feat: add allocated server readiness control

This commit is contained in:
Josh Creek
2026-09-01 09:12:10 +01:00
parent 5b80c97337
commit 6caf719158
8 changed files with 218 additions and 4 deletions
+5
View File
@@ -54,6 +54,7 @@ var local_player_name := "Player"
# signed authorisation in hello rather than putting it in the endpoint URL.
var join_authorisation := ""
var require_join_authorisation := false
var admissions_open := true
var _allowed_join_authorisations: Dictionary = {}
var _active_join_peers: Dictionary = {} # opaque authorisation -> peer_id
var _join_history: Dictionary = {} # token -> {generation, lost_at}
@@ -98,6 +99,7 @@ func _on_shutting_down() -> void:
_join_authorisation_context.clear()
_join_signing_key = PackedByteArray()
require_join_authorisation = false
admissions_open = true
func configure_join_authorisations(tokens: Array, context: Dictionary, signing_key: PackedByteArray = PackedByteArray()) -> bool:
@@ -122,6 +124,9 @@ func configure_join_authorisations(tokens: Array, context: Dictionary, signing_k
func _on_peer_disconnected(peer_id: int) -> void:
if not multiplayer.is_server():
return
if not admissions_open:
await _reject(multiplayer.get_remote_sender_id(), "server is draining")
return
NetworkManager.invalidate_peer(peer_id)
_remove_player(peer_id)
+24
View File
@@ -1,6 +1,7 @@
extends Node
const NetCodec = preload("res://scripts/net_codec.gd")
const ServerControlScript = preload("res://scripts/server_control.gd")
# Headless dedicated server entry point (task 1.6). Parses CLI args, hosts
# via NetworkManager, logs structured lines, and watches for physics-tick
@@ -26,6 +27,8 @@ const NetCodec = preload("res://scripts/net_codec.gd")
var _last_physics_frame := 0
var config: ServerConfig = null
var _watchdog_armed := false # skip the first _process(): engine startup scheduling can batch several physics frames before the first idle frame runs, which isn't a real overrun
var _control: ServerControl = null
var _drain_requested := false
func _ready() -> void:
@@ -77,6 +80,15 @@ func _ready() -> void:
printerr("cosmic-clash-server: refusing to start with invalid join-authorisations-file")
get_tree().quit(1)
return
_control = ServerControlScript.new()
_control.name = "ServerControl"
_control.drain_requested.connect(_on_drain_requested)
get_tree().root.add_child.call_deferred(_control)
var control_err := _control.start(int(config.get_value("readiness-port")), OS.get_environment(String(config.get_value("drain-token-env"))))
if control_err != OK:
printerr("cosmic-clash-server: refusing to start with invalid readiness control port")
get_tree().quit(1)
return
NetworkManager.client_connected.connect(_on_client_connected)
NetworkManager.client_disconnected.connect(_on_client_disconnected)
@@ -88,6 +100,8 @@ func _ready() -> void:
ServerLog.error("server_boot_failed", {"port": port, "error": error_string(err)})
get_tree().quit(1)
return
if _control != null:
_control.set_process_ready(true)
_install_match_loop()
ServerLog.info("server_started", {
"port": port, "max_clients": max_clients, "log_level": ServerLog.level_name(),
@@ -119,6 +133,10 @@ func _install_match_loop() -> void:
func _process(_delta: float) -> void:
NetworkManager.poll()
if _drain_requested:
var scene := get_tree().current_scene
if not (is_instance_valid(scene) and scene.is_in_group("game")) and MatchNet.roster.is_empty():
get_tree().quit(0)
var current := Engine.get_physics_frames()
var steps := current - _last_physics_frame
_last_physics_frame = current
@@ -149,3 +167,9 @@ func _on_player_joined(peer_id: int, player_name: String) -> void:
func _on_player_left(peer_id: int) -> void:
ServerLog.info("player_left", {"peer_id": peer_id, "roster": MatchNet.roster.size()})
func _on_drain_requested() -> void:
_drain_requested = true
MatchNet.admissions_open = false
ServerLog.info("server_draining", {"reason": "control_request"})
+5
View File
@@ -77,6 +77,8 @@ static func specs() -> Array[Spec]:
out.append(Spec.new("region", Kind.STRING, "", "allocation", "Assigned region: EU or NA"))
out.append(Spec.new("join-authorisations-file", Kind.STRING, "", "allocation", "JSON array of control-plane signed join envelopes mounted for this match"))
