Files
cortiq-gateway/src/sysmon.rs
T
infosave2007 15de36be3b feat: ops & UX batch — jobs survive restarts, logs/system in the console, media queue, gallery, chat, exact stream tokens
Fifteen changes aimed at the first day of real use:

- Import and media jobs persist to <data>/jobs-*.json and reload on start
  (running ones settle as errors); the Register button no longer vanishes
  because the gateway restarted.
- Docker ships the cortiq binary (built in the builder stage) — local .cmf
  chat models and image/video generation now work in containers, where
  auto-install never could (no cargo in the runtime image). libvulkan1 added
  for optional GPU offload.
- Open admin console on 0.0.0.0 without a token now warns in the log and
  shows a dismissible banner — the VPS footgun is at least labeled.
- "Restart gateway" button in Settings: stops managed model servers, spawns
  a fresh copy (bind retried while the port frees), Docker relies on the
  container restart policy instead.
- Dashboard "System" panel: CPU sparkline + load, RAM (with the gateway's
  own RSS), free disk at the models dir — sampled by sysinfo every 2 s.
- Featured model cards warn "not enough disk" / "may not fit in RAM" before
  the download, from the same live snapshot.
- Log viewer in the sidebar: a 500-line in-memory ring fed by a second
  ANSI-free tracing layer; filter, level, pause, copy.
- Update check: crates.io polled twice a day, the console shows an
  "update available" notice.
- Media generations queue up (with position shown) instead of being
  rejected; progress gained an honest ETA from measured throughput.
- Generation gallery under the image/video tabs: lazy PPM thumbnails,
  click to reopen with seed/steps, delete.
- Playground chat is a real dialogue now: history is resent, bubbles,
  Clear, Cmd/Ctrl+Enter.
- "Connect your app" snippets (curl / Python / JS) on the keys page, with
  the real key inlined right after creation.
- One-click benchmark on the Models page via `cortiq bench --json`.
- Config export now downloads the actual gateway.toml (comments intact);
  import accepts TOML (validated, hot-reloaded) and the legacy JSON.
- Streaming token counts are exact when the model server provides usage
  (cortiq-server patch, shipped separately); the gateway fallback now
  counts content chunks (1/token on cortiq) instead of chars/4.

Wizard's Finish lands on the Playground. 37 new strings in all 7 languages.
2026-08-07 17:07:48 +03:00

87 lines
2.9 KiB
Rust

//! Host metrics sampler for the admin dashboard: CPU load, RAM, free disk at
//! the models dir, and the gateway's own RSS. One background task refreshes a
//! snapshot every 2 s; the API endpoint only reads it.
use serde::Serialize;
use std::sync::{Arc, Mutex};
#[derive(Clone, Default, Serialize)]
pub struct Snapshot {
pub ts: u64,
/// Whole-machine CPU usage 0..100 (average over all cores).
pub cpu_percent: f32,
pub cores: usize,
pub load1: f64,
pub ram_total: u64,
pub ram_used: u64,
/// Disk that holds models_dir.
pub disk_total: u64,
pub disk_free: u64,
/// Resident memory of the gateway process itself.
pub process_rss: u64,
}
pub struct SysMon {
snap: Mutex<Snapshot>,
}
impl SysMon {
pub fn snapshot(&self) -> Snapshot {
self.snap.lock().unwrap().clone()
}
}
fn now() -> u64 {
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.unwrap_or_default()
.as_secs()
}
/// Start the sampler. `models_dir` picks which disk's free space is reported.
pub fn spawn(models_dir: String) -> Arc<SysMon> {
let mon = Arc::new(SysMon {
snap: Mutex::new(Snapshot::default()),
});
let ret = mon.clone();
tokio::task::spawn_blocking(move || {
use sysinfo::{Disks, ProcessesToUpdate, System};
let mut sys = System::new();
let pid = sysinfo::Pid::from_u32(std::process::id());
let models_abs = std::fs::canonicalize(&models_dir)
.unwrap_or_else(|_| std::path::PathBuf::from(&models_dir));
loop {
sys.refresh_cpu_usage();
sys.refresh_memory();
let _ = sys.refresh_processes(ProcessesToUpdate::Some(&[pid]), true);
let disks = Disks::new_with_refreshed_list();
// the disk whose mount point is the longest prefix of models_dir
let mut best: Option<(usize, u64, u64)> = None;
for d in disks.list() {
let mp = d.mount_point();
if models_abs.starts_with(mp) {
let len = mp.as_os_str().len();
if best.map(|(l, _, _)| len > l).unwrap_or(true) {
best = Some((len, d.total_space(), d.available_space()));
}
}
}
let (disk_total, disk_free) = best.map(|(_, t, f)| (t, f)).unwrap_or((0, 0));
let snap = Snapshot {
ts: now(),
cpu_percent: sys.global_cpu_usage(),
cores: sys.cpus().len(),
load1: System::load_average().one,
ram_total: sys.total_memory(),
ram_used: sys.used_memory(),
disk_total,
disk_free,
process_rss: sys.process(pid).map(|p| p.memory()).unwrap_or(0),
};
*mon.snap.lock().unwrap() = snap;
std::thread::sleep(std::time::Duration::from_secs(2));
}
});
ret
}