Merge pull request 'broker: upgrade and rollback keep a stopped actor stopped' (#3) from upgrade-keeps-stopped into main

Reviewed-on: #3

PROTOCOL.md

@@ -125,8 +125,8 @@ the request: the request's `type` in past tense (`spawned`, `upgraded`,
 | `type` | Fields | Effect |
 | --- | --- | --- |
 | `spawn` | `actor`, `wasm`, `source`?, `built_by`? | test, then start a new actor |
-| `upgrade` | `actor`, `wasm`, `source`?, `built_by`? | test, then swap the version |
-| `rollback` | `actor`, `version` | go back to an older version |
+| `upgrade` | `actor`, `wasm`, `source`?, `built_by`? | test, then swap the version: a running actor is stopped (normal shutdown) and starts the new version; a stopped actor gets the new version and stays stopped, with its mailbox untouched, until `start`. The answer has `running` |
+| `rollback` | `actor`, `version` | go back to an older version; like `upgrade`, a stopped actor stays stopped. The answer has `running` |
 | `stop`, `start` | `actor` | stop or start an actor |
 | `remove` | `actor` | stop the actor (normal shutdown), then delete its whole folder `/actor/<id>/` (all versions, `data/`, `public/`, logs); answer `{"type": "removed", "actor"}`. Messages to it are then undeliverable, and the ID can be spawned again. An unknown actor or a native one (`broker`, `console`, `cargo`, `fs`) is an `error` |
 | `subscribe`, `unsubscribe` | `actor` | receive (or not) what `actor` publishes |
@@ -212,7 +212,8 @@ instance. A version without test files passes.
 
 **Swap.** The broker holds the mailbox, stops the old instance, makes the
 top-level `actor.wasm` and `source/` a copy of the new version, and starts
-it. A rollback does the same with the older version.
+it. A stopped actor is not started: it keeps its mailbox and runs the new
+version at the next `start`. A rollback does the same with the older version.
 
 **Crashes.** The broker restarts a crashed actor after 0.5 s, then doubles
 the delay up to 30 s. A new version that crashes 3 times within 30 seconds

cli/src/broker.rs

@@ -331,12 +331,13 @@ impl Broker {
         Ok((component, tests))
     }
 
-    /// Make `version` the current `actor.wasm`, `source/`, and `actor.json`.
-    pub fn install(&self, id: &str, version: u64) -> Result<()> {
+    /// Make `version` the current `actor.wasm`, `source/`, and `actor.json`,
+    /// and record whether the actor runs.
+    pub fn install(&self, id: &str, version: u64, running: bool) -> Result<()> {
         self.world.install_files(id, version)?;
         self.update_meta(id, |m| {
             m.version = Some(version);
-            m.running = true;
+            m.running = running;
         })
     }
 
@@ -360,7 +361,7 @@ impl Broker {
 
     async fn create_version(self: &Arc<Self>, id: &str, meta: &VersionMeta, wasm: &Path, source: Option<&Path>) -> Result<Value> {
         let (_, tests) = self.try_version(id, meta, wasm, source).await?;
-        self.install(id, meta.version)?;
+        self.install(id, meta.version, true)?;
         self.start_supervisor(id, meta.version, true);
         Ok(json!({"type": "spawned", "actor": id, "version": meta.version, "tests": tests}))
     }

