[management] add domain and service cleanup migration (#5850)

client/firewall/create_linux.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 	"os"
+	"strconv"
 
 	"github.com/coreos/go-iptables/iptables"
 	"github.com/google/nftables"
@@ -35,20 +36,27 @@ const SKIP_NFTABLES_ENV = "NB_SKIP_NFTABLES_CHECK"
 type FWType int
 
 func NewFirewall(iface IFaceMapper, stateManager *statemanager.Manager, flowLogger nftypes.FlowLogger, disableServerRoutes bool, mtu uint16) (firewall.Manager, error) {
-	// on the linux system we try to user nftables or iptables
-	// in any case, because we need to allow netbird interface traffic
-	// so we use AllowNetbird traffic from these firewall managers
-	// for the userspace packet filtering firewall
+	// We run in userspace mode and force userspace firewall was requested. We don't attempt native firewall.
+	if iface.IsUserspaceBind() && forceUserspaceFirewall() {
+		log.Info("forcing userspace firewall")
+		return createUserspaceFirewall(iface, nil, disableServerRoutes, flowLogger, mtu)
+	}
+
+	// Use native firewall for either kernel or userspace, the interface appears identical to netfilter
 	fm, err := createNativeFirewall(iface, stateManager, disableServerRoutes, mtu)
 
+	// Kernel cannot fall back to anything else, need to return error
 	if !iface.IsUserspaceBind() {
 		return fm, err
 	}
 
+	// Fall back to the userspace packet filter if native is unavailable
 	if err != nil {
 		log.Warnf("failed to create native firewall: %v. Proceeding with userspace", err)
+		return createUserspaceFirewall(iface, nil, disableServerRoutes, flowLogger, mtu)
 	}
-	return createUserspaceFirewall(iface, fm, disableServerRoutes, flowLogger, mtu)
+
+	return fm, nil
 }
 
 func createNativeFirewall(iface IFaceMapper, stateManager *statemanager.Manager, routes bool, mtu uint16) (firewall.Manager, error) {
@@ -160,3 +168,17 @@ func isIptablesClientAvailable(client *iptables.IPTables) bool {
 	_, err := client.ListChains("filter")
 	return err == nil
 }
+
+func forceUserspaceFirewall() bool {
+	val := os.Getenv(EnvForceUserspaceFirewall)
+	if val == "" {
+		return false
+	}
+
+	force, err := strconv.ParseBool(val)
+	if err != nil {
+		log.Warnf("failed to parse %s: %v", EnvForceUserspaceFirewall, err)
+		return false
+	}
+	return force
+}

client/firewall/iface.go

@@ -7,6 +7,12 @@ import (
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 )
 
+// EnvForceUserspaceFirewall forces the use of the userspace packet filter even when
+// native iptables/nftables is available. This only applies when the WireGuard interface
+// runs in userspace mode. When set, peer ACLs are handled by USPFilter instead of
+// kernel netfilter rules.
+const EnvForceUserspaceFirewall = "NB_FORCE_USERSPACE_FIREWALL"
+
 // IFaceMapper defines subset methods of interface required for manager
 type IFaceMapper interface {
 	Name() string

client/firewall/iptables/manager_linux.go

@@ -33,7 +33,6 @@ type Manager struct {
 type iFaceMapper interface {
 	Name() string
 	Address() wgaddr.Address
-	IsUserspaceBind() bool
 }
 
 // Create iptables firewall manager
@@ -64,10 +63,9 @@ func Create(wgIface iFaceMapper, mtu uint16) (*Manager, error) {
 func (m *Manager) Init(stateManager *statemanager.Manager) error {
 	state := &ShutdownState{
 		InterfaceState: &InterfaceState{
-			NameStr:       m.wgIface.Name(),
-			WGAddress:     m.wgIface.Address(),
-			UserspaceBind: m.wgIface.IsUserspaceBind(),
-			MTU:           m.router.mtu,
+			NameStr:   m.wgIface.Name(),
+			WGAddress: m.wgIface.Address(),
+			MTU:       m.router.mtu,
 		},
 	}
 	stateManager.RegisterState(state)
@@ -203,12 +201,10 @@ func (m *Manager) Close(stateManager *statemanager.Manager) error {
 	return nberrors.FormatErrorOrNil(merr)
 }
 
-// AllowNetbird allows netbird interface traffic
+// AllowNetbird allows netbird interface traffic.
+// This is called when USPFilter wraps the native firewall, adding blanket accept
+// rules so that packet filtering is handled in userspace instead of by netfilter.
 func (m *Manager) AllowNetbird() error {
-	if !m.wgIface.IsUserspaceBind() {
-		return nil
-	}
-
 	_, err := m.AddPeerFiltering(
 		nil,
 		net.IP{0, 0, 0, 0},

client/firewall/iptables/manager_linux_test.go

@@ -47,8 +47,6 @@ func (i *iFaceMock) Address() wgaddr.Address {
 	panic("AddressFunc is not set")
 }
 
-func (i *iFaceMock) IsUserspaceBind() bool { return false }
-
 func TestIptablesManager(t *testing.T) {
 	ipv4Client, err := iptables.NewWithProtocol(iptables.ProtocolIPv4)
 	require.NoError(t, err)

client/firewall/iptables/state_linux.go

@@ -9,10 +9,9 @@ import (
 )
 
 type InterfaceState struct {
-	NameStr       string         `json:"name"`
-	WGAddress     wgaddr.Address `json:"wg_address"`
-	UserspaceBind bool           `json:"userspace_bind"`
-	MTU           uint16         `json:"mtu"`
+	NameStr   string         `json:"name"`
+	WGAddress wgaddr.Address `json:"wg_address"`
+	MTU       uint16         `json:"mtu"`
 }
 
 func (i *InterfaceState) Name() string {
@@ -23,10 +22,6 @@ func (i *InterfaceState) Address() wgaddr.Address {
 	return i.WGAddress
 }
 
