v4.8.16

changelog.md

@@ -1,5 +1,70 @@
 # Changelog
 
+## 2026-03-17 - 4.8.16 - fix(release)
+bump package version to 4.8.15
+
+- Updates the package.json version field from 4.8.13 to 4.8.15.
+
+## 2026-03-17 - 4.8.13 - fix(remoteingress-protocol)
+require a flush after each written frame to bound TLS buffer growth
+
+- Remove the unflushed byte threshold and stop queueing additional writes while a flush is pending
+- Simplify write and flush error logging after dropping unflushed byte tracking
+- Update tunnel I/O comments to reflect the stricter flush behavior that avoids OOM and connection resets
+
+## 2026-03-17 - 4.8.12 - fix(tunnel)
+prevent tunnel backpressure buffering from exhausting memory and cancel stream handlers before TLS shutdown
+
+- stop self-waking and writing new frames while a flush is pending to avoid unbounded TLS session buffer growth under load
+- reorder edge and hub shutdown cleanup so stream cancellation happens before TLS close_notify, preventing handlers from blocking on dead channels
+- add load tests covering sustained large transfers, burst traffic, and rapid stream churn to verify tunnel stability
+
+## 2026-03-17 - 4.8.11 - fix(remoteingress-core)
+stop data frame send loops promptly when stream cancellation is triggered
+
+- Use cancellation-aware tokio::select! around data channel sends in both edge and hub stream forwarding paths
+- Prevent stalled or noisy shutdown behavior when stream or client cancellation happens while awaiting frame delivery
+
+## 2026-03-17 - 4.8.10 - fix(remoteingress-core)
+guard tunnel frame sends with cancellation to prevent async send deadlocks
+
+- Wrap OPEN, CLOSE, CLOSE_BACK, WINDOW_UPDATE, and cleanup channel sends in cancellation-aware tokio::select! blocks.
+- Avoid indefinite blocking when tunnel, stream, or writer tasks are cancelled while awaiting channel capacity.
+- Improve shutdown reliability for edge and hub stream handling under tunnel failure conditions.
+
+## 2026-03-17 - 4.8.9 - fix(repo)
+no changes to commit
+
+
+## 2026-03-17 - 4.8.8 - fix(remoteingress-core)
+cancel stale edge connections when an edge reconnects
+
+- Remove any existing edge entry before registering a reconnected edge
+- Trigger the previous connection's cancellation token so stale sessions shut down immediately instead of waiting for TCP keepalive
+
+## 2026-03-17 - 4.8.7 - fix(remoteingress-core)
+perform graceful TLS shutdown on edge and hub tunnel streams
+
+- Send TLS close_notify before cleanup to avoid peer disconnect warnings on both tunnel endpoints
+- Wrap stream shutdown in a 2 second timeout so connection teardown does not block cleanup
+
+## 2026-03-17 - 4.8.6 - fix(remoteingress-core)
+initialize disconnect reason only when set in hub loop break paths
+
+- Replace the default "unknown" disconnect reason with an explicitly assigned string and document that all hub loop exits set it before use
+- Add an allow attribute for unused assignments to avoid warnings around the deferred initialization pattern
+
+## 2026-03-17 - 4.8.5 - fix(repo)
+no changes to commit
+
+
+## 2026-03-17 - 4.8.4 - fix(remoteingress-core)
+prevent stream stalls by guaranteeing flow-control updates and avoiding bounded per-stream channel overflows
+
+- Replace bounded per-stream data channels with unbounded channels on edge and hub, relying on existing WINDOW_UPDATE flow control to limit bytes in flight
+- Use awaited sends for FRAME_WINDOW_UPDATE and FRAME_WINDOW_UPDATE_BACK so updates are not dropped and streams do not deadlock under backpressure
+- Clean up stream state when channel receivers have already exited instead of closing active streams because a bounded queue filled
+
 ## 2026-03-17 - 4.8.3 - fix(protocol,edge)
 optimize tunnel frame handling and zero-copy uploads in edge I/O
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@serve.zone/remoteingress",
-  "version": "4.8.3",
+  "version": "4.8.16",
   "private": false,
   "description": "Edge ingress tunnel for DcRouter - accepts incoming TCP connections at network edge and tunnels them to DcRouter SmartProxy preserving client IP via PROXY protocol v1.",
   "main": "dist_ts/index.js",

