s.settings.Focus()
// Re-center (minimal-WM only; see centerWhenReady).
s.centerWhenReady(s.settings)
s.mu.Lock()
fresh := s.settings == nil
if fresh {
s.settings = s.newSettingsWindow()
s.armReady(s.settings)
}
w := s.settings
if fresh {
s.pendingTab[w.ID()] = target
}
s.mu.Unlock()
if !fresh {
s.app.Event.Emit(EventSettingsOpen, target)
}
s.showWhenReady(w)
}
// OpenBrowserLogin shows the SSO popup, creating it on first use.
@@ -440,13 +471,167 @@ func (s *WindowManager) OpenMain() {
// ShowMain brings the main window forward (re-centering on minimal WMs). The single entry
// point every surface (tray, SIGUSR1, welcome) should use so centering applies uniformly.
func (s *WindowManager) ShowMain() {
if s.mainWindow == nil {
s.showWhenReady(s.MainWindow())
}
func (s *WindowManager) MainWindow() *application.WebviewWindow {
s.mu.Lock()
defer s.mu.Unlock()
if s.mainWindow == nil && s.newMain != nil {
s.mainWindow = s.newMain()
s.armReady(s.mainWindow)
}
return s.mainWindow
}
func (s *WindowManager) armReady(w *application.WebviewWindow) {
if w == nil {
return
}
s.mainWindow.Show()
s.mainWindow.Focus()
// Re-center (minimal-WM only; see centerWhenReady).
s.centerWhenReady(s.mainWindow)
created := time.Now()
w.RegisterHook(events.Common.WindowRuntimeReady, func(_ *application.WindowEvent) {
log.Infof("window %q runtime ready after %s", w.Name(), time.Since(created).Round(time.Millisecond))
timer := time.AfterFunc(paintedFallback, func() {
s.markReady(w, "fallback")
})
s.mu.Lock()
s.fallbackTimers[w.ID()] = timer
s.mu.Unlock()
})
}
func (s *WindowManager) watchPainted() {
s.app.Event.On(EventWindowPainted, func(e *application.CustomEvent) {
w := s.windowByName(e.Sender)
if w == nil {
log.Infof("painted event from unknown sender %q", e.Sender)
return
}
s.markReady(w, "painted")
})
}
func (s *WindowManager) forgetWindowLocked(w *application.WebviewWindow) {
if w == nil {
return
}
id := w.ID()
if timer := s.fallbackTimers[id]; timer != nil {
timer.Stop()
}
delete(s.fallbackTimers, id)
delete(s.ready, id)
delete(s.showPending, id)
delete(s.showAsked, id)
delete(s.pendingTab, id)
kept := s.hiddenForLogin[:0]
for _, hidden := range s.hiddenForLogin {
if hidden != application.Window(w) {
kept = append(kept, hidden)
}
}
s.hiddenForLogin = kept
}
func (s *WindowManager) windowByName(name string) *application.WebviewWindow {
s.mu.Lock()
defer s.mu.Unlock()
switch name {
case "main":
return s.mainWindow
case "settings":
return s.settings
default:
return nil
}
}
func (s *WindowManager) markReady(w *application.WebviewWindow, source string) {
id := w.ID()
s.mu.Lock()
already := s.ready[id]
s.ready[id] = true
wanted := s.showPending[id]
asked := s.showAsked[id]
tab, hasTab := s.pendingTab[id]
if timer := s.fallbackTimers[id]; timer != nil {
timer.Stop()
delete(s.fallbackTimers, id)
}
delete(s.showPending, id)
delete(s.showAsked, id)
delete(s.pendingTab, id)
s.mu.Unlock()
if already {
return
}
if hasTab {
s.app.Event.Emit(EventSettingsOpen, tab)
}
waited := "no show waiting"
if wanted && !asked.IsZero() {
waited = time.Since(asked).Round(time.Millisecond).String()
}
log.Infof("window %q ready via %s, show waited %s", w.Name(), source, waited)
if wanted {
s.showNow(w)
}
}
func (s *WindowManager) showWhenReady(w *application.WebviewWindow) {
if w == nil {
return
}
id := w.ID()
s.mu.Lock()
ready := s.ready[id]
if !ready {
s.showPending[id] = true
s.showAsked[id] = time.Now()
}
s.mu.Unlock()
if ready {
log.Infof("window %q already ready, showing now", w.Name())
s.showNow(w)
return
}
log.Infof("window %q not ready yet, deferring show", w.Name())
}
func (s *WindowManager) showNow(w *application.WebviewWindow) {
w.Show()
w.Focus()
s.centerWhenReady(w)
}
func (s *WindowManager) ShowMainAt(url string) {
w := s.MainWindow()
if w == nil {
return
}
w.SetURL(url)
s.showWhenReady(w)
}
func (s *WindowManager) SetMainFactory(f func() *application.WebviewWindow) {
s.mu.Lock()
defer s.mu.Unlock()
s.newMain = f
}
func (s *WindowManager) ForgetMain() {
s.mu.Lock()
defer s.mu.Unlock()
s.forgetWindowLocked(s.mainWindow)
s.mainWindow = nil
}
// SetRecenterOnShow installs the recenterOnShow predicate (see the field).

