fix: metadata-only update() never rewrites the noun record — the unconditional whole-vector save turned per-entity stat touches into full rewrites+fsync, amplifying read-heavy sweeps into disk saturation on a production deployment
Also: idle PathResolver stats tick no longer logs NaN% every minute (logs only on new traffic, via prodLog); graph-lsm-* key family recognized as system resources (kills the per-boot unknown-key warning on provider-backed brains). Four regression pins in tests/integration/update-write-granularity.
This commit is contained in:
parent
64049631bc
commit
cb717be275
4 changed files with 155 additions and 15 deletions
126
tests/integration/update-write-granularity.test.ts
Normal file
126
tests/integration/update-write-granularity.test.ts
Normal file
|
|
@ -0,0 +1,126 @@
|
|||
/**
|
||||
* @module tests/integration/update-write-granularity
|
||||
* @description Write-granularity law for update() (SELF-ENGINE-RESTART-GRIND,
|
||||
* 2026-07-29): a metadata-only update must NEVER rewrite the noun record —
|
||||
* the record carries the full vector, so an unconditional save turns every
|
||||
* metadata touch into a whole-vector rewrite + fsync. Under a read-heavy
|
||||
* consumer sweep bumping per-entity stats this amplified into disk saturation
|
||||
* on a production deployment. Laws:
|
||||
* (1) metadata-only update() → zero saveNoun calls (metadata leg only);
|
||||
* (2) data/vector/type-changing update() → saveNoun runs (the vector leg and
|
||||
* HNSW reindex still happen when the vector side actually changed);
|
||||
* (3) the metadata-only path still lands: merged metadata readable, _rev
|
||||
* bumped, find() by the new field sees the entity.
|
||||
*/
|
||||
import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'
|
||||
import { Brainy } from '../../src/brainy.js'
|
||||
import { NounType } from '../../src/types/graphTypes.js'
|
||||
|
||||
const stubEmbedding = async (text: string): Promise<number[]> => {
|
||||
const hash = text.split('').reduce((acc, char) => acc + char.charCodeAt(0), 0)
|
||||
return new Array(384).fill(0).map((_, i) => Math.sin(hash + i))
|
||||
}
|
||||
|
||||
describe('update() write granularity', () => {
|
||||
let brain: Brainy
|
||||
|
||||
beforeEach(async () => {
|
||||
brain = new Brainy({
|
||||
requireSubtype: false,
|
||||
storage: { type: 'memory' as const },
|
||||
embeddingFunction: stubEmbedding
|
||||
})
|
||||
await brain.init()
|
||||
})
|
||||
|
||||
afterEach(async () => {
|
||||
await brain.close()
|
||||
})
|
||||
|
||||
it('metadata-only update never rewrites the noun record (no vector rewrite)', async () => {
|
||||
const id = await brain.add({
|
||||
data: 'granularity law subject',
|
||||
type: NounType.Concept,
|
||||
metadata: { touched: 0 }
|
||||
})
|
||||
|
||||
const storage = (brain as any).storage
|
||||
const saveNounSpy = vi.spyOn(storage, 'saveNoun')
|
||||
|
||||
await brain.update({ id, metadata: { touched: 1 } })
|
||||
|
||||
expect(saveNounSpy).not.toHaveBeenCalled()
|
||||
saveNounSpy.mockRestore()
|
||||
|
||||
// The metadata leg still landed with full semantics.
|
||||
const after = await brain.get(id, { includeVectors: true })
|
||||
expect(after?.metadata?.touched).toBe(1)
|
||||
expect(after?._rev).toBe(2)
|
||||
expect(Array.isArray(after?.vector) && after!.vector!.length).toBe(384)
|
||||
|
||||
const found = await brain.find({ where: { touched: 1 } })
|
||||
expect(found.some((r: any) => r.id === id)).toBe(true)
|
||||
})
|
||||
|
||||
it('confidence/weight/subtype-only updates also skip the noun record', async () => {
|
||||
const id = await brain.add({
|
||||
data: 'reserved-field touch subject',
|
||||
type: NounType.Concept,
|
||||
metadata: {}
|
||||
})
|
||||
|
||||
const storage = (brain as any).storage
|
||||
const saveNounSpy = vi.spyOn(storage, 'saveNoun')
|
||||
|
||||
await brain.update({ id, confidence: 0.5, weight: 2, subtype: 'note' })
|
||||
|
||||
expect(saveNounSpy).not.toHaveBeenCalled()
|
||||
saveNounSpy.mockRestore()
|
||||
|
||||
const after = await brain.get(id)
|
||||
expect(after?.confidence).toBe(0.5)
|
||||
expect(after?.subtype).toBe('note')
|
||||
})
|
||||
|
||||
it('data-changing update still writes the noun record and reindexes', async () => {
|
||||
const id = await brain.add({
|
||||
data: 'original embedded text',
|
||||
type: NounType.Concept,
|
||||
metadata: {}
|
||||
})
|
||||
|
||||
const before = await brain.get(id, { includeVectors: true })
|
||||
|
||||
const storage = (brain as any).storage
|
||||
const saveNounSpy = vi.spyOn(storage, 'saveNoun')
|
||||
|
||||
await brain.update({ id, data: 'completely different embedded text' })
|
||||
|
||||
expect(saveNounSpy).toHaveBeenCalled()
|
||||
saveNounSpy.mockRestore()
|
||||
|
||||
const after = await brain.get(id, { includeVectors: true })
|
||||
expect(after?.data).toBe('completely different embedded text')
|
||||
expect(after?.vector).not.toEqual(before?.vector)
|
||||
})
|
||||
|
||||
it('explicit-vector update still writes the noun record', async () => {
|
||||
const id = await brain.add({
|
||||
data: 'vector swap subject',
|
||||
type: NounType.Concept,
|
||||
metadata: {}
|
||||
})
|
||||
|
||||
const storage = (brain as any).storage
|
||||
const saveNounSpy = vi.spyOn(storage, 'saveNoun')
|
||||
|
||||
const newVector = new Array(384).fill(0).map((_, i) => Math.cos(i))
|
||||
await brain.update({ id, vector: newVector })
|
||||
|
||||
expect(saveNounSpy).toHaveBeenCalled()
|
||||
saveNounSpy.mockRestore()
|
||||
|
||||
const after = await brain.get(id, { includeVectors: true })
|
||||
expect(after?.vector?.[0]).toBeCloseTo(1) // cos(0)
|
||||
})
|
||||
})
|
||||
Loading…
Add table
Add a link
Reference in a new issue