-func (i *InterfaceState) IsUserspaceBind() bool {
-	return i.UserspaceBind
-}
-
 type ShutdownState struct {
 	sync.Mutex
 

client/firewall/nftables/manager_linux.go

@@ -40,7 +40,6 @@ func getTableName() string {
 type iFaceMapper interface {
 	Name() string
 	Address() wgaddr.Address
-	IsUserspaceBind() bool
 }
 
 // Manager of iptables firewall
@@ -106,10 +105,9 @@ func (m *Manager) Init(stateManager *statemanager.Manager) error {
 	// cleanup using Close() without needing to store specific rules.
 	if err := stateManager.UpdateState(&ShutdownState{
 		InterfaceState: &InterfaceState{
-			NameStr:       m.wgIface.Name(),
-			WGAddress:     m.wgIface.Address(),
-			UserspaceBind: m.wgIface.IsUserspaceBind(),
-			MTU:           m.router.mtu,
+			NameStr:   m.wgIface.Name(),
+			WGAddress: m.wgIface.Address(),
+			MTU:       m.router.mtu,
 		},
 	}); err != nil {
 		log.Errorf("failed to update state: %v", err)
@@ -205,12 +203,10 @@ func (m *Manager) RemoveNatRule(pair firewall.RouterPair) error {
 	return m.router.RemoveNatRule(pair)
 }
 
-// AllowNetbird allows netbird interface traffic
+// AllowNetbird allows netbird interface traffic.
+// This is called when USPFilter wraps the native firewall, adding blanket accept
+// rules so that packet filtering is handled in userspace instead of by netfilter.
 func (m *Manager) AllowNetbird() error {
-	if !m.wgIface.IsUserspaceBind() {
-		return nil
-	}
-
 	m.mutex.Lock()
 	defer m.mutex.Unlock()
 

client/firewall/nftables/manager_linux_test.go

@@ -52,8 +52,6 @@ func (i *iFaceMock) Address() wgaddr.Address {
 	panic("AddressFunc is not set")
 }
 
-func (i *iFaceMock) IsUserspaceBind() bool { return false }
-
 func TestNftablesManager(t *testing.T) {
 
 	// just check on the local interface

client/firewall/nftables/state_linux.go

@@ -8,10 +8,9 @@ import (
 )
 
 type InterfaceState struct {
-	NameStr       string         `json:"name"`
-	WGAddress     wgaddr.Address `json:"wg_address"`
-	UserspaceBind bool           `json:"userspace_bind"`
-	MTU           uint16         `json:"mtu"`
+	NameStr   string         `json:"name"`
+	WGAddress wgaddr.Address `json:"wg_address"`
+	MTU       uint16         `json:"mtu"`
 }
 
 func (i *InterfaceState) Name() string {
@@ -22,10 +21,6 @@ func (i *InterfaceState) Address() wgaddr.Address {
 	return i.WGAddress
 }
 
-func (i *InterfaceState) IsUserspaceBind() bool {
-	return i.UserspaceBind
-}
-
 type ShutdownState struct {
 	InterfaceState *InterfaceState `json:"interface_state,omitempty"`
 }

client/internal/acl/manager_test.go

@@ -19,6 +19,9 @@ import (
 var flowLogger = netflow.NewManager(nil, []byte{}, nil).GetLogger()
 
 func TestDefaultManager(t *testing.T) {
+	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
+
 	networkMap := &mgmProto.NetworkMap{
 		FirewallRules: []*mgmProto.FirewallRule{
 			{
@@ -135,6 +138,7 @@ func TestDefaultManager(t *testing.T) {
 func TestDefaultManagerStateless(t *testing.T) {
 	// stateless currently only in userspace, so we have to disable kernel
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 	t.Setenv("NB_DISABLE_CONNTRACK", "true")
 
 	networkMap := &mgmProto.NetworkMap{
@@ -194,6 +198,7 @@ func TestDefaultManagerStateless(t *testing.T) {
 // This tests the full ACL manager -> uspfilter integration.
 func TestDenyRulesNotAccumulatedOnRepeatedApply(t *testing.T) {
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 
 	networkMap := &mgmProto.NetworkMap{
 		FirewallRules: []*mgmProto.FirewallRule{
@@ -258,6 +263,7 @@ func TestDenyRulesNotAccumulatedOnRepeatedApply(t *testing.T) {
 // up when they're removed from the network map in a subsequent update.
 func TestDenyRulesCleanedUpOnRemoval(t *testing.T) {
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 
 	ctrl := gomock.NewController(t)
 	defer ctrl.Finish()
@@ -339,6 +345,7 @@ func TestDenyRulesCleanedUpOnRemoval(t *testing.T) {
 // one added without leaking.
 func TestRuleUpdateChangingAction(t *testing.T) {
 	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
 
 	ctrl := gomock.NewController(t)
 	defer ctrl.Finish()

combined/cmd/config.go

@@ -179,9 +179,11 @@ type StoreConfig struct {
 
 // ReverseProxyConfig contains reverse proxy settings
 type ReverseProxyConfig struct {
-	TrustedHTTPProxies      []string `yaml:"trustedHTTPProxies"`
-	TrustedHTTPProxiesCount uint     `yaml:"trustedHTTPProxiesCount"`
-	TrustedPeers            []string `yaml:"trustedPeers"`
+	TrustedHTTPProxies            []string `yaml:"trustedHTTPProxies"`
+	TrustedHTTPProxiesCount       uint     `yaml:"trustedHTTPProxiesCount"`
+	TrustedPeers                  []string `yaml:"trustedPeers"`
+	AccessLogRetentionDays        int      `yaml:"accessLogRetentionDays"`
+	AccessLogCleanupIntervalHours int      `yaml:"accessLogCleanupIntervalHours"`
 }
 
