Files
OmniRoute/tests/unit/probe-6835-oom-uncapped.test.ts
Diego Rodrigues de Sa e Souza 3d4f3e4960 test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966) (#11968)
* test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966)

Two shards on release/v3.8.51 went red in one day with the same signature —
"ENOTEMPTY, Directory not empty: /tmp/omniroute-<test>-XXXXXX" — from
combo-same-provider-cascade (Unit Tests fast-path 4/4, on a PR that touches only
.github/) and auth-policy-embeddings-webfetch-7785 (the 20k-test TIA step). Both pass
alone and on re-run: the cleanup races something still writing into the directory
(SQLite WAL/-shm checkpoint, a worker, the backup) and under a loaded hosted runner
the window opens. 1154 test files do their own cleanup with
fs.rmSync(dir, { recursive: true, force: true }); 57 already asked for retries.

One-shot codemod (scripts/ad-hoc/codemod-rm-maxretries.mjs, kept for the record):
every rm / rmSync / rmdirSync option object with `recursive: true` and no
`maxRetries` gains `maxRetries: 5, retryDelay: 100` — Node itself then retries
ENOTEMPTY/EBUSY/EPERM for up to ~0.5 s before giving up. 2243 call sites in 1292
files under tests/, the shared tests/_setup/isolateDataDir.ts exit hook included.
Only the option object changes: no call site, assertion or import is touched.

Validation: prettier and ESLint (with the frozen suppressions) clean on all 1292
files; a random 20-file sample runs green (quota-redis-store hangs identically on
the untouched tree — it needs a Redis on localhost, an environment matter). The
four unit shards on this PR are the full run.

* fix(quality): let check-forgotten-sibling-tests read a 1,000-file diff

The gate shells out to `git diff` through execFileSync with Node's default 1 MB
maxBuffer; the 1,292-file codemod in this PR is the first diff large enough to
overflow it, and the gate died with `spawnSync git ENOBUFS` before comparing
anything. 64 MB is far above any real PR and costs nothing when unused.
2026-08-29 01:17:40 -03:00

60 lines
2.0 KiB
TypeScript

import { test } from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
test("getDbInstance() eventually caps a persistently-OOMing sql.js probe (#6835)", async () => {
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-6835-oom-"));
process.env.DATA_DIR = tmpDir;
const sqliteFile = path.join(tmpDir, "storage.sqlite");
fs.mkdirSync(sqliteFile); // forces better-sqlite3/node:sqlite to fail synchronously (EISDIR-style)
await import("../../src/lib/db/adapters/driverFactory.ts");
const core = await import("../../src/lib/db/core.ts");
const fakeAdapter = {
driver: "sql.js" as const,
open: true,
name: sqliteFile,
prepare() {
throw new Error("out of memory");
},
exec() {
throw new Error("out of memory");
},
pragma() {
throw new Error("out of memory");
},
transaction<T>(fn: (...a: unknown[]) => T) {
return fn;
},
immediate() {},
async backup() {},
checkpoint() {},
close() {},
raw: null,
};
(
globalThis as unknown as { __omnirouteSqlJsAdapters: Map<string, unknown> }
).__omnirouteSqlJsAdapters = new Map([[sqliteFile, fakeAdapter]]);
const errors: string[] = [];
for (let i = 0; i < 8; i++) {
try {
core.getDbInstance();
errors.push("(no error)");
break;
} catch (err: unknown) {
errors.push(err instanceof Error ? err.message : String(err));
}
}
const anyAborted = errors.some((e) => e.includes("Aborting startup"));
assert.ok(
anyAborted,
"Expected getDbInstance() to eventually give up with a terminal " +
"'Aborting startup'-style diagnostic after repeated OOM probe failures, the same way it " +
"already does for generic corruption (#6632). Instead every call re-threw an identical, " +
"uncapped OOM error:\n" +
errors.map((e, i) => ` [${i}] ${e}`).join("\n")
);
fs.rmSync(tmpDir, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
});