feat(relay): replace global Mutex<RoomManager> with DashMap sharding
Some checks failed
Mirror to GitHub / mirror (push) Failing after 24s
Build Release Binaries / build-amd64 (push) Failing after 3m41s

Eliminates the single-lock bottleneck for media forwarding. Before:
all participants across all rooms competed for one Mutex. Now rooms
are stored in DashMap (64 internal shards with per-shard RwLocks).

Changes:
- RoomManager.rooms: HashMap → DashMap<String, Room>
- Per-room quality tracking (qualities, current_tier moved into Room)
- Arc<Mutex<RoomManager>> → Arc<RoomManager> everywhere
- 20 .lock().await sites removed across room.rs, main.rs, federation.rs, ws.rs
- federation forward_to_peers: clone peer list, release lock, then send
- ACL uses std::sync::Mutex (rarely accessed, non-async)

Concurrency improvement:
- Before: 100 rooms × 10 people = 1000 tasks → 1 Mutex
- After: distributed across 64 DashMap shards, ~15 tasks per shard avg
- Rooms are fully independent — room A never blocks room B

314 tests passing, 0 regressions.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Siavash Sameni
2026-04-13 12:17:57 +04:00
parent 2514151a89
commit a52b011fb5
7 changed files with 239 additions and 208 deletions

View File

@@ -31,7 +31,7 @@ use crate::session_mgr::SessionManager;
/// Shared state for WebSocket handlers.
#[derive(Clone)]
pub struct WsState {
pub room_mgr: Arc<Mutex<RoomManager>>,
pub room_mgr: Arc<RoomManager>,
pub session_mgr: Arc<Mutex<SessionManager>>,
pub auth_url: Option<String>,
pub metrics: Arc<RelayMetrics>,
@@ -143,10 +143,9 @@ async fn handle_ws_connection(socket: WebSocket, room: String, state: WsState) {
// 4. Join room with WS sender
let addr: SocketAddr = ([0, 0, 0, 0], 0).into();
let participant_id = {
let mut mgr = state.room_mgr.lock().await;
match mgr.join_ws(&room, addr, tx, fingerprint.as_deref()) {
match state.room_mgr.join_ws(&room, addr, tx, fingerprint.as_deref()) {
Ok(id) => {
state.metrics.active_rooms.set(mgr.list().len() as i64);
state.metrics.active_rooms.set(state.room_mgr.list().len() as i64);
id
}
Err(e) => {
@@ -184,10 +183,7 @@ async fn handle_ws_connection(socket: WebSocket, room: String, state: WsState) {
loop {
match ws_rx.next().await {
Some(Ok(Message::Binary(data))) => {
let others = {
let mgr = state.room_mgr.lock().await;
mgr.others(&room, participant_id)
};
let others = state.room_mgr.others(&room, participant_id);
for other in &others {
let _ = other.send_raw(&data).await;
}
@@ -214,11 +210,8 @@ async fn handle_ws_connection(socket: WebSocket, room: String, state: WsState) {
reg.unregister_local(fp);
}
{
let mut mgr = state.room_mgr.lock().await;
mgr.leave(&room, participant_id);
state.metrics.active_rooms.set(mgr.list().len() as i64);
}
state.room_mgr.leave(&room, participant_id);
state.metrics.active_rooms.set(state.room_mgr.list().len() as i64);
let session_id_str: String = session_id.iter().map(|b| format!("{b:02x}")).collect();
state.metrics.remove_session_metrics(&session_id_str);