Files
pnpm/agent/server/src/metadataStore.ts
Zoltan Kochan ccc606ed15 feat: pnpm agent — server-side resolution for faster installs (#11251)
## Summary

Adds an opt-in **pnpm agent** server that resolves dependencies server-side and streams only the files missing from the client's content-addressable store.

- **`@pnpm/agent.server`** — multi-process HTTP server (Node.js `cluster`) with SQLite-backed metadata and file caches
- **`@pnpm/agent.client`** — streams an NDJSON response, dispatches worker threads to fetch files while the server is still resolving
- **New config**: `agent` in `pnpm-workspace.yaml` (opt-in)

## How it works

1. Client reads integrity hashes from its local store index
2. Sends `POST /v1/install` with dependencies + store integrities
3. Server resolves the dependency tree using pnpm's `install({ lockfileOnly: true })`, with a SQLite-backed `PackageMetaCache` for fast repeat resolution
4. As each package resolves, a wrapped `storeController.requestPackage` looks up its files and immediately streams digests the client is missing (NDJSON `D` lines)
5. Client reads the stream line by line; digest batches fill up and dispatch worker threads to `POST /v1/files` — file downloads overlap with server-side resolution
6. After resolution, server sends index entries (`I` lines) and lockfile (`L` line)
7. Client writes index entries to store, then runs headless install with a wrapped `fetchPackage` that calls `readPkgFromCafs` with `verifyStoreIntegrity: false` (files are trusted from the agent)
8. `/v1/files` response is gzip-streamed (274MB → ~80MB) — server pipes through `createGzip`, worker pipes through `createGunzip`, parsing and writing files to CAFS as data arrives

## Performance

1351-package project, cold local store, warm server (localhost):

| Scenario | Time |
|----------|------|
| Vanilla pnpm install (cold OS cache) | ~48s |
| Vanilla pnpm install (warm OS cache) | ~34s |
| With pnpm agent (consistent) | **~33s** |

### Key optimizations

1. **SQLite metadata cache** — server-side resolution drops from ~3.4s to ~0.9s
2. **SQLite file store** — consistent read performance regardless of OS file cache state
3. **Streaming `/v1/install`** — file digests stream during resolution, downloads start before resolution finishes
4. **Gzip-streamed `/v1/files`** — whole-stream gzip (274MB → ~80MB), significant savings on remote servers
5. **Worker-thread streaming HTTP** — workers pipe gzip → parse → write to CAFS as data arrives, no buffering
6. **No rehashing** — server-provided digests used directly, skipping 33K SHA-512 computations
7. **No re-verification** — wrapped `fetchPackage` calls `readPkgFromCafs` with `verifyStoreIntegrity: false`
8. **Direct `writeFileSync` with `wx`** — no stat + temp + rename
9. **Pre-packed msgpack** — server sends raw store index buffers, client writes directly to SQLite
10. **WAL checkpoint** — ensures store index entries written by agent are visible to headless install's worker threads

## Usage

Start the server:
```bash
node agent/server/lib/bin.js
```

Configure in `pnpm-workspace.yaml`:
```yaml
agent: http://localhost:4873
```
2026-04-20 11:56:46 +02:00

134 lines
4.2 KiB
TypeScript

import { readdirSync, readFileSync } from 'node:fs'
import { createRequire } from 'node:module'
import path from 'node:path'
import type { DatabaseSync as _DatabaseSync } from 'node:sqlite'
const { DatabaseSync } = createRequire(import.meta.url)('node:sqlite') as typeof import('node:sqlite')
// Matches @pnpm/resolving.npm-resolver's PackageMetaCache interface
// without adding a dependency on it.
interface PackageMetaCache {
get: (key: string) => unknown | undefined
set: (key: string, meta: unknown) => void
has: (key: string) => boolean
}
/**
* SQLite-backed PackageMetaCache for the pnpm agent server.
*
* Stores package metadata as pre-serialized JSON blobs keyed by cache key.
* Much faster than reading hundreds of .jsonl files from disk on every
* resolution — one indexed SQLite lookup vs file open + JSON parse.
*
* The server populates this at startup from the existing .jsonl cache files.
* Subsequent metadata fetches (from npm) also update SQLite via `set()`.
*/
export class MetadataStore implements PackageMetaCache {
private db: _DatabaseSync
private getStmt!: ReturnType<_DatabaseSync['prepare']>
private setStmt!: ReturnType<_DatabaseSync['prepare']>
private hasStmt!: ReturnType<_DatabaseSync['prepare']>
constructor (dbPath: string) {
this.db = new DatabaseSync(dbPath)
this.db.exec('PRAGMA busy_timeout=5000')
this.db.exec('PRAGMA journal_mode=WAL')
this.db.exec('PRAGMA synchronous=NORMAL')
this.db.exec(`
CREATE TABLE IF NOT EXISTS meta (
key TEXT PRIMARY KEY,
value TEXT NOT NULL
)
`)
this.getStmt = this.db.prepare('SELECT value FROM meta WHERE key = ?')
this.setStmt = this.db.prepare('INSERT OR REPLACE INTO meta (key, value) VALUES (?, ?)')
this.hasStmt = this.db.prepare('SELECT 1 FROM meta WHERE key = ?')
}
get (key: string): unknown | undefined {
const row = this.getStmt.get(key) as { value: string } | undefined
if (!row) return undefined
return JSON.parse(row.value)
}
set (key: string, meta: unknown): void {
this.setStmt.run(key, JSON.stringify(meta))
}
has (key: string): boolean {
return this.hasStmt.get(key) !== undefined
}
/**
* Import all .jsonl metadata files from the cache directory into SQLite.
* Each .jsonl file has: line 1 = headers (etag/modified), line 2 = metadata JSON.
* We store the parsed metadata (with etag attached) under the cache key.
*/
importFromCacheDir (cacheDir: string): number {
const metaDirs = ['v11/metadata', 'v11/metadata-full', 'v11/metadata-full-filtered']
let imported = 0
this.db.exec('BEGIN')
try {
for (const metaDir of metaDirs) {
const baseDir = path.join(cacheDir, metaDir)
let registries: string[]
try {
registries = readdirSync(baseDir)
} catch {
continue
}
for (const registry of registries) {
const regDir = path.join(baseDir, registry)
let files: string[]
try {
files = readdirSync(regDir)
} catch {
continue
}
const isFullMeta = metaDir.includes('full')
for (const file of files) {
if (!file.endsWith('.jsonl')) continue
const pkgName = decodeURIComponent(file.replace('.jsonl', ''))
const cacheKey = isFullMeta ? `${pkgName}:full` : pkgName
if (this.has(cacheKey)) continue
try {
const content = readFileSync(path.join(regDir, file), 'utf-8')
const newlineIdx = content.indexOf('\n')
if (newlineIdx === -1) continue
const headerLine = content.substring(0, newlineIdx)
const metaLine = content.substring(newlineIdx + 1)
const headers = JSON.parse(headerLine)
const meta = JSON.parse(metaLine)
meta.etag = headers.etag
meta.modified = headers.modified
this.setStmt.run(cacheKey, JSON.stringify(meta))
imported++
} catch {
// Skip corrupt files
}
}
}
}
this.db.exec('COMMIT')
} catch (err) {
this.db.exec('ROLLBACK')
throw err
}
return imported
}
close (): void {
this.db.close()
}
}