perf: v2.5.10 — ready for 10+ concurrent users, leaner locally
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).
This commit is contained in:
+20
-10
@@ -14,6 +14,7 @@ const {
|
||||
BAD_RANGE,
|
||||
} = require("../lib/source-filter");
|
||||
const scoped = require("../lib/scoped-stats");
|
||||
const { runRead } = require("../lib/read-pool");
|
||||
|
||||
const { calculateCost, dailyTokenRows, costWhere } = require("./pricing");
|
||||
|
||||
@@ -34,12 +35,12 @@ const USAGE_TOKEN_COLS = {
|
||||
* With a range, counts follow it and tokens/cost come from the cost rows of the
|
||||
* days in it (`token_usage` has no date); the daily charts keep 365 days.
|
||||
*/
|
||||
function computeAnalytics({ scope = null, range = null, tzModifier = "+0 minutes" } = {}) {
|
||||
function computeAnalytics(
|
||||
{ scope = null, range = null, tzModifier = "+0 minutes" } = {},
|
||||
events = scoped.eventAggregates(db, scope || (range ? ALL : null), range, tzModifier)
|
||||
) {
|
||||
const sc = scope || (range ? ALL : null);
|
||||
const toolUsage = sc ? scoped.toolUsageCounts(db, sc, range) : stmts.toolUsageCounts.all();
|
||||
const dailyEvents = sc
|
||||
? scoped.dailyEventCounts(db, sc, tzModifier)
|
||||
: stmts.dailyEventCounts.all(tzModifier);
|
||||
const { toolUsage, dailyEvents, eventTypes, avgEvents } = events;
|
||||
const dailySessions = sc
|
||||
? scoped.dailySessionCounts(db, sc, tzModifier)
|
||||
: stmts.dailySessionCounts.all(tzModifier);
|
||||
@@ -56,10 +57,6 @@ function computeAnalytics({ scope = null, range = null, tzModifier = "+0 minutes
|
||||
const totalSubagents = sc
|
||||
? scoped.totalSubagentCount(db, sc, range)
|
||||
: stmts.totalSubagentCount.get();
|
||||
const eventTypes = sc ? scoped.eventTypeCounts(db, sc, range) : stmts.eventTypeCounts.all();
|
||||
const avgEvents = sc
|
||||
? scoped.avgEventsPerSession(db, sc, range)
|
||||
: stmts.avgEventsPerSession.get();
|
||||
|
||||
// Total cost exactly as GET /api/pricing/cost computes it (baselines, the
|
||||
// per-day rate, the same scope and range), so the two numbers always agree.
|
||||
@@ -108,7 +105,20 @@ router.get("/", (req, res) => {
|
||||
if (parseTool(req) === false) return res.status(400).json(BAD_TOOL);
|
||||
const range = parseRange(req);
|
||||
if (range === false) return res.status(400).json(BAD_RANGE);
|
||||
res.json(computeAnalytics({ scope: parseScope(req), range, tzModifier }));
|
||||
const scope = parseScope(req);
|
||||
// The events scans run in the read worker (a 365-day daily count is ~0.5 s
|
||||
// on a large DB), and a 10 s memo lets every open dashboard share one run.
|
||||
runRead(
|
||||
"analyticsEvents",
|
||||
{ scope: scope || (range ? ALL : null), range, tzModifier },
|
||||
{ maxAgeMs: 10_000 }
|
||||
)
|
||||
.then((events) => res.json(computeAnalytics({ scope, range, tzModifier }, events)))
|
||||
.catch((err) =>
|
||||
res
|
||||
.status(err.code === "EREADTIMEOUT" ? 503 : 500)
|
||||
.json({ error: { code: err.code, message: err.message } })
|
||||
);
|
||||
});
|
||||
|
||||
module.exports = router;
|
||||
|
||||
Reference in New Issue
Block a user