 // DefaultConfig returns a CombinedConfig with default values
@@ -645,7 +647,9 @@ func (c *CombinedConfig) ToManagementConfig() (*nbconfig.Config, error) {
 
 	// Build reverse proxy config
 	reverseProxy := nbconfig.ReverseProxy{
-		TrustedHTTPProxiesCount: mgmt.ReverseProxy.TrustedHTTPProxiesCount,
+		TrustedHTTPProxiesCount:       mgmt.ReverseProxy.TrustedHTTPProxiesCount,
+		AccessLogRetentionDays:        mgmt.ReverseProxy.AccessLogRetentionDays,
+		AccessLogCleanupIntervalHours: mgmt.ReverseProxy.AccessLogCleanupIntervalHours,
 	}
 	for _, p := range mgmt.ReverseProxy.TrustedHTTPProxies {
 		if prefix, err := netip.ParsePrefix(p); err == nil {

infrastructure_files/observability/grafana/dashboards/management.json

@@ -302,7 +302,7 @@
             "uid": "${datasource}"
           },
           "editorMode": "code",
-          "expr": "rate(management_account_peer_meta_update_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+          "expr": "rate(management_account_peer_meta_update_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
           "instant": false,
           "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
           "range": true,
@@ -410,7 +410,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.5,sum(increase(management_account_get_peer_network_map_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.5,sum(increase(management_account_get_peer_network_map_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -426,7 +426,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.9,sum(increase(management_account_get_peer_network_map_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.9,sum(increase(management_account_get_peer_network_map_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -443,7 +443,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99,sum(increase(management_account_get_peer_network_map_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.99,sum(increase(management_account_get_peer_network_map_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -545,7 +545,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.5,sum(increase(management_account_update_account_peers_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.5,sum(increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -561,7 +561,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.9,sum(increase(management_account_update_account_peers_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.9,sum(increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -578,7 +578,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99,sum(increase(management_account_update_account_peers_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.99,sum(increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -694,7 +694,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.5,sum(increase(management_grpc_updatechannel_queue_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.5,sum(increase(management_grpc_updatechannel_queue_length_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -710,7 +710,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.9,sum(increase(management_grpc_updatechannel_queue_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.9,sum(increase(management_grpc_updatechannel_queue_length_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -727,7 +727,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99,sum(increase(management_grpc_updatechannel_queue_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
+              "expr": "histogram_quantile(0.99,sum(increase(management_grpc_updatechannel_queue_length_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le,cluster,environment,job))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "hide": false,
@@ -841,7 +841,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_store_persistence_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_store_persistence_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -853,7 +853,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_store_persistence_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_store_persistence_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -866,7 +866,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_store_persistence_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_store_persistence_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -963,7 +963,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_store_transaction_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_store_transaction_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -975,7 +975,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_store_transaction_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_store_transaction_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -988,7 +988,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_store_transaction_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_store_transaction_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1085,7 +1085,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_store_global_lock_acquisition_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_store_global_lock_acquisition_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -1097,7 +1097,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_store_global_lock_acquisition_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_store_global_lock_acquisition_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -1110,7 +1110,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_store_global_lock_acquisition_duration_ms_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_store_global_lock_acquisition_duration_ms_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1221,7 +1221,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "rate(management_idp_authenticate_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+              "expr": "rate(management_idp_authenticate_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
               "instant": false,
               "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
               "range": true,
@@ -1317,7 +1317,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "rate(management_idp_get_account_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+              "expr": "rate(management_idp_get_account_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
               "instant": false,
               "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
               "range": true,
@@ -1413,7 +1413,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "rate(management_idp_update_user_meta_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
+              "expr": "rate(management_idp_update_user_meta_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])",
               "instant": false,
               "legendFormat": "{{cluster}}/{{environment}}/{{job}}",
               "range": true,
@@ -1523,7 +1523,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "sum(rate(management_http_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"GET|OPTIONS\"}[$__rate_interval])) by (job,method)",
+              "expr": "sum(rate(management_http_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"GET|OPTIONS\"}[$__rate_interval])) by (job,method)",
               "instant": false,
               "legendFormat": "{{method}}",
               "range": true,
@@ -1619,7 +1619,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "sum(rate(management_http_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"POST|PUT|DELETE\"}[$__rate_interval])) by (job,method)",
+              "expr": "sum(rate(management_http_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",method=~\"POST|PUT|DELETE\"}[$__rate_interval])) by (job,method)",
               "instant": false,
               "legendFormat": "{{method}}",
               "range": true,
@@ -1715,7 +1715,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -1727,7 +1727,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -1740,7 +1740,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"read\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1837,7 +1837,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.50, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
               "instant": false,
               "legendFormat": "p50",
               "range": true,
@@ -1849,7 +1849,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.90, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p90",
@@ -1862,7 +1862,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
+              "expr": "histogram_quantile(0.99, sum(rate(management_http_request_duration_ms_total_milliseconds_bucket{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\",type=~\"write\"}[5m])) by (le))",
               "hide": false,
               "instant": false,
               "legendFormat": "p99",
@@ -1963,7 +1963,7 @@
                 "uid": "${datasource}"
               },
               "editorMode": "code",
-              "expr": "sum(rate(management_http_request_counter_ratio_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (job,exported_endpoint,method)",
+              "expr": "sum(rate(management_http_request_counter_total{cluster=~\"$cluster\",environment=~\"$environment\",job=~\"$job\",host=~\"$host\"}[$__rate_interval])) by (job,exported_endpoint,method)",
               "hide": false,
               "instant": false,
               "legendFormat": "{{method}}-{{exported_endpoint}}",
@@ -3222,7 +3222,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "builder",
-              "expr": "sum by(le) (increase(management_grpc_updatechannel_queue_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
+              "expr": "sum by(le) (increase(management_grpc_updatechannel_queue_length_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,
@@ -3323,7 +3323,7 @@
               },
               "disableTextWrap": false,
               "editorMode": "builder",
-              "expr": "sum by(le) (increase(management_account_update_account_peers_duration_ms_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
+              "expr": "sum by(le) (increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{application=\"management\", environment=\"$environment\", host=~\"$host\"}[$__rate_interval]))",
               "format": "heatmap",
               "fullMetaSearch": false,
               "includeNullMetadata": true,

