feat(link): bidirectional links + trap_exit (roadmap #3)

Add Erlang-style process links so an abnormal death fate-shares across a
link set, with trap_exit to convert that into a message instead.

- Slot.links: Vec<Pid>, bidirectional; reset in all three lifecycle sites.
- Actor.trap: Option<Sender<ExitSignal>>, fresh per spawn (a restarted
  child starts un-trapped; no fourth reset site).
- link/unlink free functions on self_pid(); trap_exit() -> Receiver<ExitSignal>
  (a dedicated inbox, distinct from the monitor Down channel).
- finalize_actor clears reverse links under the lock (always; keeps the
  cascade acyclic), then propagates abnormal deaths post-lock: trapping peer
  gets an ExitSignal message and survives, non-trapping peer is request_stop'd.
  Normal exit never propagates. Dead-pid link delivers an immediate NoProc
  (message if trapping, else request_stop(self) -- never a silent no-op).
- ExitSignal reuses DownReason and carries no panic payload (joiner-only).

Tests in tests/link.rs cover the propagate/trap/normal/dead-pid/unlink cases.
This commit is contained in:
smarm-dev
2026-06-07 21:51:56 +00:00
parent 59998ce79e
commit 8ac11a57ac
6 changed files with 443 additions and 2 deletions
+223
View File
@@ -0,0 +1,223 @@
//! Link + trap_exit tests (roadmap item #3).
//!
//! A *link* is bidirectional and persistent (contrast a monitor, which is
//! unidirectional and one-shot). When a linked actor dies *abnormally* — a
//! panic or a cooperative `request_stop` — the death propagates to the peer:
//!
//! - a peer that has NOT trapped exits is cooperatively `request_stop`'d, so
//! a crash fate-shares across the link set (Erlang's "let it crash");
//! - a peer that HAS called `trap_exit()` instead receives an [`ExitSignal`]
//! *message* on its trap inbox and survives.
//!
//! A *normal* exit never propagates — not even to a trapping peer. Linking an
//! already-dead pid delivers an immediate exit signal (`NoProc`): a message to
//! a trapping caller, a `request_stop` to a non-trapping one.
//!
//! These cases are deterministic under the single-thread runtime: an actor
//! runs until it parks/yields, so the relative order of link setup, the
//! triggering death, and the propagated signal is fixed.
use smarm::{
channel, link, monitor, run, self_pid, spawn, trap_exit, unlink, yield_now, DownReason,
};
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::Arc;
/// Sets its flag when dropped — proves a propagated stop unwound the peer's
/// stack (running Drop) rather than leaking it.
struct DropFlag(Arc<AtomicBool>);
impl Drop for DropFlag {
fn drop(&mut self) {
self.0.store(true, Ordering::SeqCst);
}
}
/// Abnormal death of one linked actor cooperatively stops its non-trapping
/// peer, and the peer's Drop guards run during the propagated unwind.
#[test]
fn linked_pair_one_panics_other_is_stopped() {
let dropped = Arc::new(AtomicBool::new(false));
let saw_stopped = Arc::new(AtomicBool::new(false));
let (d, s) = (dropped.clone(), saw_stopped.clone());
run(move || {
// B parks on recv (kept open by a retained sender) so it is alive and
// suspended when the propagated stop arrives.
let hb = spawn(move || {
let _g = DropFlag(d);
let (tx, rx) = channel::<u8>();
let _keep = tx;
let _ = rx.recv(); // parks until the link-propagated stop unwinds us
});
let b = hb.pid();
let down_b = monitor(b);
// A links B, then panics. The panic propagates along the link to B.
let ha = spawn(move || {
link(b);
panic!("boom");
});
let dn = down_b.recv().expect("monitor channel closed before Down");
assert_eq!(dn.pid, b, "Down reported the wrong pid");
if matches!(dn.reason, DownReason::Stopped) {
s.store(true, Ordering::SeqCst);
}
drop(ha);
let _ = hb.join();
});
assert!(
saw_stopped.load(Ordering::SeqCst),
"peer should be Stopped by the propagated abnormal exit"
);
assert!(
dropped.load(Ordering::SeqCst),
"peer's Drop guard must run during the propagated cancellation unwind"
);
}
/// A trapping peer receives an abnormal death as an `ExitSignal` message and
