Federated relay tier: peer flooding, per-member isolation, registry admission and relay discovery

This commit is contained in:
George Coles
2026-09-15 06:49:43 -04:00
parent d30e612be8
commit 2c97fd523f
11 changed files with 759 additions and 177 deletions
+229 -38
View File
@@ -3,7 +3,7 @@ use std::net::SocketAddr;
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant};
use anyhow::Result;
use anyhow::{Result, anyhow};
use axum::extract::{Query, State};
use axum::http::{StatusCode, header};
use axum::response::{IntoResponse, Response};
@@ -15,13 +15,40 @@ use tokio::net::TcpListener;
use crate::crypto::{now_ts, poll_signing_bytes, random_nonce, verify_signature};
use crate::message::{Envelope, TYPE_AGGREGATE, TYPE_QUERY, TYPE_RESPONSE, timestamp_is_fresh};
use crate::registry::Watcher;
pub const DEFAULT_CAPACITY: usize = 256;
const CHALLENGE_TTL: Duration = Duration::from_secs(120);
const SEEN_TTL: Duration = Duration::from_secs(30);
#[derive(Clone, Debug)]
pub struct RelayOptions {
pub capacity: usize,
pub peers: Vec<String>,
pub url: Option<String>,
pub registry: Option<String>,
pub ma_key: Option<String>,
pub max_hops: usize,
}
impl Default for RelayOptions {
fn default() -> Self {
Self {
capacity: DEFAULT_CAPACITY,
peers: Vec::new(),
url: None,
registry: None,
ma_key: None,
max_hops: 3,
}
}
}
#[derive(Default)]
struct MemberQueue {
items: VecDeque<(u64, Envelope)>,
lagging: bool,
missed: u64,
}
struct Challenge {
@@ -32,57 +59,136 @@ struct Challenge {
struct Inner {
members: HashMap<String, MemberQueue>,
challenges: HashMap<String, Challenge>,
seen: HashMap<String, Instant>,
seq: u64,
}
pub struct Relay {
inner: Mutex<Inner>,
capacity: usize,
options: RelayOptions,
registry: Option<Arc<Watcher>>,
client: reqwest::Client,
}
impl Relay {
pub fn new(capacity: usize) -> Arc<Self> {
Arc::new(Self {
pub fn new(options: RelayOptions) -> Result<Arc<Self>> {
let registry = match (options.registry.as_deref(), options.ma_key.as_deref()) {
(Some(source), Some(ma_key)) => Some(Watcher::new(source, ma_key, None)),
(Some(_), None) => return Err(anyhow!("registry configured without ma_key")),
_ => None,
};
if !options.peers.is_empty() && options.url.is_none() {
return Err(anyhow!("--url is required when --peer is set"));
}
let relay = Arc::new(Self {
inner: Mutex::new(Inner {
members: HashMap::new(),
challenges: HashMap::new(),
seen: HashMap::new(),
seq: 0,
}),
capacity,
})
options,
registry,
client: reqwest::Client::builder()
.timeout(Duration::from_secs(5))
.build()?,
});
if let Some(watcher) = &relay.registry {
watcher.load_initial();
}
Ok(relay)
}
fn push(&self, targets: Option<&str>, envelope: Envelope) -> Result<usize, StatusCode> {
let mut inner = self.inner.lock().expect("relay lock");
if inner
.members
.values()
.any(|q| q.items.len() >= self.capacity)
{
return Err(StatusCode::TOO_MANY_REQUESTS);
fn admit(&self, envelope: &Envelope) -> bool {
match &self.registry {
Some(watcher) => {
watcher.refresh_if_changed();
watcher.authorized(&envelope.key, now_ts()).is_some()
}
None => true,
}
}
fn mark_seen(&self, signature: &str) -> bool {
let mut inner = self.inner.lock().expect("relay lock");
let now = Instant::now();
inner
.seen
.retain(|_, at| now.duration_since(*at) < SEEN_TTL);
if inner.seen.contains_key(signature) {
return false;
}
