fix(flush): the gate settles its waiter from the machine, never from a chain
Some checks failed
CI / Node 22 (push) Successful in 12m26s
CI / Node 24 (push) Successful in 12m19s
CI / Bun (latest) (push) Successful in 12m28s
CI / Integration + conformance (Node 22) (push) Failing after 17m12s
Some checks failed
CI / Node 22 (push) Successful in 12m26s
CI / Node 24 (push) Successful in 12m19s
CI / Bun (latest) (push) Successful in 12m28s
CI / Integration + conformance (Node 22) (push) Failing after 17m12s
The single-flight gate queued its follow-up as `leader.catch().then(() => this.flush())`. That waiter is settled ONLY by resolving the very promise the leader is being awaited through, so the moment anything inside a flush body awaits flush(), the promise graph closes on itself and nobody resolves — an unbounded hang, not a slow flush, presenting exactly like a bulk write timing out. No current call site awaits a flush from inside one, so this is a latent cycle rather than an observed one; the gate should not depend on that staying true. The queue is now a bare deferred. The leader's finally opens the gate and PROMOTES the waiter to a new leader, settling the deferred from that run; the finally returns nothing, so the leader never awaits its own follower. Every exit runs the same promotion — the leader resolving, the leader rejecting, the promoted run rejecting — so a queued caller is settled exactly once on every path, and a synchronous failure starting the promoted run is reported to the waiter instead of thrown into the leader's finally. close() drains both handles. tests/unit/brainy/flush-single-flight.test.ts pins the invariant on each path that must settle a waiter: many callers during one flush all resolve within a bound (one body, one follow-up, peak concurrency 1); a REJECTING leader still runs and settles the queued waiter; a rejecting follow-up settles its waiter and leaves the gate open; and the leader returns without waiting for a deliberately slower follower.
This commit is contained in:
parent
ebb3a4bf13
commit
dea3ec2031
3 changed files with 243 additions and 18 deletions
175
tests/unit/brainy/flush-single-flight.test.ts
Normal file
175
tests/unit/brainy/flush-single-flight.test.ts
Normal file
|
|
@ -0,0 +1,175 @@
|
|||
/**
|
||||
* @module tests/unit/brainy/flush-single-flight
|
||||
* @description THE FLUSH GATE NEVER STRANDS A WAITER.
|
||||
*
|
||||
* The gate serialises flushes: one body runs, at most one waits. The failure
|
||||
* mode that shape invites is a promise CYCLE — a queued follow-up expressed as
|
||||
* `leader.then(() => this.flush())` is settled only by resolving the promise
|
||||
* the leader is being awaited through, so anything that awaits `flush()` from
|
||||
* inside a flush body closes the graph on itself and nobody ever resolves.
|
||||
* That is an unbounded hang, not a slow flush, and it presents exactly like a
|
||||
* test timing out inside a bulk write.
|
||||
*
|
||||
* The gate therefore settles its waiter from the MACHINE (a bare deferred
|
||||
* promoted in the leader's `finally`), never from a chain. The laws pinned
|
||||
* here, each on a path that must settle the waiter:
|
||||
*
|
||||
* (a) many callers during one running flush → one body, one follow-up, and
|
||||
* EVERY caller resolves within a bound;
|
||||
* (b) the leader REJECTS → its own caller rejects, and the queued caller is
|
||||
* still run and still settled;
|
||||
* (c) the promoted follow-up itself rejects → its waiter rejects (settled,
|
||||
* not stranded) and the gate is left open for the next flush;
|
||||
* (d) the leader's promise does not wait for its follower.
|
||||
*/
|
||||
|
||||
import { describe, it, expect, afterEach } from 'vitest'
|
||||
import { Brainy } from '../../../src/brainy'
|
||||
import { NounType } from '../../../src/types/graphTypes'
|
||||
|
||||
type GateInternals = {
|
||||
_flushInFlight: Promise<void> | null
|
||||
_flushQueued: Promise<void> | null
|
||||
_flushBodyRuns: number
|
||||
_flushConcurrencyPeak: number
|
||||
_flushSteps: () => Promise<void>
|
||||
kickBackgroundFlush: (reason: 'threshold' | 'idle') => void
|
||||
}
|
||||
|
||||
/** Fail loudly rather than hanging the suite: a stranded waiter never settles. */
|
||||
function withinBound<T>(p: Promise<T>, ms: number, what: string): Promise<T> {
|
||||
let timer: ReturnType<typeof setTimeout>
|
||||
return Promise.race([
|
||||
p,
|
||||
new Promise<never>((_, reject) => {
|
||||
timer = setTimeout(() => reject(new Error(`${what} did not settle within ${ms}ms`)), ms)
|
||||
})
|
||||
]).finally(() => clearTimeout(timer)) as Promise<T>
|
||||
}
|
||||
|
||||
describe('the flush gate settles every waiter', () => {
|
||||
const brains: Brainy<any>[] = []
|
||||
|
||||