View File

@@ -174,7 +174,7 @@ func NewTray(app *application.App, window *application.WebviewWindow, svc TraySe
// in the right locale — no English flash then re-paint.
loc: svc.Localizer,
}
t.updater = newTrayUpdater(app, window, svc.Update, svc.Notifier, t.loc, func() { t.applyIcon() }, func() { t.relayoutMenu() })
t.updater = newTrayUpdater(app, t.showMainAt, svc.Update, svc.Notifier, t.loc, func() { t.applyIcon() }, func() { t.relayoutMenu() })
t.tray = app.SystemTray.New()
// Seed panel-theme detection before the first paint so the initial icon
// matches the panel's light/dark scheme (Linux only).
@@ -241,9 +241,6 @@ func (t *Tray) ShowWindow() {
w.Focus()
return
}
if t.window == nil {
return
}
// Route through WindowManager so the main window is centered on first
// show — minimal WMs (fluxbox, the XEmbed tray path) otherwise drop it in
// the top-left corner.
@@ -251,8 +248,40 @@ func (t *Tray) ShowWindow() {
t.svc.WindowManager.ShowMain()
return
}
t.window.Show()
t.window.Focus()
if w := t.mainWindow(); w != nil {
w.Show()
w.Focus()
}
}
func (t *Tray) mainWindow() *application.WebviewWindow {
if t.svc.WindowManager == nil {
return t.window
}
return t.svc.WindowManager.MainWindow()
}
func (t *Tray) showMain() {
if t.svc.WindowManager != nil {
t.svc.WindowManager.ShowMain()
return
}
if w := t.mainWindow(); w != nil {
w.Show()
w.Focus()
}
}
func (t *Tray) showMainAt(url string) {
if t.svc.WindowManager != nil {
t.svc.WindowManager.ShowMainAt(url)
return
}
if w := t.mainWindow(); w != nil {
w.SetURL(url)
w.Show()
w.Focus()
}
}
// applyLanguage re-renders every translated surface in the Localizer's current

View File

@@ -30,10 +30,7 @@ const (
// handleSessionExpired notifies and brings the window forward so the user can reconnect.
func (t *Tray) handleSessionExpired() {
t.notify(t.loc.T("notify.sessionExpired.title"), t.loc.T("notify.sessionExpired.body"), notifyIDSessionExpired)
if t.window != nil {
t.window.Show()
t.window.Focus()
}
t.showMain()
}
// applySessionExpiry refreshes the cached SSO deadline and reports whether it changed.
@@ -307,6 +304,7 @@ func (t *Tray) openSessionExtendFlow() {
}
seconds := int(time.Until(deadline).Seconds())
if seconds <= 0 {
t.showMain()
t.app.Event.Emit(services.EventTriggerLogin)
return
}

View File

@@ -19,7 +19,7 @@ import (
// trayUpdater owns the tray UI that reacts to auto-update. Composed inside Tray.
type trayUpdater struct {
app *application.App
window *application.WebviewWindow
showMainAt func(url string)
update *services.Update
notifier *Notifier
loc *Localizer
@@ -36,10 +36,10 @@ type trayUpdater struct {
progressWindowOpen bool
}
func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *Notifier, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
func newTrayUpdater(app *application.App, showMainAt func(url string), update *services.Update, notifier *Notifier, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
u := &trayUpdater{
app: app,
window: window,
showMainAt: showMainAt,
update: update,
notifier: notifier,
loc: loc,
@@ -185,14 +185,12 @@ func (u *trayUpdater) sendUpdateNotification(st updater.State) {
// openProgressWindow points the main window at the /update progress page and
// brings it forward.
func (u *trayUpdater) openProgressWindow(version string) {
if u.window == nil {
if u.showMainAt == nil {
return
}
url := "/#/update"
if version != "" {
url += "?version=" + version
}
u.window.SetURL(url)
u.window.Show()
u.window.Focus()
u.showMainAt(url)
}

