[client] Feature/client metrics

.github/workflows/golang-test-windows.yml

@@ -63,10 +63,15 @@ jobs:
       - run: PsExec64 -s -w ${{ github.workspace }} C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe env -w GOMODCACHE=${{ env.cache }}
       - run: PsExec64 -s -w ${{ github.workspace }} C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe env -w GOCACHE=${{ env.modcache }}
       - run: PsExec64 -s -w ${{ github.workspace }} C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe mod tidy
-      - run: echo "files=$(go list ./... | ForEach-Object { $_ } | Where-Object { $_ -notmatch '/management' } | Where-Object { $_ -notmatch '/relay' } | Where-Object { $_ -notmatch '/signal' } | Where-Object { $_ -notmatch '/proxy' } | Where-Object { $_ -notmatch '/combined' })" >> $env:GITHUB_ENV
+      - name: Generate test script
+        run: |
+          $packages = go list ./... | Where-Object { $_ -notmatch '/management' } | Where-Object { $_ -notmatch '/relay' } | Where-Object { $_ -notmatch '/signal' } | Where-Object { $_ -notmatch '/proxy' } | Where-Object { $_ -notmatch '/combined' }
+          $goExe = "C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe"
+          $cmd = "$goExe test -tags=devcert -timeout 10m -p 1 $($packages -join ' ') > test-out.txt 2>&1"
+          Set-Content -Path "${{ github.workspace }}\run-tests.cmd" -Value $cmd
 
       - name: test
-        run: PsExec64 -s -w ${{ github.workspace }} cmd.exe /c "C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe test -tags=devcert -timeout 10m -p 1 ${{ env.files }} > test-out.txt 2>&1"
+        run: PsExec64 -s -w ${{ github.workspace }} cmd.exe /c "${{ github.workspace }}\run-tests.cmd"
       - name: test output
         if: ${{ always() }}
         run: Get-Content test-out.txt

client/internal/connect.go

@@ -23,6 +23,7 @@ import (
 	"github.com/netbirdio/netbird/client/iface/netstack"
 	"github.com/netbirdio/netbird/client/internal/dns"
 	"github.com/netbirdio/netbird/client/internal/listener"
+	"github.com/netbirdio/netbird/client/internal/metrics"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
@@ -50,6 +51,7 @@ type ConnectClient struct {
 
 	engine        *Engine
 	engineMutex   sync.Mutex
+	clientMetrics *metrics.ClientMetrics
 	updateManager *updater.Manager
 
 	persistSyncResponse bool
@@ -133,10 +135,34 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}
 	}()
 
+	// Stop metrics push on exit
+	defer func() {
+		if c.clientMetrics != nil {
+			c.clientMetrics.StopPush()
+		}
+	}()
+
 	log.Infof("starting NetBird client version %s on %s/%s", version.NetbirdVersion(), runtime.GOOS, runtime.GOARCH)
 
 	nbnet.Init()
 
+	// Initialize metrics once at startup (always active for debug bundles)
+	if c.clientMetrics == nil {
+		agentInfo := metrics.AgentInfo{
+			DeploymentType: metrics.DeploymentTypeUnknown,
+			Version:        version.NetbirdVersion(),
+			OS:             runtime.GOOS,
+			Arch:           runtime.GOARCH,
+		}
+		c.clientMetrics = metrics.NewClientMetrics(agentInfo)
+		log.Debugf("initialized client metrics")
+
+		// Start metrics push if enabled (uses daemon context, persists across engine restarts)
+		if metrics.IsMetricsPushEnabled() {
+			c.clientMetrics.StartPush(c.ctx, metrics.PushConfigFromEnv())
+		}
+	}
+
 	backOff := &backoff.ExponentialBackOff{
 		InitialInterval:     time.Second,
 		RandomizationFactor: 1,
@@ -223,6 +249,16 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		mgmNotifier := statusRecorderToMgmConnStateNotifier(c.statusRecorder)
 		mgmClient.SetConnStateListener(mgmNotifier)
 
