feat(remoteingress): add heartbeat PING/PONG and liveness timeouts; implement fast-reconnect/backoff reset and JS crash-recovery auto-restart

This commit is contained in:
2026-03-03 11:47:50 +00:00
parent d6a07c28a0
commit 45a2811f3e
7 changed files with 241 additions and 5 deletions

View File

@@ -3,6 +3,6 @@
*/
export const commitinfo = {
name: '@serve.zone/remoteingress',
version: '4.3.0',
version: '4.4.0',
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.'
}

View File

@@ -40,9 +40,16 @@ export interface IEdgeConfig {
secret: string;
}
const MAX_RESTART_ATTEMPTS = 10;
const MAX_RESTART_BACKOFF_MS = 30_000;
export class RemoteIngressEdge extends EventEmitter {
private bridge: InstanceType<typeof plugins.smartrust.RustBridge<TEdgeCommands>>;
private started = false;
private stopping = false;
private savedConfig: IEdgeConfig | null = null;
private restartBackoffMs = 1000;
private restartAttempts = 0;
private statusInterval: ReturnType<typeof setInterval> | undefined;
constructor() {
@@ -109,11 +116,17 @@ export class RemoteIngressEdge extends EventEmitter {
edgeConfig = config;
}
this.savedConfig = edgeConfig;
this.stopping = false;
const spawned = await this.bridge.spawn();
if (!spawned) {
throw new Error('Failed to spawn remoteingress-bin');
}
// Register crash recovery handler
this.bridge.on('exit', this.handleCrashRecovery);
await this.bridge.sendCommand('startEdge', {
hubHost: edgeConfig.hubHost,
hubPort: edgeConfig.hubPort ?? 8443,
@@ -122,6 +135,8 @@ export class RemoteIngressEdge extends EventEmitter {
});
this.started = true;
this.restartAttempts = 0;
this.restartBackoffMs = 1000;
// Start periodic status logging
this.statusInterval = setInterval(async () => {
@@ -142,6 +157,7 @@ export class RemoteIngressEdge extends EventEmitter {
* Stop the edge and kill the Rust process.
*/
public async stop(): Promise<void> {
this.stopping = true;
if (this.statusInterval) {
clearInterval(this.statusInterval);
this.statusInterval = undefined;
@@ -152,6 +168,7 @@ export class RemoteIngressEdge extends EventEmitter {
} catch {
// Process may already be dead
}
this.bridge.removeListener('exit', this.handleCrashRecovery);
this.bridge.kill();
this.started = false;
}
@@ -170,4 +187,55 @@ export class RemoteIngressEdge extends EventEmitter {
public get running(): boolean {
return this.bridge.running;
}
/**
* Handle unexpected Rust binary crash — auto-restart with backoff.
*/
private handleCrashRecovery = async (code: number | null, signal: string | null) => {
if (this.stopping || !this.started || !this.savedConfig) {
return;
}
console.error(
`[RemoteIngressEdge] Rust binary crashed (code=${code}, signal=${signal}), ` +
`attempt ${this.restartAttempts + 1}/${MAX_RESTART_ATTEMPTS}`
);
this.started = false;
if (this.restartAttempts >= MAX_RESTART_ATTEMPTS) {
console.error('[RemoteIngressEdge] Max restart attempts reached, giving up');
this.emit('crashRecoveryFailed');
return;
}
await new Promise(resolve => setTimeout(resolve, this.restartBackoffMs));
this.restartBackoffMs = Math.min(this.restartBackoffMs * 2, MAX_RESTART_BACKOFF_MS);
this.restartAttempts++;
try {
const spawned = await this.bridge.spawn();
if (!spawned) {
console.error('[RemoteIngressEdge] Failed to respawn binary');
return;
}
this.bridge.on('exit', this.handleCrashRecovery);
await this.bridge.sendCommand('startEdge', {
hubHost: this.savedConfig.hubHost,
hubPort: this.savedConfig.hubPort ?? 8443,
edgeId: this.savedConfig.edgeId,
secret: this.savedConfig.secret,
});
this.started = true;
this.restartAttempts = 0;
this.restartBackoffMs = 1000;
console.log('[RemoteIngressEdge] Successfully recovered from crash');
this.emit('crashRecovered');
} catch (err) {
console.error(`[RemoteIngressEdge] Crash recovery failed: ${err}`);
}
};
}

