announcements answered when lacking

A neighbour now answers an announcement only if it lacks some of the
announced heads.  Heads that merely differ are no longer enough, since
they do while writes go on.  The check reads the document, so it runs
off the message consumer, as the pull check already does.

4 files changed, 34 insertions, 10 deletions

diff --git a/src/swarm/peer/inbound.rs b/src/swarm/peer/inbound.rs
index 1454c3e..28066cb 100644
--- a/src/swarm/peer/inbound.rs
+++ b/src/swarm/peer/inbound.rs
@@ -143,13 +143,31 @@ pub(crate) async fn handle_message(
             crate::swarm::blob::handle(state, &peer, blob).await;
         }
         transport::ParsedMessage::Status(remote) => {
-            // An announcement is no keepalive; it is answered only if our heads differ,
-            // so the announcer learns what we have that it lacks.
+            // An announcement is no keepalive; it is answered only if we lack some of the
+            // heads it announced (`relay::lacks`), so the announcer learns what we have
+            // that it lacks while we pull. Having all of them, we are as far or further,
+            // and what we have further we announced ourselves; differing heads alone are
+            // no reason, as changes on their way to us make them differ while writes go on.
             if !remote.announcing {
                 status_received(state, &peer).await;
             }
             let local = on_status(state, &peer, &remote, reactivated).await;
-            if remote.announcing && local.heads == remote.heads {
+            if remote.announcing {
+                if local.heads != remote.heads {
+                    // Off the consumer: telling which heads we lack takes the document's
+                    // lock.
+                    let (state, peer) = (state.clone(), peer.clone());
+                    tokio::spawn(async move {
+                        if crate::swarm::relay::lacks(&state, &remote.heads).await
+                            && let Err(error) = state
+                                .transport
+                                .send_message(&peer, &ParsedMessage::StatusReply(local))
+                                .await
+                        {
+                            debug!(peer = %peer, error = %format!("{error:#}"), "STATUS_REPLY failed");
+                        }
+                    });
+                }
                 return Ok(());
             }
             if let Err(error) = state
diff --git a/src/swarm/peer/keepalive.rs b/src/swarm/peer/keepalive.rs
index 8362d73..f4e961f 100644
--- a/src/swarm/peer/keepalive.rs
+++ b/src/swarm/peer/keepalive.rs
@@ -33,8 +33,8 @@ pub(crate) async fn send_status(state: &AppState, peer: &str) -> Result<()> {
 }
 
 /// Sends `peer` a STATUS announcing our new heads (`swarm::relay`): no keepalive, so it
-/// leaves the keepalives' schedule as it is, and it is answered only if the peer's heads
-/// differ (`Status::announcing`). Whom we reach only `with_reaches` (`swarm::reach`):
+/// leaves the keepalives' schedule as it is, and it is answered only if the peer lacks
+/// some of our heads (`Status::announcing`). Whom we reach only `with_reaches` (`swarm::reach`):
 /// announcements of heads go often.
 pub(crate) async fn announce_heads(state: &AppState, peer: &str, with_reaches: bool) -> Result<()> {
     let local = local_status(state, peer).await;
diff --git a/src/swarm/reach.rs b/src/swarm/reach.rs
index 7bd0f73..5c89d04 100644
--- a/src/swarm/reach.rs
+++ b/src/swarm/reach.rs
@@ -72,8 +72,8 @@ pub(crate) fn published(state: &AppState) -> Vec<u64> {
 
 /// With the peer worker's periodic pass (every 5 s), and at once when a member we said
 /// we reach stops answering (`reached_stops_answering`): whom we reach now; if it changed,
-/// our neighbours are told at once (a STATUS each, unanswered if the heads are the
-/// same). A change that is undone within a pass isn't told.
+/// our neighbours are told at once (a STATUS each, unanswered unless they lack some of
+/// our heads). A change that is undone within a pass isn't told.
 pub(crate) async fn check(state: &AppState) {
     let now = measure(state).await;
     {
@@ -109,8 +109,8 @@ pub(crate) fn reached_stops_answering(state: &AppState, peer: &str) -> bool {
         .is_some_and(|keys| keys.contains(&topology::pair_key(peer)))
 }
 
-/// A STATUS to `peer` with whom we reach: as an announcement (unanswered if the heads
-/// are the same), but with `reaches`.
+/// A STATUS to `peer` with whom we reach: as an announcement (unanswered unless it lacks
+/// some of our heads), but with `reaches`.
 async fn tell(state: &AppState, peer: &str) -> anyhow::Result<()> {
     announce_heads(state, peer, true).await
 }
diff --git a/src/swarm/relay.rs b/src/swarm/relay.rs
index 53c1065..99c1381 100644
--- a/src/swarm/relay.rs
+++ b/src/swarm/relay.rs
@@ -5,7 +5,7 @@
 //! further by itself but along a writer's tree. So after applying changes from one
 //! neighbour, a node *announces*
 //! its new heads to its other neighbours with a STATUS (heads, about 100 bytes, not the
-//! changes; no keepalive, and answered only by a neighbour whose heads differ). A
+//! changes; no keepalive, and answered only by a neighbour that lacks some of them). A
 //! neighbour that sees heads it lacks *pulls*: it enters the
 //! announced heads as the peer's heads in its sync state, Automerge asks for what's
 //! missing (`need`), and the announcer answers with exactly those changes. Regular
@@ -218,6 +218,12 @@ pub(crate) struct Pulling {
     waiting: HashMap<String, transport::Status>,
 }
 
+/// Whether we lack any of `heads` (with a digest, any of the sample it lists).
+pub(crate) async fn lacks(state: &AppState, heads: &HeadsSummary) -> bool {
+    let replica = state.doc.read().await;
+    !crate::document::changes::missing(&replica.doc, heads.listed()).is_empty()
+}
+
 /// A keepalive from `peer`: if it has heads we lack, pull them (one peer at a time; a
 /// busy slot queues the peer). Returns whether a pull started.
 pub(crate) async fn pull_if_behind(