rust/crates/remoteingress-core/src/edge.rs

@@ -24,8 +24,9 @@ enum EdgeFrameAction {
 
 /// Per-stream state tracked in the edge's client_writers map.
 struct EdgeStreamState {
-    /// Channel to deliver FRAME_DATA_BACK payloads to the hub_to_client task.
+    /// Unbounded channel to deliver FRAME_DATA_BACK payloads to the hub_to_client task.
-    back_tx: mpsc::Sender<Vec<u8>>,
+    /// Unbounded because flow control (WINDOW_UPDATE) already limits bytes-in-flight.
+    back_tx: mpsc::UnboundedSender<Vec<u8>>,
     /// Send window for FRAME_DATA (upload direction).
     /// Decremented by the client reader, incremented by FRAME_WINDOW_UPDATE_BACK from hub.
     send_window: Arc<AtomicU32>,
@@ -300,10 +301,13 @@ async fn handle_edge_frame(
 ) -> EdgeFrameAction {
     match frame.frame_type {
         FRAME_DATA_BACK => {
+            // Dispatch to per-stream unbounded channel. Flow control (WINDOW_UPDATE)
+            // limits bytes-in-flight, so the channel won't grow unbounded. send() only
+            // fails if the receiver is dropped (hub_to_client task already exited).
             let mut writers = client_writers.lock().await;
             if let Some(state) = writers.get(&frame.stream_id) {
-                if state.back_tx.try_send(frame.payload).is_err() {
+                if state.back_tx.send(frame.payload).is_err() {
-                    log::warn!("Stream {} back-channel full, closing", frame.stream_id);
+                    // Receiver dropped — hub_to_client task already exited, clean up
                     writers.remove(&frame.stream_id);
                 }
             }
@@ -515,6 +519,7 @@ async fn connect_to_hub_and_run(
     // Single-owner I/O engine — no tokio::io::split, no mutex
     let mut tunnel_io = remoteingress_protocol::TunnelIo::new(tls_stream, Vec::new());
 
+
     let liveness_timeout_dur = Duration::from_secs(45);
     let mut last_activity = Instant::now();
     let mut liveness_deadline = Box::pin(sleep_until(last_activity + liveness_timeout_dur));
@@ -583,13 +588,23 @@ async fn connect_to_hub_and_run(
         }
     };
 
-    // Cleanup
+    // Cancel stream tokens FIRST so stream handlers exit immediately.
+    // If we TLS-shutdown first, stream handlers are stuck sending to dead channels
+    // for up to 2 seconds while the shutdown times out on a dead connection.
     connection_token.cancel();
     stun_handle.abort();
     for (_, h) in port_listeners.drain() {
         h.abort();
     }
 
+    // Graceful TLS shutdown: send close_notify so the hub sees a clean disconnect.
+    // Stream handlers are already cancelled, so no new data is being produced.
+    let mut tls_stream = tunnel_io.into_inner();
+    let _ = tokio::time::timeout(
+        Duration::from_secs(2),
+        tls_stream.shutdown(),
+    ).await;
+
     result
 }
 
@@ -727,12 +742,18 @@ async fn handle_client_connection(
     // Send OPEN frame with PROXY v1 header via control channel
     let proxy_header = build_proxy_v1_header(&client_ip, edge_ip, client_port, dest_port);
     let open_frame = encode_frame(stream_id, FRAME_OPEN, proxy_header.as_bytes());
-    if tunnel_ctrl_tx.send(open_frame).await.is_err() {
+    let send_ok = tokio::select! {
+        result = tunnel_ctrl_tx.send(open_frame) => result.is_ok(),
+        _ = client_token.cancelled() => false,
+    };
+    if !send_ok {
         return;
     }
 
-    // Set up channel for data coming back from hub (capacity 16 is sufficient with flow control)
+    // Per-stream unbounded back-channel. Flow control (WINDOW_UPDATE) limits
-    let (back_tx, mut back_rx) = mpsc::channel::<Vec<u8>>(1024);
+    // bytes-in-flight, so this won't grow unbounded. Unbounded avoids killing
+    // streams due to channel overflow — backpressure slows streams, never kills them.
+    let (back_tx, mut back_rx) = mpsc::unbounded_channel::<Vec<u8>>();
     // Adaptive initial window: scale with current stream count to keep total in-flight
     // data within the 32MB budget. Prevents burst flooding when many streams open.
     let initial_window = remoteingress_protocol::compute_window_for_stream_count(
@@ -779,10 +800,16 @@ async fn handle_client_connection(
                             if consumed_since_update >= threshold {
                                 let increment = consumed_since_update.min(adaptive_window);
                                 let frame = encode_window_update(stream_id, FRAME_WINDOW_UPDATE, increment);
-                                if wu_tx.try_send(frame).is_ok() {
+                                // Use send().await for guaranteed delivery — dropping WINDOW_UPDATEs
-                                    consumed_since_update -= increment;
+                                // causes permanent flow stalls. Safe: runs in per-stream task, not main loop.
+                                tokio::select! {
+                                    result = wu_tx.send(frame) => {
+                                        if result.is_ok() {
+                                            consumed_since_update -= increment;
+                                        }
+                                    }
+                                    _ = hub_to_client_token.cancelled() => break,
                                 }
-                                // If try_send fails, keep accumulating — retry on next threshold
                             }
                         }
                         None => break,
@@ -794,7 +821,10 @@ async fn handle_client_connection(
         // Send final window update for any remaining consumed bytes
         if consumed_since_update > 0 {
             let frame = encode_window_update(stream_id, FRAME_WINDOW_UPDATE, consumed_since_update);
-            let _ = wu_tx.try_send(frame);
+            tokio::select! {
+                _ = wu_tx.send(frame) => {}
+                _ = hub_to_client_token.cancelled() => {}
+            }
         }
         let _ = client_write.shutdown().await;
     });
@@ -846,10 +876,11 @@ async fn handle_client_connection(
                         send_window.fetch_sub(n as u32, Ordering::Release);
                         encode_frame_header(&mut buf, stream_id, FRAME_DATA, n);
                         let data_frame = buf[..FRAME_HEADER_SIZE + n].to_vec();
-                        if tunnel_data_tx.send(data_frame).await.is_err() {
+                        let sent = tokio::select! {
-                            log::warn!("Stream {} data channel closed, closing", stream_id);
+                            result = tunnel_data_tx.send(data_frame) => result.is_ok(),
-                            break;
+                            _ = client_token.cancelled() => false,
-                        }
+                        };
+                        if !sent { break; }
                     }
                     Err(_) => break,
                 }
@@ -870,9 +901,13 @@ async fn handle_client_connection(
     ).await;
 
