sendnrw/netbird
2
0
Fork 0
mirror of https://github.com/netbirdio/netbird.git synced 2026-07-23 17:01:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

[client] Fix blocked status lock via relay manager path (#6547)

Browse Source 
* peer/status: move relay-state reads off the main mux

GetRelayStates held d.mux (RLock) while calling into the relay
Manager (RelayStates/RelayConnectError/ServerURLs). Those calls can be
slow or block on the relay manager's own locks while it is reconnecting,
which kept the central Status mutex held and stalled every peer state
writer (UpdatePeerState, ReplaceOfflinePeers, etc.) contending for it.

Guard relayMgr/relayStates with a dedicated muxRelays mutex and release
it before invoking the relay Manager, so the relay read path no longer
contends with the hot peer-state writers on d.mux.

* peer/status: clone relay states in nil-manager path

Return a cloned snapshot of d.relayStates when relayMgr is nil so callers
cannot mutate the shared cached state, matching the non-nil path.
This commit is contained in:
Zoltan Papp
2026-06-28 12:45:33 +02:00
committed by GitHub
parent fd96b8c12f
commit 1b29995ece
1 changed files with 13 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
client/internal/peer/status.go
View File

@@ -192,6 +192,7 @@ func (s *StatusChangeSubscription) Events() chan map[string]RouterState {
// Pure read methods take RLock; anything that mutates state takes Lock.
type Status struct {
mux sync.RWMutex
muxRelays sync.RWMutex
peers map[string]State
ipToKey map[string]string
changeNotify map[string]map[string]*StatusChangeSubscription // map[peerID]map[subscriptionID]*StatusChangeSubscription
@@ -244,8 +245,8 @@ func NewRecorder(mgmAddress string) *Status {
}
func (d *Status) SetRelayMgr(manager *relayClient.Manager) {
d.mux.Lock()
defer d.mux.Unlock()
d.muxRelays.Lock()
defer d.muxRelays.Unlock()
d.relayMgr = manager
}
@@ -906,8 +907,8 @@ func (d *Status) MarkSignalConnected() {
}
func (d *Status) UpdateRelayStates(relayResults []relay.ProbeResult) {
d.mux.Lock()
defer d.mux.Unlock()
d.muxRelays.Lock()
defer d.muxRelays.Unlock()
d.relayStates = relayResults
}
@@ -1018,24 +1019,26 @@ func (d *Status) GetSignalState() SignalState {
// GetRelayStates returns the stun/turn/permanent relay states
func (d *Status) GetRelayStates() []relay.ProbeResult {
d.mux.RLock()
defer d.mux.RUnlock()
d.muxRelays.RLock()
if d.relayMgr == nil {
return d.relayStates
defer d.muxRelays.RUnlock()
return slices.Clone(d.relayStates)
}
relayMgr := d.relayMgr
// extend the list of stun, turn servers with the relay server connections
relayStates := slices.Clone(d.relayStates)
d.muxRelays.RUnlock()
states := d.relayMgr.RelayStates()
states := relayMgr.RelayStates()
if len(states) == 0 {
// no relay connection tracked yet; surface configured servers as
// unavailable with the real reconnect error when known
err := relayClient.ErrRelayClientNotConnected
if connErr := d.relayMgr.RelayConnectError(); connErr != nil {
if connErr := relayMgr.RelayConnectError(); connErr != nil {
err = connErr
}
for _, r := range d.relayMgr.ServerURLs() {
for _, r := range relayMgr.ServerURLs() {
relayStates = append(relayStates, relay.ProbeResult{
URI: r,
Err: err,