ca821008e2
Measured on a copy of a real 1.2 GB / 253K-event database, 10 simulated browsers + 10 hooks/s for 90 s: event-loop delay p99 1239 ms → 32 ms (max 2.0 s → 94 ms), 266 failed requests → 0, 74 → 111 requests/s served, server RSS 633 → 346 MB. Entry bundle 975 KB raw → 394 KB (106 KB brotli). Server - /api/analytics: the events-table scans run in the read worker (scoped-stats eventAggregates, read-pool job analyticsEvents); runRead takes maxAgeMs — analytics 10 s, /api/workflows 30 s — keyed by the args - /api/workflows/skill-usage: +event_type and a tool_name range instead of LIKE, so it uses idx_events_tool (784 ms → a few ms) - idx_events_session_type_tool (session_id, event_type, tool_name, created_at) replaces idx_events_session_type: covering reads for session stats, the hook dedupes and the import resume point (1.2 s → 20 ms); 64 MB cache_size and 256 MB mmap_size on both connections - WAL: the server sets wal_autocheckpoint = 0 and checkpoints PASSIVE every DASHBOARD_WAL_CHECKPOINT_MS (5 s) from the read worker's own writable connection; a failed checkpoint restores the automatic one (hook COMMIT p95 109 ms → 15 ms at 100 hooks/s) - tmux: one list-sessions answers a whole GET /api/lanes and the heal beat (liveSessions), shared for 1 s and cleared by this process's new/kill — GET /api/run's sync spawns had blocked 60 s of a 90 s run; the heal beat skips tmux when nothing runs; attach options chained into 2 spawns - hooks: TurnDuration/APIError deduped against one read per hook instead of a query per transcript entry (23 ms/hook on a 763-turn session); one lane scan per hook; hourly upserts skip rows that did not grow; frames are sent after the transaction commits (and after the pane binding); new_event carries its row id; a split pane's (slot 1–9) hooks no longer rebind the lane's session_id - watchdog liveness probe runs ps asynchronously; transcript newline scan via indexOf; startup subagent backfill fingerprints the files it already checked - pty attach: backpressure (pause past 1 MB unsent, resume under 256 KB) - static: hashed assets served from their pre-compressed .br/.gz sibling Client - hidden tabs neither refetch on WS events nor poll (useLiveRefresh, panes, lane cards, git header, changes panel, settings); no per-tab hourly /updates/check (the server already checks) - refetch storms throttled (workspace tree/session list 3 s, /api/run only on a run-key change, notification pane lookup only when shown); WS reconnect jitter; terminal retry backoff 1.5 → 30 s, stops on 1008 - heavier throttles for aggregates (15 s) and detail views; Monitor keepIfSame; GET in-flight dedupe in request() - lazy Dashboard/History, xterm (with the first terminal), lane modals, Sagi (only while enabled); only the active locale loads; Workspace chunk prefetched on a /workspace deep link - Sagi: no work while disabled, pupil via CSS variables, memo avatar - build: .br/.gz siblings, sourcemap hidden; service worker no longer caches /assets/ (cache v3 drops the old one) Tests: scripts/test-server.js drops the GIT_DIR-family variables a hook exports, so a suite run from a linked worktree's pre-commit can no longer commit into the real repository or set core.bare. Docs: ARCHITECTURE, DATABASE, API, DEPLOYMENT, client README, docs/plans/perf/README.md (audit, checklist, results).
163 lines
6.0 KiB
JavaScript
163 lines
6.0 KiB
JavaScript
/**
|
|
* @file Runs the dashboard's heavy read-only aggregations in a worker thread
|
|
* on its own SQLite connection, so a slow one never blocks the event loop that
|
|
* serves every other page, hook and websocket. Identical requests in flight are
|
|
* shared (and, when the caller asks, reused for a short window), a job over
|
|
* `AGENTHUB_READ_TIMEOUT_MS` (default 60 s) is answered with `EREADTIMEOUT` and
|
|
* its worker replaced, and `AGENTHUB_READ_WORKER=0` — or a worker that cannot
|
|
* start — runs the job inline as before. The server's periodic WAL checkpoint
|
|
* also runs here (`walCheckpoint`). This file is also the worker's entry point.
|
|
* @author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>
|
|
*/
|
|
|
|
const { Worker, isMainThread, workerData, parentPort } = require("node:worker_threads");
|
|
|
|
/** Read-only jobs by name: (connection, args) → plain data. */
|
|
const JOBS = {
|
|
workflows: (conn, a) =>
|
|
require("./workflow-stats").computeWorkflowData(
|
|
conn,
|
|
{ status: a.status || null, tool: a.tool || null, range: a.range || null },
|
|
a.sections || null
|
|
),
|
|
// Not a read: the worker runs it on its own writable connection (below), so
|
|
// the checkpoint's copy into the database file never blocks the event loop.
|
|
walCheckpoint: (conn) => conn.pragma("wal_checkpoint(PASSIVE)", { simple: false }),
|
|
analyticsEvents: (conn, a) =>
|
|
require("./scoped-stats").eventAggregates(conn, a.scope, a.range, a.tzModifier),
|
|
};
|
|
|
|
function timeoutMs() {
|
|
return Number(process.env.AGENTHUB_READ_TIMEOUT_MS) || 60_000;
|
|
}
|
|
|
|
function codedError(message, code) {
|
|
return Object.assign(new Error(message), { code });
|
|
}
|
|
|
|
// ponytail: one worker, so heavy reads queue behind each other (the event loop
|
|
// stays free either way); a small pool if concurrent heavy reads ever pile up.