     // NOW send CLOSE — the response has been fully delivered (or timed out).
+    // select! with cancellation guard prevents indefinite blocking if tunnel dies.
     if !client_token.is_cancelled() {
         let close_frame = encode_frame(stream_id, FRAME_CLOSE, &[]);
-        let _ = tunnel_data_tx.send(close_frame).await;
+        tokio::select! {
+            _ = tunnel_data_tx.send(close_frame) => {}
+            _ = client_token.cancelled() => {}
+        }
     }
 
     // Clean up

rust/crates/remoteingress-core/src/hub.rs

@@ -14,10 +14,6 @@ use remoteingress_protocol::*;
 
 type HubTlsStream = tokio_rustls::server::TlsStream<TcpStream>;
 
-/// Per-stream data channel capacity. With 4MB window and 32KB frames,
-/// at most ~128 frames are in-flight. 256 provides comfortable headroom.
-const PER_STREAM_DATA_CAPACITY: usize = 256;
-
 /// Result of processing a frame.
 #[allow(dead_code)]
 enum FrameAction {
@@ -27,8 +23,10 @@ enum FrameAction {
 
 /// Per-stream state tracked in the hub's stream map.
 struct HubStreamState {
-    /// Channel to deliver FRAME_DATA payloads to the upstream writer task.
+    /// Unbounded channel to deliver FRAME_DATA payloads to the upstream writer task.
-    data_tx: mpsc::Sender<Vec<u8>>,
+    /// Unbounded because flow control (WINDOW_UPDATE) already limits bytes-in-flight.
+    /// A bounded channel would kill streams instead of applying backpressure.
+    data_tx: mpsc::UnboundedSender<Vec<u8>>,
     /// Cancellation token for this stream.
     cancel_token: CancellationToken,
     /// Send window for FRAME_DATA_BACK (download direction).
@@ -138,7 +136,7 @@ struct ConnectedEdgeInfo {
     peer_addr: String,
     edge_stream_count: Arc<AtomicU32>,
     config_tx: mpsc::Sender<EdgeConfigUpdate>,
-    #[allow(dead_code)] // kept alive for Drop — cancels child tokens when edge is removed
+    /// Used to cancel the old connection when an edge reconnects.
     cancel_token: CancellationToken,
 }
 
@@ -348,7 +346,7 @@ async fn handle_hub_frame(
             });
 
             // Create channel for data from edge to this stream
-            let (stream_data_tx, mut stream_data_rx) = mpsc::channel::<Vec<u8>>(PER_STREAM_DATA_CAPACITY);
+            let (stream_data_tx, mut stream_data_rx) = mpsc::unbounded_channel::<Vec<u8>>();
             // Adaptive initial window: scale with current stream count
             // to keep total in-flight data within the 32MB budget.
             let initial_window = compute_window_for_stream_count(
@@ -426,10 +424,16 @@ async fn handle_hub_frame(
                                             if consumed_since_update >= threshold {
                                                 let increment = consumed_since_update.min(adaptive_window);
                                                 let frame = encode_window_update(stream_id, FRAME_WINDOW_UPDATE_BACK, increment);
-                                                if wub_tx.try_send(frame).is_ok() {
+                                                // Use send().await for guaranteed delivery — dropping WINDOW_UPDATEs
-                                                    consumed_since_update -= increment;
+                                                // causes permanent flow stalls. Safe: runs in per-stream task, not main loop.
+                                                tokio::select! {
+                                                    result = wub_tx.send(frame) => {
+                                                        if result.is_ok() {
+                                                            consumed_since_update -= increment;
+                                                        }
+                                                    }
+                                                    _ = writer_token.cancelled() => break,
                                                 }
-                                                // If try_send fails, keep accumulating — retry on next threshold
                                             }
                                         }
                                         None => break,
@@ -441,7 +445,10 @@ async fn handle_hub_frame(
                         // Send final window update for remaining consumed bytes
                         if consumed_since_update > 0 {
                             let frame = encode_window_update(stream_id, FRAME_WINDOW_UPDATE_BACK, consumed_since_update);
-                            let _ = wub_tx.try_send(frame);
+                            tokio::select! {
+                                _ = wub_tx.send(frame) => {}
+                                _ = writer_token.cancelled() => {}
+                            }
                         }
                         let _ = up_write.shutdown().await;
                     });
@@ -494,10 +501,11 @@ async fn handle_hub_frame(
                                         send_window.fetch_sub(n as u32, Ordering::Release);
                                         encode_frame_header(&mut buf, stream_id, FRAME_DATA_BACK, n);
                                         let frame = buf[..FRAME_HEADER_SIZE + n].to_vec();
-                                        if data_writer_tx.send(frame).await.is_err() {
+                                        let sent = tokio::select! {
-                                            log::warn!("Stream {} data channel closed, closing", stream_id);
+                                            result = data_writer_tx.send(frame) => result.is_ok(),
-                                            break;
+                                            _ = stream_token.cancelled() => false,
-                                        }
+                                        };
+                                        if !sent { break; }
                                     }
                                     Err(_) => break,
                                 }
@@ -507,10 +515,13 @@ async fn handle_hub_frame(
                     }
 
