Compare commits

..

No commits in common. "108bab6a9027c797d5a461ab3eb54fe4499151a2" and "ebfc751471da5972194169ac19a7c18da1e071e5" have entirely different histories.

4 changed files with 3 additions and 201 deletions

View File

@ -137,16 +137,6 @@ pub struct Bridge {
last_rtt_ms: f64,
last_sample_at: Instant,
last_valid_recv: Instant,
/// Set when a suspend/resume is detected, cleared once a reconnect actually
/// succeeds. Waking is precisely when the network is least likely to be
/// ready — Wi-Fi has not reassociated yet — so a single attempt fired
/// milliseconds after resume usually fails, and a one-shot forced reconnect
/// then fell back to the ordinary 25s stall heuristic. That heuristic keys
/// off a monotonic clock which does not advance while the machine is
/// asleep, so it could take a further 25s of real uptime to fire, or not
/// fire at all. Retrying until success removes the dependency on either.
forced_reconnect_pending: bool,
last_forced_reconnect_try: Instant,
}
impl Bridge {
@ -183,8 +173,6 @@ impl Bridge {
last_rtt_ms: 0.0,
last_sample_at: Instant::now(),
last_valid_recv: Instant::now(),
forced_reconnect_pending: false,
last_forced_reconnect_try: Instant::now(),
})
}
@ -267,27 +255,7 @@ impl Bridge {
let _ = tx.send(UiEvent::Log(format!(
"Resumed after ~{}s suspend — forcing clean reconnect", wall_gap.as_secs()
))).await;
self.forced_reconnect_pending = true;
self.last_forced_reconnect_try = Instant::now() - Duration::from_secs(60);
}
// Keep retrying a resume-triggered reconnect until one lands.
// The first attempt fires within half a second of waking, when
// the NIC is typically still reassociating, so treating it as
// one-shot left the tunnel dead until some other timer noticed.
if self.running
&& self.forced_reconnect_pending
&& self.last_forced_reconnect_try.elapsed() >= Duration::from_secs(3)
{
self.last_forced_reconnect_try = Instant::now();
self.handle_keepalive(true, &mut sessions_opt, &mut udp_rx_opt, &mut proxy_guard, &mut stream_map, &tx, &proxy_tx, &mut proxy_rx).await;
// handle_keepalive refreshes last_valid_recv only when a
// session was actually established, so this is a real
// success check rather than "we tried".
if self.last_valid_recv.elapsed() < Duration::from_secs(3) {
self.forced_reconnect_pending = false;
let _ = tx.send(UiEvent::Log("Reconnected after suspend".into())).await;
}
}
if self.running {
self.emit_metrics(&tx).await;
@ -304,12 +272,7 @@ impl Bridge {
}
}
proxy_ev = proxy_rx.recv(), if self.running && sessions_opt.as_ref().map(|s| {
// Upper bound matches MAX_CWND_PACKETS in ostp-core's congestion
// controller. The old 16384 ceiling let ~20 MB sit in flight,
// which on a mobile uplink is minutes of buffered queue rather
// than throughput — the app kept handing over data long after
// the path had stopped draining it.
s.iter().any(|ses| ses.machine.in_flight_count() < ses.machine.cwnd_packets().clamp(16, 1024))
s.iter().any(|ses| ses.machine.in_flight_count() < ses.machine.cwnd_packets().clamp(16, 16384))
}).unwrap_or(true) => {
self.handle_proxy_event(proxy_ev, &mut sessions_opt, &mut stream_map, &tx, &proxy_tx).await;
}