management/internals/modules/reverseproxy/accesslogs/manager/manager.go

@@ -106,13 +106,23 @@ func (m *managerImpl) CleanupOldAccessLogs(ctx context.Context, retentionDays in
 
 // StartPeriodicCleanup starts a background goroutine that periodically cleans up old access logs
 func (m *managerImpl) StartPeriodicCleanup(ctx context.Context, retentionDays, cleanupIntervalHours int) {
-	if retentionDays <= 0 {
-		log.WithContext(ctx).Debug("periodic access log cleanup disabled: retention days is 0 or negative")
+	if retentionDays < 0 {
+		log.WithContext(ctx).Debug("periodic access log cleanup disabled: retention days is negative")
 		return
 	}
 
+	if retentionDays == 0 {
+		retentionDays = 7
+		log.WithContext(ctx).Debugf("no retention days specified for access log cleanup, defaulting to %d days", retentionDays)
+	} else {
+		log.WithContext(ctx).Debugf("access log retention period set to %d days", retentionDays)
+	}
+
 	if cleanupIntervalHours <= 0 {
 		cleanupIntervalHours = 24
+		log.WithContext(ctx).Debugf("no cleanup interval specified for access log cleanup, defaulting to %d hours", cleanupIntervalHours)
+	} else {
+		log.WithContext(ctx).Debugf("access log cleanup interval set to %d hours", cleanupIntervalHours)
 	}
 
 	cleanupCtx, cancel := context.WithCancel(ctx)

management/internals/modules/reverseproxy/accesslogs/manager/manager_test.go

@@ -121,7 +121,7 @@ func TestCleanupWithExactBoundary(t *testing.T) {
 }
 
 func TestStartPeriodicCleanup(t *testing.T) {
-	t.Run("periodic cleanup disabled with zero retention", func(t *testing.T) {
+	t.Run("periodic cleanup disabled with negative retention", func(t *testing.T) {
 		ctrl := gomock.NewController(t)
 		defer ctrl.Finish()
 
@@ -135,7 +135,7 @@ func TestStartPeriodicCleanup(t *testing.T) {
 		ctx, cancel := context.WithCancel(context.Background())
 		defer cancel()
 
-		manager.StartPeriodicCleanup(ctx, 0, 1)
+		manager.StartPeriodicCleanup(ctx, -1, 1)
 
 		time.Sleep(100 * time.Millisecond)
 

management/internals/modules/reverseproxy/domain/domain.go

@@ -30,3 +30,8 @@ func (d *Domain) EventMeta() map[string]any {
 		"validated":      d.Validated,
 	}
 }
+
+func (d *Domain) Copy() *Domain {
+	dCopy := *d
+	return &dCopy
+}

management/internals/server/config/config.go

@@ -203,7 +203,7 @@ type ReverseProxy struct {
 
 	// AccessLogRetentionDays specifies the number of days to retain access logs.
 	// Logs older than this duration will be automatically deleted during cleanup.
-	// A value of 0 or negative means logs are kept indefinitely (no cleanup).
+	// A value of 0 will default to 7 days. Negative means logs are kept indefinitely (no cleanup).
 	AccessLogRetentionDays int
 
 	// AccessLogCleanupIntervalHours specifies how often (in hours) to run the cleanup routine.

management/server/account.go

@@ -742,11 +742,6 @@ func (am *DefaultAccountManager) DeleteAccount(ctx context.Context, accountID, u
 		return status.Errorf(status.Internal, "failed to build user infos for account %s: %v", accountID, err)
 	}
 
-	err = am.serviceManager.DeleteAllServices(ctx, accountID, userID)
-	if err != nil {
-		return status.Errorf(status.Internal, "failed to delete service %s: %v", accountID, err)
-	}
-
 	for _, otherUser := range account.Users {
 		if otherUser.Id == userID {
 			continue

management/server/account_test.go

@@ -15,7 +15,6 @@ import (
 	"time"
 