inner.seen.insert(signature.to_string(), now);
true
}
fn push_local(&self, target: Option<&str>, envelope: Envelope) -> Result<usize, StatusCode> {
let mut inner = self.inner.lock().expect("relay lock");
inner.seq += 1;
let seq = inner.seq;
match targets {
match target {
Some(member) => {
let Some(queue) = inner.members.get_mut(member) else {
return Err(StatusCode::NOT_FOUND);
};
if queue.items.len() >= self.options.capacity {
queue.lagging = true;
queue.missed += 1;
return Err(StatusCode::TOO_MANY_REQUESTS);
}
queue.items.push_back((seq, envelope));
Ok(1)
}
None => {
let from = envelope.key.clone();
inner.members.entry(from).or_default();
let publisher = envelope.key.clone();
inner.members.entry(publisher).or_default();
let mut delivered = 0;
for queue in inner.members.values_mut() {
queue.items.push_back((seq, envelope.clone()));
delivered += 1;
if queue.items.len() >= self.options.capacity {
queue.lagging = true;
queue.missed += 1;
} else {
queue.items.push_back((seq, envelope.clone()));
delivered += 1;
}
}
Ok(delivered)
}
}
}
fn forward(&self, envelope: Envelope, origin: Option<&str>, hops: usize) {
if self.options.peers.is_empty() {
return;
}
let Some(url) = self.options.url.clone() else {
return;
};
let peers: Vec<String> = self
.options
.peers
.iter()
.filter(|peer| Some(peer.as_str()) != origin)
.cloned()
.collect();
if peers.is_empty() {
return;
}
let client = self.client.clone();
tokio::spawn(async move {
for peer in peers {
let target = format!(
"{}/v1/federation?origin={}&hops={}",
peer.trim_end_matches('/'),
url,
hops
);
if let Err(error) = client.post(&target).json(&envelope).send().await {
eprintln!("federation forward to {peer} failed: {error}");
}
}
});
}
}
pub fn router(relay: Arc<Relay>) -> Router {
@@ -90,13 +196,30 @@ pub fn router(relay: Arc<Relay>) -> Router {
.route("/health", get(health))
.route("/v1/challenge", get(challenge))
.route("/v1/publish", post(publish))
.route("/v1/federation", post(federation))
.route("/v1/unicast", post(unicast))
.route("/v1/poll", get(poll))
.with_state(relay)
}
pub async fn run(listener: TcpListener, capacity: usize) -> Result<()> {
let relay = Relay::new(capacity);
pub async fn run(listener: TcpListener, options: RelayOptions) -> Result<()> {
let relay = Relay::new(options)?;
if let Some(watcher) = relay.registry.clone() {
if watcher.is_url() {
let client = relay.client.clone();
if let Err(error) = watcher.fetch(&client).await {
eprintln!("initial registry fetch failed: {error}");
}
tokio::spawn(async move {
loop {
tokio::time::sleep(Duration::from_secs(60)).await;
if let Err(error) = watcher.fetch(&client).await {
eprintln!("registry fetch failed: {error}");
}
}
});
}
}
axum::serve(listener, router(relay)).await?;
Ok(())
}
@@ -152,14 +275,65 @@ async fn publish(State(relay): State<Arc<Relay>>, Json(envelope): Json<Envelope>
if envelope.msg_type != TYPE_QUERY {
return bad_request("relay carries broadcast queries only");
}
match relay.push(None, envelope) {
Ok(delivered) => (
StatusCode::ACCEPTED,
Json(json!({ "delivered": delivered })),
)
.into_response(),
Err(status) => backpressure(status),
if !relay.admit(&envelope) {
return bad_request("sender not admitted");
}
relay.mark_seen(&envelope.sig);
let delivered = relay.push_local(None, envelope.clone()).unwrap_or(0);
relay.forward(envelope, None, 1);
(