View File

@ -65,18 +65,6 @@ const MIN_CWND_PACKETS: u64 = 2;
/// Min RTT expiry window (after which we re-probe)
const MIN_RTT_EXPIRY: Duration = Duration::from_secs(10);
/// Minimum RTO (RFC 6298: 1s in TCP; we use 50ms since we own the protocol)
/// Absolute ceiling on the congestion window, in packets. At a ~1200-byte MTU
/// this is roughly 1.2 MB in flight — already far above the bandwidth-delay
/// product of any link this protocol realistically runs over, so anything
/// beyond it is standing queue, not throughput. The client previously allowed
/// up to 16384 packets (~20 MB), which on a mobile uplink is minutes of buffer.
const MAX_CWND_PACKETS: u64 = 1024;
/// SRTT/min_rtt ratio at which slow start stops. Doubling is what fills a deep
/// buffer fastest, so growth must end when the queue starts building rather
/// than waiting for a loss that a deep buffer may never produce.
const RTT_INFLATION_EXIT_SLOW_START: f64 = 2.0;
/// SRTT/min_rtt ratio treated as a standing queue that must be actively drained.
const RTT_INFLATION_BACKOFF: f64 = 4.0;
const RTO_MIN: Duration = Duration::from_millis(50);
/// Maximum RTO
const RTO_MAX: Duration = Duration::from_secs(16);
@ -210,46 +198,9 @@ impl CongestionController {
/// Congestion-window growth shared by both ACK paths (slow start / probe).
fn grow_window(&mut self, bytes: u64) {
// ── Delay-based congestion signal ────────────────────────────────────
// A loss-only controller is blind on a deeply-buffered path, and mobile
// carrier buffers are very deep: they absorb a burst instead of dropping
// it, so no loss is ever signalled and cwnd keeps growing. The queue —
// not the link — is what grows, and the standing delay it adds shows up
// as RTT inflating far above the path's floor. Left unchecked this is a
// positive feedback loop: bigger queue -> larger RTT samples -> larger
// SRTT -> larger RTO -> retransmits pile on -> bigger queue, which is
// how a session ends up reporting multi-second (even multi-minute) RTT
// and stalls video until the buffer finally drains or the user
// reconnects. Treat sustained RTT inflation as congestion in its own
// right, exactly as it is.
let inflation = if self.rtt_initialized && !self.min_rtt.is_zero() {
self.srtt.as_secs_f64() / self.min_rtt.as_secs_f64()
} else {
1.0
};
if inflation >= RTT_INFLATION_BACKOFF {
// Standing queue is severe — actively drain it.
self.cwnd = (self.cwnd / 2).max(MIN_CWND_PACKETS * self.mtu);
self.ssthresh = self.cwnd;
self.phase = Phase::ProbeBandwidth;
tracing::debug!(cwnd = self.cwnd, inflation, "congestion: draining standing queue");
self.clamp_cwnd();
return;
}
// State machine
match self.phase {
Phase::SlowStart => {
// Exponential doubling is what fills a deep buffer fastest, so
// leave slow start as soon as the queue starts to build rather
// than waiting for the loss that may never come.
if inflation >= RTT_INFLATION_EXIT_SLOW_START {
self.ssthresh = self.cwnd;
self.phase = Phase::ProbeBandwidth;
tracing::debug!(cwnd = self.cwnd, inflation, "congestion: RTT inflation ended slow start");
self.clamp_cwnd();
return;
}
// Exponential growth: increase cwnd by acked bytes (doubles per RTT)
self.cwnd = self.cwnd.saturating_add(bytes);
if self.cwnd >= self.ssthresh {
@ -262,21 +213,6 @@ impl CongestionController {
self.cwnd = self.cwnd.saturating_add(bytes * self.mtu / self.cwnd.max(1));
}
}
self.clamp_cwnd();
}
/// Hard ceiling on the congestion window.
///
/// Independent of any estimate: no real path this protocol runs over has a
/// bandwidth-delay product anywhere near this, so a window above it is
/// buffered queue rather than data in transit. Without it, slow start on a
/// buffer that never drops could grow the window into the tens of megabytes.
fn clamp_cwnd(&mut self) {
let ceiling = MAX_CWND_PACKETS.saturating_mul(self.mtu);
if self.cwnd > ceiling {
self.cwnd = ceiling;
}
}
/// Record a loss event.
@ -396,53 +332,6 @@ mod tests {
assert!(cc.cwnd() < initial);
}
/// The bufferbloat case: a deep buffer absorbs everything, so NOTHING is
/// ever lost, but the standing queue inflates RTT. A loss-only controller
/// grows cwnd forever here — which is how a session ends up reporting
/// multi-second RTT and stalling video.
#[test]
fn test_rtt_inflation_halts_growth_without_any_loss() {
let mut cc = CongestionController::new(1200);
// Establish a low path floor; this becomes min_rtt.
for _ in 0..4 {
cc.on_send(1200);
cc.on_ack(1200, Duration::from_millis(20));
}
let cwnd_before = cc.cwnd();
// Queue builds: RTT climbs far above the floor, still zero loss.
for _ in 0..20 {
cc.on_send(1200);
cc.on_ack(1200, Duration::from_millis(400));
}
assert!(
cc.cwnd() <= cwnd_before,
"cwnd kept growing while the queue was inflating RTT ({} -> {})",
cwnd_before,
cc.cwnd()
);
}
/// cwnd must never exceed the absolute ceiling, however long slow start
/// runs unopposed — above it the window is buffered queue, not throughput.
#[test]
fn test_cwnd_never_exceeds_absolute_ceiling() {
let mut cc = CongestionController::new(1200);
// Constant RTT: no inflation signal, so only the hard cap can stop this.
for _ in 0..5000 {
cc.on_send(1200);
cc.on_ack(1200, Duration::from_millis(30));
}
assert!(
cc.cwnd() <= MAX_CWND_PACKETS * 1200,
"cwnd {} exceeded the {}-packet ceiling",
cc.cwnd(),
MAX_CWND_PACKETS
);
}
#[test]
fn test_isolated_slow_start_loss_does_not_exit_slow_start() {
// A single dropped packet (wireless noise, a brief handover blip) is

