mirror of
https://github.com/stablyai/orca.git
synced 2026-10-25 16:03:53 +00:00
Jinwoo-HandOrca
d0b067e7f0
Hidden panes are exempt from pendingData flow control (main gate-drops their bytes after ingestion), so N background agents ran unbounded ahead on the one shared daemon->main stream socket (measured 192MB user-space backlog) and visible-pane echo waited FIFO behind it — typing appeared seconds late whenever several agents burst on a loaded machine (8x512KB/s + 12 CPU spinners: p50 293ms fix-off; 12x1MB/s: 6.1s). Mechanism (replaces producer pacing — no reveal catch-up, ever): - Shallow socket write gate (128KB) + per-session fairness bypass bounds echo latency by construction; kernel-flush refill sentinel keeps held bulk draining at full speed (drain-only refill capped at ~8MB/s). - Backgrounded sessions' queued output is keep-tail dropped (newest 512KB kept, in-order dataGap replaces the middle); a ~2MB GLOBAL budget shrinks per-session keep-tails (floor 64KB) so a worktree switch never waits behind the aggregate. Reply-eliciting query bytes (DSR/DA/OSC probes) are salvaged from dropped spans. - Notifications are structurally lossless: the daemon runs the same shared scanners main uses (bell/OSC 133/pr-link/2031) over every byte BEFORE drop decisions and relays facts in byte order; ordered background markers hand scan authority back and forth, seeded with the emulator's partial escape tail so a sequence split across the handoff neither phantom-fires nor goes missing. Titles/agent-status stay main-side (kept-tail convergent). - Main: background = hidden AND no remote view subscriber (a live mobile/web view is never thinned); on dataGap main resets cross-chunk parse carries, drops the headless mobile mirror, and reuses the hidden-drop model-restore marker. Wire: three new stream events, tolerated within protocol v19 (old mains ignore unknown events; old daemons never see the trigger). Kill switches: ORCA_DAEMON_BACKGROUND_STREAM_DROP=0, ORCA_DAEMON_SHALLOW_SOCKET_GATE=0. A/B (pnpm bench:multi-workspace-typing): 8x512KB/s + 12 CPU workers p50 293ms/p90 647ms -> 15/21ms (= baseline); 12x1MB/s 6,146ms -> 20ms; light loads unchanged; zero missing echoes. Latin hidden-restore e2e green (probe-verified aggregate-drain root cause). New deterministic repro harness: tests/e2e/terminal-multi-workspace-typing-latency.spec.ts + CPU pressure workers. Co-authored-by: Orca <help@stably.ai>
22 lines
760 B
JavaScript
22 lines
760 B
JavaScript
#!/usr/bin/env node
|
|
/**
|
|
* Busy-spins one CPU core to emulate a loaded machine during latency benches
|
|
* (the "every workspace is running an agent and the whole box is hot" case).
|
|
* Spawn N of these to occupy N cores; kill to release.
|
|
*
|
|
* Usage: node cpu-pressure-worker.mjs [maxDurationMs]
|
|
* The duration failsafe (default 10 min) prevents orphaned spinners if the
|
|
* spawning bench dies without cleanup.
|
|
*/
|
|
const maxDurationMs = Number(process.argv[2]) > 0 ? Number(process.argv[2]) : 10 * 60 * 1000
|
|
const deadline = Date.now() + maxDurationMs
|
|
|
|
let x = 1
|
|
while (Date.now() < deadline) {
|
|
// Hot integer loop between deadline checks; no yields, no allocation.
|
|
for (let i = 0; i < 5_000_000; i++) {
|
|
x = (x * 31 + 7) % 1000003
|
|
}
|
|
}
|
|
process.exit(0)
|