 	"github.com/golang/mock/gomock"
-	"github.com/netbirdio/netbird/shared/management/status"
 	"github.com/prometheus/client_golang/prometheus/push"
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
@@ -23,6 +22,9 @@ import (
 	"go.opentelemetry.io/otel/metric/noop"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
+	"github.com/netbirdio/netbird/shared/management/status"
+
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller"
@@ -1815,6 +1817,13 @@ func TestAccount_Copy(t *testing.T) {
 				Targets:   []*service.Target{},
 			},
 		},
+		Domains: []*domain.Domain{
+			{
+				ID:        "domain1",
+				Domain:    "test.com",
+				AccountID: "account1",
+			},
+		},
 		NetworkMapCache: &types.NetworkMapBuilder{},
 	}
 	account.InitOnce()

management/server/migration/migration.go

@@ -489,6 +489,102 @@ func MigrateJsonToTable[T any](ctx context.Context, db *gorm.DB, columnName stri
 	return nil
 }
 
+// hasForeignKey checks whether a foreign key constraint exists on the given table and column.
+func hasForeignKey(db *gorm.DB, table, column string) bool {
+	var count int64
+
+	switch db.Name() {
+	case "postgres":
+		db.Raw(`
+			SELECT COUNT(*) FROM information_schema.key_column_usage kcu
+			JOIN information_schema.table_constraints tc
+			  ON tc.constraint_name = kcu.constraint_name
+			  AND tc.table_schema = kcu.table_schema
+			WHERE tc.constraint_type = 'FOREIGN KEY'
+			  AND kcu.table_name = ?
+			  AND kcu.column_name = ?
+		`, table, column).Scan(&count)
+	case "mysql":
+		db.Raw(`
+			SELECT COUNT(*) FROM information_schema.key_column_usage
+			WHERE table_schema = DATABASE()
+			  AND table_name = ?
+			  AND column_name = ?
+			  AND referenced_table_name IS NOT NULL
+		`, table, column).Scan(&count)
+	default: // sqlite
+		type fkInfo struct {
+			From string
+		}
+		var fks []fkInfo
+		db.Raw(fmt.Sprintf("PRAGMA foreign_key_list(%s)", table)).Scan(&fks)
+		for _, fk := range fks {
+			if fk.From == column {
+				return true
+			}
+		}
+		return false
+	}
+
+	return count > 0
+}
+
+// CleanupOrphanedResources deletes rows from the table of model T where the foreign
+// key column (fkColumn) references a row in the table of model R that no longer exists.
+func CleanupOrphanedResources[T any, R any](ctx context.Context, db *gorm.DB, fkColumn string) error {
+	var model T
+	var refModel R
+
+	if !db.Migrator().HasTable(&model) {
+		log.WithContext(ctx).Debugf("table for %T does not exist, no cleanup needed", model)
+		return nil
+	}
+
+	if !db.Migrator().HasTable(&refModel) {
+		log.WithContext(ctx).Debugf("referenced table for %T does not exist, no cleanup needed", refModel)
+		return nil
+	}
+
+	stmtT := &gorm.Statement{DB: db}
+	if err := stmtT.Parse(&model); err != nil {
+		return fmt.Errorf("parse model %T: %w", model, err)
+	}
+	childTable := stmtT.Schema.Table
+
+	stmtR := &gorm.Statement{DB: db}
+	if err := stmtR.Parse(&refModel); err != nil {
+		return fmt.Errorf("parse reference model %T: %w", refModel, err)
+	}
+	parentTable := stmtR.Schema.Table
+
+	if !db.Migrator().HasColumn(&model, fkColumn) {
+		log.WithContext(ctx).Debugf("column %s does not exist in table %s, no cleanup needed", fkColumn, childTable)
+		return nil
+	}
+
+	// If a foreign key constraint already exists on the column, the DB itself
+	// enforces referential integrity and orphaned rows cannot exist.
+	if hasForeignKey(db, childTable, fkColumn) {
+		log.WithContext(ctx).Debugf("foreign key constraint for %s already exists on %s, no cleanup needed", fkColumn, childTable)
+		return nil
+	}
+
+	result := db.Exec(
+		fmt.Sprintf(
+			"DELETE FROM %s WHERE %s NOT IN (SELECT id FROM %s)",
+			childTable, fkColumn, parentTable,
+		),
+	)
+	if result.Error != nil {
+		return fmt.Errorf("cleanup orphaned rows in %s: %w", childTable, result.Error)
+	}
+
+	log.WithContext(ctx).Infof("Cleaned up %d orphaned rows from %s where %s had no matching row in %s",
+		result.RowsAffected, childTable, fkColumn, parentTable)
+
+	return nil
+}
+
 func RemoveDuplicatePeerKeys(ctx context.Context, db *gorm.DB) error {
 	if !db.Migrator().HasTable("peers") {
 		log.WithContext(ctx).Debug("peers table does not exist, skipping duplicate key cleanup")

