feat(supervisor): gate spawns on the wait-for condition

This commit is contained in:
2026-08-07 15:46:38 +02:00
parent 4c34e336a2
commit 9307af46a8
2 changed files with 280 additions and 6 deletions
+279 -6
View File
@@ -43,6 +43,13 @@ pub enum StopAck {
NotRunning,
}
#[derive(Debug, Clone)]
pub struct WaitProgress {
pub description: String,
pub started_at: Instant,
pub timeout: Duration,
}
#[derive(Debug, Clone)]
pub struct Status {
pub state: ServerState,
@@ -51,6 +58,7 @@ pub struct Status {
pub started_at: Option<Instant>,
pub restart_count: u32,
pub last_exit: Option<i32>,
pub waiting: Option<WaitProgress>,
}
#[derive(Clone)]
@@ -79,6 +87,7 @@ pub struct SupervisorTask<S: Spawner> {
last_exit: Option<i32>,
started_at: Option<Instant>,
current_pid: Option<u32>,
waiting: Option<WaitProgress>,
}
impl<S: Spawner> SupervisorTask<S> {
@@ -105,6 +114,7 @@ impl<S: Spawner> SupervisorTask<S> {
last_exit: None,
started_at: None,
current_pid: None,
waiting: None,
}
}
@@ -116,6 +126,7 @@ impl<S: Spawner> SupervisorTask<S> {
started_at: self.started_at,
restart_count: self.restart_count,
last_exit: self.last_exit,
waiting: self.waiting.clone(),
});
}
@@ -137,11 +148,22 @@ impl<S: Spawner> SupervisorTask<S> {
child = Some(c);
let _ = ack.send(StartAck::Started);
}
Err(err) => {
Err(StartFailure::Spawn(err)) => {
warn!(name = %self.cfg.name, error = %err, "spawn failed");
self.set_state(ServerState::Failed);
let _ = ack.send(StartAck::SpawnFailed(err.to_string()));
}
Err(StartFailure::WaitTimedOut) => {
warn!(name = %self.cfg.name, "wait-for timed out");
self.set_state(ServerState::Failed);
let _ = ack.send(StartAck::SpawnFailed(
"wait-for timed out".to_string(),
));
}
Err(StartFailure::Cancelled) => {
self.set_state(ServerState::Stopped);
}
Err(StartFailure::Shutdown) => return,
}
}
}
@@ -161,10 +183,18 @@ impl<S: Spawner> SupervisorTask<S> {
match self.do_start(StartCause::Restart).await {
Ok(c) => child = Some(c),
Err(err) => {
Err(StartFailure::Spawn(err)) => {
warn!(name = %self.cfg.name, error = %err, "restart spawn failed");
self.set_state(ServerState::Failed);
}
Err(StartFailure::WaitTimedOut) => {
warn!(name = %self.cfg.name, "wait-for timed out");
self.set_state(ServerState::Failed);
}
Err(StartFailure::Cancelled) => {
self.set_state(ServerState::Stopped);
}
Err(StartFailure::Shutdown) => return,
}
let _ = ack.send(());
@@ -267,10 +297,18 @@ impl<S: Spawner> SupervisorTask<S> {
Action::RetryNow => {
match self.do_start(StartCause::Restart).await {
Ok(c) => child = Some(c),
Err(err) => {
Err(StartFailure::Spawn(err)) => {
warn!(name = %self.cfg.name, error = %err, "restart spawn failed");
self.set_state(ServerState::Failed);
}
Err(StartFailure::WaitTimedOut) => {
warn!(name = %self.cfg.name, "wait-for timed out");
self.set_state(ServerState::Failed);
}
Err(StartFailure::Cancelled) => {
self.set_state(ServerState::Stopped);
}
Err(StartFailure::Shutdown) => return,
}
}
Action::Cancel => {
@@ -286,10 +324,85 @@ impl<S: Spawner> SupervisorTask<S> {
}
}
async fn do_start(&mut self, cause: StartCause) -> std::io::Result<S::Child> {
async fn await_ready(&mut self) -> GateOutcome {
let Some(wait) = self.cfg.wait_for.clone() else {
return GateOutcome::Ready;
};
