Files
voice-cat/tests/test_reaper_timeout.cpp

207 lines
7.2 KiB
C++
Raw Normal View History

fix(net): broadcast LEFT on disconnect, add keepalive/reaper, cap PLC hiss Three reported bugs traced to one root cause plus two missing designed features: 1. Stale users + eternal PLC hiss (root cause): ConnSession::close() silently erased dropped users without broadcasting UserEvent::LEFT, so peers never learned the user left and their audio engines never called remove_stream — Opus PLC synthesized comfort noise forever. Fix: broadcast_left() helper + close() broadcasts LEFT before erasing. 2. PLC cap (defense-in-depth): on_playback now caps pure PLC at ~2s, then emits digital silence so a stale stream can never hiss forever even if remove_stream is skipped. Resets automatically on fresh packets. 3. No timeout / no ping: client never sent Ping, server had no last_seen / reaper, so half-open connections (NAT timeout, wifi loss, sleep) left ghost users forever. Fix: client Ping every 15s with RTT measurement, ConnSession::last_seen bumped on every inbound TCP/UDP frame, steady_timer reaper sweeps every 15s and drops sessions older than 45s (configurable via server::Config). 4. UDP KEEPALIVE: client sends plaintext kFrameKeepalive every 5s; server bumps last_seen + echoes back. Keeps NAT bindings alive and lets media activity defer the reaper independently of TCP. 5. Graceful client disconnect: vc_disconnect() sends Disconnect{code=0} via a flag-based io-thread exit (no double-close race); server handles client-sent Disconnect with immediate close() + LEFT broadcast. 3 new tests: disconnect_left, plc_cap, reaper_timeout. 21/21 ctest green. Docs: protocol.md §6/§7, voice.md §6, architecture.md §5, PROGRESS.md.
2026-06-18 01:18:33 +02:00
/*
* test_reaper_timeout verifies the server's keepalive reaper (docs/protocol.md §7).
*
* Simulates a half-open connection: client B authenticates then goes completely silent
* (no TCP traffic, no pings the 15s ping interval far exceeds the test's 2s reaper
* timeout). Client A stays alive by sending channel text every 500ms, which bumps its
* last_seen on the server. After ~2s the reaper drops B: B's TCP connection is closed
* (B sees VC_EVENT_DISCONNECTED) and A receives VC_EVENT_USER_LEFT for B (the Tier 1
* LEFT-broadcast fires from close()).
*
* This catches the "ghost user forever" failure mode for half-open connections (NAT
* timeout, wifi loss without RST, laptop sleep) that never produce a TCP EOF.
*/
#include <cstdio>
#ifdef VOICECAT_HAS_NET
#include <atomic>
#include <chrono>
#include <condition_variable>
#include <filesystem>
#include <mutex>
#include <string>
#include <thread>
#include <vector>
#include "voicecat.h"
#include "server.h"
#include "db.h"
struct EventStore {
std::mutex mu;
std::condition_variable cv;
bool auth_ok{false};
uint32_t self_user_id{0};
bool channel_list_received{false};
bool disconnected{false};
std::vector<uint32_t> left_users;
vc_client* client{nullptr};
const char* label{nullptr};
};
static void on_event(void* user, const vc_event* ev) {
auto* s = static_cast<EventStore*>(user);
std::lock_guard lk(s->mu);
switch (ev->type) {
case VC_EVENT_SERVER_IDENTITY:
vc_confirm_server_identity(s->client, 1);
break;
case VC_EVENT_AUTH_RESULT:
s->auth_ok = (ev->result == VC_OK);
s->self_user_id = ev->user_id;
break;
case VC_EVENT_CHANNEL_LIST:
s->channel_list_received = true;
break;
case VC_EVENT_USER_LEFT:
s->left_users.push_back(ev->user_id);
break;
case VC_EVENT_DISCONNECTED:
s->disconnected = true;
break;
default:
break;
}
s->cv.notify_all();
}
template <typename Pred>
static bool wait_for(EventStore& s, Pred pred, int timeout_ms) {
auto deadline = std::chrono::steady_clock::now() + std::chrono::milliseconds(timeout_ms);
std::unique_lock lk(s.mu);
return s.cv.wait_until(lk, deadline, [&] { return pred(s); });
}
static int g_failures = 0;
