mirror of
https://github.com/netbirdio/netbird.git
synced 2026-05-20 15:49:55 +00:00
[management] Fence peer status updates with a session token (#6193)
* [management] Fence peer status updates with a session token The connect/disconnect path used a best-effort LastSeen-after-streamStart comparison to decide whether a status update should land. Under contention — a re-sync arriving while the previous stream's disconnect was still in flight, or two management replicas seeing the same peer at once — the check was a read-then-decide-then-write window: any UPDATE in between caused the wrong row to be written. The Go-side time.Now() that fed the comparison also drifted under lock contention, since it was captured seconds before the write actually committed. Replace it with an integer-nanosecond fencing token stored alongside the status. Every gRPC sync stream uses its open time (UnixNano) as its token. Connects only land when the incoming token is strictly greater than the stored one; disconnects only land when the incoming token equals the stored one (i.e. we're the stream that owns the current session). Both are single optimistic-locked UPDATEs — no read-then-write, no transaction wrapper. LastSeen is now written by the database itself (CURRENT_TIMESTAMP). The caller never supplies it, so the value always reflects the real moment of the UPDATE rather than the moment the caller queued the work — which was already off by minutes under heavy lock contention. Side effects (geo lookup, peer-login-expiration scheduling, network-map fan-out) are explicitly documented as running after the fence UPDATE commits, never inside it. Geo also skips the update when realIP equals the stored ConnectionIP, dropping a redundant SavePeerLocation call on same-IP reconnects. Tests cover the three semantic cases (matched disconnect lands, stale disconnect dropped, stale connect dropped) plus a 16-goroutine race test that asserts the highest token always wins. * [management] Add SessionStartedAt to peer status updates Stored `SessionStartedAt` for fencing token propagation across goroutines and updated database queries/functions to handle the new field. Removed outdated geolocation handling logic and adjusted tests for concurrency safety. * Rename `peer_status_required_approval` to `peer_status_requires_approval` in SQL store fields
This commit is contained in:
@@ -38,7 +38,8 @@ type MockAccountManager struct {
|
||||
GetUserFromUserAuthFunc func(ctx context.Context, userAuth auth.UserAuth) (*types.User, error)
|
||||
ListUsersFunc func(ctx context.Context, accountID string) ([]*types.User, error)
|
||||
GetPeersFunc func(ctx context.Context, accountID, userID, nameFilter, ipFilter string) ([]*nbpeer.Peer, error)
|
||||
MarkPeerConnectedFunc func(ctx context.Context, peerKey string, connected bool, realIP net.IP, syncTime time.Time) error
|
||||
MarkPeerConnectedFunc func(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error
|
||||
MarkPeerDisconnectedFunc func(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error
|
||||
SyncAndMarkPeerFunc func(ctx context.Context, accountID string, peerPubKey string, meta nbpeer.PeerSystemMeta, realIP net.IP, syncTime time.Time) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, int64, error)
|
||||
DeletePeerFunc func(ctx context.Context, accountID, peerKey, userID string) error
|
||||
GetNetworkMapFunc func(ctx context.Context, peerKey string) (*types.NetworkMap, error)
|
||||
@@ -227,7 +228,14 @@ func (am *MockAccountManager) SyncAndMarkPeer(ctx context.Context, accountID str
|
||||
return nil, nil, nil, 0, status.Errorf(codes.Unimplemented, "method MarkPeerConnected is not implemented")
|
||||
}
|
||||
|
||||
func (am *MockAccountManager) OnPeerDisconnected(_ context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
|
||||
func (am *MockAccountManager) OnPeerDisconnected(ctx context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
|
||||
// Mirror DefaultAccountManager.OnPeerDisconnected: drive the fencing
|
||||
// hook so tests that inject MarkPeerDisconnectedFunc actually observe
|
||||
// disconnect events. Falls through to nil when no hook is set, which
|
||||
// is the original behaviour.
|
||||
if am.MarkPeerDisconnectedFunc != nil {
|
||||
return am.MarkPeerDisconnectedFunc(ctx, peerPubKey, accountID, streamStartTime.UnixNano())
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -328,13 +336,21 @@ func (am *MockAccountManager) GetAccountIDByUserID(ctx context.Context, userAuth
|
||||
}
|
||||
|
||||
// MarkPeerConnected mock implementation of MarkPeerConnected from server.AccountManager interface
|
||||
func (am *MockAccountManager) MarkPeerConnected(ctx context.Context, peerKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error {
|
||||
func (am *MockAccountManager) MarkPeerConnected(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error {
|
||||
if am.MarkPeerConnectedFunc != nil {
|
||||
return am.MarkPeerConnectedFunc(ctx, peerKey, connected, realIP, syncTime)
|
||||
return am.MarkPeerConnectedFunc(ctx, peerKey, realIP, accountID, sessionStartedAt)
|
||||
}
|
||||
return status.Errorf(codes.Unimplemented, "method MarkPeerConnected is not implemented")
|
||||
}
|
||||
|
||||
// MarkPeerDisconnected mock implementation of MarkPeerDisconnected from server.AccountManager interface
|
||||
func (am *MockAccountManager) MarkPeerDisconnected(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error {
|
||||
if am.MarkPeerDisconnectedFunc != nil {
|
||||
return am.MarkPeerDisconnectedFunc(ctx, peerKey, accountID, sessionStartedAt)
|
||||
}
|
||||
return status.Errorf(codes.Unimplemented, "method MarkPeerDisconnected is not implemented")
|
||||
}
|
||||
|
||||
// DeleteAccount mock implementation of DeleteAccount from server.AccountManager interface
|
||||
func (am *MockAccountManager) DeleteAccount(ctx context.Context, accountID, userID string) error {
|
||||
if am.DeleteAccountFunc != nil {
|
||||
|
||||
Reference in New Issue
Block a user