View File

@@ -50,9 +50,19 @@ export interface IHubConfig {
};
}
type TAllowedEdge = { id: string; secret: string; listenPorts?: number[]; stunIntervalSecs?: number };
const MAX_RESTART_ATTEMPTS = 10;
const MAX_RESTART_BACKOFF_MS = 30_000;
export class RemoteIngressHub extends EventEmitter {
private bridge: InstanceType<typeof plugins.smartrust.RustBridge<THubCommands>>;
private started = false;
private stopping = false;
private savedConfig: IHubConfig | null = null;
private savedEdges: TAllowedEdge[] = [];
private restartBackoffMs = 1000;
private restartAttempts = 0;
constructor() {
super();
@@ -98,11 +108,17 @@ export class RemoteIngressHub extends EventEmitter {
* Start the hub — spawns the Rust binary and starts the tunnel server.
*/
public async start(config: IHubConfig = {}): Promise<void> {
this.savedConfig = config;
this.stopping = false;
const spawned = await this.bridge.spawn();
if (!spawned) {
throw new Error('Failed to spawn remoteingress-bin');
}
// Register crash recovery handler
this.bridge.on('exit', this.handleCrashRecovery);
await this.bridge.sendCommand('startHub', {
tunnelPort: config.tunnelPort ?? 8443,
targetHost: config.targetHost ?? '127.0.0.1',
@@ -112,18 +128,22 @@ export class RemoteIngressHub extends EventEmitter {
});
this.started = true;
this.restartAttempts = 0;
this.restartBackoffMs = 1000;
}
/**
* Stop the hub and kill the Rust process.
*/
public async stop(): Promise<void> {
this.stopping = true;
if (this.started) {
try {
await this.bridge.sendCommand('stopHub', {} as Record<string, never>);
} catch {
// Process may already be dead
}
this.bridge.removeListener('exit', this.handleCrashRecovery);
this.bridge.kill();
this.started = false;
}
@@ -132,7 +152,8 @@ export class RemoteIngressHub extends EventEmitter {
/**
* Update the list of allowed edges that can connect to this hub.
*/
public async updateAllowedEdges(edges: Array<{ id: string; secret: string; listenPorts?: number[]; stunIntervalSecs?: number }>): Promise<void> {
public async updateAllowedEdges(edges: TAllowedEdge[]): Promise<void> {
this.savedEdges = edges;
await this.bridge.sendCommand('updateAllowedEdges', { edges });
}
@@ -149,4 +170,62 @@ export class RemoteIngressHub extends EventEmitter {
public get running(): boolean {
return this.bridge.running;
}
/**
* Handle unexpected Rust binary crash — auto-restart with backoff.
*/
private handleCrashRecovery = async (code: number | null, signal: string | null) => {
if (this.stopping || !this.started || !this.savedConfig) {
return;
}
console.error(
`[RemoteIngressHub] Rust binary crashed (code=${code}, signal=${signal}), ` +
`attempt ${this.restartAttempts + 1}/${MAX_RESTART_ATTEMPTS}`
);
this.started = false;
if (this.restartAttempts >= MAX_RESTART_ATTEMPTS) {
console.error('[RemoteIngressHub] Max restart attempts reached, giving up');
this.emit('crashRecoveryFailed');
return;
}
await new Promise(resolve => setTimeout(resolve, this.restartBackoffMs));
this.restartBackoffMs = Math.min(this.restartBackoffMs * 2, MAX_RESTART_BACKOFF_MS);
this.restartAttempts++;
try {
const spawned = await this.bridge.spawn();
if (!spawned) {
console.error('[RemoteIngressHub] Failed to respawn binary');
return;
}
this.bridge.on('exit', this.handleCrashRecovery);
const config = this.savedConfig;
await this.bridge.sendCommand('startHub', {
tunnelPort: config.tunnelPort ?? 8443,
targetHost: config.targetHost ?? '127.0.0.1',
...(config.tls?.certPem && config.tls?.keyPem
? { tlsCertPem: config.tls.certPem, tlsKeyPem: config.tls.keyPem }
: {}),
});
// Restore allowed edges
if (this.savedEdges.length > 0) {
await this.bridge.sendCommand('updateAllowedEdges', { edges: this.savedEdges });
}
this.started = true;
this.restartAttempts = 0;
this.restartBackoffMs = 1000;
console.log('[RemoteIngressHub] Successfully recovered from crash');
this.emit('crashRecovered');
} catch (err) {
console.error(`[RemoteIngressHub] Crash recovery failed: ${err}`);
}
};
}