afterEach(async () => {
|
||||
for (const b of brains.splice(0)) {
|
||||
try { await b.close() } catch { /* already closed */ }
|
||||
}
|
||||
})
|
||||
|
||||
async function openBrain(): Promise<Brainy<any>> {
|
||||
const brain = new Brainy({ requireSubtype: false, storage: { type: 'memory' } })
|
||||
brains.push(brain)
|
||||
await brain.init()
|
||||
await brain.add({ data: 'a write, so a flush has work', type: NounType.Thing })
|
||||
return brain
|
||||
}
|
||||
|
||||
it('(a) every caller arriving during one flush resolves, and only one follows', async () => {
|
||||
const brain = await openBrain()
|
||||
const inner = brain as unknown as GateInternals
|
||||
|
||||
const realSteps = inner._flushSteps.bind(inner)
|
||||
inner._flushSteps = async () => {
|
||||
await new Promise((r) => setTimeout(r, 120))
|
||||
return realSteps()
|
||||
}
|
||||
|
||||
const runsBefore = inner._flushBodyRuns
|
||||
const leader = brain.flush()
|
||||
await new Promise((r) => setTimeout(r, 20))
|
||||
|
||||
const joiners = [brain.flush(), brain.flush(), brain.flush(), brain.flush()]
|
||||
for (let i = 0; i < 4; i++) inner.kickBackgroundFlush('threshold')
|
||||
expect(inner._flushQueued, 'exactly one waiter is queued').not.toBeNull()
|
||||
|
||||
await withinBound(Promise.all([leader, ...joiners]), 15_000, 'the flush callers')
|
||||
|
||||
expect(inner._flushBodyRuns - runsBefore).toBe(2)
|
||||
expect(inner._flushConcurrencyPeak).toBe(1)
|
||||
expect(inner._flushQueued).toBeNull()
|
||||
})
|
||||
|
||||
it('(b) a leader that REJECTS still runs and settles the queued waiter', async () => {
|
||||
const brain = await openBrain()
|
||||
const inner = brain as unknown as GateInternals
|
||||
|
||||
const realSteps = inner._flushSteps.bind(inner)
|
||||
let call = 0
|
||||
inner._flushSteps = async () => {
|
||||
call++
|
||||
await new Promise((r) => setTimeout(r, 80))
|
||||
if (call === 1) throw new Error('injected: the leader flush failed')
|
||||
return realSteps()
|
||||
}
|
||||
|
||||
const leader = brain.flush()
|
||||
await new Promise((r) => setTimeout(r, 20))
|
||||
const queued = brain.flush()
|
||||
|
||||
await expect(leader).rejects.toThrow(/injected: the leader flush failed/)
|
||||
// The waiter is NOT collateral damage of the leader's failure: it gets its
|
||||
// own run, and it settles.
|
||||
await withinBound(queued, 15_000, 'the queued waiter after a failed leader')
|
||||
expect(call).toBe(2)
|
||||
expect(inner._flushQueued).toBeNull()
|
||||
expect(inner._flushInFlight).toBeNull()
|
||||
})
|
||||
|
||||
it('(c) a promoted follow-up that rejects settles its waiter and opens the gate', async () => {
|
||||
const brain = await openBrain()
|
||||
const inner = brain as unknown as GateInternals
|
||||
|
||||
const realSteps = inner._flushSteps.bind(inner)
|
||||
let call = 0
|
||||
inner._flushSteps = async () => {
|
||||
call++
|
||||
await new Promise((r) => setTimeout(r, 80))
|
||||
if (call === 2) throw new Error('injected: the follow-up flush failed')
|
||||
return realSteps()
|
||||
}
|
||||
|
||||
const leader = brain.flush()
|
||||
await new Promise((r) => setTimeout(r, 20))
|
||||
const queued = brain.flush()
|
||||
|
||||
await withinBound(leader, 15_000, 'the leader')
|
||||
await withinBound(
|
||||
expect(queued).rejects.toThrow(/injected: the follow-up flush failed/),
|
||||
15_000,
|
||||
'the rejected follow-up'
|
||||
)
|
||||
// The gate is open: a later flush still runs.
|
||||
inner._flushSteps = realSteps
|
||||
await brain.add({ data: 'another write', type: NounType.Thing })
|
||||
await withinBound(brain.flush(), 15_000, 'the flush after a failed follow-up')
|
||||
expect(inner._flushInFlight).toBeNull()
|
||||
expect(inner._flushQueued).toBeNull()
|
||||
})
|
||||
|
||||
it('(d) the leader does not wait for its follower', async () => {
|
||||
const brain = await openBrain()
|
||||
const inner = brain as unknown as GateInternals
|
||||
|
||||
const realSteps = inner._flushSteps.bind(inner)
|
||||
let call = 0
|
||||
inner._flushSteps = async () => {
|
||||
call++
|
||||
// The follow-up is deliberately far slower than the leader.
|
||||
await new Promise((r) => setTimeout(r, call === 1 ? 60 : 600))
|
||||
return realSteps()
|
||||
}
|
||||
|
||||
const leader = brain.flush()
|
||||
await new Promise((r) => setTimeout(r, 20))
|
||||
const queued = brain.flush()
|
||||
|
||||
const t0 = Date.now()
|
||||
await withinBound(leader, 15_000, 'the leader')
|
||||
const leaderWall = Date.now() - t0
|
||||
// If the leader awaited its follower it could not return before the
|
||||
// follower's own 600ms body had run.
|
||||
expect(leaderWall).toBeLessThan(500)
|
||||
|
||||
await withinBound(queued, 15_000, 'the follower')
|
||||
})
|
||||
})
|
||||
Reference in a new issue