                     // Send CLOSE_BACK via DATA channel (must arrive AFTER last DATA_BACK).
-                    // Use send().await to guarantee delivery (try_send silently drops if full).
+                    // select! with cancellation guard prevents indefinite blocking if tunnel dies.
                     if !stream_token.is_cancelled() {
                         let close_frame = encode_frame(stream_id, FRAME_CLOSE_BACK, &[]);
-                        let _ = data_writer_tx.send(close_frame).await;
+                        tokio::select! {
+                            _ = data_writer_tx.send(close_frame) => {}
+                            _ = stream_token.cancelled() => {}
+                        }
                     }
 
                     writer_for_edge_data.abort();
@@ -521,27 +532,32 @@ async fn handle_hub_frame(
                 if let Err(e) = result {
                     log::error!("Stream {} error: {}", stream_id, e);
                     // Send CLOSE_BACK via DATA channel on error (must arrive after any DATA_BACK).
-                    // Use send().await to guarantee delivery.
                     if !stream_token.is_cancelled() {
                         let close_frame = encode_frame(stream_id, FRAME_CLOSE_BACK, &[]);
-                        let _ = data_writer_tx.send(close_frame).await;
+                        tokio::select! {
+                            _ = data_writer_tx.send(close_frame) => {}
+                            _ = stream_token.cancelled() => {}
+                        }
                     }
                 }
 
-                // Signal main loop to remove stream from the map
+                // Signal main loop to remove stream from the map.
-                let _ = cleanup.send(stream_id).await;
+                // Cancellation guard prevents indefinite blocking if cleanup channel is full.
+                tokio::select! {
+                    _ = cleanup.send(stream_id) => {}
+                    _ = stream_token.cancelled() => {}
+                }
                 stream_counter.fetch_sub(1, Ordering::Relaxed);
             });
         }
         FRAME_DATA => {
-            // Non-blocking dispatch to per-stream channel.
+            // Dispatch to per-stream unbounded channel. Flow control (WINDOW_UPDATE)
-            // With flow control, the sender should rarely exceed the channel capacity.
+            // limits bytes-in-flight, so the channel won't grow unbounded. send() only
+            // fails if the receiver is dropped (stream handler already exited).
             if let Some(state) = streams.get(&frame.stream_id) {
-                if state.data_tx.try_send(frame.payload).is_err() {
+                if state.data_tx.send(frame.payload).is_err() {
-                    log::warn!("Stream {} data channel full, closing stream", frame.stream_id);
+                    // Receiver dropped — stream handler already exited, clean up
-                    if let Some(state) = streams.remove(&frame.stream_id) {
+                    streams.remove(&frame.stream_id);
-                        state.cancel_token.cancel();
-                    }
                 }
             }
         }
@@ -674,6 +690,13 @@ async fn handle_edge_connection(
 
     {
         let mut edges = connected.lock().await;
+        // If this edge already has an active connection (reconnect scenario),
+        // cancel the old connection so it shuts down immediately instead of
+        // lingering until TCP keepalive detects the dead socket.
+        if let Some(old) = edges.remove(&edge_id) {
+            log::info!("Edge {} reconnected, cancelling old connection", edge_id);
+            old.cancel_token.cancel();
+        }
         edges.insert(
             edge_id.clone(),
             ConnectedEdgeInfo {
@@ -732,7 +755,10 @@ async fn handle_edge_connection(
     // Single-owner I/O engine — no tokio::io::split, no mutex
     let mut tunnel_io = remoteingress_protocol::TunnelIo::new(tls_stream, Vec::new());
 
-    let mut disconnect_reason = "unknown".to_string();
+
+    // Assigned in every break path of the hub_loop before use at the end.
+    #[allow(unused_assignments)]
+    let mut disconnect_reason = String::new();
 
     'hub_loop: loop {
         // Drain completed stream cleanups from spawned tasks
@@ -819,9 +845,19 @@ async fn handle_edge_connection(
         }
     }
 
-    // Cleanup: cancel edge token to propagate to all child tasks
+    // Cancel stream tokens FIRST so stream handlers exit immediately.
+    // If we TLS-shutdown first, stream handlers are stuck sending to dead channels
+    // for up to 2 seconds while the shutdown times out on a dead connection.
     edge_token.cancel();
     config_handle.abort();
+
+    // Graceful TLS shutdown: send close_notify so the edge sees a clean disconnect.
+    // Stream handlers are already cancelled, so no new data is being produced.
+    let mut tls_stream = tunnel_io.into_inner();
+    let _ = tokio::time::timeout(
+        Duration::from_secs(2),
+        tls_stream.shutdown(),
+    ).await;
     {
         let mut edges = connected.lock().await;
         edges.remove(&edge_id);

