perf(generations): discover generations by directory name, not by walking the log
MEASURED on a copy of a real store (14,056 nouns / 72,679 verbs, an 11 GB
generation history): the generation-store phase cost 55,538 ms of a WARM
REOPEN after a clean close — with the fold correctly skipped, so nothing in
that phase's name explained it.
This is what it was doing. Discovering which generations exist on disk called
listRawObjects('_generations'), which RECURSES the whole tree and returns
every file in every generation directory — to extract a set of integers that
the top-level directory NAMES already spell out. The cost scales with the
entire history, is paid on every open, warm or cold, and grows for the life of
the store.
A one-level door — listRawPrefixes(prefix), the immediate child directory
names — is added to the storage seam. The filesystem adapter answers it with a
single readdir; BaseStorage derives it from the recursive listing, so an
adapter without a cheap implementation is never wrong, only never faster; and
the generation store falls back to the old listing when the door is absent.
One behavioural difference, stated: an EMPTY generation directory is now
discovered where the file listing could not see it. Above the committed
watermark that is a crash scar, and recovery already has an explicit branch
for it ("indeterminate partial dir" — dropped, narrated). Below it, it becomes
a resolvable generation holding no records, which is what an empty generation
means.
Suites: the durability kill matrix (15), db-mvcc (30), history repacking (4),
rollback trapdoor (3), entity-tree stamp (4) and the full unit suite (2,105)
all green.
This commit is contained in:
parent
0304350a41
commit
9ada83c58b
4 changed files with 84 additions and 5 deletions
|
|
@ -537,12 +537,29 @@ export class GenerationStore {
|
|||
this.horizonGen = finiteGen(manifest?.horizon, 'manifest horizon')
|
||||
this.counter = Math.max(finiteGen(counterFile?.generation, 'generation counter'), this.committed)
|
||||
|
||||
// Discover existing generation record directories.
|
||||
const recordPaths = await this.storage.listRawObjects(GENERATIONS_PREFIX)
|
||||
// Discover existing generation record directories — BY DIRECTORY NAME.
|
||||
// This used to call listRawObjects(), which recurses the whole
|
||||
// `_generations/` tree and returns every file in every generation, to
|
||||
// extract a set of integers the top-level directory names already spell.
|
||||
// MEASURED on a real store with an 11 GB generation history: the phase
|
||||
// this sits in cost 55,538 ms of a WARM REOPEN after a clean close, with
|
||||
// no fold to blame — this walk is what it was doing. An adapter without
|
||||
// the one-level door falls back to the recursive listing, unchanged.
|
||||
const seenGens = new Set<number>()
|
||||
for (const p of recordPaths) {
|
||||
const gen = parseGenerationFromPath(p)
|
||||
if (gen !== null) seenGens.add(gen)
|
||||
const oneLevel = (
|
||||
this.storage as { listRawPrefixes?: (prefix: string) => Promise<string[]> }
|
||||
).listRawPrefixes
|
||||
if (typeof oneLevel === 'function') {
|
||||
for (const name of await oneLevel.call(this.storage, GENERATIONS_PREFIX)) {
|
||||
const gen = Number(name)
|
||||
if (Number.isSafeInteger(gen) && gen >= 0) seenGens.add(gen)
|
||||
}
|
||||
} else {
|
||||
const recordPaths = await this.storage.listRawObjects(GENERATIONS_PREFIX)
|
||||
for (const p of recordPaths) {
|
||||
const gen = parseGenerationFromPath(p)
|
||||
if (gen !== null) seenGens.add(gen)
|
||||
}
|
||||
}
|
||||
|
||||
let rolledBack = 0
|
||||
|
|
|
|||
|
|
@ -450,6 +450,21 @@ export interface GenerationStorage {
|
|||
deleteRawObject(path: string): Promise<void>
|
||||
/** List raw object paths under a prefix (normalized, `.gz`-stripped). */
|
||||
listRawObjects(prefix: string): Promise<string[]>
|
||||
/**
|
||||
* OPTIONAL: the IMMEDIATE child directory names under a prefix — one level,
|
||||
* no recursion, no file paths.
