sendnrw/netbird
2
0
Fork 0
mirror of https://github.com/netbirdio/netbird.git synced 2026-09-21 14:19:08 +02:00
Code Issues Packages Projects Releases Wiki Activity

[client] Sweep network-bound connections when the OS switches networks

Browse Source 
On a network switch (e.g. cellular to WiFi) the management, signal and
relay sockets stay bound to the old network and look alive until the OS
tears them down — measured at 5 seconds of dead air on Android, while
the UI kept claiming Connected. The Android client papered over this
with a full engine restart, paying for it with a torn-down TUN device
and discarded peer state.

Introduce client/netsweep: connections register on dial and deregister
on close, and a sweep closes everything registered while aborting
in-flight dials through sweep-cancellable dial contexts. The aborted
dials matter: a relay dial started on the dying network would otherwise
hold the reconnect loop hostage for the QUIC handshake timeout. After a
sweep every failure surfaces as an ordinary read/write error and the
existing retry loops redial immediately on the new network.

The sweeper reaches the three long-lived connections through the same
options that carry the netstate gate: a gRPC dial option wraps the
management and signal transports (reconnects included), and the relay
client wraps its connection in one place for the picker, the guard and
foreign relays alike. Everything is nil-safe; platforms that inject no
sweeper are untouched.

Mobile clients expose the sweep as NotifyNetworkChange. Measured on
Android against the engine restart it replaces: recovery in 1.6s
instead of 3.2s, no Disconnected flash, and the TUN device, WireGuard
config and peer state survive.
This commit is contained in:
Zoltan Papp
2026-08-11 00:58:50 +02:00
parent 8fb3e707af
commit 072fa8143b
10 changed files with 168 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
client/internal/connect.go
+17 -5
View File
@@ -39,6 +39,7 @@ import (
"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"
@@ -76,6 +77,10 @@ type ConnectClient struct {
// 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.
@@ -87,6 +92,11 @@ 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,
@@ -312,7 +322,8 @@ 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))
mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled,
mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper))
if err != nil {
// On daemon shutdown / Down() the parent context is cancelled
// and the dial fails with "context canceled". Wrapping that
@@ -387,7 +398,7 @@ 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)
signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netState, c.sweeper)
if err != nil {
log.Error(err)
return wrapErr(err)
@@ -424,7 +435,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
}
relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
relayClient.WithNetworkState(c.netState))
relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
c.statusRecorder.SetRelayMgr(relayManager)
if len(relayURLs) > 0 {
if token != nil {
@@ -712,7 +723,7 @@ 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) (*signal.GrpcClient, error) {
func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) {
var sigTLSEnabled bool
if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
sigTLSEnabled = true
@@ -720,7 +731,8 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
sigTLSEnabled = false
}
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled, signal.WithNetworkState(netState))
signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
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)