mapper/batcher: replace connected map with per-node disconnectedAt

The Batcher's connected field (*xsync.Map[types.NodeID, *time.Time])
encoded three states via pointer semantics:

  - nil value:    node is connected
  - non-nil time: node disconnected at that timestamp
  - key missing:  node was never seen

This was error-prone (nil meaning 'connected' inverts Go idioms),
redundant with b.nodes + hasActiveConnections(), and required keeping
two parallel maps in sync. It also contained a bug in RemoveNode where
new(time.Now()) was used instead of &now, producing a zero time.

Replace the separate connected map with a disconnectedAt field on
multiChannelNodeConn (atomic.Pointer[time.Time]), tracked directly
on the object that already manages the node's connections.

Changes:
  - Add disconnectedAt field and helpers (markConnected, markDisconnected,
    isConnected, offlineDuration) to multiChannelNodeConn
  - Remove the connected field from Batcher
  - Simplify IsConnected from two map lookups to one
  - Simplify ConnectedMap and Debug from two-map iteration to one
  - Rewrite cleanupOfflineNodes to scan b.nodes directly
  - Remove the markDisconnectedIfNoConns helper
  - Update all tests and benchmarks

Fixes #3141
This commit is contained in:
Kristoffer Dalby 2026-03-14 14:06:52 +00:00
parent 60317064fd
commit 87b8507ac9
6 changed files with 148 additions and 191 deletions

View file

@ -52,6 +52,12 @@ type multiChannelNodeConn struct {
closeOnce sync.Once
updateCount atomic.Int64
// disconnectedAt records when the last connection was removed.
// nil means the node is considered connected (or newly created);
// non-nil means the node disconnected at the stored timestamp.
// Used by cleanupOfflineNodes to evict stale entries.
disconnectedAt atomic.Pointer[time.Time]
// lastSentPeers tracks which peers were last sent to this node.
// This enables computing diffs for policy changes instead of sending
// full peer lists (which clients interpret as "no change" when empty).
@ -162,6 +168,41 @@ func (mc *multiChannelNodeConn) getActiveConnectionCount() int {
return len(mc.connections)
}
// markConnected clears the disconnect timestamp, indicating the node
// has an active connection.
func (mc *multiChannelNodeConn) markConnected() {
mc.disconnectedAt.Store(nil)
}
// markDisconnected records the current time as the moment the node
// lost its last connection. Used by cleanupOfflineNodes to determine
// how long the node has been offline.
func (mc *multiChannelNodeConn) markDisconnected() {
now := time.Now()
mc.disconnectedAt.Store(&now)
}
// isConnected returns true if the node has active connections or has
// not been marked as disconnected.
func (mc *multiChannelNodeConn) isConnected() bool {
if mc.hasActiveConnections() {
return true
}
return mc.disconnectedAt.Load() == nil
}
// offlineDuration returns how long the node has been disconnected.
// Returns 0 if the node is connected or has never been marked as disconnected.
func (mc *multiChannelNodeConn) offlineDuration() time.Duration {
t := mc.disconnectedAt.Load()
if t == nil {
return 0
}
return time.Since(*t)
}
// appendPending appends changes to this node's pending change list.
// Thread-safe via pendingMu; does not contend with the connection mutex.
func (mc *multiChannelNodeConn) appendPending(changes ...change.Change) {