rust/crates/remoteingress-protocol/src/lib.rs

@@ -312,11 +312,11 @@ impl<S: AsyncRead + AsyncWrite + Unpin> TunnelIo<S> {
         cancel_token: &tokio_util::sync::CancellationToken,
     ) -> Poll<TunnelEvent> {
         // 1. WRITE: drain ctrl queue first, then data queue.
-        //    TLS poll_write writes plaintext to session buffer (always Ready).
+        //    Write one frame, set flush_needed, then flush must complete before
-        //    Batch up to 16 frames per poll cycle.
+        //    writing more. This prevents unbounded TLS session buffer growth.
         //    Safe: `self.write` and `self.stream` are disjoint fields.
         let mut writes = 0;
-        while self.write.has_work() && writes < 16 {
+        while self.write.has_work() && writes < 16 && !self.write.flush_needed {
             let from_ctrl = !self.write.ctrl_queue.is_empty();
             let frame = if from_ctrl {
                 self.write.ctrl_queue.front().unwrap()
@@ -327,6 +327,8 @@ impl<S: AsyncRead + AsyncWrite + Unpin> TunnelIo<S> {
 
             match Pin::new(&mut self.stream).poll_write(cx, remaining) {
                 Poll::Ready(Ok(0)) => {
+                    log::error!("TunnelIo: poll_write returned 0 (write zero), ctrl_q={} data_q={}",
+                        self.write.ctrl_queue.len(), self.write.data_queue.len());
                     return Poll::Ready(TunnelEvent::WriteError(
                         std::io::Error::new(std::io::ErrorKind::WriteZero, "write zero"),
                     ));
@@ -341,7 +343,11 @@ impl<S: AsyncRead + AsyncWrite + Unpin> TunnelIo<S> {
                         writes += 1;
                     }
                 }
-                Poll::Ready(Err(e)) => return Poll::Ready(TunnelEvent::WriteError(e)),
+                Poll::Ready(Err(e)) => {
+                    log::error!("TunnelIo: poll_write error: {} (ctrl_q={} data_q={})",
+                        e, self.write.ctrl_queue.len(), self.write.data_queue.len());
+                    return Poll::Ready(TunnelEvent::WriteError(e));
+                }
                 Poll::Pending => break,
             }
         }
@@ -349,8 +355,13 @@ impl<S: AsyncRead + AsyncWrite + Unpin> TunnelIo<S> {
         // 2. FLUSH: push encrypted data from TLS session to TCP.
         if self.write.flush_needed {
             match Pin::new(&mut self.stream).poll_flush(cx) {
-                Poll::Ready(Ok(())) => self.write.flush_needed = false,
+                Poll::Ready(Ok(())) => {
-                Poll::Ready(Err(e)) => return Poll::Ready(TunnelEvent::WriteError(e)),
+                    self.write.flush_needed = false;
+                }
+                Poll::Ready(Err(e)) => {
+                    log::error!("TunnelIo: poll_flush error: {}", e);
+                    return Poll::Ready(TunnelEvent::WriteError(e));
+                }
                 Poll::Pending => {} // TCP waker will notify us
             }
         }
@@ -386,12 +397,19 @@ impl<S: AsyncRead + AsyncWrite + Unpin> TunnelIo<S> {
                     // Partial data — loop to call poll_read again so the TCP
                     // waker is re-registered when it finally returns Pending.
                 }
-                Poll::Ready(Err(e)) => return Poll::Ready(TunnelEvent::ReadError(e)),
+                Poll::Ready(Err(e)) => {
+                    log::error!("TunnelIo: poll_read error: {}", e);
+                    return Poll::Ready(TunnelEvent::ReadError(e));
+                }
                 Poll::Pending => break,
             }
         }
 
-        // 4. CHANNELS: drain ctrl into ctrl_queue, data into data_queue.
+        // 4. CHANNELS: drain ctrl (always — priority), data (only if queue is small).
+        //    Ctrl frames must never be delayed — always drain fully.
+        //    Data frames are gated: keep data in the bounded channel for proper
+        //    backpressure when TLS writes are slow. Without this gate, the internal
+        //    data_queue (unbounded VecDeque) grows to hundreds of MB under throttle → OOM.
         let mut got_new = false;
         loop {
             match ctrl_rx.poll_recv(cx) {
@@ -404,15 +422,17 @@ impl<S: AsyncRead + AsyncWrite + Unpin> TunnelIo<S> {
                 Poll::Pending => break,
             }
         }
-        loop {
+        if self.write.data_queue.len() < 64 {
-            match data_rx.poll_recv(cx) {
+            loop {
-                Poll::Ready(Some(frame)) => { self.write.data_queue.push_back(frame); got_new = true; }
+                match data_rx.poll_recv(cx) {
-                Poll::Ready(None) => {
+                    Poll::Ready(Some(frame)) => { self.write.data_queue.push_back(frame); got_new = true; }
-                    return Poll::Ready(TunnelEvent::WriteError(
+                    Poll::Ready(None) => {
-                        std::io::Error::new(std::io::ErrorKind::BrokenPipe, "data channel closed"),
+                        return Poll::Ready(TunnelEvent::WriteError(
-                    ));
+                            std::io::Error::new(std::io::ErrorKind::BrokenPipe, "data channel closed"),
+                        ));
+                    }
+                    Poll::Pending => break,
                 }
-                Poll::Pending => break,
             }
         }
 
@@ -424,10 +444,12 @@ impl<S: AsyncRead + AsyncWrite + Unpin> TunnelIo<S> {
             return Poll::Ready(TunnelEvent::Cancelled);
         }
 
