perf(hotpath): add cpu_hotspot_ring bench and send-chain optimization plan

- Add measure_all to PeerMap and CidrSet impl blocks (hotpath::measure_all)
- Add [profile.hotpath] for samply-compatible builds (strip=false, debug=line-tables-only)
- Add cpu_hotspot_ring example: 2-node ring tunnel with data-plane flooding (~234K pps)
- Add plans/006-send-chain-cpu-optimization.md based on hotpath+samply 423M sample analysis
  Key findings: dashmap redundancy (14.9%), metrics overhead (8.3%), mpsc (14.1%)
  Target: reduce send_msg_internal from 3.26us to ~2us per packet

easytier/src/gateway/mod.rs

@@ -32,6 +32,7 @@ pub(crate) struct CidrSet {
     mapped_to_real: Arc<DashMap<cidr::Ipv4Cidr, cidr::Ipv4Cidr>>,
 }
 
+#[cfg_attr(feature = "hotpath", hotpath::measure_all)]
 impl CidrSet {
     pub fn new(global_ctx: ArcGlobalCtx) -> Self {
         let mut ret = Self {

easytier/src/peers/peer_map.rs

@@ -38,6 +38,7 @@ pub struct PeerMap {
     alive_client_urls: Arc<Mutex<multimap::MultiMap<url::Url, PeerConnId>>>,
 }
 
+#[cfg_attr(feature = "hotpath", hotpath::measure_all)]
 impl PeerMap {
     pub fn new(packet_send: PacketRecvChan, global_ctx: ArcGlobalCtx, my_peer_id: PeerId) -> Self {
         PeerMap {
@@ -132,7 +133,6 @@ impl PeerMap {
         peer_id == self.my_peer_id || self.peer_map.contains_key(&peer_id)
     }
 
-    #[cfg_attr(feature = "hotpath", hotpath::measure(impl_type = "PeerMap"))]
     pub async fn send_msg_directly(&self, msg: ZCPacket, dst_peer_id: PeerId) -> Result<(), Error> {
         if dst_peer_id == self.my_peer_id {
             let packet_send = self.packet_send.clone();
@@ -164,7 +164,6 @@ impl PeerMap {
         Ok(())
     }
 
-    #[cfg_attr(feature = "hotpath", hotpath::measure(impl_type = "PeerMap"))]
     pub async fn get_gateway_peer_id(
         &self,
         dst_peer_id: PeerId,