View File

@@ -21,8 +21,6 @@ import (
"google.golang.org/grpc/connectivity"
nbgrpc "github.com/netbirdio/netbird/client/grpc"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/client/system"
"github.com/netbirdio/netbird/encryption"
"github.com/netbirdio/netbird/shared/management/domain"
@@ -64,13 +62,6 @@ type GrpcClient struct {
connStateCallbackLock sync.RWMutex
serverURL string
// netState gates the stream retry loop on OS-reported network
// availability; nil (the default) disables gating.
netState *netstate.State
// sweeper cuts the transport connections on network change; nil disables it.
sweeper *netsweep.Sweeper
// syncStreamErr holds the last Sync stream error, or nil while the stream
// is established and healthy. GetServerKey succeeds even when the peer
// cannot sync (e.g. the server returns "settings not found"), so the
@@ -120,43 +111,16 @@ func MaxRecvMsgSize() int {
return size
}
// ClientOption configures optional GrpcClient behavior.
type ClientOption func(*GrpcClient)
// WithNetworkState injects the OS network availability state that gates the
// stream retry loop; without it gating is disabled.
func WithNetworkState(netState *netstate.State) ClientOption {
return func(c *GrpcClient) { c.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) ClientOption {
return func(c *GrpcClient) { c.sweeper = sweeper }
}
// NewClient creates a new client to Management service
func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool, opts ...ClientOption) (*GrpcClient, error) {
// Options apply before dialing: the sweeper must wrap the first connection too.
c := &GrpcClient{
key: ourPrivateKey,
ctx: ctx,
connStateCallbackLock: sync.RWMutex{},
serverURL: addr,
}
for _, opt := range opts {
opt(c)
}
func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
var conn *grpc.ClientConn
var extraOpts []grpc.DialOption
if maxSize := MaxRecvMsgSize(); maxSize > 0 {
extraOpts = append(extraOpts, grpc.WithDefaultCallOptions(grpc.MaxCallRecvMsgSize(maxSize)))
log.Infof("management gRPC max receive message size set to %d bytes", maxSize)
}
if c.sweeper != nil {
extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
}
var conn *grpc.ClientConn
operation := func() error {
var err error
conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.ManagementComponent, extraOpts...)
@@ -172,9 +136,16 @@ func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsE
return nil, err
}
c.conn = conn
c.realClient = proto.NewManagementServiceClient(conn)
return c, nil
realClient := proto.NewManagementServiceClient(conn)
return &GrpcClient{
key: ourPrivateKey,
realClient: realClient,
ctx: ctx,
conn: conn,
connStateCallbackLock: sync.RWMutex{},
serverURL: addr,
}, nil
}
// GetServerURL returns the management server URL
@@ -237,16 +208,6 @@ func (c *GrpcClient) withMgmtStream(
) error {
backOff := defaultBackoff(ctx)
operation := func() error {
// suspend reconnect attempts while the OS reports no usable network.
// Wait only errors on a cancelled context, which means shutdown, so
// stop the loop without reporting a failure.
if waited, err := c.netState.Wait(ctx); err != nil {
log.Debugf("management connection context has been canceled while offline, this usually indicates shutdown")
return nil
} else if waited {
backOff.Reset()
}
log.Debugf("management connection state %v", c.conn.GetState())
connState := c.conn.GetState()

View File

@@ -14,7 +14,6 @@ import (
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netsweep"
auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
"github.com/netbirdio/netbird/shared/relay/client/dialer"
netErr "github.com/netbirdio/netbird/shared/relay/client/dialer/net"
@@ -185,10 +184,6 @@ type Client struct {
// datagram-sized transport is avoided on subsequent connects. Shared via
// the manager.
transportFallback *transportFallback
// sweeper cuts the relay connection on network change; the read loop
// reports the disconnect and the guard reconnects. Shared via the manager.
sweeper *netsweep.Sweeper
// datagramFallbackTriggered guards a single fallback per connection so a
// burst of oversized datagrams triggers one reconnect, not many.
datagramFallbackTriggered atomic.Bool
@@ -398,12 +393,6 @@ func (c *Client) Close() error {
}
func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
// A sweep cancels this context, so a dial started on the old network
// aborts instead of waiting out its handshake timeout.
dial := c.sweeper.StartDial(ctx)
defer dial.Release()
ctx = dial.Ctx()
mode := transportModeFromEnv()
dialers := c.getDialers(mode)
@@ -428,19 +417,12 @@ func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
return nil, fmt.Errorf("dial via FQDN: %w", err)
}
}
// Read the transport off the concrete connection: the sweeper's wrapper
// embeds net.Conn only, so it does not promote Protocol().
c.relayConn = conn
c.datagramFallbackTriggered.Store(false)
if tc, ok := conn.(transportConn); ok {
c.transport = tc.Protocol()
}
conn, err := dial.WrapConn(conn)
if err != nil {
return nil, fmt.Errorf("register connection: %w", err)
}
c.relayConn = conn
c.datagramFallbackTriggered.Store(false)
instanceURL, err := c.handShake(ctx)
if err != nil {
cErr := conn.Close()

