diff options
Diffstat (limited to 'packages/meshbay-node/tests/test_transfer_slots_wire.py')
| -rw-r--r-- | packages/meshbay-node/tests/test_transfer_slots_wire.py | 346 |
1 files changed, 346 insertions, 0 deletions
diff --git a/packages/meshbay-node/tests/test_transfer_slots_wire.py b/packages/meshbay-node/tests/test_transfer_slots_wire.py new file mode 100644 index 0000000..db8c17a --- /dev/null +++ b/packages/meshbay-node/tests/test_transfer_slots_wire.py @@ -0,0 +1,346 @@ +""" +Transfer leases over the session, rather than over `TransferSlots` alone. + +test_transfer_slots.py proves the decisions; this proves the seam. Both exist +because the seam is where this repo's defects have actually lived — a reply +routed by arrival order, a session popped from a dict without its work being +stopped, a slot released by a `finally` nobody reached. + +Three things can only be checked here: + + - the handlers answer under the right shape, and refuse another connection's + transfer id; + - **losing the connection gives everything back.** That is the primary + reclaim, and it is a hook (`shutdown_tasks`) rather than a timer, so a test + of the pool alone would never touch it; + - a slot freed by one peer is *announced* to the peer waiting on it. A grant + nobody hears about is precisely the "stuck at waiting" report the design + exists to prevent, and it would look correct in the pool. +""" + +import pytest + +# Every test drives a message handler, and in the node a message handler always +# runs inside the event loop: `_do_transfer_open` starts the sweeper task there. +# Calling these synchronously tested a situation that cannot happen and failed +# on "no current event loop" the moment the sweeper stopped being faked. +pytestmark = pytest.mark.asyncio + +from meshbay_common.protocol import MNP +from meshbay_node.transfers import DOWNLOAD, UPLOAD +from meshbay_node.transport.webrtc_server import WebRTCPeerSession + + +class _Session(WebRTCPeerSession): + """A session with the DataChannel replaced by a list, and nothing else.""" + + def __init__(self, ctx, *, key, user, group="g1"): + self._ctx = ctx + self._registry_key = key + self._user_id = user + self._group_id = group + self.sent: list[dict] = [] + + def _send(self, msg): + self.sent.append(msg) + + def _spawn(self, coro): # pragma: no cover - not used by these tests + coro.close() + return None + + def last(self, mtype=MNP.TRANSFER_STATE): + return next(m for m in reversed(self.sent) if m.get("type") == mtype) + + +@pytest.fixture +def ctx(): + """A transport context, with the sweeper stopped on the way out. + + A task left running past the end of its test is a warning in the next one + and a hang in the worst case; the sweeper is started on demand by design, so + tearing it down is the test's job. + """ + c: dict = {"_peers": {}} + yield c + task = c.get("_transfer_sweeper") + if task is not None: + task.cancel() + + +def _join(ctx, key, user, group="g1") -> _Session: + s = _Session(ctx, key=key, user=user, group=group) + ctx["_peers"][key] = s + return s + + +async def test_a_granted_transfer_is_answered_as_granted(ctx): + peer = _join(ctx, "s1", "alice") + peer._do_transfer_open({"tr": "t1", "kind": DOWNLOAD, "bytes": 10}) + reply = peer.last() + assert reply["state"] == "granted" + assert reply["tr"] == "t1" + assert reply["kind"] == DOWNLOAD + assert reply["used"] == 1 and reply["cap"] >= 1 + + +async def test_a_queued_transfer_is_told_how_many_are_ahead(ctx): + peer = _join(ctx, "s1", "alice") + peer._slots().per_member[DOWNLOAD] = 1 + peer._do_transfer_open({"tr": "t1"}) + peer._do_transfer_open({"tr": "t2"}) + peer._do_transfer_open({"tr": "t3"}) + assert [m["state"] for m in peer.sent] == ["granted", "queued", "queued"] + assert peer.sent[-1]["ahead"] == 1 + + +async def test_the_reply_carries_no_name_and_no_path(ctx): + """A lease holds neither, and `transfer_state` stays in clear — so this is + the message where a filename would quietly become metadata on the wire.""" + peer = _join(ctx, "s1", "alice") + peer._do_transfer_open({"tr": "t1", "name": "Some Saga.mkv", + "path": "/srv/films"}) + assert set(peer.last()) <= { + "type", "v", "tr", "state", "kind", "used", "cap", "node_used", + "node_cap", "ahead", "reason"} + + +async def test_closing_frees_the_slot(ctx): + peer = _join(ctx, "s1", "alice") + peer._do_transfer_open({"tr": "t1"}) + peer._do_transfer_close({"tr": "t1", "reason": "done"}) + assert peer.last()["state"] == "closed" + assert peer._slots().in_use(DOWNLOAD) == 0 + + +async def test_one_peer_cannot_close_anothers_transfer(ctx): + """A denial of service one random id away, otherwise.""" + alice = _join(ctx, "s1", "alice") + bob = _join(ctx, "s2", "bob") + alice._do_transfer_open({"tr": "t1"}) + bob._do_transfer_close({"tr": "t1"}) + assert bob.last("error")["code"] == "not_your_transfer" + assert "t1" in alice._slots().leases + + +async def test_one_peer_cannot_open_on_anothers_id(ctx): + alice = _join(ctx, "s1", "alice") + bob = _join(ctx, "s2", "bob") + alice._do_transfer_open({"tr": "t1"}) + bob._do_transfer_open({"tr": "t1"}) + assert bob.last("error")["code"] == "not_your_transfer" + + +async def test_a_transfer_with_no_id_is_refused(ctx): + peer = _join(ctx, "s1", "alice") + peer._do_transfer_open({"kind": DOWNLOAD}) + assert peer.last("error")["code"] == "bad_transfer_id" + + +# ── the reclaim that matters ──────────────────────────────────────────────── + +async def test_losing_the_connection_gives_everything_back(ctx): + peer = _join(ctx, "s1", "alice") + peer._do_transfer_open({"tr": "t1"}) + peer._do_transfer_open({"tr": "t2", "kind": UPLOAD}) + peer._release_transfers() + slots = peer._slots() + assert slots.leases == {} + assert slots.in_use(DOWNLOAD) == 0 and slots.in_use(UPLOAD) == 0 + + +async def test_the_freed_slot_reaches_the_peer_that_was_waiting(ctx): + """ + The seam this file exists for. In the pool, granting is correct; if the + grant is not pushed, the waiting client sits on "waiting" for ever with a + node that believes it is streaming — and every unit test still passes. + """ + alice = _join(ctx, "s1", "alice") + bob = _join(ctx, "s2", "bob") + alice._slots().caps[DOWNLOAD] = 1 + + alice._do_transfer_open({"tr": "a1"}) + bob._do_transfer_open({"tr": "b1"}) + assert bob.last()["state"] == "queued" + + alice._release_transfers() + assert bob.last()["state"] == "granted", ( + "bob was granted the slot and never told") + assert bob.last()["tr"] == "b1" + + +async def test_a_grant_crossing_groups_still_reaches_its_peer(ctx): + """The pools are node-wide and `_peer_registry` is per group (finding H1), + so the peer to notify is not necessarily in the notifier's own registry.""" + groups = {"g1": {"_peers": {}}, "g2": {"_peers": {}}} + ctx = {"groups": groups} + alice = _Session(ctx, key="s1", user="alice", group="g1") + groups["g1"]["_peers"]["s1"] = alice + bob = _Session(ctx, key="s2", user="bob", group="g2") + groups["g2"]["_peers"]["s2"] = bob + + alice._slots().caps[DOWNLOAD] = 1 + alice._do_transfer_open({"tr": "a1"}) + bob._do_transfer_open({"tr": "b1"}) + assert bob.last()["state"] == "queued" + + alice._release_transfers() + assert bob.last()["state"] == "granted", ( + "a slot freed in one group never reached the peer waiting in another") + + +async def test_raising_the_cap_notifies_who_it_starts(ctx): + """`set_capacity` arrives from the loopback API, with no session behind it — + the grants it produces still have to be pushed.""" + from meshbay_node.transport.webrtc_server import WebRTCTransport + + transport = WebRTCTransport.__new__(WebRTCTransport) + transport._ctx = ctx + peer = _join(ctx, "s1", "alice") + peer._slots().caps[DOWNLOAD] = 1 + peer._do_transfer_open({"tr": "t1"}) + peer._do_transfer_open({"tr": "t2"}) + assert peer.last()["state"] == "queued" + + transport.set_capacity(max_concurrent_downloads=4) + assert peer.last()["state"] == "granted" and peer.last()["tr"] == "t2" + + +async def test_the_operator_can_see_the_queue(ctx): + """`GET /api/transfers` is the answer to "was this peer ever queued", which + a log line cannot give when the symptom is that nothing is happening.""" + from meshbay_node import ops + + peer = _join(ctx, "s1", "alice") + peer._slots().caps[DOWNLOAD] = 1 + peer._do_transfer_open({"tr": "t1", "bytes": 5}) + peer._do_transfer_open({"tr": "t2", "bytes": 7}) + + class _T: + _ctx = ctx + + snapshot = await ops.list_transfers({"webrtc": _T()}) + assert snapshot["pools"][DOWNLOAD]["in_use"] == 1 + assert snapshot["pools"][DOWNLOAD]["queued"] == 1 + assert {x["state"] for x in snapshot["leases"]} == {"granted", "queued"} + assert all("name" not in