diff options
Diffstat (limited to 'packages/meshbay-node/src/meshbay_node/cli')
| -rw-r--r-- | packages/meshbay-node/src/meshbay_node/cli/lifecycle.py | 57 |
1 files changed, 50 insertions, 7 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/cli/lifecycle.py b/packages/meshbay-node/src/meshbay_node/cli/lifecycle.py index 901c3d5..b461055 100644 --- a/packages/meshbay-node/src/meshbay_node/cli/lifecycle.py +++ b/packages/meshbay-node/src/meshbay_node/cli/lifecycle.py @@ -55,23 +55,36 @@ def _running_status(cfg) -> dict | None: return _await_daemon(cfg, since=0, timeout=0.1) +class NodeStillRunning(RuntimeError): + pass + + def _stop_node(cfg) -> str: """Stop the node, whichever session it runs in: through its own control API - first, so it shuts down properly, then by force. Returns how it went.""" + first, so it shuts down properly, then by force. Returns how it went, and + raises NodeStillRunning when a node process is still there at the end -- + never "stopped" about a process nobody saw go.""" import time from meshbay_node.platform import ( + _pid_alive, autostart_end, + kill_pid, + node_pids, request_graceful_stop, service_end, service_state, service_status, ) + answering = _running_status(cfg) + pid = answering.get("pid") if answering else None if request_graceful_stop(cfg.data_dir, cfg.node.ui_port): how = "stopped" - elif _running_status(cfg) is None: + elif answering is None and not node_pids(): how = "not running" else: + # Asked and not gone: its control API closes first, so it may answer + # nothing while its process is still there. how = "stopped (forced)" if service_status()["installed"]: # Also leaves the task "Ready": a /run while it still reads "Running" @@ -80,7 +93,17 @@ def _stop_node(cfg) -> str: deadline = time.monotonic() + 15 while service_state().lower() == "running" and time.monotonic() < deadline: time.sleep(0.25) + if pid is not None and _pid_alive(int(pid)): + kill_pid(int(pid)) # the one that answered, by pid, wherever it came from autostart_end() # a node in this session that would not stop + deadline = time.monotonic() + 5 + while (left := node_pids()) and time.monotonic() < deadline: + time.sleep(0.25) + if left: + raise NodeStillRunning( + f"meshbay-node is still running (pid {', '.join(map(str, left))}) and could " + "not be stopped from here -- it was probably started from an " + "administrator prompt. Stop it there, or end it in Task Manager.") return how @@ -94,7 +117,12 @@ def _start_and_confirm(args, action: str) -> None: cfg = load_config(args.config or DEFAULT_CONFIG_PATH) if action == "restart": - _stop_node(cfg) + try: + _stop_node(cfg) + except NodeStillRunning as e: + # Starting another would find the port taken and quit at once. + print(f"Could not restart the node: {e}") + sys.exit(1) else: already = _running_status(cfg) if already is not None: @@ -122,6 +150,21 @@ def _start_and_confirm(args, action: str) -> None: "its files were not replaced, or another copy was started.") +def _print_stop(args) -> None: + try: + print(_stop_node(load_config(args.config or DEFAULT_CONFIG_PATH))) + except NodeStillRunning as e: + print(e) + sys.exit(1) + + +def _stop_node_or_warn(args) -> None: + try: + _stop_node(load_config(args.config or DEFAULT_CONFIG_PATH)) + except NodeStillRunning as e: + print(f"warning: {e}") + + def restart_daemon(args) -> None: if sys.platform == "win32": _start_and_confirm(args, "restart") @@ -161,7 +204,7 @@ def autostart(args) -> None: elif sub == "start": _start_and_confirm(args, "start") elif sub == "stop": - print(_stop_node(load_config(args.config or DEFAULT_CONFIG_PATH))) + _print_stop(args) elif sub == "status": st = _plat.autostart_status() if st["installed"]: @@ -186,7 +229,7 @@ def service(args) -> None: if sub == "install": # A node already running in this session holds the control API's port: # the service's own would exit at once, leaving the old one in charge. - _stop_node(load_config(args.config or DEFAULT_CONFIG_PATH)) + _stop_node_or_warn(args) try: _plat.service_install() except RuntimeError as e: @@ -201,7 +244,7 @@ def service(args) -> None: elif sub == "remove": # Deleting a task does not end its running instance: stop the node # first, or it runs on in session 0 with nothing left to stop it. - _stop_node(load_config(args.config or DEFAULT_CONFIG_PATH)) + _stop_node_or_warn(args) _plat.service_remove() print(f"Removed the {_plat.TASK_NAME!r} scheduled task.") elif sub == "start": @@ -211,7 +254,7 @@ def service(args) -> None: sys.exit(1) _start_and_confirm(args, "start") elif sub == "stop": - print(_stop_node(load_config(args.config or DEFAULT_CONFIG_PATH))) + _print_stop(args) elif sub == "status": st = _plat.service_status() if st["installed"]: |