+		// Update metrics with actual deployment type after connection
+		deploymentType := metrics.DetermineDeploymentType(mgmClient.GetServerURL())
+		agentInfo := metrics.AgentInfo{
+			DeploymentType: deploymentType,
+			Version:        version.NetbirdVersion(),
+			OS:             runtime.GOOS,
+			Arch:           runtime.GOARCH,
+		}
+		c.clientMetrics.UpdateAgentInfo(agentInfo, myPrivateKey.PublicKey().String())
+
 		log.Debugf("connected to the Management service %s", c.config.ManagementURL.Host)
 		defer func() {
 			if err = mgmClient.Close(); err != nil {
@@ -231,8 +267,10 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}()
 
 		// connect (just a connection, no stream yet) and login to Management Service to get an initial global Netbird config
+		loginStarted := time.Now()
 		loginResp, err := loginToManagement(engineCtx, mgmClient, publicSSHKey, c.config)
 		if err != nil {
+			c.clientMetrics.RecordLoginDuration(engineCtx, time.Since(loginStarted), false)
 			log.Debug(err)
 			if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 				state.Set(StatusNeedsLogin)
@@ -241,6 +279,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			}
 			return wrapErr(err)
 		}
+		c.clientMetrics.RecordLoginDuration(engineCtx, time.Since(loginStarted), true)
 		c.statusRecorder.MarkManagementConnected()
 
 		localPeerState := peer.LocalPeerState{
@@ -317,6 +356,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			Checks:         checks,
 			StateManager:   stateManager,
 			UpdateManager:  c.updateManager,
+			ClientMetrics:  c.clientMetrics,
 		}, mobileDependency)
 		engine.SetSyncResponsePersistence(c.persistSyncResponse)
 		c.engine = engine

client/internal/debug/debug.go

@@ -53,6 +53,7 @@ resolved_domains.txt: Anonymized resolved domain IP addresses from the status re
 config.txt: Anonymized configuration information of the NetBird client.
 network_map.json: Anonymized sync response containing peer configurations, routes, DNS settings, and firewall rules.
 state.json: Anonymized client state dump containing netbird states for the active profile.
+metrics.txt: Buffered client metrics in InfluxDB line protocol format. Only present when metrics collection is enabled. Peer identifiers are anonymized.
 mutex.prof: Mutex profiling information.
 goroutine.prof: Goroutine profiling information.
 block.prof: Block profiling information.
@@ -219,6 +220,11 @@ const (
 	darwinStdoutLogPath = "/var/log/netbird.err.log"
 )
 
+// MetricsExporter is an interface for exporting metrics
+type MetricsExporter interface {
+	Export(w io.Writer) error
+}
+
 type BundleGenerator struct {
 	anonymizer *anonymize.Anonymizer
 
@@ -229,6 +235,7 @@ type BundleGenerator struct {
 	logPath        string
 	cpuProfile     []byte
 	refreshStatus  func() // Optional callback to refresh status before bundle generation
+	clientMetrics  MetricsExporter
 
 	anonymize         bool
 	includeSystemInfo bool
@@ -250,6 +257,7 @@ type GeneratorDependencies struct {
 	LogPath        string
 	CPUProfile     []byte
 	RefreshStatus  func() // Optional callback to refresh status before bundle generation
+	ClientMetrics  MetricsExporter
 }
 
 func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGenerator {
@@ -268,6 +276,7 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
 		logPath:        deps.LogPath,
 		cpuProfile:     deps.CPUProfile,
 		refreshStatus:  deps.RefreshStatus,
+		clientMetrics:  deps.ClientMetrics,
 
 		anonymize:         cfg.Anonymize,
 		includeSystemInfo: cfg.IncludeSystemInfo,
@@ -351,6 +360,10 @@ func (g *BundleGenerator) createArchive() error {
 		log.Errorf("failed to add corrupted state files to debug bundle: %v", err)
 	}
 
+	if err := g.addMetrics(); err != nil {
+		log.Errorf("failed to add metrics to debug bundle: %v", err)
+	}
+
 	if err := g.addWgShow(); err != nil {
 		log.Errorf("failed to add wg show output: %v", err)
 	}
@@ -744,6 +757,30 @@ func (g *BundleGenerator) addCorruptedStateFiles() error {
 	return nil
 }
 
