feat(cluster): RFC 010 c10–c16, follow-ups and Phase 6 (squash of 16ef583..d9c62a8)
Tree snapshot of d9c62a8 (2026-08-18). The 20 source commits between
16ef583 (c9) and d9c62a8 were never pushed and the clone that held them
was lost; this commit carries their combined tree verbatim so the build
history stays auditable from the c1–c9 commits below it. Original
hashes as recorded in the session handoff:
c10 f03e94d pid targeting + auto-serialization (RemotePid, D14 name
on the wire); Phase 3 gate
c11 7ef4bad DownReason::Disconnected, wire tag 5
c12 d124162 remote monitors (Monitor/Demonitor/Down frames)
c13 9de967b connection-loss synthesis (A+B: Monitors::teardown +
unread-command Disconnected); Phase 4 gate
c14 7e822b7 eager pg eviction (reaper actor, ReaperInboxes)
dbe1a22 InboundVerdict::label(), trace::Event::ClusterInbound
31a9877 tests/channel.rs monitor-churn target gated on `go`
653559e Discovery::Withdrawn{name, addr}
c15 b41d76e distributed pg: Sync on NodeUp, Join/Leave broadcast,
NodeDown sweep, members_all; PgMsg wire type
c16 fafa881 pick_any / dispatch_any; Phase 5 complete
Phase 6 Tier A:
195c73e p4 NodeEvent::NodeDown(NodeInfo)
48fd766 p1 connector Candidate{name, addr, state}
ce8cf99 p2+p7 conn.rs select arms as Vec<Arm>; Outbound::Drained
bf24988 p6 RemotePid::from_local -> Option
9ae0380 p3 PeerStanding{Free, Claimed, Dialing}
c7d62a1 p11 cluster::Timing knobs, threaded by value
46f171d p11 cluster_disconnect un-ignored on SMARM_FAST_TIMING
Phase 6 Tier B:
391a9ae p5 cluster::RemoteDownReason{Local, Disconnected};
DownReason::Disconnected removed from core
7ddd908 p9 pg ctl channel unconditional, one cfg seam at spawn
d9c62a8 PeerNameMismatch parks the candidate; ClusterDial trace
Verified at d9c62a8: default 361/0, cluster 448/0, clippy --lib on
default / cluster / cluster+smarm-trace, fmt, 10x flake on
cluster_dial_mismatch, 5x on cluster_pg.
This commit is contained in:
+13
-20
@@ -1,5 +1,6 @@
|
||||
//! Process-group tests that run under the scheduler: `join` installs a real
|
||||
//! monitor on a live actor, and a real death drives eviction on next contact.
|
||||
//! monitor on a live actor, and a real death drives eviction (the reaper
|
||||
//! actor sweeps it; the read path hides it in the meantime).
|
||||
//! (Pure structural invariants live in the `pg` unit tests.)
|
||||
|
||||
use smarm::{channel, members, pick, run, spawn};
|
||||
@@ -35,19 +36,15 @@ fn a_dead_actor_vanishes_from_every_group_it_joined() {
|
||||
assert_eq!(members("g1"), vec![pid]);
|
||||
assert_eq!(members("g2"), vec![pid]);
|
||||
|
||||
// Release and reap the actor. finalize_actor queues the Down to our
|
||||
// monitors before unparking joiners, so by the time join() returns the
|
||||
// Down is already waiting in the membership channel.
|
||||
// Release the actor. finalize_actor queues the Down to the reaper and
|
||||
// marks the slot dead before unparking joiners, so by the time join()
|
||||
// returns every read hides the pid whether or not the reaper has run.
|
||||
tx.send(()).unwrap();
|
||||
h.join().unwrap();
|
||||
|
||||
// Drain-on-contact: touching g1 detects the death and sweeps the pid
|
||||
// out of every group (g2 included), not just g1.
|
||||
assert!(members("g1").is_empty(), "evicted from the touched group");
|
||||
assert!(
|
||||
members("g2").is_empty(),
|
||||
"and swept from the untouched group"
|
||||
);
|
||||
// Gone from every group it joined, not just one.
|
||||
assert!(members("g1").is_empty(), "gone from g1");
|
||||
assert!(members("g2").is_empty(), "and from g2");
|
||||
assert_eq!(pick("g1"), None);
|
||||
});
|
||||
}
|
||||
@@ -86,11 +83,7 @@ fn live_members_survive_a_peers_death() {
|
||||
tx_a.send(()).unwrap();
|
||||
a.join().unwrap();
|
||||
|
||||
assert_eq!(
|
||||
members("svc"),
|
||||
vec![b.pid()],
|
||||
"only the dead peer is reaped"
|
||||
);
|
||||
assert_eq!(members("svc"), vec![b.pid()], "only the dead peer is gone");
|
||||
assert_eq!(pick("svc"), Some(b.pid()));
|
||||
|
||||
tx_b.send(()).unwrap();
|
||||
@@ -123,18 +116,18 @@ fn leave_drops_a_membership_without_affecting_others() {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn joining_an_already_dead_pid_is_evicted_on_next_contact() {
|
||||
fn joining_an_already_dead_pid_never_shows_in_a_read() {
|
||||
run(|| {
|
||||
let h = spawn(|| {});
|
||||
let pid = h.pid();
|
||||
h.join().unwrap(); // actor is finalized before we join it to anything
|
||||
|
||||
// monitor() on a gone pid queues a NoProc Down immediately, so the
|
||||
// membership is reaped the next time the group is touched.
|
||||
// join() on a gone pid queues a NoProc Down to the reaper immediately;
|
||||
// reads never show it either way (slot-liveness backstop).
|
||||
join("late", pid);
|
||||
assert!(
|
||||
members("late").is_empty(),
|
||||
"dead-at-join member is reaped on read"
|
||||
"dead-at-join member never reads as live"
|
||||
);
|
||||
assert_eq!(pick("late"), None);
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user