let started_at = Instant::now();
self.waiting = Some(WaitProgress {
description: crate::ready::describe(&wait.condition),
started_at,
timeout: wait.timeout,
});
self.set_state(ServerState::Waiting);
let outcome = loop {
if crate::ready::is_ready(&wait.condition, wait.interval).await {
break GateOutcome::Ready;
}
if started_at.elapsed() >= wait.timeout {
break GateOutcome::TimedOut;
}
let mut tick = std::pin::pin!(sleep(wait.interval));
let interrupted = tokio::select! {
_ = &mut tick => None,
cmd = self.cmd_rx.recv() => match cmd {
None => Some(GateOutcome::Shutdown),
Some(SupervisorCmd::Stop { ack }) => {
let _ = ack.send(StopAck::NotRunning);
Some(GateOutcome::Cancelled)
}
Some(SupervisorCmd::Shutdown { ack }) => {
let _ = ack.send(());
Some(GateOutcome::Shutdown)
}
Some(SupervisorCmd::Start { ack }) => {
let _ = ack.send(StartAck::Started);
None
}
Some(SupervisorCmd::Restart { ack }) => {
let _ = ack.send(());
None
}
Some(SupervisorCmd::Reconfigure { new, ack }) => {
self.cfg = *new;
let _ = ack.send(());
None
}
},
};
if let Some(outcome) = interrupted {
break outcome;
}
};
self.waiting = None;
outcome
}
async fn do_start(&mut self, cause: StartCause) -> Result<S::Child, StartFailure> {
match self.await_ready().await {
GateOutcome::Ready => {}
GateOutcome::TimedOut => return Err(StartFailure::WaitTimedOut),
GateOutcome::Cancelled => return Err(StartFailure::Cancelled),
GateOutcome::Shutdown => return Err(StartFailure::Shutdown),
}
self.set_state(ServerState::Starting);
let c = self.spawner.spawn(&self.cfg, self.log_sink.clone()).await?;
let c = self
.spawner
.spawn(&self.cfg, self.log_sink.clone())
.await
.map_err(StartFailure::Spawn)?;
if cause == StartCause::Restart {
self.restart_count = self.restart_count.saturating_add(1);
@@ -339,6 +452,20 @@ enum StartCause {
Restart,
}
enum StartFailure {
Spawn(std::io::Error),
WaitTimedOut,
Cancelled,
Shutdown,
}
enum GateOutcome {
Ready,
TimedOut,
Cancelled,
Shutdown,
}
pub struct RealSpawner;
#[async_trait::async_trait]
@@ -355,9 +482,10 @@ mod tests {
use super::*;
use crate::child::MockChild;
use crate::logs::{LogSink, RotatingLogWriter};
use std::path::PathBuf;
use std::sync::{Arc, Mutex};
use tempfile::tempdir;
use xy_protocol::{RestartConfig, RestartPolicy, StopConfig};
use xy_protocol::{RestartConfig, RestartPolicy, StopConfig, WaitCondition, WaitForConfig};
struct QueueSpawner {
queue: Arc<Mutex<Vec<MockChild>>>,
@@ -394,6 +522,12 @@ mod tests {
}
}
fn cfg_with_wait(name: &str, wait: WaitForConfig) -> ServerConfig {
let mut c = cfg(name, RestartPolicy::Never, 5);
c.wait_for = Some(wait);
c
}
fn sink(name: &str) -> LogSink {
let dir = tempdir().unwrap();
let writer = RotatingLogWriter::open(&dir.path().join("s.log"), 1024, 3).unwrap();
@@ -409,6 +543,7 @@ mod tests {
started_at: None,
restart_count: 0,
last_exit: None,
waiting: None,
}
}
@@ -551,4 +686,142 @@ mod tests {
ack_rx.await.unwrap();
h.await.unwrap();
}
#[tokio::test]
async fn a_met_condition_spawns_immediately() {
let tmp = tempfile::tempdir().unwrap();
let file = tmp.path().join("sock");
std::fs::write(&file, b"").unwrap();
let cfg = cfg_with_wait(
"x",
WaitForConfig {
condition: WaitCondition::Path(file),
timeout: Duration::from_millis(500),
