brainy/tests/unit/db/pending-flush-durability.test.ts

107 lines
4.4 KiB
TypeScript
Raw Normal View History

/**
* @module tests/unit/db/pending-flush-durability
* @description Finding 8: the async group-commit flush that persists single-op
* generation HISTORY must not swallow persist failures. Before the fix a failed
* background flush was a bare `prodLog.warn` writes kept succeeding while their
* before-images silently piled up in memory, never durable and unbounded.
*
* The contract now:
* - a single transient flush failure does NOT trip the alarm (tolerance), and
* - after PENDING_FLUSH_FAILURE_THRESHOLD consecutive failures the store LATCHES
* and REFUSES further writes with a typed PendingFlushDurabilityError rather
* than accumulate un-durable history, and
* - it self-heals: once a flush finally succeeds the latch lifts and writes resume.
* Live canonical data is never touched only the immutable history is stuck.
*
* Fake timers keep the background retry/coalesce timers from firing, so the exact
* number of flush attempts (and thus the latch point) is deterministic the test
* drives every flush explicitly.
*/
import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'
import { MemoryStorage } from '../../../src/storage/adapters/memoryStorage.js'
import { GenerationStore } from '../../../src/db/generationStore.js'
import { PendingFlushDurabilityError } from '../../../src/db/errors.js'
import { NounType } from '../../../src/types/graphTypes.js'
const ID = (suffix: string): string => `00000000-0000-4000-8000-0000000000${suffix}`
const meta = (v: number): Record<string, unknown> => ({
noun: NounType.Document,
subtype: 'note',
data: `payload-v${v}`,
version: v,
_rev: v
})
describe('db/GenerationStore pending-flush durability (finding 8)', () => {
let storage: MemoryStorage
let store: GenerationStore
beforeEach(async () => {
vi.useFakeTimers()
storage = new MemoryStorage()
await storage.init()
store = new GenerationStore(storage)
await store.open()
// High size threshold so single-ops never auto-flush — the test owns every flush.
;(store as any).pendingFlushThreshold = 1000
})
afterEach(() => {
vi.useRealTimers()
})
/** One single-op write that buffers a pending generation. */
const singleOp = (id: string, v: number) =>
store.commitSingleOp({
touched: { nouns: [id], verbs: [] },
execute: async () => {
await storage.saveNounMetadata(id, meta(v))
}
})
it('latches after repeated flush failures, refuses writes, then self-heals', async () => {
// Buffer a pending generation while storage is healthy.
await singleOp(ID('aa'), 1)
// Fault the HISTORY flush (raw generation-record writes) — NOT the live
// canonical write, which uses a different path (saveNounMetadata).
const fault = Object.assign(new Error('EIO simulated'), { code: 'EIO' })
const spy = vi.spyOn(storage as any, 'writeRawObject').mockRejectedValue(fault)
// Each explicit flush fails and is accounted; the third trips the latch.
for (let i = 0; i < 3; i++) {
await expect(store.flushPendingSingleOps()).rejects.toThrow('EIO simulated')
}
// Writes are now refused LOUDLY rather than piling up un-durable history.
await expect(singleOp(ID('bb'), 1)).rejects.toBeInstanceOf(PendingFlushDurabilityError)
// The live counter did not advance for the refused write (no generation consumed).
expect(store.generation()).toBe(1)
// Storage recovers → an explicit flush drains the retained tier and lifts the latch.
spy.mockRestore()
await expect(store.flushPendingSingleOps()).resolves.toBeUndefined()
// Writes resume; the next single-op commits normally.
const receipt = await singleOp(ID('cc'), 1)
expect(receipt.generation).toBe(2)
})
it('a single transient flush failure does NOT latch — writes continue', async () => {
await singleOp(ID('aa'), 1)
const spy = vi.spyOn(storage as any, 'writeRawObject').mockRejectedValue(new Error('blip'))
await expect(store.flushPendingSingleOps()).rejects.toThrow('blip') // failure #1, below threshold
spy.mockRestore()
// Below the latch threshold → the store still accepts writes.
const receipt = await singleOp(ID('bb'), 1)
expect(receipt.generation).toBe(2)
// A subsequent healthy flush drains the tier and resets the failure counter.
await expect(store.flushPendingSingleOps()).resolves.toBeUndefined()
expect((store as any).pendingFlushFailures).toBe(0)
expect((store as any).pendingFlushError).toBeNull()
})
})