Make candidate validation timeouts configurable (#4001)

* pvf: make execution timeout configurable

* guide: add timeouts to candidate validation params

* add timeouts to candidate validation messages

* fmt

* port backing to use the backing pvf timeout

* port approval-voting to use the execution timeout

* port dispute participation to use the correct timeout

* fmt

* address grumbles & test failure

polkadot/node/core/pvf/src/execute/queue.rs

@@ -38,11 +38,17 @@ slotmap::new_key_type! { struct Worker; }
 
 #[derive(Debug)]
 pub enum ToQueue {
-	Enqueue { artifact: ArtifactPathId, params: Vec<u8>, result_tx: ResultSender },
+	Enqueue {
+		artifact: ArtifactPathId,
+		execution_timeout: Duration,
+		params: Vec<u8>,
+		result_tx: ResultSender,
+	},
 }
 
 struct ExecuteJob {
 	artifact: ArtifactPathId,
+	execution_timeout: Duration,
 	params: Vec<u8>,
 	result_tx: ResultSender,
 }
@@ -167,14 +173,14 @@ async fn purge_dead(metrics: &Metrics, workers: &mut Workers) {
 }
 
 fn handle_to_queue(queue: &mut Queue, to_queue: ToQueue) {
-	let ToQueue::Enqueue { artifact, params, result_tx } = to_queue;
+	let ToQueue::Enqueue { artifact, execution_timeout, params, result_tx } = to_queue;
 	tracing::debug!(
 		target: LOG_TARGET,
 		validation_code_hash = ?artifact.id.code_hash,
 		"enqueueing an artifact for execution",
 	);
 	queue.metrics.execute_enqueued();
-	let job = ExecuteJob { artifact, params, result_tx };
+	let job = ExecuteJob { artifact, execution_timeout, params, result_tx };
 
 	if let Some(available) = queue.workers.find_available() {
 		assign(queue, available, job);
@@ -326,7 +332,13 @@ fn assign(queue: &mut Queue, worker: Worker, job: ExecuteJob) {
 	queue.mux.push(
 		async move {
 			let _timer = execution_timer;
-			let outcome = super::worker::start_work(idle, job.artifact.clone(), job.params).await;
+			let outcome = super::worker::start_work(
+				idle,
+				job.artifact.clone(),
+				job.execution_timeout,
+				job.params,
+			)
+			.await;
 			QueueEvent::StartWork(worker, outcome, job.artifact.id, job.result_tx)
 		}
 		.boxed(),

polkadot/node/core/pvf/src/execute/worker.rs

@@ -34,8 +34,6 @@ use parity_scale_codec::{Decode, Encode};
 use polkadot_parachain::primitives::ValidationResult;
 use std::time::{Duration, Instant};
 
-const EXECUTION_TIMEOUT: Duration = Duration::from_secs(3);
-
 /// Spawns a new worker with the given program path that acts as the worker and the spawn timeout.
 ///
 /// The program should be able to handle `<program-path> execute-worker <socket-path>` invocation.
@@ -69,6 +67,7 @@ pub enum Outcome {
 pub async fn start_work(
 	worker: IdleWorker,
 	artifact: ArtifactPathId,
+	execution_timeout: Duration,
 	validation_params: Vec<u8>,
 ) -> Outcome {
 	let IdleWorker { mut stream, pid } = worker;
@@ -108,7 +107,7 @@ pub async fn start_work(
 				Ok(response) => response,
 			}
 		},
-		_ = Delay::new(EXECUTION_TIMEOUT).fuse() => {
+		_ = Delay::new(execution_timeout).fuse() => {
 			tracing::warn!(
 				target: LOG_TARGET,
 				worker_pid = %pid,