don't pin when only one routine

examples/config.yml

@@ -267,7 +267,7 @@ tun:
 
   # Linux only. pin_threads pins each tun reader/encrypt OS thread to a single CPU. This keeps every goroutine's
   # batched sends flowing through one XPS-selected NIC TX ring, so packets within a flow stay ordered on the wire
-  # instead of being sprayed across multiple TX rings and reordered. Not reloadable.
+  # instead of being sprayed across multiple TX rings and reordered. Not reloadable. Coerced to false if routines <= 1.
   #pin_threads: true
 
   # Linux only. cpu_affinity overrides which CPUs the tun reader threads pin to: a list of CPU IDs, one per routine

interface.go

@@ -202,6 +202,10 @@ func NewInterface(ctx context.Context, c *InterfaceConfig) (*Interface, error) {
 		return nil, errors.New("no connection manager")
 	}
 
+	if c.routines <= 1 {
+		c.PinThreads = false //pinning is not useful unless there's more than one tun reader
+	}
+
 	cs := c.pki.getCertState()
 	ifce := &Interface{
 		ctx:                   ctx,
@@ -388,10 +392,7 @@ func (f *Interface) listenOut(i int) {
 	f.l.Debug("underlay reader is done", "reader", i)
 }
 
-func (f *Interface) listenIn(queue tio.Queue, i int) {
+func (f *Interface) pinThisThread(i int) {
-	// Pinning this thread (and goroutine) to a single CPU keeps every sendmmsg from this goroutine going through the
-	// same TX ring on the nic, so the wire sees per-flow order. Skip entirely when tun.pin_threads is false.
-	if f.pinThreads {
 	var cpu int
 	if n := len(f.cpuAffinity); n > 0 {
 		// Explicit tun.cpu_affinity list wins; parseCpuAffinity already
@@ -410,6 +411,13 @@ func (f *Interface) listenIn(queue tio.Queue, i int) {
 	}
 }
 
+func (f *Interface) listenIn(queue tio.Queue, i int) {
+	// Pinning this thread (and goroutine) to a single CPU keeps every sendmmsg from this goroutine going through the
+	// same TX ring on the nic, so the wire sees per-flow order. Skip entirely when tun.pin_threads is false.
+	if f.pinThreads {
+		f.pinThisThread(i)
+	}
+
 	rejectBuf := make([]byte, mtu)
 	arenaSize := batch.SendBatchCap * (udp.MTU + 32)
 	sb := batch.NewSendBatch(f.writers[i], batch.SendBatchCap, arenaSize)