x and "path" not in x for x in snapshot["leases"]) + + +async def test_asking_before_anything_has_transferred_is_not_an_error(): + from meshbay_node import ops + + class _T: + _ctx: dict = {} + + snapshot = await ops.list_transfers({"webrtc": _T()}) + assert snapshot["leases"] == [] + assert snapshot["pools"][DOWNLOAD]["in_use"] == 0 + + +@pytest.mark.asyncio +async def test_the_caps_shown_are_the_operators_before_anything_transfers(): + """ + `transfers set 2 2` answers "applied now"; `transfers show` said 0/8 — + because the no-pool branch reported the module defaults rather than what the + operator had just set. Found by running it against a real node. The previous + test asserted the defaults, so it agreed with the bug: an operator would + have read that as the hot-swap doing nothing all over again. + """ + from meshbay_node import ops + + class _T: + _ctx = {"max_concurrent_downloads": 2, "max_concurrent_uploads": 3} + + snapshot = await ops.list_transfers({"webrtc": _T()}) + assert snapshot["pools"][DOWNLOAD]["cap"] == 2 + assert snapshot["pools"][UPLOAD]["cap"] == 3 + + +# ── the sweeper's lifetime ────────────────────────────────────────────────── + +async def test_the_sweeper_outlives_the_session_that_started_it(ctx): + """ + It was started with `self._spawn`, which ties a task to one session's set — + so it was cancelled the moment that peer left, and every other peer's + abandoned lease stopped being reclaimed. Nothing else would have noticed: + the node simply fills up over days. + """ + import asyncio + + from meshbay_node.transport import webrtc_server as ws + + alice = _join(ctx, "s1", "alice") + bob = _join(ctx, "s2", "bob") + # The real _spawn, so the session genuinely owns what it starts. + alice._tasks = set() + alice._spawn = ws.WebRTCPeerSession._spawn.__get__(alice) + bob._tasks = set() + bob._spawn = ws.WebRTCPeerSession._spawn.__get__(bob) + + alice._do_transfer_open({"tr": "a1"}) + bob._do_transfer_open({"tr": "b1"}) + sweeper = ctx["_transfer_sweeper"] + assert sweeper is not None and not sweeper.done() + + # Alice leaves, exactly as shutdown_tasks does it. + alice._release_transfers() + for task in list(alice._tasks): + task.cancel() + await asyncio.gather(*alice._tasks, return_exceptions=True) + await asyncio.sleep(0) + + assert not sweeper.done(), ( + "the sweeper died with the session that happened to start it; bob's " + "lease would never be reclaimed") + sweeper.cancel() + + +async def test_the_sweeper_stops_when_the_last_lease_goes(ctx): + """An idle node must run no timer — the reason this is started on demand + rather than at boot.""" + import asyncio + + from meshbay_node.transport import webrtc_server as ws + + peer = _join(ctx, "s1", "alice") + peer._tasks = set() + peer._spawn = ws.WebRTCPeerSession._spawn.__get__(peer) + + original = ws.TRANSFER_SWEEP_SECS + ws.TRANSFER_SWEEP_SECS = 0.01 + try: + peer._do_transfer_open({"tr": "t1"}) + peer._do_transfer_close({"tr": "t1"}) + sweeper = ctx["_transfer_sweeper"] + await asyncio.wait_for(sweeper, timeout=2) + assert ctx.get("_transfer_sweeper") is None + finally: + ws.TRANSFER_SWEEP_SECS = original + + +async def test_a_chunk_request_keeps_its_lease_alive(ctx): + """ + The seam that cost an afternoon. `TransferSlots.touch` existed, was tested, + and **nothing ever called it**: the node ignored `tr` on `file_req` + entirely, so `used` stayed False for every download ever made and the + sweeper revoked each grant 30 s in, while the file was transferring. + + Neither side's tests could see it — the pool was correct, the handlers were + correct, and the call between them was missing. Only the node's own log + showed it, repeating the same reclaim every 30 s. + """ + peer = _join(ctx, "s1", "alice") + peer._do_transfer_open({"tr": "t1", "bytes": 1024}) + lease = peer._slots().leases["t1"] + assert lease.used is False + + # A chunk request for a file that does not exist still counts: what marks + # the lease is the peer asking, not the node succeeding. + peer._group_ctx()["index"] = None + try: + await peer._do_file_request({"file_id": "nope", "chunk_index": 0, + "tr": "t1"}) + except Exception: + pass + assert peer._slots().leases["t1"].used is True, ( + "a chunk request under this lease did not mark it alive; the node will " + "revoke the grant in 30 seconds") |