View File

@@ -7,8 +7,6 @@ import (
"github.com/cenkalti/backoff/v4"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
)
const defaultMaxBackoffInterval = 60 * time.Second
@@ -24,19 +22,14 @@ type Guard struct {
// attempts.
maxBackoffInterval time.Duration
// netState gates reconnect attempts on OS-reported network availability;
// nil disables gating.
netState *netstate.State
// lastErr is the error from the most recent failed reconnect attempt,
// surfaced as the home relay status while disconnected.
lastErr atomic.Pointer[error]
}
// NewGuard creates a new guard for the relay client. A non-positive
// maxBackoffInterval falls back to defaultMaxBackoffInterval. A nil netState
// disables network availability gating.
func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState *netstate.State) *Guard {
// maxBackoffInterval falls back to defaultMaxBackoffInterval.
func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration) *Guard {
if maxBackoffInterval <= 0 {
maxBackoffInterval = defaultMaxBackoffInterval
}
@@ -45,7 +38,6 @@ func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState *nets
OnReconnected: make(chan struct{}, 1),
serverPicker: sp,
maxBackoffInterval: maxBackoffInterval,
netState: netState,
}
return g
}
@@ -78,21 +70,11 @@ func (g *Guard) StartReconnectTrys(ctx context.Context, relayClient *Client) {
// start a ticker to pick a new server
ticker := g.exponentTicker(ctx)
defer func() {
ticker.Stop()
}()
defer ticker.Stop()
for {
select {
case <-ticker.C:
// suspend reconnect attempts while the OS reports no usable network
if waited, err := g.netState.Wait(ctx); err != nil {
return
} else if waited {
ticker.Stop()
ticker = g.exponentTicker(ctx)
continue
}
if err := g.retry(ctx); err != nil {
log.Errorf("failed to pick new Relay server: %s", err)
g.setLastError(err)
@@ -122,13 +104,6 @@ func (g *Guard) tryToQuickReconnect(parentCtx context.Context, rc *Client) bool
return false
}
// Re-check after the wait: the disconnect that triggered this reconnect
// is often the first symptom of the network going away, so the
// availability flag typically arrives while we sleep here.
if !g.netState.IsOnline() {
return false
}
log.Infof("try to reconnect to Relay server: %s", rc.connectionURL)
if err := rc.Connect(parentCtx); err != nil {

View File

@@ -12,8 +12,6 @@ import (
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
relayAuth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
)
@@ -67,17 +65,6 @@ func WithMaxBackoffInterval(d time.Duration) ManagerOption {
return func(m *Manager) { m.maxBackoffInterval = d }
}
// WithNetworkState injects the OS network availability state that gates the
// reconnect guard; without it reconnect attempts are not gated.
func WithNetworkState(netState *netstate.State) ManagerOption {
return func(m *Manager) { m.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) ManagerOption {
return func(m *Manager) { m.sweeper = sweeper }
}
// Manager is a manager for the relay client instances. It establishes one persistent connection to the given relay URL
// and automatically reconnect to them in case disconnection.
// The manager also manage temporary relay connection. If a client wants to communicate with a client on a
@@ -105,8 +92,6 @@ type Manager struct {
mtu uint16
maxBackoffInterval time.Duration
netState *netstate.State
sweeper *netsweep.Sweeper
cleanupInterval time.Duration
keepUnusedServerTime time.Duration
@@ -143,9 +128,8 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
for _, opt := range opts {
opt(m)
}
m.serverPicker.Sweeper = m.sweeper
m.serverPicker.ServerURLs.Store(serverURLs)
m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval, m.netState)
m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval)
return m
}
@@ -370,7 +354,6 @@ func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string
relayClient := NewClientWithServerIP(serverAddress, serverIP, m.tokenStore, m.peerID, m.mtu)
relayClient.SetTransportFallback(m.transportFallback)
relayClient.sweeper = m.sweeper
err := relayClient.Connect(m.ctx)
if err != nil {
rt.Lock()