+func (g *BundleGenerator) addMetrics() error {
+	if g.clientMetrics == nil {
+		log.Debugf("skipping metrics in debug bundle: no metrics collector")
+		return nil
+	}
+
+	var buf bytes.Buffer
+	if err := g.clientMetrics.Export(&buf); err != nil {
+		return fmt.Errorf("export metrics: %w", err)
+	}
+
+	if buf.Len() == 0 {
+		log.Debugf("skipping metrics.txt in debug bundle: no metrics data")
+		return nil
+	}
+
+	if err := g.addFileToZip(&buf, "metrics.txt"); err != nil {
+		return fmt.Errorf("add metrics file to zip: %w", err)
+	}
+
+	log.Debugf("added metrics to debug bundle")
+	return nil
+}
+
 func (g *BundleGenerator) addLogfile() error {
 	if g.logPath == "" {
 		log.Debugf("skipping empty log file in debug bundle")

client/internal/engine.go

@@ -38,6 +38,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/dnsfwd"
 	"github.com/netbirdio/netbird/client/internal/expose"
 	"github.com/netbirdio/netbird/client/internal/ingressgw"
+	"github.com/netbirdio/netbird/client/internal/metrics"
 	"github.com/netbirdio/netbird/client/internal/netflow"
 	nftypes "github.com/netbirdio/netbird/client/internal/netflow/types"
 	"github.com/netbirdio/netbird/client/internal/networkmonitor"
@@ -149,6 +150,7 @@ type EngineServices struct {
 	Checks         []*mgmProto.Checks
 	StateManager   *statemanager.Manager
 	UpdateManager  *updater.Manager
+	ClientMetrics  *metrics.ClientMetrics
 }
 
 // Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -229,6 +231,9 @@ type Engine struct {
 
 	probeStunTurn *relay.StunTurnProbe
 
+	// clientMetrics collects and pushes metrics
+	clientMetrics *metrics.ClientMetrics
+
 	jobExecutor   *jobexec.Executor
 	jobExecutorWG sync.WaitGroup
 
@@ -272,6 +277,7 @@ func NewEngine(
 		checks:         services.Checks,
 		probeStunTurn:  relay.NewStunTurnProbe(relay.DefaultCacheTTL),
 		jobExecutor:    jobexec.NewExecutor(),
+		clientMetrics:  services.ClientMetrics,
 		updateManager:  services.UpdateManager,
 	}
 
@@ -813,7 +819,9 @@ func (e *Engine) handleAutoUpdateVersion(autoUpdateSettings *mgmProto.AutoUpdate
 func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	started := time.Now()
 	defer func() {
-		log.Infof("sync finished in %s", time.Since(started))
+		duration := time.Since(started)
+		log.Infof("sync finished in %s", duration)
+		e.clientMetrics.RecordSyncDuration(e.ctx, duration)
 	}()
 	e.syncMsgMux.Lock()
 	defer e.syncMsgMux.Unlock()
@@ -1061,6 +1069,7 @@ func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobR
 		StatusRecorder: e.statusRecorder,
 		SyncResponse:   syncResponse,
 		LogPath:        e.config.LogPath,
+		ClientMetrics:  e.clientMetrics,
 		RefreshStatus: func() {
 			e.RunHealthProbes(true)
 		},
@@ -1515,11 +1524,12 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 	}
 
 	serviceDependencies := peer.ServiceDependencies{
-		StatusRecorder: e.statusRecorder,
-		Signaler:       e.signaler,
-		IFaceDiscover:  e.mobileDep.IFaceDiscover,
-		RelayManager:   e.relayManager,
-		SrWatcher:      e.srWatcher,
+		StatusRecorder:  e.statusRecorder,
+		Signaler:        e.signaler,
+		IFaceDiscover:   e.mobileDep.IFaceDiscover,
+		RelayManager:    e.relayManager,
+		SrWatcher:       e.srWatcher,
+		MetricsRecorder: e.clientMetrics,
 	}
 	peerConn, err := peer.NewConn(config, serviceDependencies)
 	if err != nil {
@@ -1816,6 +1826,11 @@ func (e *Engine) GetExposeManager() *expose.Manager {
 	return e.exposeManager
 }
 