#define CHECK(cond) \
do { \
if (!(cond)) { \
std::printf("FAIL: %s (%s:%d)\n", #cond, __FILE__, __LINE__); \
++g_failures; \
} \
} while (0)
int main() {
auto tmp = std::filesystem::temp_directory_path() /
("vctest_reaper_" + std::to_string(
std::chrono::steady_clock::now().time_since_epoch().count()));
std::filesystem::create_directories(tmp);
std::string data_dir = tmp.string();
std::atomic<uint16_t> bound_port{0};
std::mutex ready_mu;
std::condition_variable ready_cv;
bool ready{false};
voicecat::server::Config cfg;
cfg.data_dir = data_dir;
cfg.bind_port = 0;
cfg.server_name = "VoiceCat-ReaperTest";
cfg.allow_guests = true;
cfg.reaper_timeout_ms = 2000; // 2s — drop sessions silent for this long
cfg.reaper_sweep_ms = 500; // check every 500ms
cfg.on_ready = [&](uint16_t p) {
bound_port.store(p);
{ std::lock_guard lk(ready_mu); ready = true; }
ready_cv.notify_all();
};
voicecat::server::Server server(cfg);
std::thread server_thread([&] { server.run(); });
{
std::unique_lock lk(ready_mu);
if (!ready_cv.wait_for(lk, std::chrono::seconds(10), [&] { return ready; })) {
std::printf("FAIL: server did not become ready\n");
server.stop();
server_thread.join();
std::filesystem::remove_all(tmp);
return 1;
}
}
uint16_t port = bound_port.load();
auto make_client = [&](const char* label, const char* nick) -> EventStore* {
auto* ev = new EventStore();
ev->label = label;
vc_callbacks cb{on_event, nullptr, ev};
vc_config cfgx{label, "0.1", VC_LOG_OFF};
ev->client = vc_client_create(&cfgx, cb);
if (!ev->client) return nullptr;
if (vc_connect(ev->client, "127.0.0.1", port) != VC_OK) return nullptr;
if (vc_authenticate_guest(ev->client, nick) != VC_OK) return nullptr;
return ev;
};
EventStore* evA = make_client("clientA", "Alpha");
CHECK(evA != nullptr);
CHECK(wait_for(*evA, [](EventStore& s) { return s.auth_ok; }, 8000));
CHECK(wait_for(*evA, [](EventStore& s) { return s.channel_list_received; }, 3000));
uint32_t a_uid = evA->self_user_id;
CHECK(a_uid != 0);
EventStore* evB = make_client("clientB", "Bravo");
CHECK(evB != nullptr);
CHECK(wait_for(*evB, [](EventStore& s) { return s.auth_ok; }, 8000));
CHECK(wait_for(*evB, [](EventStore& s) { return s.channel_list_received; }, 3000));
uint32_t b_uid = evB->self_user_id;
CHECK(b_uid != 0);
// A stays alive by sending channel text every 500ms (bumps A's last_seen on the server).
// B goes completely silent — no TCP traffic, no pings (15s ping >> 2s reaper timeout).
// Start the keepalive IMMEDIATELY: the reaper timeout is only 2s, so A must begin
// sending well before its last_seen goes stale.
std::atomic<bool> keepalive_stop{false};
std::thread keepalive([&] {
while (!keepalive_stop.load()) {
vc_send_text(evA->client, VC_TEXT_CHANNEL, 1, ".");
std::this_thread::sleep_for(std::chrono::milliseconds(500));
}
});
// Give B time to go stale and the reaper to fire (2s timeout + 500ms sweep + margin).
// A must receive VC_EVENT_USER_LEFT for B.
CHECK(wait_for(*evA, [b_uid](EventStore& s) {
for (auto u : s.left_users) if (u == b_uid) return true;
return false;
}, 10000));
// B's TCP connection is closed by the reaper → B sees VC_EVENT_DISCONNECTED.
CHECK(wait_for(*evB, [](EventStore& s) { return s.disconnected; }, 5000));
// ── Cleanup ──────────────────────────────────────────────────────────────
keepalive_stop.store(true);
keepalive.join();
vc_disconnect(evA->client);
if (!evB->disconnected) vc_disconnect(evB->client);
vc_client_destroy(evA->client);
vc_client_destroy(evB->client);
delete evA;
delete evB;
server.stop();
server_thread.join();
std::filesystem::remove_all(tmp);
if (g_failures == 0) {
std::printf("reaper_timeout: all checks passed\n");
return 0;
}
std::printf("reaper_timeout: %d failure(s)\n", g_failures);
return 1;
}
#else // !VOICECAT_HAS_NET
int main() {
std::printf("reaper_timeout: SKIP (VOICECAT_HAS_NET not defined)\n");
return 0;
}
#endif // VOICECAT_HAS_NET