feat: establish simulation scaling baseline

2026-07-16 13:07:01 +02:00
parent 4f88d15e12
commit 4be72639d8
14 changed files with 1004 additions and 15 deletions
@@ -0,0 +1,103 @@
+extends SceneTree
+
+const SimulationManagerScript := preload("res://simulation/SimulationManager.gd")
+const BenchmarkScript := preload("res://simulation/benchmark/SimulationScalingBenchmark.gd")
+
+var failures: Array[String] = []
+
+
+func _initialize() -> void:
+	call_deferred("_run")
+
+
+func _run() -> void:
+	var first := _run_case(9001)
+	var repeated := _run_case(9001)
+	var different_seed := _run_case(9002)
+	_check(not first.is_empty(), "The benchmark fixture should produce one result")
+	if first.is_empty():
+		_finish()
+		return
+	_check(first["fixture_valid"], "The prepared benchmark state should pass schema validation")
+	_check(
+		(
+			int(first["schema_version"]) == SimulationScalingBenchmark.SCHEMA_VERSION
+			and StringName(first["workload_id"]) == SimulationScalingBenchmark.WORKLOAD_ID
+			and int(first["population"]) == 12
+			and int(first["history_seed_events"]) == 24
+			and int(first["measured_ticks"]) == 8
+			and int(first["npc_updates"]) == 96
+			and is_equal_approx(float(first["tick_interval"]), 1.2)
+			and int(first["end_tick"]) - int(first["start_tick"]) == 8
+		),
+		"The result should identify the exact workload and measured update count"
+	)
+	_check(
+		(
+			int(first["elapsed_usec"]) > 0
+			and int(first["simulation_usec"]) > 0
+			and int(first["arrival_usec"]) > 0
+			and int(first["start_state_bytes"]) > 0
+			and int(first["end_state_bytes"]) >= int(first["start_state_bytes"])
+			and int(first["arrivals_processed"]) > 0
+			and int(first["events_recorded"]) > 0
+			and int(first["end_event_count"]) >= 24
+			and String(first["final_checksum"]).length() == 64
+		),
+		"The benchmark should report timing, state growth, updates, history, and a checksum"
+	)
+	for deterministic_key in [
+		"final_checksum",
+		"start_state_bytes",
+		"end_state_bytes",
+		"state_growth_bytes",
+		"start_event_count",
+		"end_event_count",
+		"events_recorded",
+		"start_known_reference_count",
+		"end_known_reference_count",
+		"arrivals_processed",
+		"warmup_arrivals",
+		"tick_interval",
+	]:
+		_check(
+			first[deterministic_key] == repeated[deterministic_key],
+			"Repeated benchmark runs should preserve %s" % deterministic_key
+		)
+	_check(
+		first["final_checksum"] != different_seed["final_checksum"],
+		"A different fixture seed should produce a different deterministic checksum"
+	)
+	_finish()
+
+
+func _run_case(seed_value: int) -> Dictionary:
+	var manager := SimulationManagerScript.new()
+	manager.simulation_seed = seed_value
+	manager.debug_logs = false
+	manager.set_process(false)
+	root.add_child(manager)
+	var benchmark := BenchmarkScript.new()
+	if not benchmark.prepare_manager(manager, 12, 24, seed_value):
+		manager.free()
+		return {}
+	var fixture_valid := SimulationStateRecord.from_json(manager.serialize_state()) != null
+	var result: Dictionary = benchmark.measure_manager(manager, 12, 24, 2, 8)
+	result["fixture_valid"] = fixture_valid
+	manager.free()
+	return result
+
+
+func _check(condition: bool, message: String) -> void:
+	if not condition:
+		failures.append(message)
+
+
+func _finish() -> void:
+	if failures.is_empty():
+		print("[TEST] Simulation scaling benchmark passed: valid fixture -> stable metrics")
+		quit(0)
+		return
+	for failure in failures:
+		push_error("[TEST] " + failure)
+	quit(1)
@@ -0,0 +1 @@
+uid://sn24dfw1g3pd