management/server/migration/migration_test.go

@@ -441,3 +441,197 @@ func TestRemoveDuplicatePeerKeys_NoTable(t *testing.T) {
 	err := migration.RemoveDuplicatePeerKeys(context.Background(), db)
 	require.NoError(t, err, "Should not fail when table does not exist")
 }
+
+type testParent struct {
+	ID string `gorm:"primaryKey"`
+}
+
+func (testParent) TableName() string {
+	return "test_parents"
+}
+
+type testChild struct {
+	ID       string `gorm:"primaryKey"`
+	ParentID string
+}
+
+func (testChild) TableName() string {
+	return "test_children"
+}
+
+type testChildWithFK struct {
+	ID       string      `gorm:"primaryKey"`
+	ParentID string      `gorm:"index"`
+	Parent   *testParent `gorm:"foreignKey:ParentID"`
+}
+
+func (testChildWithFK) TableName() string {
+	return "test_children"
+}
+
+func setupOrphanTestDB(t *testing.T, models ...any) *gorm.DB {
+	t.Helper()
+	db := setupDatabase(t)
+	for _, m := range models {
+		_ = db.Migrator().DropTable(m)
+	}
+	err := db.AutoMigrate(models...)
+	require.NoError(t, err, "Failed to auto-migrate tables")
+	return db
+}
+
+func TestCleanupOrphanedResources_NoChildTable(t *testing.T) {
+	db := setupDatabase(t)
+	_ = db.Migrator().DropTable(&testChild{})
+	_ = db.Migrator().DropTable(&testParent{})
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err, "Should not fail when child table does not exist")
+}
+
+func TestCleanupOrphanedResources_NoParentTable(t *testing.T) {
+	db := setupDatabase(t)
+	_ = db.Migrator().DropTable(&testParent{})
+	_ = db.Migrator().DropTable(&testChild{})
+
+	err := db.AutoMigrate(&testChild{})
+	require.NoError(t, err)
+
+	err = migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err, "Should not fail when parent table does not exist")
+}
+
+func TestCleanupOrphanedResources_EmptyTables(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err, "Should not fail on empty tables")
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(0), count)
+}
+
+func TestCleanupOrphanedResources_NoOrphans(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testParent{ID: "p2"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c2", ParentID: "p2"}).Error)
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(2), count, "All children should remain when no orphans")
+}
+
+func TestCleanupOrphanedResources_AllOrphans(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c1", "gone1").Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c2", "gone2").Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c3", "gone3").Error)
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(0), count, "All orphaned children should be deleted")
+}
+
+func TestCleanupOrphanedResources_MixedValidAndOrphaned(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testParent{ID: "p2"}).Error)
+
+	require.NoError(t, db.Create(&testChild{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c2", ParentID: "p2"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c3", ParentID: "p1"}).Error)
+
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c4", "gone1").Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c5", "gone2").Error)
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var remaining []testChild
+	require.NoError(t, db.Order("id").Find(&remaining).Error)
+
+	assert.Len(t, remaining, 3, "Only valid children should remain")
+	assert.Equal(t, "c1", remaining[0].ID)
+	assert.Equal(t, "c2", remaining[1].ID)
+	assert.Equal(t, "c3", remaining[2].ID)
+}
+
+func TestCleanupOrphanedResources_Idempotent(t *testing.T) {
+	db := setupOrphanTestDB(t, &testParent{}, &testChild{})
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChild{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Exec("INSERT INTO test_children (id, parent_id) VALUES (?, ?)", "c2", "gone").Error)
+
+	ctx := context.Background()
+
+	err := migration.CleanupOrphanedResources[testChild, testParent](ctx, db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(1), count)
+
+	err = migration.CleanupOrphanedResources[testChild, testParent](ctx, db, "parent_id")
+	require.NoError(t, err)
+
+	db.Model(&testChild{}).Count(&count)
+	assert.Equal(t, int64(1), count, "Count should remain the same after second run")
+}
+
+func TestCleanupOrphanedResources_SkipsWhenForeignKeyExists(t *testing.T) {
+	engine := os.Getenv("NETBIRD_STORE_ENGINE")
+	if engine != "postgres" && engine != "mysql" {
+		t.Skip("FK constraint early-exit test requires postgres or mysql")
+	}
+
+	db := setupDatabase(t)
+	_ = db.Migrator().DropTable(&testChildWithFK{})
+	_ = db.Migrator().DropTable(&testParent{})
+
+	err := db.AutoMigrate(&testParent{}, &testChildWithFK{})
+	require.NoError(t, err)
+
+	require.NoError(t, db.Create(&testParent{ID: "p1"}).Error)
+	require.NoError(t, db.Create(&testParent{ID: "p2"}).Error)
+	require.NoError(t, db.Create(&testChildWithFK{ID: "c1", ParentID: "p1"}).Error)
+	require.NoError(t, db.Create(&testChildWithFK{ID: "c2", ParentID: "p2"}).Error)
+
+	switch engine {
+	case "postgres":
+		require.NoError(t, db.Exec("ALTER TABLE test_children DROP CONSTRAINT fk_test_children_parent").Error)
+		require.NoError(t, db.Exec("DELETE FROM test_parents WHERE id = ?", "p2").Error)
+		require.NoError(t, db.Exec(
+			"ALTER TABLE test_children ADD CONSTRAINT fk_test_children_parent "+
+				"FOREIGN KEY (parent_id) REFERENCES test_parents(id) NOT VALID",
+		).Error)
+	case "mysql":
+		require.NoError(t, db.Exec("SET FOREIGN_KEY_CHECKS = 0").Error)
+		require.NoError(t, db.Exec("ALTER TABLE test_children DROP FOREIGN KEY fk_test_children_parent").Error)
+		require.NoError(t, db.Exec("DELETE FROM test_parents WHERE id = ?", "p2").Error)
+		require.NoError(t, db.Exec(
+			"ALTER TABLE test_children ADD CONSTRAINT fk_test_children_parent "+
+				"FOREIGN KEY (parent_id) REFERENCES test_parents(id)",
+		).Error)
+		require.NoError(t, db.Exec("SET FOREIGN_KEY_CHECKS = 1").Error)
+	}
+
+	err = migration.CleanupOrphanedResources[testChildWithFK, testParent](context.Background(), db, "parent_id")
+	require.NoError(t, err)
+
+	var count int64
+	db.Model(&testChildWithFK{}).Count(&count)
+	assert.Equal(t, int64(2), count, "Both rows should survive — migration must skip when FK constraint exists")
+}

management/server/store/sql_store.go

@@ -396,6 +396,11 @@ func (s *SqlStore) DeleteAccount(ctx context.Context, account *types.Account) er
 			return result.Error
 		}
 
