perf(weed/topology): diff a heartbeat without copying the volume map (#10608)

* perf(weed/topology): keep only volume ids in the heartbeat membership set

The map is used solely to test whether a known volume is still present, but it
copied the whole 152-byte VolumeInfo for every volume in the heartbeat. Presize
it too, since the count is known.

BenchmarkSyncDataNodeRegistration/100000Volumes  199670102 B/op -> 180157310 B/op

* perf(weed/topology): diff a heartbeat without copying the volume map

To find volumes the data node no longer reports, UpdateVolumes copied every
VolumeInfo on the node into a fresh slice, then deleted the missing ones one at
a time. At 100k volumes that is a 15MB copy per heartbeat to usually find
nothing. Scan the disk maps in place instead and return only what was removed.

BenchmarkSyncDataNodeRegistration/100000Volumes  180157310 B/op -> 87806436 B/op

weed/topology/data_node.go

@@ -78,22 +78,18 @@ func (dn *DataNode) doAddOrUpdateVolume(v storage.VolumeInfo) (isNew, isChanged
 // used in master to notify master clients of these changes.
 func (dn *DataNode) UpdateVolumes(actualVolumes []storage.VolumeInfo) (newVolumes, deletedVolumes, changedVolumes []storage.VolumeInfo) {
 
-	actualVolumeMap := make(map[needle.VolumeId]storage.VolumeInfo)
+	actualVolumeIds := make(map[needle.VolumeId]struct{}, len(actualVolumes))
 	for _, v := range actualVolumes {
-		actualVolumeMap[v.Id] = v
+		actualVolumeIds[v.Id] = struct{}{}
 	}
 
 	dn.Lock()
 	defer dn.Unlock()
 
-	existingVolumes := dn.getVolumes()
+	for _, c := range dn.children {
-
+		disk := c.(*Disk)
-	for _, v := range existingVolumes {
+		for _, v := range disk.RemoveVolumesNotIn(actualVolumeIds) {
-		vid := v.Id
+			glog.V(0).Infoln("Deleting volume id:", v.Id)
-		if _, ok := actualVolumeMap[vid]; !ok {
-			glog.V(0).Infoln("Deleting volume id:", vid)
-			disk := dn.getOrCreateDisk(v.DiskType)
-			disk.DeleteVolumeById(vid)
 			deletedVolumes = append(deletedVolumes, v)
 
 			deltaDiskUsage := &DiskUsageCounts{}

weed/topology/disk.go

@@ -211,6 +211,21 @@ func (d *Disk) GetVolumes() (ret []storage.VolumeInfo) {
 	return ret
 }
 
+// RemoveVolumesNotIn drops the volumes whose ids are absent from keep and
+// returns them, so a heartbeat can be diffed without first copying the whole
+// volume map out.
+func (d *Disk) RemoveVolumesNotIn(keep map[needle.VolumeId]struct{}) (removed []storage.VolumeInfo) {
+	d.Lock()
+	defer d.Unlock()
+	for vid, v := range d.volumes {
+		if _, ok := keep[vid]; !ok {
+			removed = append(removed, v)
+			delete(d.volumes, vid)
+		}
+	}
+	return removed
+}
+
 func (d *Disk) GetVolumesById(id needle.VolumeId) (storage.VolumeInfo, error) {
 	d.RLock()
 	defer d.RUnlock()