View File

@ -4,11 +4,6 @@ use thiserror::Error;
use std::collections::{BTreeMap, VecDeque};
use std::time::{Duration, Instant};
/// Upper bound on a single frame's retransmit timer, after exponential backoff
/// is applied to the adaptive RTO. Past this the session is dead from the
/// user's point of view, and waiting longer only delays recovery.
const MAX_EFFECTIVE_RTO: Duration = Duration::from_secs(8);
use crate::congestion::CongestionController;
use crate::crypto::{NoiseRole, NoiseSession, SessionCipher};
use crate::framing::{AdaptivePadder, FrameHeader, FrameKind, FramedPacket, PaddingStrategy};
@ -680,15 +675,8 @@ impl ProtocolMachine {
break;
}
// Exponential backoff, but bounded in absolute terms. base_rto is
// itself adaptive and can reach RTO_MAX (16s) on a congested path;
// multiplying that by the 64x backoff cap yields a frame that sits
// unretransmitted for ~17 MINUTES, long past the point where the
// session is simply dead to the user. Cap the product so backoff
// stays a backoff rather than an outage.
let backoff_factor = 1u64 << (frame.retries as u64).min(6);
let effective_rto = Duration::from_millis(base_rto_ms.saturating_mul(backoff_factor))
.min(MAX_EFFECTIVE_RTO);
let effective_rto = Duration::from_millis(base_rto_ms.saturating_mul(backoff_factor));
if now.duration_since(frame.last_sent) >= effective_rto {
// Only burn the retry counter and reset the RTO timer when the

View File

@ -28,12 +28,6 @@ enum Commands {
Init {
mode: String,
},
/// Hash a password for the web panel's `api.password_hash` config field
#[command(name = "hash-password", alias = "hp")]
HashPassword {
/// The password to hash. Omit to be prompted (keeps it out of shell history).
password: Option<String>,
},
/// Generate a new secure access key
#[command(name = "gk", alias = "generate-key")]
GenerateKey {
@ -926,38 +920,6 @@ async fn run_app() -> Result<()> {
match cmd {
Commands::Setup { init } => { args.setup = true; args.init = init; }
Commands::Init { mode } => { args.init = Some(mode); }
Commands::HashPassword { password } => {
// The panel stores only a hash, and until now nothing in the CLI
// could produce one: `ostp init server` writes password_hash: ""
// and the only generator lived inside the Unix-only Server+Panel
// wizard branch, leaving no supported way to set up API auth on a
// plain server.
let password = match password {
Some(p) => p,
None => {
print!("Password: ");
use std::io::Write as _;
std::io::stdout().flush().ok();
let mut buf = String::new();
std::io::stdin().read_line(&mut buf)?;
buf.trim_end_matches(['\r', '\n']).to_string()
}
};
if password.is_empty() {
anyhow::bail!("password must not be empty");
}
// Must match api.rs's handle_login byte for byte.
let hash = format!(
"{:x}",
<sha2::Sha256 as sha2::Digest>::digest(password.as_bytes())
);
println!();
println!("Add this to the \"api\" section of your config:");
println!();
println!(" \"password_hash\": \"{hash}\"");
println!();
return Ok(());
}
Commands::GenerateKey { format, count } => { args.generate_key = true; args.format = format; args.count = count; }
Commands::Links => { args.links = true; }
Commands::Check => { args.check = true; }