perf(synthesis): provably-empty pass gates + prefilters — render/expo/rn/mybatis stop scanning repos they can't match; iface memo (#1389)

Store-arc round 2 (#1388 follow-up). The synthesis pool barrier on dubbo
carried ~1.4s of passes that provably could not emit an edge for the
project: reactRenderEdges fanned out over every class before checking for
a render method (now: one indexed name lookup bounds candidates — not a
language gate, Java Litho-style render+setState still matches);
expo/rn cross-platform pairing streamed every method row without the
languages their edges require (now registry-gated: expo needs swift AND
kotlin file-languages, rn needs a JS-family caller for isBridge);
mybatis built its full java-method index before discovering there were no
mapper-XML methods (now collects the XML side first). ifaceEdges — real
work — stops re-fetching a hub interface's methods once per implementer
and skips supertype-less classes before any per-class lookup.

dubbo warm wall 8.49-8.79 → 8.14-8.24s (n=3/arm, caffeinated); barrier
784→435ms; the full removed pass work lands on low-core envelopes where
synthesis runs sequentially. Dumps byte-identical: dubbo old-vs-new,
pooled-vs-sequential, kernel-vs-wasm (441,270 rows) + excalidraw JSX-live
control (89,903 rows, 46 react-render edges reproduced). Suite 2,689 ×2
with CODEGRAPH_KERNEL_EXPECT=1.

Also ships the diagnostics that located the round (zero cost when off):
CODEGRAPH_RESOLVE_PROFILE=2 attributes per-ref time to resolveOne's
strategies (stage:*) and the name-matcher's sub-matchers (nm:*);
CODEGRAPH_SYNTH_TIMINGS now prints the store worker's decode-vs-SQL
split. Killed by measurement, recorded in the PR: import-failure negative
cache (both-outcome names exist — static imports resolve via
instance-method on jvm-miss), jvm-miss early return (1,939 later-strategy
edges), jsxEdges language gate (Java generics text produces jsx edges),
and §4d buffer→bind on Spring repos (extract() hook forces the decoded
path — kernel=0 bundles measured).

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Colby Mchenry
2026-07-20 21:15:58 -05:00
committed by GitHub
co-authored by Claude Fable 5
parent 27c3c55436
commit 082ea65f3a
5 changed files with 179 additions and 23 deletions
+47 -8
View File
@@ -2047,6 +2047,45 @@ export function matchFuzzy(
/** ArkUI attribute-helper decorators a `.attr(...)` chain may resolve to. */
const ARKUI_ATTRIBUTE_DECORATORS = new Set(['Extend', 'Styles', 'AnimatableExtend', 'Builder']);
/**
* CODEGRAPH_RESOLVE_PROFILE=2 sub-stage attribution for matchReference's
* strategy pipeline (`nm:<stage>|<refKind>|hit/miss`). Module-global because
* the matcher is a free function; each thread (main + every pool worker) has
* its own module instance, and dumpNameMatcherProfile is invoked from
* ReferenceResolver.dumpResolveProfile so worker tables surface too.
*/
const NM_PROFILE: Map<string, { n: number; ns: bigint }> | null =
process.env.CODEGRAPH_RESOLVE_PROFILE === '2' ? new Map() : null;
function nmTimed(stage: string, ref: UnresolvedRef, fn: () => ResolvedRef | null): ResolvedRef | null {
if (!NM_PROFILE) return fn();
const t0 = process.hrtime.bigint();
const r = fn();
const dt = process.hrtime.bigint() - t0;
const key = `nm:${stage}|${ref.referenceKind}|${r ? 'hit' : 'miss'}`;
const slot = NM_PROFILE.get(key);
if (slot) {
slot.n++;
slot.ns += dt;
} else {
NM_PROFILE.set(key, { n: 1, ns: dt });
}
return r;
}
/** Dump this thread's matchReference sub-stage table to stderr (no-op unless =2). */
export function dumpNameMatcherProfile(label: string): void {
if (!NM_PROFILE || NM_PROFILE.size === 0) return;
const rows = [...NM_PROFILE.entries()]
.map(([k, v]) => ({ k, n: v.n, ms: Number(v.ns / 1_000_000n) }))
.sort((a, b) => b.ms - a.ms);
for (const r of rows) {
console.error(
`[resolve-profile] ${label} ${r.k}: n=${r.n} total=${(r.ms / 1000).toFixed(1)}s avg=${((r.ms * 1000) / Math.max(1, r.n)).toFixed(0)}µs`
);
}
}
export function matchReference(
ref: UnresolvedRef,
context: ResolutionContext
@@ -2119,18 +2158,18 @@ export function matchReference(
let result: ResolvedRef | null;
// 0. File path match (e.g., "snippets/drawer-menu.liquid" → file node)
result = matchByFilePath(ref, context);
result = nmTimed('filePath', ref, () => matchByFilePath(ref, context));
if (result) return result;
// 1. Qualified name match (highest confidence)
result = matchByQualifiedName(ref, context);
result = nmTimed('qualifiedName', ref, () => matchByQualifiedName(ref, context));
if (result) return result;
// 1b. C++ chained call whose receiver is another call — `Foo::instance().bar()`
// encoded as `Foo::instance().bar` by the extractor (#645). Resolve the
// receiver's type from what the inner call returns, then the method on it.
if (ref.language === 'cpp' || ref.language === 'c') {
result = matchCppCallChain(ref, context);
result = nmTimed('cppChain', ref, () => matchCppCallChain(ref, context));
if (result) return result;
}
@@ -2139,7 +2178,7 @@ export function matchReference(
// type is the factory's `self` (PHP `: self`/`: static`, Rust `-> Self`) or
// concrete return type.
if (ref.language === 'php' || ref.language === 'rust') {
result = matchScopedCallChain(ref, context);
result = nmTimed('scopedChain', ref, () => matchScopedCallChain(ref, context));
if (result) return result;
}
@@ -2161,20 +2200,20 @@ export function matchReference(
ref.language === 'objc' ||
ref.language === 'pascal'
) {
result = matchDottedCallChain(ref, context);
result = nmTimed('dottedChain', ref, () => matchDottedCallChain(ref, context));
if (result) return result;
}
// 2. Method call pattern
result = matchMethodCall(ref, context);
result = nmTimed('methodCall', ref, () => matchMethodCall(ref, context));
if (result) return result;
// 3. Exact name match
result = matchByExactName(ref, context);
result = nmTimed('exactName', ref, () => matchByExactName(ref, context));
if (result) return result;
// 4. Fuzzy match (lowest confidence)
result = matchFuzzy(ref, context);
result = nmTimed('fuzzy', ref, () => matchFuzzy(ref, context));
if (result) return result;
return null;