out.append(Spec.new("join-authorisations-key-file", Kind.STRING, "", "allocation", "HMAC-SHA256 key file for verifying mounted join envelopes"))
out.append(Spec.new("readiness-port", Kind.INT, 7780, "allocation", "Loopback HTTP port for allocated process-ready and drain control"))
out.append(Spec.new("drain-token-env", Kind.STRING, "COSMIC_CLASH_DRAIN_TOKEN", "allocation", "Environment variable containing the allocated drain bearer token"))
return out
@@ -244,6 +246,9 @@ func _validate() -> void:
var port := int(values["port"])
if port < 1 or port > 65535:
errors.append("--port must be 1-65535, got %d" % port)
var readiness_port := int(values["readiness-port"])
if readiness_port < 1 or readiness_port > 65535:
errors.append("--readiness-port must be 1-65535, got %d" % readiness_port)
if int(values["max-clients"]) < 1:
errors.append("--max-clients must be at least 1, got %d" % int(values["max-clients"]))
if float(values["match-length"]) <= 0.0:
+106
View File
@@ -0,0 +1,106 @@
class_name ServerControl
extends Node
# Small loopback HTTP control surface for allocated servers. The Go supervisor
# uses GET /ready as the explicit process-ready probe and POST /drain during a
# controlled termination. Direct/community servers do not start this node.
signal drain_requested
var _listener := TCPServer.new()
var _peers: Array = []
var _ready_for_connections := false
var _draining := false
var _drain_token := ""
func start(port: int, drain_token: String = "") -> Error:
if port < 1 or port > 65535:
return ERR_INVALID_PARAMETER
_drain_token = drain_token
return _listener.listen(port, "127.0.0.1")
func stop() -> void:
_listener.stop()
for peer in _peers:
if is_instance_valid(peer):
peer.disconnect_from_host()
_peers.clear()
func set_process_ready(value: bool) -> void:
_ready_for_connections = value and not _draining
func is_draining() -> bool:
return _draining
func _exit_tree() -> void:
stop()
func _process(_delta: float) -> void:
while _listener.is_connection_available():
_peers.append(_listener.take_connection())
for i in range(_peers.size() - 1, -1, -1):
var peer: StreamPeerTCP = _peers[i]
if peer.get_status() != StreamPeerTCP.STATUS_CONNECTED:
_peers.remove_at(i)
continue
var available := peer.get_available_bytes()
if available <= 0:
continue
var request := peer.get_utf8_string(available)
if "\r\n\r\n" not in request:
continue
_respond(peer, request)
_peers.remove_at(i)
func _respond(peer: StreamPeerTCP, request: String) -> void:
var lines := request.split("\r\n")
var first := lines[0].split(" ") if not lines.is_empty() else PackedStringArray()
var method := String(first[0]) if first.size() > 0 else ""
var path := String(first[1]) if first.size() > 1 else ""
var status := 404
var reason := "Not Found"
var body := ""
if method == "GET" and path == "/ready":
status = 200 if _ready_for_connections else 503
reason = "OK" if status == 200 else "Service Unavailable"
elif method == "GET" and path == "/health":
status = 200
reason = "OK"
elif method == "POST" and path == "/drain":
var supplied := ""
for line in lines:
if line.begins_with("Authorization: Bearer "):
supplied = line.substr("Authorization: Bearer ".length())
if _drain_token.is_empty() or not _constant_time_equal(supplied, _drain_token):
status = 401
reason = "Unauthorized"
else:
_draining = true
_ready_for_connections = false
drain_requested.emit()
status = 202
reason = "Accepted"
else:
status = 405 if method in ["GET", "POST"] else 400
reason = "Method Not Allowed" if status == 405 else "Bad Request"
body = "{\"status\":\"%s\"}" % ("ready" if status == 200 else "not_ready")
var response := "HTTP/1.1 %d %s\r\nContent-Type: application/json\r\nContent-Length: %d\r\nConnection: close\r\n\r\n%s" % [status, reason, body.to_utf8_buffer().size(), body]
peer.put_data(response.to_utf8_buffer())
peer.disconnect_from_host()
func _constant_time_equal(a: String, b: String) -> bool:
var left := a.to_utf8_buffer()
var right := b.to_utf8_buffer()
var difference := left.size() ^ right.size()
var length := mini(left.size(), right.size())
for i in length:
difference |= left[i] ^ right[i]
return difference == 0