|
|
let worker = null;
|
|
let seq = 0;
|
|
const pending = new Map(); // id → { resolve, reject, timer, w }
|
|
const inflight = new Map(); // job+args → Promise
|
|
const recent = new Map(); // job+args → { at, result } for callers passing maxAgeMs
|
|
|
|
function spawn(dbPath) {
|
|
const w = new Worker(__filename, { workerData: { agenthubReadWorker: true, dbPath } });
|
|
w.on("message", ({ id, result, error }) => {
|
|
const p = pending.get(id);
|
|
if (!p) return;
|
|
pending.delete(id);
|
|
clearTimeout(p.timer);
|
|
if (error) p.reject(codedError(error.message, error.code));
|
|
else p.resolve(result);
|
|
});
|
|
const fail = (err) => {
|
|
if (worker === w) worker = null;
|
|
for (const [id, p] of pending) {
|
|
if (p.w !== w) continue;
|
|
pending.delete(id);
|
|
clearTimeout(p.timer);
|
|
p.reject(err);
|
|
}
|
|
};
|
|
w.on("error", fail);
|
|
w.on("exit", (code) => fail(codedError(`read worker exited (${code})`, "EREADWORKER")));
|
|
w.unref(); // after the listeners: adding a "message" listener refs it again
|
|
return w;
|
|
}
|
|
|
|
function runInline(job, args) {
|
|
const { db } = require("../db");
|
|
return Promise.resolve().then(() => JOBS[job](db, args));
|
|
}
|
|
|
|
function dispatch(job, args) {
|
|
if (process.env.AGENTHUB_READ_WORKER === "0") return runInline(job, args);
|
|
try {
|
|
if (!worker) worker = spawn(require("../db").DB_PATH);
|
|
} catch {
|
|
return runInline(job, args);
|
|
}
|
|
const w = worker;
|
|
return new Promise((resolve, reject) => {
|
|
const id = ++seq;
|
|
const ms = timeoutMs();
|
|
const timer = setTimeout(() => {
|
|
// The stuck query keeps its thread until SQLite returns; the next job
|
|
// gets a fresh worker. Jobs queued behind it are rejected by `exit`.
|
|
pending.delete(id);
|
|
if (worker === w) worker = null;
|
|
w.terminate();
|
|
reject(codedError(`read query took over ${ms} ms`, "EREADTIMEOUT"));
|
|
}, ms);
|
|
timer.unref?.();
|
|
pending.set(id, { resolve, reject, timer, w });
|
|
w.postMessage({ id, job, args });
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Run a named read job off the event loop. Concurrent calls with the same job
|
|
* and args share one run; with `maxAgeMs`, a result that young is reused too,
|
|
* so N open dashboards cost one query per window instead of N. Args are part
|
|
* of the key, so a result is only reused for the very same query.
|
|
*
|
|
* @param {keyof JOBS} job
|
|
* @param {object} [args] structured-cloneable
|
|
* @param {{maxAgeMs?: number}} [opts]
|
|
* @returns {Promise<any>}
|
|
*/
|
|
function runRead(job, args = {}, { maxAgeMs = 0 } = {}) {
|
|
if (!JOBS[job]) return Promise.reject(codedError(`unknown read job ${job}`, "EBADJOB"));
|
|
const key = `${job}:${JSON.stringify(args)}`;
|
|
const now = Date.now();
|
|
const fresh = recent.get(key);
|
|
if (fresh && now - fresh.at < maxAgeMs) return Promise.resolve(fresh.result);
|
|
const hit = inflight.get(key);
|
|
if (hit) return hit;
|
|
const p = dispatch(job, args)
|
|
.then((result) => {
|
|
if (maxAgeMs > 0) {
|
|
// ponytail: drop-expired-on-write keeps this bounded by the keys used
|
|
// within one window; an LRU if a caller ever varies args per request.
|
|
for (const [k, v] of recent) if (now - v.at > 60_000) recent.delete(k);
|
|
recent.set(key, { at: Date.now(), result });
|
|
}
|
|
return result;
|
|
})
|
|
.finally(() => inflight.delete(key));
|
|
inflight.set(key, p);
|
|
return p;
|
|
}
|
|
|
|
if (!isMainThread && workerData?.agenthubReadWorker) {
|
|
// Same driver order as server/db.js: better-sqlite3, else node:sqlite.
|
|
const open = () => {
|
|
try {
|
|
const Database = require("better-sqlite3");
|
|
return new Database(workerData.dbPath);
|
|
} catch {
|
|
const Database = require("../compat-sqlite");
|
|
return new Database(workerData.dbPath);
|
|
}
|
|
};
|
|
const conn = open();
|
|
let writer = null; // walCheckpoint's connection, opened on first use
|
|
conn.pragma("busy_timeout = 5000");
|
|
conn.pragma("query_only = ON"); // this connection can never write
|
|
conn.pragma("cache_size = -65536"); // same read tuning as server/db.js
|
|
conn.pragma("mmap_size = 268435456");
|
|
parentPort.on("message", ({ id, job, args }) => {
|
|
try {
|
|
const c = job === "walCheckpoint" ? (writer ??= open()) : conn;
|
|
parentPort.postMessage({ id, result: JOBS[job](c, args) });
|
|
} catch (err) {
|
|
parentPort.postMessage({ id, error: { message: err.message, code: err.code } });
|
|
}
|
|
});
|
|
}
|
|
|
|
module.exports = { runRead };
|