diff options
4 files changed, 148 insertions, 6 deletions
diff --git a/packages/meshbay-hub/src/meshbay_hub/static/downloads.js b/packages/meshbay-hub/src/meshbay_hub/static/downloads.js index ce1901c..c790394 100644 --- a/packages/meshbay-hub/src/meshbay_hub/static/downloads.js +++ b/packages/meshbay-hub/src/meshbay_hub/static/downloads.js @@ -232,6 +232,16 @@ const SW_KEEPALIVE_MS = 10000; // target does not ping for ever. Bounded because the alternative is a timer // whose lifetime depends on every caller remembering to close its sink. const SW_KEEPALIVE_IDLE_MS = 120000; +// How long to spend waking the worker, and then confirming it holds the stream, +// before starting the navigation that has to find it. +// +// Both are answered in milliseconds when the worker is alive. They exist for +// when it is not: `pending` lives in the worker's memory, and one with nothing +// to do is terminated within tens of seconds — which a long upload spends +// without giving it a single event. A stream handed to a worker in that state +// is lost, and the iframe then wakes it with nothing to find, which is a 404 +// from the hub and fifteen seconds of silence per attempt. +const SW_WAKE_BUDGET_MS = 3000; // Holds a *successful* controller, or an in-flight attempt. Never a failure — // see serviceWorker(). The previous version cached the rejected/null result @@ -504,6 +514,35 @@ export async function openStreamedDownload(filename, size = 0, { return null; } +/** + * Get the worker running, and know that it is. + * + * `mbdl-ping` exists already — the page sends it every ten seconds *while* + * writing, because a streaming response does not count as activity and Firefox + * kills an idle worker mid-download. Nothing sent one before *starting* a + * download, which is the case that fails after a long upload has left the + * worker with nothing to do for minutes. + * + * Never fatal: a worker that does not answer may still be perfectly able to + * serve, and the caller finds that out the honest way. + */ +async function _wake(worker) { + const chan = new MessageChannel(); + const pong = new Promise((resolve) => { + chan.port1.onmessage = () => resolve(true); + }); + try { + worker.postMessage({ type: 'mbdl-ping' }, [chan.port2]); + } catch { + return false; + } + const awake = await Promise.race([ + pong, new Promise((r) => setTimeout(() => r(false), SW_WAKE_BUDGET_MS)), + ]); + try { chan.port1.close(); } catch { /* already gone */ } + return awake; +} + async function _attemptStreamedDownload(filename, size, attempt, controlMs, servedMs) { const worker = await serviceWorker(controlMs); @@ -517,12 +556,23 @@ async function _attemptStreamedDownload(filename, size, attempt, // backpressure that will never be relieved, which reads as a download frozen // after one chunk rather than as an error. const chan = new MessageChannel(); + let markReady = null; + const held = new Promise((resolve) => { markReady = resolve; }); const serving = new Promise((resolve) => { chan.port1.onmessage = (e) => { - if (e.data && e.data.type === 'mbdl-serving') resolve(true); + if (!e.data) return; + // The worker says it has the stream. Waiting for this is what stops the + // navigation racing a worker that was asleep when we posted. + if (e.data.type === 'mbdl-ready') markReady(true); + if (e.data.type === 'mbdl-serving') resolve(true); }; }); + // Wake it first, and wait for the answer. A worker that has been idle through + // a long upload is terminated, and a message posted to it in that state is + // lost — silently, which is the whole difficulty. + await _wake(worker); + try { worker.postMessage({ type: 'mbdl', id, filename, size, readable, port: chan.port2 }, [readable, chan.port2]); @@ -536,6 +586,12 @@ async function _attemptStreamedDownload(filename, size, attempt, return null; } + // Confirmed, not assumed. A worker that predates this sends no answer, and + // then navigating anyway is exactly what this code did before. + await Promise.race([ + held, new Promise((r) => setTimeout(r, SW_WAKE_BUDGET_MS)), + ]); + const frame = document.createElement('iframe'); frame.hidden = true; frame.src = `${PREFIX_PATH}${id}`; diff --git a/packages/meshbay-hub/src/meshbay_hub/static/sw.js b/packages/meshbay-hub/src/meshbay_hub/static/sw.js index 309ecc1..5f663f9 100644 --- a/packages/meshbay-hub/src/meshbay_hub/static/sw.js +++ b/packages/meshbay-hub/src/meshbay_hub/static/sw.js @@ -89,6 +89,21 @@ self.addEventListener('message', (event) => { // stream and the page's first write blocks for good. port: data.port || null, }); + // Say so, on the port the page is already listening to. + // + // `pending` is in memory, and a worker with nothing to do is terminated: + // Chrome after tens of seconds, which a long upload spends without giving + // this worker a single event. A stream posted to a worker in that state is + // lost, the iframe then wakes it with no entry to find, and the request falls + // through to the network — measured as a 404 from the hub and thirty seconds + // of nothing, twice, before the download started at all. + // + // The page waits for this before navigating, so the entry is known to be here + // rather than hoped to be. A page talking to an older worker gets no answer + // and navigates anyway, which is what it did before. + if (data.port) { + try { data.port.postMessage({ type: 'mbdl-ready', id: data.id }); } catch { /* gone */ } + } // A tab that is closed before it navigates would leave a stream here for the // life of the worker. setTimeout(() => pending.delete(data.id), 60000); diff --git a/packages/meshbay-hub/tests/test_downloads.py b/packages/meshbay-hub/tests/test_downloads.py index 41ae5d3..afb85d6 100644 --- a/packages/meshbay-hub/tests/test_downloads.py +++ b/packages/meshbay-hub/tests/test_downloads.py @@ -175,9 +175,23 @@ def