swarm/network: Revised depth and health for Kademlia (#18354)

* swarm/network: Revised depth calculation with tests

* swarm/network: WIP remove redundant "full" function

* swarm/network: WIP peerpot refactor

* swarm/network: Make test methods submethod of peerpot and embed kad

* swarm/network: Remove commented out code

* swarm/network: Rename health test functions

* swarm/network: Too many n's

* swarm/network: Change hive Healthy func to accept addresses

* swarm/network: Add Healthy proxy method for api in hive

* swarm/network: Skip failing test out of scope for PR

* swarm/network: Skip all tests dependent on SuggestPeers

* swarm/network: Remove commented code and useless kad Pof member

* swarm/network: Remove more unused code, add counter on depth test errors

* swarm/network: WIP Create Healthy assertion tests

* swarm/network: Roll back health related methods receiver change

* swarm/network: Hardwire network minproxbinsize in swarm sim

* swarm/network: Rework Health test to strict

Pending add test for saturation
And add test for as many as possible up to saturation

* swarm/network: Skip discovery tests (dependent on SuggestPeer)

* swarm/network: Remove useless minProxBinSize in stream

* swarm/network: Remove unnecessary testing.T param to assert health

* swarm/network: Implement t.Helper() in checkHealth

* swarm/network: Rename check back to assert now that we have helper magic

* swarm/network: Revert WaitTillHealthy change (deferred to nxt PR)

* swarm/network: Kademlia tests GotNN => ConnectNN

* swarm/network: Renames and comments

* swarm/network: Add comments

swarm/network/stream/common_test.go

@@ -35,7 +35,6 @@ import (
 	p2ptest "github.com/ethereum/go-ethereum/p2p/testing"
 	"github.com/ethereum/go-ethereum/swarm/network"
 	"github.com/ethereum/go-ethereum/swarm/network/simulation"
-	"github.com/ethereum/go-ethereum/swarm/pot"
 	"github.com/ethereum/go-ethereum/swarm/state"
 	"github.com/ethereum/go-ethereum/swarm/storage"
 	"github.com/ethereum/go-ethereum/swarm/testutil"
@@ -57,7 +56,7 @@ var (
 	bucketKeyRegistry  = simulation.BucketKey("registry")
 
 	chunkSize = 4096
-	pof       = pot.DefaultPof(256)
+	pof       = network.Pof
 )
 
 func init() {

swarm/network/stream/delivery_test.go

@@ -453,8 +453,6 @@ func TestDeliveryFromNodes(t *testing.T) {
 }
 
 func testDeliveryFromNodes(t *testing.T, nodes, conns, chunkCount int, skipCheck bool) {
-
-	t.Skip("temporarily disabled as simulations.WaitTillHealthy cannot be trusted")
 	sim := simulation.New(map[string]simulation.ServiceFunc{
 		"streamer": func(ctx *adapters.ServiceContext, bucket *sync.Map) (s node.Service, cleanup func(), err error) {
 			node := ctx.Config.Node()
@@ -543,6 +541,7 @@ func testDeliveryFromNodes(t *testing.T, nodes, conns, chunkCount int, skipCheck
 		}
 
 		log.Debug("Waiting for kademlia")
+		// TODO this does not seem to be correct usage of the function, as the simulation may have no kademlias
 		if _, err := sim.WaitTillHealthy(ctx, 2); err != nil {
 			return err
 		}

swarm/network/stream/intervals_test.go

@@ -53,7 +53,6 @@ func TestIntervalsLiveAndHistory(t *testing.T) {
 
 func testIntervals(t *testing.T, live bool, history *Range, skipCheck bool) {
 
-	t.Skip("temporarily disabled as simulations.WaitTillHealthy cannot be trusted")
 	nodes := 2
 	chunkCount := dataChunkCount
 	externalStreamName := "externalStream"

swarm/network/stream/snapshot_retrieval_test.go

@@ -246,7 +246,6 @@ simulation's `action` function.
 The snapshot should have 'streamer' in its service list.
 */
 func runRetrievalTest(chunkCount int, nodeCount int) error {
-
 	sim := simulation.New(retrievalSimServiceMap)
 	defer sim.Close()
 

swarm/network/stream/snapshot_sync_test.go

@@ -182,8 +182,6 @@ func streamerFunc(ctx *adapters.ServiceContext, bucket *sync.Map) (s node.Servic
 }
 
 func testSyncingViaGlobalSync(t *testing.T, chunkCount int, nodeCount int) {
-
-	t.Skip("temporarily disabled as simulations.WaitTillHealthy cannot be trusted")
 	sim := simulation.New(simServiceMap)
 	defer sim.Close()
 
@@ -332,7 +330,6 @@ kademlia network. The snapshot should have 'streamer' in its service list.
 */
 func testSyncingViaDirectSubscribe(t *testing.T, chunkCount int, nodeCount int) error {
 
-	t.Skip("temporarily disabled as simulations.WaitTillHealthy cannot be trusted")
 	sim := simulation.New(map[string]simulation.ServiceFunc{
 		"streamer": func(ctx *adapters.ServiceContext, bucket *sync.Map) (s node.Service, cleanup func(), err error) {
 			n := ctx.Config.Node()
@@ -555,9 +552,7 @@ func mapKeysToNodes(conf *synctestConfig) {
 		np, _, _ = pot.Add(np, a, pof)
 	}
 
-	var kadMinProxSize = 2
-
-	ppmap := network.NewPeerPotMap(kadMinProxSize, conf.addrs)
+	ppmap := network.NewPeerPotMap(network.NewKadParams().MinProxBinSize, conf.addrs)
 
 	//for each address, run EachNeighbour on the chunk hashes pot to identify closest nodes
 	log.Trace(fmt.Sprintf("Generated hash chunk(s): %v", conf.hashes))

swarm/network/stream/syncer_test.go

@@ -69,7 +69,6 @@ func createMockStore(globalStore mock.GlobalStorer, id enode.ID, addr *network.B
 
 func testSyncBetweenNodes(t *testing.T, nodes, conns, chunkCount int, skipCheck bool, po uint8) {
 
-	t.Skip("temporarily disabled as simulations.WaitTillHealthy cannot be trusted")
 	sim := simulation.New(map[string]simulation.ServiceFunc{
 		"streamer": func(ctx *adapters.ServiceContext, bucket *sync.Map) (s node.Service, cleanup func(), err error) {
 			var store storage.ChunkStore

swarm/network/stream/visualized_snapshot_sync_sim_test.go

@@ -96,7 +96,6 @@ func watchSim(sim *simulation.Simulation) (context.Context, context.CancelFunc)
 //This test requests bogus hashes into the network
 func TestNonExistingHashesWithServer(t *testing.T) {
 
-	t.Skip("temporarily disabled as simulations.WaitTillHealthy cannot be trusted")
 	nodeCount, _, sim := setupSim(retrievalSimServiceMap)
 	defer sim.Close()
 
@@ -211,6 +210,7 @@ func TestSnapshotSyncWithServer(t *testing.T) {
 		},
 	}).WithServer(":8888") //start with the HTTP server
 
+	nodeCount, chunkCount, sim := setupSim(simServiceMap)
 	defer sim.Close()
 
 	log.Info("Initializing test config")