+// GetClientMetrics returns the client metrics
+func (e *Engine) GetClientMetrics() *metrics.ClientMetrics {
+	return e.clientMetrics
+}
+
 func findIPFromInterfaceName(ifaceName string) (net.IP, error) {
 	iface, err := net.InterfaceByName(ifaceName)
 	if err != nil {

client/internal/engine_test.go

@@ -828,7 +828,7 @@ func TestEngine_UpdateNetworkMapWithRoutes(t *testing.T) {
 				WgPrivateKey: key,
 				WgPort:       33100,
 				MTU:          iface.DefaultMTU,
-			}, EngineServices{
+	}, EngineServices{
 				SignalClient:   &signal.MockClient{},
 				MgmClient:      &mgmt.MockClient{},
 				RelayManager:   relayMgr,
@@ -1035,7 +1035,7 @@ func TestEngine_UpdateNetworkMapWithDNSUpdate(t *testing.T) {
 				WgPrivateKey: key,
 				WgPort:       33100,
 				MTU:          iface.DefaultMTU,
-			}, EngineServices{
+	}, EngineServices{
 				SignalClient:   &signal.MockClient{},
 				MgmClient:      &mgmt.MockClient{},
 				RelayManager:   relayMgr,
@@ -1566,7 +1566,7 @@ func createEngine(ctx context.Context, cancel context.CancelFunc, setupKey strin
 	}
 
 	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
-	e, err := NewEngine(ctx, cancel, conf, EngineServices{
+e, err := NewEngine(ctx, cancel, conf, EngineServices{
 		SignalClient:   signalClient,
 		MgmClient:      mgmtClient,
 		RelayManager:   relayMgr,

client/internal/metrics/connection_type.go

@@ -0,0 +1,17 @@
+package metrics
+
+// ConnectionType represents the type of peer connection
+type ConnectionType string
+
+const (
+	// ConnectionTypeICE represents a direct peer-to-peer connection using ICE
+	ConnectionTypeICE ConnectionType = "ice"
+
+	// ConnectionTypeRelay represents a relayed connection
+	ConnectionTypeRelay ConnectionType = "relay"
+)
+
+// String returns the string representation of the connection type
+func (c ConnectionType) String() string {
+	return string(c)
+}

client/internal/metrics/deployment_type.go

@@ -0,0 +1,51 @@
+package metrics
+
+import (
+	"net/url"
+	"strings"
+)
+
+// DeploymentType represents the type of NetBird deployment
+type DeploymentType int
+
+const (
+	// DeploymentTypeUnknown represents an unknown or uninitialized deployment type
+	DeploymentTypeUnknown DeploymentType = iota
+
+	// DeploymentTypeCloud represents a cloud-hosted NetBird deployment
+	DeploymentTypeCloud
+
+	// DeploymentTypeSelfHosted represents a self-hosted NetBird deployment
+	DeploymentTypeSelfHosted
+)
+
+// String returns the string representation of the deployment type
+func (d DeploymentType) String() string {
+	switch d {
+	case DeploymentTypeCloud:
+		return "cloud"
+	case DeploymentTypeSelfHosted:
+		return "selfhosted"
+	default:
+		return "unknown"
+	}
+}
+
+// DetermineDeploymentType determines if the deployment is cloud or self-hosted
+// based on the management URL string
+func DetermineDeploymentType(managementURL string) DeploymentType {
+	if managementURL == "" {
+		return DeploymentTypeUnknown
+	}
+
+	u, err := url.Parse(managementURL)
+	if err != nil {
+		return DeploymentTypeSelfHosted
+	}
+
+	if strings.ToLower(u.Hostname()) == "api.netbird.io" {
+		return DeploymentTypeCloud
+	}
+
+	return DeploymentTypeSelfHosted
+}