/// keeps running instead of being torn down.
#[test]
fn trap_exit_turns_abnormal_death_into_a_message() {
let ok = Arc::new(AtomicBool::new(false));
let o = ok.clone();
run(move || {
let h = spawn(move || {
let inbox = trap_exit();
// Spawn the peer from here so we control ordering: it is enqueued
// behind us and runs once we park on `inbox.recv()`.
let ha = spawn(|| panic!("peer down"));
let a = ha.pid();
link(a);
// Parks here; A then runs, panics, and the trap message wakes us.
let sig = inbox.recv().expect("trap inbox closed without a signal");
if sig.from == a && matches!(sig.reason, DownReason::Panic) {
o.store(true, Ordering::SeqCst);
}
drop(ha);
});
let _ = h.join();
});
assert!(
ok.load(Ordering::SeqCst),
"trapping peer should receive ExitSignal{{from, Panic}} and survive"
);
}
/// A normal exit never propagates — a trapping linked peer sees no message and
/// stays alive.
#[test]
fn normal_exit_does_not_propagate() {
let empty = Arc::new(AtomicBool::new(false));
let e = empty.clone();
run(move || {
let h = spawn(move || {
let inbox = trap_exit();
let ha = spawn(|| { /* exits normally, immediately */ });
let a = ha.pid();
link(a);
yield_now(); // let A run to completion and finalize
// A exited normally: nothing should have landed on the inbox.
if let Ok(None) = inbox.try_recv() {
e.store(true, Ordering::SeqCst);
}
drop(ha);
});
let _ = h.join();
});
assert!(
empty.load(Ordering::SeqCst),
"normal exit must not deliver any ExitSignal to a trapping peer"
);
}
/// Linking an already-dead pid from a non-trapping actor stops the caller
/// (no silent no-op).
#[test]
fn link_to_dead_pid_stops_a_nontrapping_caller() {
let dropped = Arc::new(AtomicBool::new(false));
let saw_stopped = Arc::new(AtomicBool::new(false));
let (d, s) = (dropped.clone(), saw_stopped.clone());
run(move || {
let ha = spawn(|| {});
let a = ha.pid();
ha.join().unwrap(); // A finishes and is reclaimed → `a` is now stale
let hb = spawn(move || {
let _g = DropFlag(d);
link(a); // dead target, not trapping → request_stop(self)
loop {
smarm::check!(); // observation point to realize the stop
}
});
let b = hb.pid();
let down_b = monitor(b);
let dn = down_b.recv().expect("monitor channel closed before Down");
if matches!(dn.reason, DownReason::Stopped) {
s.store(true, Ordering::SeqCst);
}
let _ = hb.join();
});
assert!(
saw_stopped.load(Ordering::SeqCst),
"linking a dead pid (non-trapping) should stop the caller"
);
assert!(dropped.load(Ordering::SeqCst), "Drop guard must run");
}
/// Linking an already-dead pid from a trapping actor delivers an immediate
/// `NoProc` exit message instead of killing it.
#[test]
fn link_to_dead_pid_messages_a_trapping_caller() {
let ok = Arc::new(AtomicBool::new(false));
let o = ok.clone();
run(move || {
let ha = spawn(|| {});
let a = ha.pid();
ha.join().unwrap(); // `a` is now stale
let hb = spawn(move || {
let inbox = trap_exit();
link(a); // dead target, trapping → immediate NoProc message
let sig = inbox.recv().expect("trap inbox closed without a signal");
if sig.from == a && matches!(sig.reason, DownReason::NoProc) {
o.store(true, Ordering::SeqCst);
}
});
let _ = hb.join();
});
assert!(
ok.load(Ordering::SeqCst),
"linking a dead pid (trapping) should deliver a NoProc ExitSignal"
);
}
/// `unlink` removes the relationship in both directions: an abnormal death no
/// longer reaches the formerly-linked peer.
#[test]
fn unlink_prevents_propagation() {
let survived = Arc::new(AtomicBool::new(false));
let sv = survived.clone();
run(move || {
let h = spawn(move || {
let b = self_pid();
let inbox = trap_exit();
let ha = spawn(move || {
link(b);
unlink(b);
panic!("boom"); // abnormal, but the link is gone
});
yield_now(); // let A link, unlink, and panic
// Unlinked before death → no ExitSignal should have arrived.
if let Ok(None) = inbox.try_recv() {
sv.store(true, Ordering::SeqCst);
}
drop(ha);
});
let _ = h.join();
});
assert!(
survived.load(Ordering::SeqCst),
"unlinked peer must not receive a propagated exit"
);
}