+		result = tx.Select(clause.Associations).Delete(account.Services, "account_id = ?", account.Id)
+		if result.Error != nil {
+			return result.Error
+		}
+
 		result = tx.Select(clause.Associations).Delete(account)
 		if result.Error != nil {
 			return result.Error
@@ -2099,7 +2104,8 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 		var createdAt, certIssuedAt sql.NullTime
 		var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
 		var mode, source, sourcePeer sql.NullString
-		var terminated sql.NullBool
+		var terminated, portAutoAssigned sql.NullBool
+		var listenPort sql.NullInt64
 		err := row.Scan(
 			&s.ID,
 			&s.AccountID,
@@ -2116,8 +2122,8 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 			&sessionPrivateKey,
 			&sessionPublicKey,
 			&mode,
-			&s.ListenPort,
-			&s.PortAutoAssigned,
+			&listenPort,
+			&portAutoAssigned,
 			&source,
 			&sourcePeer,
 			&terminated,
@@ -2164,6 +2170,12 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 		if terminated.Valid {
 			s.Terminated = terminated.Bool
 		}
+		if portAutoAssigned.Valid {
+			s.PortAutoAssigned = portAutoAssigned.Bool
+		}
+		if listenPort.Valid {
+			s.ListenPort = uint16(listenPort.Int64)
+		}
 		s.Targets = []*rpservice.Target{}
 		return &s, nil
 	})

management/server/store/sql_store_test.go

@@ -22,6 +22,8 @@ import (
 	"github.com/stretchr/testify/require"
 
 	nbdns "github.com/netbirdio/netbird/dns"
+	proxydomain "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
+	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/internals/modules/zones"
 	"github.com/netbirdio/netbird/management/internals/modules/zones/records"
 	resourceTypes "github.com/netbirdio/netbird/management/server/networks/resources/types"
@@ -350,6 +352,35 @@ func TestSqlite_DeleteAccount(t *testing.T) {
 		},
 	}
 
+	account.Services = []*rpservice.Service{
+		{
+			ID:        "service_id",
+			AccountID: account.Id,
+			Name:      "test service",
+			Domain:    "svc.example.com",
+			Enabled:   true,
+			Targets: []*rpservice.Target{
+				{
+					AccountID: account.Id,
+					ServiceID: "service_id",
+					Host:      "localhost",
+					Port:      8080,
+					Protocol:  "http",
+					Enabled:   true,
+				},
+			},
+		},
+	}
+
+	account.Domains = []*proxydomain.Domain{
+		{
+			ID:        "domain_id",
+			Domain:    "custom.example.com",
+			AccountID: account.Id,
+			Validated: true,
+		},
+	}
+
 	err = store.SaveAccount(context.Background(), account)
 	require.NoError(t, err)
 
@@ -411,6 +442,20 @@ func TestSqlite_DeleteAccount(t *testing.T) {
 		require.NoError(t, err, "expecting no error after removing DeleteAccount when searching for network resources")
 		require.Len(t, resources, 0, "expecting no network resources to be found after DeleteAccount")
 	}
+
+	domains, err := store.ListCustomDomains(context.Background(), account.Id)
+	require.NoError(t, err, "expecting no error after DeleteAccount when searching for custom domains")
+	require.Len(t, domains, 0, "expecting no custom domains to be found after DeleteAccount")
+
+	var services []*rpservice.Service
+	err = store.(*SqlStore).db.Model(&rpservice.Service{}).Find(&services, "account_id = ?", account.Id).Error
+	require.NoError(t, err, "expecting no error after DeleteAccount when searching for services")
+	require.Len(t, services, 0, "expecting no services to be found after DeleteAccount")
+
+	var targets []*rpservice.Target
+	err = store.(*SqlStore).db.Model(&rpservice.Target{}).Find(&targets, "account_id = ?", account.Id).Error
+	require.NoError(t, err, "expecting no error after DeleteAccount when searching for service targets")
+	require.Len(t, targets, 0, "expecting no service targets to be found after DeleteAccount")
 }
 
 func Test_GetAccount(t *testing.T) {

management/server/store/sqlstore_bench_test.go

@@ -20,6 +20,7 @@ import (
 	"github.com/stretchr/testify/assert"
 
 	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	resourceTypes "github.com/netbirdio/netbird/management/server/networks/resources/types"
 	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
@@ -265,6 +266,7 @@ func setupBenchmarkDB(b testing.TB) (*SqlStore, func(), string) {
 		&nbdns.NameServerGroup{}, &posture.Checks{}, &networkTypes.Network{},
 		&routerTypes.NetworkRouter{}, &resourceTypes.NetworkResource{},
 		&types.AccountOnboarding{}, &service.Service{}, &service.Target{},
+		&domain.Domain{},
 	}
 
 	for i := len(models) - 1; i >= 0; i-- {

management/server/store/store.go

@@ -448,6 +448,12 @@ func getMigrationsPreAuto(ctx context.Context) []migrationFunc {
 		func(db *gorm.DB) error {
 			return migration.RemoveDuplicatePeerKeys(ctx, db)
 		},
+		func(db *gorm.DB) error {
+			return migration.CleanupOrphanedResources[rpservice.Service, types.Account](ctx, db, "account_id")
+		},
+		func(db *gorm.DB) error {
+			return migration.CleanupOrphanedResources[domain.Domain, types.Account](ctx, db, "account_id")
+		},
 	}
 }
 