|
||||
*
|
||||
* Why it exists: discovering which generations are on disk needs only the
|
||||
* top-level directory NAMES under `_generations/`, but the only door for it
|
||||
* was `listRawObjects`, which recurses the whole tree and returns every file
|
||||
* in every generation. On a store with a long history that is a full walk of
|
||||
* the entire generation log, paid on EVERY open, to learn a set of integers
|
||||
* the directory names already spell out.
|
||||
*
|
||||
* An adapter without this door keeps working — the caller falls back to the
|
||||
* recursive listing.
|
||||
*/
|
||||
listRawPrefixes?(prefix: string): Promise<string[]>
|
||||
/** Remove every object under a prefix (and the directory itself on disk). */
|
||||
removeRawPrefix(prefix: string): Promise<void>
|
||||
/** Durability barrier: fsync the given object paths (no-op in memory). */
|
||||
|
|
|
|||
|
|
@ -686,6 +686,30 @@ export class FileSystemStorage extends BaseStorage {
|
|||
return pruned
|
||||
}
|
||||
|
||||
/**
|
||||
* @description The IMMEDIATE child directory names under a prefix — ONE
|
||||
* `readdir`, no recursion, no file paths. See the seam's JSDoc
|
||||
* (`src/db/types.ts`) for what this replaced: discovering the generations on
|
||||
* disk walked the entire generation log on every open, reading out every
|
||||
* file in every generation, to learn the set of integers the top-level
|
||||
* directory names already spell.
|
||||
* @param prefix - Storage-root-relative directory prefix.
|
||||
* @returns The child directory names (not paths); empty when the prefix does
|
||||
* not exist.
|
||||
*/
|
||||
public override async listRawPrefixes(prefix: string): Promise<string[]> {
|
||||
await this.ensureInitialized()
|
||||
const fullPath = path.join(this.rootDir, prefix)
|
||||
try {
|
||||
const entries = await fs.promises.readdir(fullPath, { withFileTypes: true })
|
||||
return entries.filter((e: { isDirectory: () => boolean }) => e.isDirectory())
|
||||
.map((e: { name: string }) => e.name)
|
||||
} catch (error: any) {
|
||||
if (error?.code === 'ENOENT') return []
|
||||
throw error
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Primitive operation: List objects under path prefix
|
||||
* All metadata operations use this internally via base class routing
|
||||
|
|
|
|||
|
|
@ -1437,6 +1437,29 @@ export abstract class BaseStorage extends BaseStorageAdapter {
|
|||
return this.listObjectsUnderPath(prefix)
|
||||
}
|
||||
|
||||
/**
|
||||
* @description The IMMEDIATE child directory names under a prefix — one
|
||||
* level, no recursion. See the seam's JSDoc (`db/types.ts`) for why a
|
||||
* separate door exists. This default derives them from the recursive
|
||||
* listing, so it is never WRONG, only never faster; the filesystem adapter
|
||||
* overrides it with a single directory read.
|
||||
* @param prefix - Storage-root-relative directory prefix.
|
||||
* @returns The child directory names (not paths), in listing order.
|
||||
*/
|
||||
public async listRawPrefixes(prefix: string): Promise<string[]> {
|
||||
await this.ensureInitialized()
|
||||
const paths = await this.listObjectsUnderPath(prefix)
|
||||
const normalizedPrefix = prefix.endsWith('/') ? prefix : `${prefix}/`
|
||||
const names = new Set<string>()
|
||||
for (const p of paths) {
|
||||
const rest = p.startsWith(normalizedPrefix) ? p.slice(normalizedPrefix.length) : null
|
||||
if (rest === null) continue
|
||||
const slash = rest.search(/[/\\]/)
|
||||
if (slash > 0) names.add(rest.slice(0, slash))
|
||||
}
|
||||
return [...names]
|
||||
}
|
||||
|
||||
/**
|
||||
* Remove every object under a storage-root-relative prefix. The filesystem
|
||||
* adapter overrides this with a recursive directory removal; this default
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue