Supervise boot services with uniform five-second upgrade grace

2026-11-01 20:51:08 +00:00
parent 4da8a28392
commit 959ddf46ff
15 changed files with 943 additions and 99 deletions
@@ -0,0 +1,115 @@
+//! Controlled-clock coverage of both upgrade windows and discovery exclusion.
+use super::*;
+use crate::{
+    process::{Process, ProcessInfo},
+    runtime::Runtime,
+    world::World,
+};
+use tokio::{
+    sync::mpsc,
+    task::JoinHandle,
+    time::{Instant, advance},
+};
+
+/// A process with active work that ignores both superseded and EOF.
+fn process(
+    host: &Host,
+    pid: &str,
+    method: &str,
+) -> (mpsc::UnboundedReceiver<serde_json::Value>, JoinHandle<()>) {
+    let (input, incoming) = mpsc::unbounded_channel();
+    let task = tokio::spawn(std::future::pending());
+    host.0.state.lock().unwrap().processes.insert(
+        pid.into(),
+        Process {
+            info: ProcessInfo {
+                plugin: "notes".into(),
+                version: "old".into(),
+                method: method.into(),
+                params: json!({}),
+                parent: None,
+                detached: true,
+                start_time: 0,
+                state: "running".into(),
+            },
+            memory: sausage_vfs::Memory::default(),
+            files: sausage_vfs::Process::default(),
+            store_ended: watch::channel(true).0,
+            input: Some(input),
+            abort: Some(task.abort_handle()),
+            caller: "console".into(),
+            id: None,
+            answer: None,
+            ended: watch::channel(false).0,
+            stopped: false,
+            superseded: false,
+        },
+    );
+    (incoming, task)
+}
+
+/// PROTOCOL 3.7/3.6: five seconds running, then five seconds stopping; discovery is untouched.
+#[tokio::test]
+async fn two_five_second_windows_and_discovery_exclusion() {
+    let dir = tempfile::tempdir().unwrap();
+    let root = dir.path().join("world");
+    World::create(&root).unwrap();
+    let host = Host::test_world(&root, Runtime::new(&dir.path().join("cache")).unwrap())
+        .await
+        .unwrap();
+    let (mut input, work) = process(&host, "old-work", "work");
+    let (mut discovery_input, discovery) = process(&host, "old-discovery", "rpc.discover");
+    let upgrade = host.snapshot_upgrade("notes", "old".into(), "new");
+    assert_eq!(upgrade.processes.len(), 1);
+    tokio::time::pause();
+    let start = Instant::now();
+    host.begin_upgrade(upgrade);
+    assert_eq!(
+        input.recv().await.unwrap(),
+        json!({"jsonrpc":"2.0","method":"rpc.superseded","params":{"current":"new"}})
+    );
+    // Run the upgrade dispatcher, then its per-process task, so the deadline is armed.
+    tokio::task::yield_now().await;
+    tokio::task::yield_now().await;
+    let window = Duration::from_secs(5);
+    assert_eq!(UPGRADE_GRACE, window);
+    // tokio::time::sleep documents millisecond granularity; the paused driver
+    // may round a deadline up by one tick. Check each window independently.
+    let tick = Duration::from_millis(1);
+    let before_deadline = window - tick;
+    advance(before_deadline).await;
+    tokio::task::yield_now().await;
+    assert_eq!(host.processes()["old-work"].state, "running");
+    assert!(!work.is_finished());
+    advance(tick).await;
+    assert!(
+        input.recv().await.is_none(),
+        "EOF at grace, even with active work"
+    );
+    let stopped = Instant::now();
+    assert!((window..=window + tick).contains(&(stopped - start)));
+    assert_eq!(host.processes()["old-work"].state, "stopping");
+    // begin_retire schedules the independent PROTOCOL 3.6 deadline.
+    tokio::task::yield_now().await;
+    advance(before_deadline).await;
+    tokio::task::yield_now().await;
+    assert!(
+        !work.is_finished(),
+        "on_stop still has its full five seconds"
+    );
+    advance(tick).await;
+    assert!(work.await.unwrap_err().is_cancelled());
+    assert!((window..=window + tick).contains(&(Instant::now() - stopped)));
+    assert_eq!(host.processes()["old-discovery"].state, "running");
+    assert!(matches!(
+        discovery_input.try_recv(),
+        Err(mpsc::error::TryRecvError::Empty)
+    ));
+    assert!(!discovery.is_finished());
+    discovery.abort();
+    let _ = discovery.await;
+    // Synthetic processes have no execution cleanup task; discard only this test table.
+    host.0.shutdown.store(true, Ordering::SeqCst);
+    host.0.state.lock().unwrap().processes.clear();
+    host.stop().await;
+}