cli/src/supervisor.rs

@@ -220,17 +220,16 @@ impl Supervisor {
 
     /// Make `version` current. It is compiled first (unless `component` is
     /// given): if that fails, nothing changes. `data/` and `public/` stay as
-    /// they are.
+    /// they are. A stopped actor stays stopped.
     async fn install(&mut self, version: u64, component: Option<Component>) -> Result<()> {
         let component = match component {
             Some(c) => c,
             None => self.broker.load_version(&self.id, version)?,
         };
         self.stop().await;
-        self.broker.install(&self.id, version)?;
+        self.broker.install(&self.id, version, self.running)?;
         self.version = version;
         self.component = Some(component);
-        self.running = true;
         self.restarts = 0;
         self.restart_at = None;
         Ok(())
@@ -239,20 +238,26 @@ impl Supervisor {
     async fn upgrade(&mut self, version: u64, component: Component, requester: String) -> Result<Value> {
         let previous = self.version;
         self.install(version, Some(component)).await?;
+        if !self.running {
+            // Installed, not started: main runs and mail is read at the next `start`.
+            return Ok(json!({"type": "upgraded", "actor": self.id, "version": version, "previous": previous, "running": false}));
+        }
         self.probation = Some(Probation { previous, since: Instant::now(), crashes: 0, requester });
         if let Err(e) = self.start().await {
             self.rollback(previous).await?;
             bail!("version {version} did not start ({e:#}); rolled back to {previous}");
         }
-        Ok(json!({"type": "upgraded", "actor": self.id, "version": version, "previous": previous}))
+        Ok(json!({"type": "upgraded", "actor": self.id, "version": version, "previous": previous, "running": true}))
     }
 
     async fn rollback(&mut self, version: u64) -> Result<Value> {
         let from = self.version;
         self.install(version, None).await?;
         self.probation = None;
-        self.start().await?;
-        Ok(json!({"type": "rolled_back", "actor": self.id, "from": from, "to": version}))
+        if self.running {
+            self.start().await?;
+        }
+        Ok(json!({"type": "rolled_back", "actor": self.id, "from": from, "to": version, "running": self.running}))
     }
 
     /// Handle a control request. Returns `true` when the supervisor ends.

cli/tests/host.rs

@@ -506,6 +506,50 @@ async fn rolls_back_a_crash_loop_to_the_previous_version_without_restoring_data(
     host.stop().await;
 }
 
+#[tokio::test]
+async fn upgrade_and_rollback_keep_a_stopped_actor_stopped() {
+    let world = create_world("upgrade-stopped");
+    let wasm = toolbox_wasm().clone();
+    let (host, mut mailbox) = start(&world).await;
+    let source = passing_source(&world, "source");
+    spawn_type(&host, &mut mailbox, "sleeper", &wasm, &source).await;
+    let stopped = request(&host, &mut mailbox, json!({"type": "stop", "actor": "sleeper"})).await;
+    assert_eq!(stopped.body["type"], "stopped");
+
+    let upgraded = upgrade_actor(&host, &mut mailbox, "sleeper", &wasm, &source).await;
+    assert_eq!(upgraded.body["type"], "upgraded", "{upgraded:?}");
+    assert_eq!(upgraded.body["version"], 2);
+    assert_eq!(upgraded.body["running"], false);
+    let meta = world.read_meta("sleeper");
+    assert_eq!((meta.version, meta.running), (Some(2), false));
+
+    // Mail waits in the mailbox: the stopped actor reads nothing.
+    let waiting = host.broker.send("console", Some("sleeper"), None, None, json!({"type": "version"}));
+    assert!(
+        tokio::time::timeout(Duration::from_millis(500), receive_reply(&mut mailbox, &waiting, Duration::from_secs(10)))
+            .await
+            .is_err(),
+        "a stopped actor must not answer"
+    );
+
+    let rolled_back = request(&host, &mut mailbox, json!({"type": "rollback", "actor": "sleeper", "version": 1})).await;
+    assert_eq!(rolled_back.body["type"], "rolled_back", "{rolled_back:?}");
+    assert_eq!(rolled_back.body["running"], false);
+    assert!(!world.read_meta("sleeper").running);
+
+    // `start` runs the installed version and delivers the waiting message.
+    let started = request(&host, &mut mailbox, json!({"type": "start", "actor": "sleeper"})).await;
+    assert_eq!(started.body["type"], "started");
+    let answer = receive_reply(&mut mailbox, &waiting, Duration::from_secs(10)).await;
+    assert_eq!(answer.body["version"], "1");
+
+    // A running actor still restarts on the new version.
+    let running = upgrade_actor(&host, &mut mailbox, "sleeper", &wasm, &source).await;
+    assert_eq!(running.body["running"], true);
+    assert_eq!(ask(&host, &mut mailbox, "sleeper", json!({"type": "version"})).await.body["version"], "3");
+    host.stop().await;
+}
+
 #[tokio::test]
 async fn explicit_rollback_keeps_current_data() {
     let world = create_world("explicit-rollback");