fix(container): companion probes are passive — no builds inside reconcile checks

Root cause of the .198 load spiral (2026-07-28): needs_repair() called
ensure_image_present() every 30s tick to render the expected unit, so
under IO pressure the image-existence check timed out, read as "image
missing", and a 900s podman build ran inside the PROBE while the
companion was up — each build pegging the disk that made probes fail.

- needs_repair() is now build/pull-free: unit file present → service
  is-active (10s cap; a hung systemctl reads as "assume active", never
  as dead) → unit matches one of the three image refs install_one could
  have written → context-newer-than-image staleness only when the unit
  uses the auto-built :latest.
- Per-companion 10-min repair cooldown after a failed install_one, so a
  failing build retries at most every REPAIR_COOLDOWN instead of every
  reconcile tick.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
archipelago 2026-07-28 06:54:29 -04:00
parent 73228114b9
commit 43130f33f0

View File

@ -22,8 +22,10 @@
//! single declarative call.
use anyhow::{Context, Result};
use std::collections::HashMap;
use std::path::PathBuf;
use std::time::Duration;
use std::sync::{LazyLock, Mutex};
use std::time::{Duration, Instant};
use tokio::fs;
use tokio::process::Command;
use tracing::{info, warn};
@ -35,6 +37,15 @@ const COMPANION_REGISTRY: &str = "146.59.87.168:3000/lfg2025";
const COMPANION_IMAGE_CHECK_TIMEOUT: Duration = Duration::from_secs(15);
const COMPANION_BUILD_TIMEOUT: Duration = Duration::from_secs(900);
const COMPANION_PULL_TIMEOUT: Duration = Duration::from_secs(300);
/// After a failed repair (image build/pull included), leave the companion
/// alone for this long. Without it, a node under IO pressure retried a 900s
/// image build every 30s reconcile tick — each build pegging the disk that
/// made the probes fail in the first place (live-diagnosed on zaza-optiplex
/// 2026-07-28: load 50, podman scans starved, apps page stuck).
const REPAIR_COOLDOWN: Duration = Duration::from_secs(600);
static REPAIR_FAILED_AT: LazyLock<Mutex<HashMap<&'static str, Instant>>> =
LazyLock::new(|| Mutex::new(HashMap::new()));
/// Static description of one companion. The full list per backend
/// app_id lives in `companions_for`.
@ -464,12 +475,28 @@ pub async fn reconcile(installed_apps: &[String]) -> Vec<(String, anyhow::Error)
match needs_repair(spec).await {
Ok(false) => {}
Ok(true) => {
if let Some(failed_at) =
REPAIR_FAILED_AT.lock().unwrap().get(spec.name).copied()
{
if failed_at.elapsed() < REPAIR_COOLDOWN {
continue;
}
}
info!(
companion = spec.name,
"reconcile: companion not active, repairing"
);
if let Err(e) = install_one(spec).await {
failures.push((spec.name.to_string(), e));
match install_one(spec).await {
Ok(()) => {
REPAIR_FAILED_AT.lock().unwrap().remove(spec.name);
}
Err(e) => {
REPAIR_FAILED_AT
.lock()
.unwrap()
.insert(spec.name, Instant::now());
failures.push((spec.name.to_string(), e));
}
}
}
Err(e) => {
@ -484,19 +511,58 @@ pub async fn reconcile(installed_apps: &[String]) -> Vec<(String, anyhow::Error)
/// Does this companion need install_one to be re-run? Returns true if
/// the unit file is missing, stale, or the service is not active.
///
/// This probe runs every reconcile tick for every companion, so it must be
/// PASSIVE: no image builds, no pulls. It used to call ensure_image_present
/// to render the expected unit — under IO pressure the image-existence check
/// inside timed out, read as "image missing", and a 900s `podman build` ran
/// inside the probe even though the companion was up (the .198 load spiral).
async fn needs_repair(spec: &CompanionSpec) -> Result<bool> {
let dir = quadlet::unit_dir().await?;
let unit_path = dir.join(format!("{}.container", spec.name));
if !fs::try_exists(&unit_path).await.unwrap_or(false) {
return Ok(true);
}
let expected_image = ensure_image_present(spec).await?;
let expected_unit = build_unit(spec, &expected_image);
if expected_unit.render() != fs::read_to_string(&unit_path).await.unwrap_or_default() {
let svc = format!("{}.service", spec.name);
// A hung `systemctl is-active` under IO pressure must not read as
// "companion dead" — that's a repair (and possibly an image build) fired
// off exactly when the node can least afford one.
match tokio::time::timeout(Duration::from_secs(10), quadlet::is_active(&svc)).await {
Ok(active) => {
if !active {
return Ok(true);
}
}
Err(_) => {
warn!(
companion = spec.name,
"is-active probe timed out; assuming active"
);
}
}
// Service is running. Flag it stale only on definitive, cheap signals:
// the on-disk unit matching none of the image refs install_one could
// have written, or a local build context newer than the built image.
let on_disk = fs::read_to_string(&unit_path).await.unwrap_or_default();
let local_image = format!("localhost/{}:latest", spec.image_base);
let local_image_compat = format!("localhost/{}:local", spec.image_base);
let registry_image = format!("{}/{}:latest", COMPANION_REGISTRY, spec.image_base);
let matches_known_shape = [&local_image, &local_image_compat, &registry_image]
.iter()
.any(|img| build_unit(spec, img).render() == on_disk);
if !matches_known_shape {
return Ok(true);
}
let svc = format!("{}.service", spec.name);
Ok(!quadlet::is_active(&svc).await)
if on_disk.contains(&local_image) && !on_disk.contains(&local_image_compat) {
for dir in spec.build_dir_candidates {
let dockerfile = PathBuf::from(dir).join("Dockerfile");
if fs::try_exists(&dockerfile).await.unwrap_or(false) {
// Conservative on any timeout/error inside: reuse the cache.
return Ok(context_is_newer_than_image(dir, &local_image).await);
}
}
}
Ok(false)
}
#[cfg(test)]