-        // 6. SELF-WAKE: only when we have frames AND flush is done.
+        // 6. SELF-WAKE: only when flush is complete AND we have work.
-        //    If flush is pending, the TCP write-readiness waker will notify us.
+        //    When flush is Pending, the TCP write-readiness waker will notify us.
-        //    If we got new channel frames, wake to write them.
+        //    CRITICAL: do NOT self-wake when flush_needed — poll_write always returns
-        if got_new || (!self.write.flush_needed && self.write.has_work()) {
+        //    Ready (TLS buffers in-memory), so self-waking causes a tight spin loop
+        //    that fills the TLS session buffer unboundedly -> OOM -> ECONNRESET.
+        if !self.write.flush_needed && (got_new || self.write.has_work()) {
             cx.waker().wake_by_ref();
         }
 

test/test.loadtest.node.ts

@@ -0,0 +1,402 @@
+import { expect, tap } from '@push.rocks/tapbundle';
+import * as net from 'net';
+import * as stream from 'stream';
+import * as crypto from 'crypto';
+import { RemoteIngressHub, RemoteIngressEdge } from '../ts/index.js';
+
+// ---------------------------------------------------------------------------
+// Helpers (self-contained — same patterns as test.flowcontrol.node.ts)
+// ---------------------------------------------------------------------------
+
+async function findFreePorts(count: number): Promise<number[]> {
+  const servers: net.Server[] = [];
+  const ports: number[] = [];
+  for (let i = 0; i < count; i++) {
+    const server = net.createServer();
+    await new Promise<void>((resolve) => server.listen(0, '127.0.0.1', resolve));
+    ports.push((server.address() as net.AddressInfo).port);
+    servers.push(server);
+  }
+  await Promise.all(servers.map((s) => new Promise<void>((resolve) => s.close(() => resolve()))));
+  return ports;
+}
+
+type TrackingServer = net.Server & { destroyAll: () => void };
+
+function startEchoServer(port: number, host: string): Promise<TrackingServer> {
+  return new Promise((resolve, reject) => {
+    const connections = new Set<net.Socket>();
+    const server = net.createServer((socket) => {
+      connections.add(socket);
+      socket.on('close', () => connections.delete(socket));
+      let proxyHeaderParsed = false;
+      let pendingBuf = Buffer.alloc(0);
+      socket.on('data', (data: Buffer) => {
+        if (!proxyHeaderParsed) {
+          pendingBuf = Buffer.concat([pendingBuf, data]);
+          const idx = pendingBuf.indexOf('\r\n');
+          if (idx !== -1) {
+            proxyHeaderParsed = true;
+            const remainder = pendingBuf.subarray(idx + 2);
+            if (remainder.length > 0) socket.write(remainder);
+          }
+          return;
+        }
+        socket.write(data);
+      });
+      socket.on('error', () => {});
+    }) as TrackingServer;
+    server.destroyAll = () => {
+      for (const conn of connections) conn.destroy();
+      connections.clear();
+    };
+    server.on('error', reject);
+    server.listen(port, host, () => resolve(server));
+  });
+}
+
+function sendAndReceive(port: number, data: Buffer, timeoutMs = 30000): Promise<Buffer> {
+  return new Promise((resolve, reject) => {
+    const chunks: Buffer[] = [];
+    let totalReceived = 0;
+    const expectedLength = data.length;
+    let settled = false;
+
+    const client = net.createConnection({ host: '127.0.0.1', port }, () => {
+      client.write(data);
+      client.end();
+    });
+
+    const timer = setTimeout(() => {
+      if (!settled) {
+        settled = true;
+        client.destroy();
+        reject(new Error(`Timeout after ${timeoutMs}ms — received ${totalReceived}/${expectedLength} bytes`));
+      }
+    }, timeoutMs);
+
+    client.on('data', (chunk: Buffer) => {
+      chunks.push(chunk);
+      totalReceived += chunk.length;
+      if (totalReceived >= expectedLength && !settled) {
+        settled = true;
+        clearTimeout(timer);
+        client.destroy();
+        resolve(Buffer.concat(chunks));
+      }
+    });
+
+    client.on('end', () => {
+      if (!settled) {
+        settled = true;
+        clearTimeout(timer);
+        resolve(Buffer.concat(chunks));
+      }
+    });
+
+    client.on('error', (err) => {
+      if (!settled) {
+        settled = true;
+        clearTimeout(timer);
+        reject(err);
+      }
+    });
+  });
+}
+
+function sha256(buf: Buffer): string {
+  return crypto.createHash('sha256').update(buf).digest('hex');
+}
+
+// ---------------------------------------------------------------------------
+// Throttle Proxy: rate-limits TCP traffic between edge and hub
+// ---------------------------------------------------------------------------
+
+class ThrottleTransform extends stream.Transform {
+  private bytesPerSec: number;
+  private bucket: number;
+  private lastRefill: number;
+  private destroyed_: boolean = false;
+
+  constructor(bytesPerSecond: number) {
+    super();
+    this.bytesPerSec = bytesPerSecond;
