perf(synthesis): fan dynamic-dispatch passes across the resolver pool, byte-identical graphs (#1321)

The ~36 independent synthesis passes (callback/event/framework wiring) ran
sequentially on the indexer's main thread — 2.0s of a 4,402-file Java repo's
index, and the stage where kernel-class repos die (#1212). They now live in
an explicit registry (SYNTH_PASSES) and, when the resolver pool is alive
(>=150k-ref repos), fan out across its read-only workers: dubbo synthesis
2,024ms -> ~900ms (-55%), total fresh init 13.5s -> 11.9s. Graphs verified
byte-for-byte identical on both the pool path (dubbo) and the sequential
path (excalidraw).

Why this is safe: no pass's edges persist until the ordered merge, so every
pass sees the same committed post-resolution DB state in either mode, and
results merge in registry order regardless of completion order — the
first-seen dedup is unchanged. The pool now survives through synthesis
(destroy moved after it) instead of being torn down moments before the one
stage that could reuse it.

Robustness: a pass that fails on a worker (crash, OOM) is retried on the
main thread — a synthesizer blow-up now costs one worker instead of the
whole index, which is half the #1212 story on very large repos.

Also: ref-row cleanup deletes now run as one transaction with a cached
statement instead of one implicit commit per 500-row chunk (mechanically
fewer WAL commits; matters most on HDD-class storage). A set-based rewrite
of failed-ref parking was tried, measured ~zero on NVMe, and dropped — the
remaining persist cost is edge-index B-tree maintenance, not statement
dispatch.

SYNTH_PROGRESS_STEPS now derives from the registry (passes + fixed marks);
the pin test counts registry entries plus literal __mark sites.

Suite green (2444). Sequential-path timing unchanged on excalidraw.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Colby Mchenry
2026-07-16 18:07:51 -05:00
committed by GitHub
co-authored by Claude Fable 5
parent a2f3c31a97
commit cf38ef65af
7 changed files with 268 additions and 99 deletions
+37 -2
View File
@@ -13,9 +13,15 @@ import { Worker } from 'worker_threads';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import type { UnresolvedReference } from '../types';
import type { Edge, UnresolvedReference } from '../types';
import type { ResolvedRef, UnresolvedRef } from './types';
/** One synthesis pass's output: its edge list + worker-measured wall clock. */
export interface SynthPassResult {
edges: Edge[];
ms: number;
}
export interface ChunkResult {
resolved: ResolvedRef[];
unresolved: UnresolvedRef[];
@@ -55,6 +61,7 @@ export class ResolverPool {
private workers: PoolWorker[] = [];
private nextId = 0;
private waiters = new Map<number, { resolve: (r: ChunkResult) => void; reject: (e: Error) => void }>();
private synthWaiters = new Map<number, { resolve: (r: SynthPassResult) => void; reject: (e: Error) => void }>();
private failed: Error | null = null;
/**
@@ -85,7 +92,7 @@ export class ResolverPool {
readyReject = reject;
});
const pw: PoolWorker = { worker, ready, busy: 0 };
worker.on('message', (msg: { type: string; id?: number; message?: string } & Partial<ChunkResult>) => {
worker.on('message', (msg: { type: string; id?: number; message?: string; edges?: Edge[]; ms?: number } & Partial<ChunkResult>) => {
if (msg.type === 'ready') {
readyResolve();
} else if (msg.type === 'result' && msg.id !== undefined) {
@@ -99,6 +106,11 @@ export class ResolverPool {
deferredThisMember: msg.deferredThisMember!,
byMethod: msg.byMethod!,
});
} else if (msg.type === 'synth-result' && msg.id !== undefined) {
pw.busy--;
const waiter = this.synthWaiters.get(msg.id);
this.synthWaiters.delete(msg.id);
waiter?.resolve({ edges: msg.edges ?? [], ms: msg.ms ?? 0 });
} else if (msg.type === 'error') {
pw.busy--;
const err = new Error(`resolver worker: ${msg.message}`);
@@ -106,6 +118,10 @@ export class ResolverPool {
const waiter = this.waiters.get(msg.id)!;
this.waiters.delete(msg.id);
waiter.reject(err);
} else if (msg.id !== undefined && this.synthWaiters.has(msg.id)) {
const waiter = this.synthWaiters.get(msg.id)!;
this.synthWaiters.delete(msg.id);
waiter.reject(err);
} else {
this.fail(err);
}
@@ -130,6 +146,8 @@ export class ResolverPool {
if (!this.failed) this.failed = err;
for (const [, waiter] of this.waiters) waiter.reject(this.failed);
this.waiters.clear();
for (const [, waiter] of this.synthWaiters) waiter.reject(this.failed);
this.synthWaiters.clear();
}
/** Whether this batch is worth fanning out. */
@@ -175,6 +193,23 @@ export class ResolverPool {
return out;
}
/**
* Run one synthesis pass (by SYNTH_PASSES name) on the least-busy worker.
* The worker reads the committed graph on its own connection and returns
* the pass's edge list; the caller merges in canonical order. Rejects on
* worker failure — the caller retries the pass on the main thread.
*/
async runSynthPass(passName: string): Promise<SynthPassResult> {
if (this.failed) throw this.failed;
const id = this.nextId++;
const pw = this.workers.reduce((a, b) => (b.busy < a.busy ? b : a));
pw.busy++;
return new Promise<SynthPassResult>((resolve, reject) => {
this.synthWaiters.set(id, { resolve, reject });
pw.worker.postMessage({ type: 'synth', id, pass: passName });
});
}
async destroy(): Promise<void> {
await Promise.all(
this.workers.map(