View File

@@ -9,7 +9,6 @@ import (
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/client/netsweep"
auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
)
@@ -31,7 +30,6 @@ type ServerPicker struct {
MTU uint16
ConnectionTimeout time.Duration
TransportFallback *transportFallback
Sweeper *netsweep.Sweeper
}
func (sp *ServerPicker) PickServer(parentCtx context.Context) (*Client, error) {
@@ -75,7 +73,6 @@ func (sp *ServerPicker) startConnection(ctx context.Context, resultChan chan con
log.Infof("try to connecting to relay server: %s", url)
relayClient := NewClient(url, sp.TokenStore, sp.PeerID, sp.MTU)
relayClient.SetTransportFallback(sp.TransportFallback)
relayClient.sweeper = sp.Sweeper
err := relayClient.Connect(ctx)
resultChan <- connResult{
RelayClient: relayClient,

View File

@@ -19,8 +19,6 @@ import (
"google.golang.org/grpc/status"
nbgrpc "github.com/netbirdio/netbird/client/grpc"
"github.com/netbirdio/netbird/client/netstate"
"github.com/netbirdio/netbird/client/netsweep"
"github.com/netbirdio/netbird/encryption"
"github.com/netbirdio/netbird/shared/management/client"
"github.com/netbirdio/netbird/shared/signal/proto"
@@ -67,13 +65,6 @@ type GrpcClient struct {
connStateCallback ConnStateNotifier
connStateCallbackLock sync.RWMutex
// netState gates the Receive retry loop on OS-reported network
// availability; nil (the default) disables gating.
netState *netstate.State
// sweeper cuts the transport connections on network change; nil disables it.
sweeper *netsweep.Sweeper
onReconnectedListenerFn func()
decryptionWorker *Worker
@@ -97,43 +88,13 @@ type GrpcClient struct {
watchdogWg sync.WaitGroup
}
// ClientOption configures optional GrpcClient behavior.
type ClientOption func(*GrpcClient)
// WithNetworkState injects the OS network availability state that gates the
// Receive retry loop; without it gating is disabled.
func WithNetworkState(netState *netstate.State) ClientOption {
return func(c *GrpcClient) { c.netState = netState }
}
// WithSweeper injects the network change sweeper.
func WithSweeper(sweeper *netsweep.Sweeper) ClientOption {
return func(c *GrpcClient) { c.sweeper = sweeper }
}
// NewClient creates a new Signal client
func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled bool, opts ...ClientOption) (*GrpcClient, error) {
// Options apply before dialing: the sweeper must wrap the first connection too.
c := &GrpcClient{
ctx: ctx,
key: key,
mux: sync.Mutex{},
status: StreamDisconnected,
connStateCallbackLock: sync.RWMutex{},
}
for _, opt := range opts {
opt(c)
}
var extraOpts []grpc.DialOption
if c.sweeper != nil {
extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
}
func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
var conn *grpc.ClientConn
operation := func() error {
var err error
conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent, extraOpts...)
conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent)
if err != nil {
return fmt.Errorf("create connection: %w", err)
}
@@ -148,9 +109,15 @@ func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled boo
log.Debugf("connected to Signal Service: %v", conn.Target())
c.signalConn = conn
c.realClient = proto.NewSignalExchangeClient(conn)
return c, nil
return &GrpcClient{
realClient: proto.NewSignalExchangeClient(conn),
ctx: ctx,
signalConn: conn,
key: key,
mux: sync.Mutex{},
status: StreamDisconnected,
connStateCallbackLock: sync.RWMutex{},
}, nil
}
func (c *GrpcClient) StreamConnected() bool {
@@ -201,15 +168,6 @@ func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Mes
var backOff = defaultBackoff(ctx)
operation := func() error {
// suspend reconnect attempts while the OS reports no usable network.
// Wait only errors on a cancelled context, which means shutdown, so
// stop the loop without reporting a failure.
if waited, err := c.netState.Wait(ctx); err != nil {
log.Debugf("signal connection context has been canceled while offline, this usually indicates shutdown")
return nil
} else if waited {
backOff.Reset()
}
c.notifyStreamDisconnected()