+    this.bucket = bytesPerSecond;
+    this.lastRefill = Date.now();
+  }
+
+  _transform(chunk: Buffer, _encoding: BufferEncoding, callback: stream.TransformCallback) {
+    if (this.destroyed_) return;
+
+    const now = Date.now();
+    const elapsed = (now - this.lastRefill) / 1000;
+    this.bucket = Math.min(this.bytesPerSec, this.bucket + elapsed * this.bytesPerSec);
+    this.lastRefill = now;
+
+    if (chunk.length <= this.bucket) {
+      this.bucket -= chunk.length;
+      callback(null, chunk);
+    } else {
+      // Not enough budget — delay the entire chunk (don't split)
+      const deficit = chunk.length - this.bucket;
+      this.bucket = 0;
+      const delayMs = Math.min((deficit / this.bytesPerSec) * 1000, 1000);
+      setTimeout(() => {
+        if (this.destroyed_) { callback(); return; }
+        this.lastRefill = Date.now();
+        this.bucket = 0;
+        callback(null, chunk);
+      }, delayMs);
+    }
+  }
+
+  _destroy(err: Error | null, callback: (error: Error | null) => void) {
+    this.destroyed_ = true;
+    callback(err);
+  }
+}
+
+interface ThrottleProxy {
+  server: net.Server;
+  close: () => Promise<void>;
+}
+
+async function startThrottleProxy(
+  listenPort: number,
+  targetHost: string,
+  targetPort: number,
+  bytesPerSecond: number,
+): Promise<ThrottleProxy> {
+  const connections = new Set<net.Socket>();
+  const server = net.createServer((clientSock) => {
+    connections.add(clientSock);
+    const upstream = net.createConnection({ host: targetHost, port: targetPort });
+    connections.add(upstream);
+
+    const throttleUp = new ThrottleTransform(bytesPerSecond);
+    const throttleDown = new ThrottleTransform(bytesPerSecond);
+
+    clientSock.pipe(throttleUp).pipe(upstream);
+    upstream.pipe(throttleDown).pipe(clientSock);
+
+    let cleaned = false;
+    const cleanup = (source: string, err?: Error) => {
+      if (cleaned) return;
+      cleaned = true;
+      if (err) {
+        console.error(`[ThrottleProxy] cleanup triggered by ${source}: ${err.message}`);
+      } else {
+        console.error(`[ThrottleProxy] cleanup triggered by ${source} (no error)`);
+      }
+      console.error(`[ThrottleProxy] stack:`, new Error().stack);
+      throttleUp.destroy();
+      throttleDown.destroy();
+      clientSock.destroy();
+      upstream.destroy();
+      connections.delete(clientSock);
+      connections.delete(upstream);
+    };
+    clientSock.on('error', (e) => cleanup('clientSock.error', e));
+    upstream.on('error', (e) => cleanup('upstream.error', e));
+    throttleUp.on('error', (e) => cleanup('throttleUp.error', e));
+    throttleDown.on('error', (e) => cleanup('throttleDown.error', e));
+    clientSock.on('close', () => cleanup('clientSock.close'));
+    upstream.on('close', () => cleanup('upstream.close'));
+  });
+
+  await new Promise<void>((resolve) => server.listen(listenPort, '127.0.0.1', resolve));
+  return {
+    server,
+    close: async () => {
+      for (const c of connections) c.destroy();
+      connections.clear();
+      await new Promise<void>((resolve) => server.close(() => resolve()));
+    },
+  };
+}
+
+// ---------------------------------------------------------------------------
+// Test state
+// ---------------------------------------------------------------------------
+
+let hub: RemoteIngressHub;
+let edge: RemoteIngressEdge;
+let echoServer: TrackingServer;
+let throttle: ThrottleProxy;
+let hubPort: number;
+let proxyPort: number;
+let edgePort: number;
+
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+tap.test('setup: start throttled tunnel (100 Mbit/s)', async () => {
+  [hubPort, proxyPort, edgePort] = await findFreePorts(3);
+
+  echoServer = await startEchoServer(edgePort, '127.0.0.2');
+
+  // Throttle proxy: edge → proxy → hub at 100 Mbit/s (12.5 MB/s)
+  throttle = await startThrottleProxy(proxyPort, '127.0.0.1', hubPort, 12.5 * 1024 * 1024);
+
+  hub = new RemoteIngressHub();
+  edge = new RemoteIngressEdge();
+
+  await hub.start({ tunnelPort: hubPort, targetHost: '127.0.0.2' });
+  await hub.updateAllowedEdges([
+    { id: 'test-edge', secret: 'test-secret', listenPorts: [edgePort] },
+  ]);
+
+  const connectedPromise = new Promise<void>((resolve, reject) => {
+    const timeout = setTimeout(() => reject(new Error('Edge did not connect within 10s')), 10000);
+    edge.once('tunnelConnected', () => {
+      clearTimeout(timeout);
+      resolve();
+    });
+  });
+
+  // Edge connects through throttle proxy
+  await edge.start({
+    hubHost: '127.0.0.1',
+    hubPort: proxyPort,
+    edgeId: 'test-edge',
+    secret: 'test-secret',
+    bindAddress: '127.0.0.1',
+  });
+
+  await connectedPromise;
+  await new Promise((resolve) => setTimeout(resolve, 500));
+
+  const status = await edge.getStatus();
+  expect(status.connected).toBeTrue();
+});
+
+tap.test('throttled: 5 streams x 20MB each through 100Mbit tunnel', async () => {
+  const streamCount = 5;
