rsp2k/headscale
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

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

Browse source 
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
Download patch file Download diff file Expand all files Collapse all files

21
hscontrol/mapper/batcher_bench_test.go
View file

@ -150,12 +150,11 @@ func BenchmarkUpdateSentPeers(b *testing.B) {
// helper, it doesn't register cleanup and suppresses logging.
func benchBatcher(nodeCount, bufferSize int) (*Batcher, map[types.NodeID]chan *tailcfg.MapResponse) {
b := &Batcher{
tick: time.NewTicker(1 * time.Hour), // never fires during bench
workers: 4,
workCh: make(chan work, 4*200),
nodes: xsync.NewMap[types.NodeID, *multiChannelNodeConn](),
connected: xsync.NewMap[types.NodeID, *time.Time](),
done: make(chan struct{}),
tick: time.NewTicker(1 * time.Hour), // never fires during bench
workers: 4,
workCh: make(chan work, 4*200),
nodes: xsync.NewMap[types.NodeID, *multiChannelNodeConn](),
done: make(chan struct{}),
}
channels := make(map[types.NodeID]chan *tailcfg.MapResponse, nodeCount)
@ -172,7 +171,6 @@ func benchBatcher(nodeCount, bufferSize int) (*Batcher, map[types.NodeID]chan *t
entry.lastUsed.Store(time.Now().Unix())
mc.addConnection(entry)
b.nodes.Store(id, mc)
b.connected.Store(id, nil)
channels[id] = ch
}
@ -471,7 +469,7 @@ func BenchmarkConnectedMap(b *testing.B) {
for _, nodeCount := range []int{10, 100, 1000} {
b.Run(fmt.Sprintf("%dnodes", nodeCount), func(b *testing.B) {
batcher, _ := benchBatcher(nodeCount, 1)
batcher, channels := benchBatcher(nodeCount, 1)
defer func() {
close(batcher.done)
@ -481,8 +479,11 @@ func BenchmarkConnectedMap(b *testing.B) {
// Disconnect 10% of nodes for a realistic mix
for i := 1; i <= nodeCount; i++ {
if i%10 == 0 {
now := time.Now()
batcher.connected.Store(types.NodeID(i), &now) //nolint:gosec // benchmark
id := types.NodeID(i) //nolint:gosec // benchmark
if mc, ok := batcher.nodes.Load(id); ok {
mc.removeConnectionByChannel(channels[id])
mc.markDisconnected()
}
}
}