mirror of
https://github.com/netbirdio/netbird.git
synced 2026-09-25 16:19:07 +02:00
[relay] evict foreign client cache on disconnect (#6015)
* [relay] evict foreign client cache on disconnect When a foreign relay's TCP connection drops, the manager's onServerDisconnected handler only triggered reconnect logic for the home server; the disconnected foreign entry stayed in the relayClients cache. Subsequent OpenConn calls reused the closed client until the 60-second cleanup tick evicted it, breaking peer connectivity through that relay for up to a minute. Evict the foreign entry from the cache on disconnect so the next OpenConn dials a fresh client. Also: - Make the reconnect backoff cap configurable via WithMaxBackoffInterval ManagerOption; the previous hard-coded 60s constant forced TestAutoReconnect to sleep ~61s. Test now polls Ready() and finishes in ~2s. - Add NB_HOME_RELAY_SERVERS env var that overrides the relay URL list received from management, so a peer can be pinned to a specific home relay (used by the netbird-conn-lab Edge 4 reproducer). * [client] treat empty NB_HOME_RELAY_SERVERS as unset Returning (urls=[], ok=true) when the env var contained only separators or whitespace caused callers to wipe the mgmt-provided relay list, leaving the peer with no relays. Treat a parsed-empty result the same as an unset env.
This commit is contained in:
@@ -2,6 +2,7 @@ package client
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -360,7 +361,8 @@ func TestAutoReconnect(t *testing.T) {
|
||||
t.Fatalf("failed to serve manager: %s", err)
|
||||
}
|
||||
|
||||
clientAlice := NewManager(mCtx, toURL(srvCfg), "alice", iface.DefaultMTU)
|
||||
clientAlice := NewManager(mCtx, toURL(srvCfg), "alice", iface.DefaultMTU,
|
||||
WithMaxBackoffInterval(2*time.Second))
|
||||
err = clientAlice.Serve()
|
||||
if err != nil {
|
||||
t.Fatalf("failed to serve manager: %s", err)
|
||||
@@ -384,7 +386,9 @@ func TestAutoReconnect(t *testing.T) {
|
||||
}
|
||||
|
||||
log.Infof("waiting for reconnection")
|
||||
time.Sleep(reconnectingTimeout + 1*time.Second)
|
||||
if err := waitForReady(ctx, clientAlice, 15*time.Second); err != nil {
|
||||
t.Fatalf("manager did not reconnect: %s", err)
|
||||
}
|
||||
|
||||
log.Infof("reopent the connection")
|
||||
_, err = clientAlice.OpenConn(ctx, ra, "bob")
|
||||
@@ -393,6 +397,21 @@ func TestAutoReconnect(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func waitForReady(ctx context.Context, m *Manager, timeout time.Duration) error {
|
||||
deadline := time.Now().Add(timeout)
|
||||
for time.Now().Before(deadline) {
|
||||
if m.Ready() {
|
||||
return nil
|
||||
}
|
||||
select {
|
||||
case <-time.After(100 * time.Millisecond):
|
||||
case <-ctx.Done():
|
||||
return ctx.Err()
|
||||
}
|
||||
}
|
||||
return fmt.Errorf("manager not ready within %s", timeout)
|
||||
}
|
||||
|
||||
func TestNotifierDoubleAdd(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user