test_backpressure_is_real(tmp_path): # The transfer list may carry more than the stream — a reply port rides # along now — so this asserts that `readable` is transferred, not the exact # shape of the list. - transfer = fn[fn.index("worker.postMessage("):] - transfer = transfer[transfer.index("["):transfer.index("]") + 1] - assert "readable" in transfer, "the readable half must be transferred, not copied" + # + # And every `postMessage` in here, not the first: a ping is sent to wake the + # worker before it is handed anything, and it carries only a port. Reading + # the first one would have moved this check onto the ping the day it was + # added, leaving the stream unguarded while still passing. + posts = [] + rest = fn + while "worker.postMessage(" in rest: + rest = rest[rest.index("worker.postMessage("):] + # Bounded by the call's own end: the keep-alive ping transfers nothing + # at all, and reaching past it for a `[` would read the next call's. + posts.append(rest[:rest.index(");") + 2]) + rest = rest[len("worker.postMessage("):] + lists = [c[c.index("["):c.index("]") + 1] for c in posts if "[" in c] + assert len(posts) >= 2, "the wake-up and the stream are both posted from here" + assert any("readable" in t for t in lists), ( + "the readable half must be transferred, not copied") assert "writer.write(bytes)" in fn assert "return null" in fn, "a browser that cannot transfer streams must say so" diff --git a/packages/meshbay-hub/tests/test_streamed_download_reliability.py b/packages/meshbay-hub/tests/test_streamed_download_reliability.py index bfd4a89..e1b3800 100644 --- a/packages/meshbay-hub/tests/test_streamed_download_reliability.py +++ b/packages/meshbay-hub/tests/test_streamed_download_reliability.py @@ -50,15 +50,37 @@ globalThis.localStorage = { }; const PLAN = %(plan)s; const log = { registers: 0, claims: 0, navigations: 0, served: 0, - unregisters: 0 }; + unregisters: 0, wakes: 0 }; // The worker as the page sees it: something with postMessage. It answers a // navigation by posting mbdl-serving back on the port it was handed, which is // exactly the confirmation the real sw.js sends from its fetch handler. let controller = null; const pendingByFrame = new Map(); +// Set before the controller exists, because the declaration below is what +// the temporal dead zone protects. +let asleep = PLAN.workerAsleep; const makeController = () => ({ postMessage: (msg, transfer) => { + // A worker with nothing to do is terminated, and `pending` goes with it. + // A ping wakes it; anything else posted while it sleeps is simply lost, + // which is what makes this failure silent. + if (asleep) { + if (msg.type === 'mbdl-ping') { + asleep = false; + log.wakes += 1; + if (msg.ports || (transfer && transfer[0])) { + const port = (transfer && transfer[0]) || null; + if (port) setTimeout(() => port.postMessage({type: 'mbdl-pong'}), 0); + } + } + return; + } + if (msg.type === 'mbdl-ping') { + const port = (transfer && transfer[0]) || null; + if (port) setTimeout(() => port.postMessage({type: 'mbdl-pong'}), 0); + return; + } if (msg.type === 'mbdl-claim') { log.claims += 1; // A worker that actually claims when asked, which is what sw.js does. @@ -70,6 +92,9 @@ const makeController = () => ({ } if (msg.type !== 'mbdl') return; pendingByFrame.set('/_mbdl/' + msg.id, msg.port); + // The worker says it has it, which is what the page waits for. + if (msg.port) setTimeout(() => msg.port.postMessage({type: 'mbdl-ready', + id: msg.id}), 0); }, }); @@ -167,7 +192,8 @@ def _run(tmp_path, body, *, control_after_ms=0, active=True, serve="always", register_throws=False, control_budget_ms=800, ready_settles=True, register_hangs=False, active_after_unregister=False, control_on_claim=False, - controlled_at_load=False, registered_at_load=False): + controlled_at_load=False, registered_at_load=False, + worker_asleep=False): module = tmp_path / "downloads.mjs" module.write_text(DOWNLOADS.read_text()) (tmp_path / "package.json").write_text('{"type":"module"}') @@ -181,6 +207,7 @@ def _run(tmp_path, body, *, control_after_ms=0, active=True, "activeAfterUnregister": active_after_unregister, "controlOnClaim": control_on_claim, "registeredAtLoad": registered_at_load, + "workerAsleep": worker_asleep, } script = tmp_path / "case.mjs" script.write_text( @@ -530,3 +557,33 @@ def test_the_streamed_target_says_it_cannot_be_paused(tmp_path): if (target) await target.writable.close(); """) assert out["pausable"] is False + + +# ── a worker that was asleep when we posted ───────────────────────────────── + +def test_a_sleeping_worker_is_woken_before_it_is_handed_a_stream(tmp_path): + """Reported from Chrome: a download started while an upload was running took + thirty seconds to begin, every time. + + `pending` lives in the worker's memory and a worker with nothing to do is + terminated — which is what a long upload leaves it, for minutes, since a + WebRTC transfer gives it no events at all. The stream posted to it was lost; + the iframe then woke it with nothing to find and the request fell through to + the network, measured in the console as a 404 from the hub and fifteen + seconds of silence, twice. + + `mbdl-ping` already existed — sent every ten seconds *while* writing, for + the same reason. Nothing sent one before *starting*. + """ + out = _run(tmp_path, """ + const target = await M.openStreamedDownload('film.mkv', 20e9, FAST); + out.target = target !== null; + out.wakes = log.wakes; + out.navigations = log.navigations; + if (target) await target.writable.close(); + """, worker_asleep=True) + assert out["target"] is True, "the download never started" + assert out["wakes"] == 1, "the worker was handed a stream while asleep" + assert out["navigations"] == 1, ( + f"took {out['navigations']} attempts — the first one was wasted on a " + "worker that had not been woken") |