management/server/types/account.go

@@ -18,6 +18,7 @@ import (
 
 	"github.com/netbirdio/netbird/client/ssh/auth"
 	nbdns "github.com/netbirdio/netbird/dns"
+	proxydomain "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/internals/modules/zones"
 	"github.com/netbirdio/netbird/management/internals/modules/zones/records"
@@ -101,6 +102,7 @@ type Account struct {
 	DNSSettings            DNSSettings                       `gorm:"embedded;embeddedPrefix:dns_settings_"`
 	PostureChecks          []*posture.Checks                 `gorm:"foreignKey:AccountID;references:id"`
 	Services               []*service.Service                `gorm:"foreignKey:AccountID;references:id"`
+	Domains                []*proxydomain.Domain             `gorm:"foreignKey:AccountID;references:id"`
 	// Settings is a dictionary of Account settings
 	Settings         *Settings                        `gorm:"embedded;embeddedPrefix:settings_"`
 	Networks         []*networkTypes.Network          `gorm:"foreignKey:AccountID;references:id"`
@@ -911,6 +913,11 @@ func (a *Account) Copy() *Account {
 		services = append(services, svc.Copy())
 	}
 
+	domains := []*proxydomain.Domain{}
+	for _, domain := range a.Domains {
+		domains = append(domains, domain.Copy())
+	}
+
 	return &Account{
 		Id:                     a.Id,
 		CreatedBy:              a.CreatedBy,
@@ -936,6 +943,7 @@ func (a *Account) Copy() *Account {
 		Onboarding:             a.Onboarding,
 		NetworkMapCache:        a.NetworkMapCache,
 		nmapInitOnce:           a.nmapInitOnce,
+		Domains:                domains,
 	}
 }
 

shared/relay/client/client.go

@@ -333,7 +333,7 @@ func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
 	dialers := c.getDialers()
 
 	rd := dialer.NewRaceDial(c.log, dialer.DefaultConnectionTimeout, c.connectionURL, dialers...)
-	conn, err := rd.Dial()
+	conn, err := rd.Dial(ctx)
 	if err != nil {
 		return nil, err
 	}

shared/relay/client/dialer/race_dialer.go

@@ -40,10 +40,10 @@ func NewRaceDial(log *log.Entry, connectionTimeout time.Duration, serverURL stri
 	}
 }
 
-func (r *RaceDial) Dial() (net.Conn, error) {
+func (r *RaceDial) Dial(ctx context.Context) (net.Conn, error) {
 	connChan := make(chan dialResult, len(r.dialerFns))
 	winnerConn := make(chan net.Conn, 1)
-	abortCtx, abort := context.WithCancel(context.Background())
+	abortCtx, abort := context.WithCancel(ctx)
 	defer abort()
 
 	for _, dfn := range r.dialerFns {

shared/relay/client/dialer/race_dialer_test.go

@@ -78,7 +78,7 @@ func TestRaceDialEmptyDialers(t *testing.T) {
 	serverURL := "test.server.com"
 
 	rd := NewRaceDial(logger, DefaultConnectionTimeout, serverURL)
-	conn, err := rd.Dial()
+	conn, err := rd.Dial(context.Background())
 	if err == nil {
 		t.Errorf("Expected an error with empty dialers, got nil")
 	}
@@ -104,7 +104,7 @@ func TestRaceDialSingleSuccessfulDialer(t *testing.T) {
 	}
 
 	rd := NewRaceDial(logger, DefaultConnectionTimeout, serverURL, mockDialer)
-	conn, err := rd.Dial()
+	conn, err := rd.Dial(context.Background())
 	if err != nil {
 		t.Errorf("Expected no error, got %v", err)
 	}
@@ -137,7 +137,7 @@ func TestRaceDialMultipleDialersWithOneSuccess(t *testing.T) {
 	}
 
 	rd := NewRaceDial(logger, DefaultConnectionTimeout, serverURL, mockDialer1, mockDialer2)
-	conn, err := rd.Dial()
+	conn, err := rd.Dial(context.Background())
 	if err != nil {
 		t.Errorf("Expected no error, got %v", err)
 	}
@@ -160,7 +160,7 @@ func TestRaceDialTimeout(t *testing.T) {
 	}
 
 	rd := NewRaceDial(logger, 3*time.Second, serverURL, mockDialer)
-	conn, err := rd.Dial()
+	conn, err := rd.Dial(context.Background())
 	if err == nil {
 		t.Errorf("Expected an error, got nil")
 	}
@@ -188,7 +188,7 @@ func TestRaceDialAllDialersFail(t *testing.T) {
 	}
 
 	rd := NewRaceDial(logger, DefaultConnectionTimeout, serverURL, mockDialer1, mockDialer2)
-	conn, err := rd.Dial()
+	conn, err := rd.Dial(context.Background())
 	if err == nil {
 		t.Errorf("Expected an error, got nil")
 	}
@@ -230,7 +230,7 @@ func TestRaceDialFirstSuccessfulDialerWins(t *testing.T) {
 	}
 
 	rd := NewRaceDial(logger, DefaultConnectionTimeout, serverURL, mockDialer1, mockDialer2)
-	conn, err := rd.Dial()
+	conn, err := rd.Dial(context.Background())
 	if err != nil {
 		t.Errorf("Expected no error, got %v", err)
 	}