StatusCode::ACCEPTED,
Json(json!({ "delivered": delivered })),
)
.into_response()
}
#[derive(Deserialize)]
struct FederationParams {
origin: Option<String>,
hops: Option<usize>,
}
async fn federation(
State(relay): State<Arc<Relay>>,
Query(params): Query<FederationParams>,
Json(envelope): Json<Envelope>,
) -> Response {
let Some(origin) = params.origin.clone() else {
return bad_request("origin required");
};
if !relay.options.peers.iter().any(|peer| peer == &origin) {
return bad_request("unknown peer origin");
}
if envelope.verify().is_err() {
return bad_request("invalid signature");
}
if !timestamp_is_fresh(envelope.ts, now_ts()) {
return bad_request("stale timestamp");
}
if envelope.msg_type != TYPE_QUERY {
return bad_request("relay carries broadcast queries only");
}
if !relay.admit(&envelope) {
return bad_request("sender not admitted");
}
if !relay.mark_seen(&envelope.sig) {
return (
StatusCode::ACCEPTED,
Json(json!({ "delivered": 0, "duplicate": true })),
)
.into_response();
}
let delivered = relay.push_local(None, envelope.clone()).unwrap_or(0);
let hops = params.hops.unwrap_or(1);
if hops < relay.options.max_hops {
relay.forward(envelope, Some(&origin), hops + 1);
}
(
StatusCode::ACCEPTED,
Json(json!({ "delivered": delivered })),
)
.into_response()
}
#[derive(Deserialize)]
@@ -181,14 +355,17 @@ async fn unicast(
if envelope.msg_type != TYPE_RESPONSE && envelope.msg_type != TYPE_AGGREGATE {
return bad_request("unicast carries responses and aggregates only");
}
match relay.push(Some(&params.to), envelope) {
if !relay.admit(&envelope) {
return bad_request("sender not admitted");
}
match relay.push_local(Some(&params.to), envelope) {
Ok(_) => (StatusCode::OK, Json(json!({ "delivered": true }))).into_response(),
Err(StatusCode::NOT_FOUND) => (
StatusCode::NOT_FOUND,
Json(json!({ "error": "member not connected" })),
)
.into_response(),
Err(status) => backpressure(status),
Err(status) => backpressure(status, 0),
}
}
@@ -225,15 +402,29 @@ async fn poll(State(relay): State<Arc<Relay>>, Query(params): Query<PollParams>)
let timeout = Duration::from_millis(params.timeout_ms.unwrap_or(25_000).min(60_000));
let deadline = Instant::now() + timeout;
loop {
let batch: Vec<Envelope> = {
let (batch, lagged): (Vec<Envelope>, Option<u64>) = {
let mut inner = relay.inner.lock().expect("relay lock");
let queue = inner.members.entry(params.member.clone()).or_default();
queue
.items
.drain(..)
.map(|(_, envelope)| envelope)
.collect()
if queue.lagging {
let missed = queue.missed;
queue.lagging = false;
queue.missed = 0;
queue.items.clear();
(Vec::new(), Some(missed))
} else {
(
queue
.items
.drain(..)
.map(|(_, envelope)| envelope)
.collect(),
None,
)
}
};
if let Some(missed) = lagged {
return backpressure(StatusCode::TOO_MANY_REQUESTS, missed);
}
if !batch.is_empty() {
return (StatusCode::OK, Json(json!({ "messages": batch }))).into_response();
}
@@ -252,11 +443,11 @@ fn unauthorized(message: &str) -> Response {
(StatusCode::UNAUTHORIZED, Json(json!({ "error": message }))).into_response()
}
fn backpressure(status: StatusCode) -> Response {
fn backpressure(status: StatusCode, missed: u64) -> Response {
(
status,
[(header::RETRY_AFTER, "1")],
Json(json!({ "error": "transport backpressure" })),
Json(json!({ "error": "lagging", "missed": missed })),
)
.into_response()
}