interval: Duration::from_millis(10),
},
);
let (mock, ctl) = MockChild::new(1);
let queue = Arc::new(Mutex::new(vec![mock]));
let spawner = QueueSpawner { queue };
let (status_tx, mut status_rx) = watch::channel(initial_status(&cfg));
let (cmd_tx, cmd_rx) = mpsc::channel(8);
let task = SupervisorTask::new(cfg, sink("x"), spawner, status_tx, cmd_rx);
let h = tokio::spawn(task.run());
let (ack_tx, ack_rx) = oneshot::channel();
cmd_tx
.send(SupervisorCmd::Start { ack: ack_tx })
.await
.unwrap();
assert_eq!(ack_rx.await.unwrap(), StartAck::Started);
wait_for(&mut status_rx, ServerState::Running).await;
drop(ctl);
let (ack_tx, ack_rx) = oneshot::channel();
cmd_tx
.send(SupervisorCmd::Shutdown { ack: ack_tx })
.await
.unwrap();
ack_rx.await.unwrap();
h.await.unwrap();
}
#[tokio::test]
async fn a_timed_out_gate_fails_without_spawning_or_touching_the_retry_budget() {
let cfg = cfg_with_wait(
"x",
WaitForConfig {
condition: WaitCondition::Path(PathBuf::from("/definitely/not/here.sock")),
timeout: Duration::from_millis(80),
interval: Duration::from_millis(10),
},
);
// An empty queue: any spawn attempt panics, which is the assertion that
// a timed-out gate never reaches the spawner.
let queue = Arc::new(Mutex::new(Vec::new()));
let spawner = QueueSpawner { queue };
let (status_tx, mut status_rx) = watch::channel(initial_status(&cfg));
let (cmd_tx, cmd_rx) = mpsc::channel(8);
let task = SupervisorTask::new(cfg, sink("x"), spawner, status_tx, cmd_rx);
let h = tokio::spawn(task.run());
let (ack_tx, _ack_rx) = oneshot::channel();
cmd_tx
.send(SupervisorCmd::Start { ack: ack_tx })
.await
.unwrap();
wait_for(&mut status_rx, ServerState::Waiting).await;
wait_for(&mut status_rx, ServerState::Failed).await;
assert_eq!(
status_rx.borrow().restart_count,
0,
"waiting must not consume the restart budget"
);
let (ack_tx, ack_rx) = oneshot::channel();
cmd_tx
.send(SupervisorCmd::Shutdown { ack: ack_tx })
.await
.unwrap();
ack_rx.await.unwrap();
h.await.unwrap();
}
#[tokio::test]
async fn stop_during_a_wait_cancels_promptly() {
let cfg = cfg_with_wait(
"x",
WaitForConfig {
condition: WaitCondition::Path(PathBuf::from("/definitely/not/here.sock")),
timeout: Duration::from_secs(30),
interval: Duration::from_millis(10),
},
);
let queue = Arc::new(Mutex::new(Vec::new()));
let spawner = QueueSpawner { queue };
let (status_tx, mut status_rx) = watch::channel(initial_status(&cfg));
let (cmd_tx, cmd_rx) = mpsc::channel(8);
let task = SupervisorTask::new(cfg, sink("x"), spawner, status_tx, cmd_rx);
let h = tokio::spawn(task.run());
let (ack_tx, _ack_rx) = oneshot::channel();
cmd_tx
.send(SupervisorCmd::Start { ack: ack_tx })
.await
.unwrap();
wait_for(&mut status_rx, ServerState::Waiting).await;
let (ack_tx, ack_rx) = oneshot::channel();
cmd_tx
.send(SupervisorCmd::Stop { ack: ack_tx })
.await
.unwrap();
// The 30s timeout would swamp this if the poll loop were not interruptible.
tokio::time::timeout(Duration::from_secs(2), ack_rx)
.await
.expect("stop must not wait for the gate timeout")
.unwrap();
wait_for(&mut status_rx, ServerState::Stopped).await;
let (ack_tx, ack_rx) = oneshot::channel();
cmd_tx
.send(SupervisorCmd::Shutdown { ack: ack_tx })
.await
.unwrap();
ack_rx.await.unwrap();
h.await.unwrap();
}
}