+  const payloadSize = 20 * 1024 * 1024; // 20MB per stream = 100MB total round-trip
+
+  const payloads = Array.from({ length: streamCount }, () => crypto.randomBytes(payloadSize));
+  const promises = payloads.map((data) => {
+    const hash = sha256(data);
+    return sendAndReceive(edgePort, data, 300000).then((received) => ({
+      sent: hash,
+      received: sha256(received),
+      sizeOk: received.length === payloadSize,
+    }));
+  });
+
+  const results = await Promise.all(promises);
+  const failures = results.filter((r) => !r.sizeOk || r.sent !== r.received);
+  expect(failures.length).toEqual(0);
+
+  const status = await edge.getStatus();
+  expect(status.connected).toBeTrue();
+});
+
+tap.test('throttled: slow consumer with 20MB does not kill other streams', async () => {
+  // Open a connection that creates download-direction backpressure:
+  // send 20MB but DON'T read the response — client TCP receive buffer fills
+  const slowSock = net.createConnection({ host: '127.0.0.1', port: edgePort });
+  await new Promise<void>((resolve) => slowSock.on('connect', resolve));
+  const slowData = crypto.randomBytes(20 * 1024 * 1024);
+  slowSock.write(slowData);
+  slowSock.end();
+  // Don't read — backpressure builds on the download path
+
+  // Wait for backpressure to develop
+  await new Promise((r) => setTimeout(r, 2000));
+
+  // Meanwhile, 5 normal echo streams with 20MB each must complete
+  const payload = crypto.randomBytes(20 * 1024 * 1024);
+  const hash = sha256(payload);
+  const promises = Array.from({ length: 5 }, () =>
+    sendAndReceive(edgePort, payload, 300000).then((r) => ({
+      hash: sha256(r),
+      sizeOk: r.length === payload.length,
+    }))
+  );
+  const results = await Promise.all(promises);
+  const failures = results.filter((r) => !r.sizeOk || r.hash !== hash);
+  expect(failures.length).toEqual(0);
+
+  // Tunnel still alive
+  const status = await edge.getStatus();
+  expect(status.connected).toBeTrue();
+
+  slowSock.destroy();
+});
+
+tap.test('throttled: rapid churn — 3 x 20MB long + 50 x 1MB short streams', async () => {
+  // 3 long streams (20MB each) running alongside 50 short streams (1MB each)
+  const longPayload = crypto.randomBytes(20 * 1024 * 1024);
+  const longHash = sha256(longPayload);
+  const longPromises = Array.from({ length: 3 }, () =>
+    sendAndReceive(edgePort, longPayload, 300000).then((r) => ({
+      hash: sha256(r),
+      sizeOk: r.length === longPayload.length,
+    }))
+  );
+
+  const shortPayload = crypto.randomBytes(1024 * 1024);
+  const shortHash = sha256(shortPayload);
+  const shortPromises = Array.from({ length: 50 }, () =>
+    sendAndReceive(edgePort, shortPayload, 300000).then((r) => ({
+      hash: sha256(r),
+      sizeOk: r.length === shortPayload.length,
+    }))
+  );
+
+  const [longResults, shortResults] = await Promise.all([
+    Promise.all(longPromises),
+    Promise.all(shortPromises),
+  ]);
+
+  const longFails = longResults.filter((r) => !r.sizeOk || r.hash !== longHash);
+  const shortFails = shortResults.filter((r) => !r.sizeOk || r.hash !== shortHash);
+  expect(longFails.length).toEqual(0);
+  expect(shortFails.length).toEqual(0);
+
+  const status = await edge.getStatus();
+  expect(status.connected).toBeTrue();
+});
+
+tap.test('throttled: 3 burst waves of 5 streams x 20MB each', async () => {
+  for (let wave = 0; wave < 3; wave++) {
+    const streamCount = 5;
+    const payloadSize = 20 * 1024 * 1024; // 20MB per stream = 100MB per wave
+
+    const promises = Array.from({ length: streamCount }, () => {
+      const data = crypto.randomBytes(payloadSize);
+      return sendAndReceive(edgePort, data, 300000).then((r) => r.length === payloadSize);
+    });
+
+    const results = await Promise.all(promises);
+    const ok = results.filter(Boolean).length;
+    expect(ok).toEqual(streamCount);
+
+    // Brief pause between waves
+    await new Promise((r) => setTimeout(r, 500));
+
+    const status = await edge.getStatus();
+    expect(status.connected).toBeTrue();
+  }
+});
+
+tap.test('throttled: tunnel still works after all load tests', async () => {
+  const data = crypto.randomBytes(1024);
+  const hash = sha256(data);
+  const received = await sendAndReceive(edgePort, data, 30000);
+  expect(sha256(received)).toEqual(hash);
+
+  const status = await edge.getStatus();
+  expect(status.connected).toBeTrue();
+});
+
+tap.test('teardown: stop tunnel', async () => {
+  await edge.stop();
+  await hub.stop();
+  if (throttle) await throttle.close();
+  await new Promise<void>((resolve) => echoServer.close(() => resolve()));
+});
+
+export default tap.start();

ts/00_commitinfo_data.ts

@@ -3,6 +3,6 @@
  */
 export const commitinfo = {
   name: '@serve.zone/remoteingress',
-  version: '4.8.3',
+  version: '4.8.16',
   description: 'Edge ingress tunnel for DcRouter - accepts incoming TCP connections at network edge and tunnels them to DcRouter SmartProxy preserving client IP via PROXY protocol v1.'
 }