api, metrics, network: check caps when deciding on next peer for a chunk (ethersphere#1749)

Author: nonsense

api/inspector.go

@@ -69,7 +69,7 @@ func (i *Inspector) DeliveriesPerPeer() map[string]int64 {
 	// iterate connection in kademlia
 	i.hive.Kademlia.EachConn(nil, 255, func(p *network.Peer, po int) bool {
 		// get how many chunks we receive for retrieve requests per peer
-		peermetric := fmt.Sprintf("chunk.delivery.%x", p.Over()[:16])
+		peermetric := fmt.Sprintf("network.retrieve.chunk.delivery.%x", p.Over()[:16])
 
 		res[fmt.Sprintf("%x", p.Over()[:16])] = metrics.GetOrRegisterCounter(peermetric, nil).Count()
 

metrics/flags.go

@@ -121,7 +121,7 @@ func datadirDiskUsage(path string, d time.Duration) {
 	for range time.Tick(d) {
 		bytes, err := dirSize(path)
 		if err != nil {
-			log.Warn("cannot get disk space", "err", err)
+			log.Trace("cannot get disk space", "err", err)
 		}
 
 		metrics.GetOrRegisterGauge("datadir.usage", nil).Update(bytes)

network/retrieval/retrieve.go

@@ -226,7 +226,11 @@ func (r *Retrieval) findPeer(ctx context.Context, req *storage.Request) (retPeer
 	r.kad.EachConn(req.Addr[:], 255, func(p *network.Peer, po int) bool {
 		id := p.ID()
 
-		// skip light nodes
+		if !p.HasCap(Spec.Name) {
+			return true
+		}
+
+		// skip light nodes, even though they support `bzz-retrieve` protocol
 		if p.LightNode {
 			return true
 		}
@@ -410,11 +414,11 @@ FINDPEER:
 
 	protoPeer := r.getPeer(sp.ID())
 	if protoPeer == nil {
-		r.logger.Warn("findPeer returned a peer to skip", "peer", sp.String(), "retry", retries)
+		r.logger.Warn("findPeer returned a peer to skip", "peer", sp.String(), "retry", retries, "ref", req.Addr)
 		req.PeersToSkip.Store(sp.ID().String(), time.Now())
 		retries++
 		if retries == maxFindPeerRetries {
-			r.logger.Error("max find peer retries reached", "max retries", maxFindPeerRetries)
+			r.logger.Error("max find peer retries reached", "max retries", maxFindPeerRetries, "ref", req.Addr)
 			return nil, ErrNoPeerFound
 		}
 

network/retrieval/retrieve_test.go

@@ -233,7 +233,7 @@ func TestRequestFromPeers(t *testing.T) {
 
 	addr := network.RandomAddr()
 	to := network.NewKademlia(addr.OAddr, network.NewKadParams())
-	protocolsPeer := protocols.NewPeer(p2p.NewPeer(dummyPeerID, "dummy", nil), nil, nil)
+	protocolsPeer := protocols.NewPeer(p2p.NewPeer(dummyPeerID, "dummy", []p2p.Cap{{Name: "bzz-retrieve", Version: 1}}), nil, nil)
 	peer := network.NewPeer(&network.BzzPeer{
 		BzzAddr:   network.RandomAddr(),
 		LightNode: false,
@@ -262,7 +262,7 @@ func TestRequestFromPeersWithLightNode(t *testing.T) {
 	addr := network.RandomAddr()
 	to := network.NewKademlia(addr.OAddr, network.NewKadParams())
 
-	protocolsPeer := protocols.NewPeer(p2p.NewPeer(dummyPeerID, "dummy", nil), nil, nil)
+	protocolsPeer := protocols.NewPeer(p2p.NewPeer(dummyPeerID, "dummy", []p2p.Cap{{Name: "bzz-retrieve", Version: 1}}), nil, nil)
 
 	// setting up a lightnode
 	peer := network.NewPeer(&network.BzzPeer{

storage/netstore.go

@@ -264,7 +264,7 @@ func (n *NetStore) RemoteFetch(ctx context.Context, req *Request, fi *Fetcher) e
 			osp.Finish()
 			break
 		case <-ctx.Done(): // global fetcher timeout
-			n.logger.Trace("remote.fetch, fail", "ref", ref)
+			n.logger.Warn("remote.fetch, global timeout fail", "ref", ref)
 			metrics.GetOrRegisterCounter("remote.fetch.timeout.global", nil).Inc(1)
 
 			osp.LogFields(olog.Bool("fail", true))