724bb44723
What: cmd/inspector/main.go: removes kad commands internal/testplanet/planet.go: Waits for contact chore to finish satellite/contact/nodesservice.go: creates an empty nodes service implementation satellite/contact/service.go: implements Local and FetchInfo methods & adds external address config value satellite/discovery/service.go: replaces kad.FetchInfo with contact.FetchInfo in Refresh() & removes Discover() satellite/peer.go: sets up contact service and endpoints storagenode/console/service.go: replaces nodeID with contact.Local() storagenode/contact/chore.go: replaces routing table with contact service storagenode/contact/nodesservice.go: creates empty implementation for ping and request info nodes service & implements RequestInfo method storagenode/contact/service.go: creates a service to return the local node and update its own capacity storagenode/monitor/monitor.go: uses contact service in place of routing table storagenode/operator.go: moves operatorconfig from kad into its own setup storagenode/peer.go: sets up contact service, chore, pingstats and endpoints satellite/overlay/config.go: changes NodeSelectionConfig.OnlineWindow default to 4hr to allow for accurate repair selection Removes kademlia setups in: cmd/storagenode/main.go cmd/storj-sim/network.go internal/testplane/planet.go internal/testplanet/satellite.go internal/testplanet/storagenode.go satellite/peer.go scripts/test-sim-backwards.sh scripts/testdata/satellite-config.yaml.lock storagenode/inspector/inspector.go storagenode/peer.go storagenode/storagenodedb/database.go Why: Replacing Kademlia Please describe the tests: • internal/testplanet/planet_test.go: TestBasic: assert that the storagenode can check in with the satellite without any errors TestContact: test that all nodes get inserted into both satellites' overlay cache during testplanet setup • satellite/contact/contact_test.go: TestFetchInfo: Tests that the FetchInfo method returns the correct info • storagenode/contact/contact_test.go: TestNodeInfoUpdated: tests that the contact chore updates the node information TestRequestInfoEndpoint: tests that the Request info endpoint returns the correct info Please describe the performance impact: Node discovery should be at least slightly more performant since each node connects directly to each satellite and no longer needs to wait for bootstrapping. It probably won't be faster in real time on start up since each node waits a random amount of time (less than 1 hr) to initialize its first connection (jitter).
99 lines
2.5 KiB
Go
99 lines
2.5 KiB
Go
// Copyright (C) 2019 Storj Labs, Inc.
|
|
// See LICENSE for copying information.
|
|
|
|
package contact
|
|
|
|
import (
|
|
"context"
|
|
"sync"
|
|
|
|
"github.com/zeebo/errs"
|
|
"go.uber.org/zap"
|
|
"google.golang.org/grpc"
|
|
"gopkg.in/spacemonkeygo/monkit.v2"
|
|
|
|
"storj.io/storj/pkg/pb"
|
|
"storj.io/storj/pkg/transport"
|
|
"storj.io/storj/satellite/overlay"
|
|
)
|
|
|
|
// Error is the default error class for contact package.
|
|
var Error = errs.Class("contact")
|
|
|
|
var mon = monkit.Package()
|
|
|
|
// Config contains configurable values for contact service
|
|
type Config struct {
|
|
ExternalAddress string `user:"true" help:"the public address of the node, useful for nodes behind NAT" default:""`
|
|
}
|
|
|
|
// Conn represents a connection
|
|
type Conn struct {
|
|
conn *grpc.ClientConn
|
|
client pb.NodesClient
|
|
}
|
|
|
|
// Service is the contact service between storage nodes and satellites.
|
|
// It is responsible for updating general node information like address, capacity, and uptime.
|
|
// It is also responsible for updating peer identity information for verifying signatures from that node.
|
|
//
|
|
// architecture: Service
|
|
type Service struct {
|
|
log *zap.Logger
|
|
|
|
mutex sync.Mutex
|
|
self *overlay.NodeDossier
|
|
|
|
overlay *overlay.Service
|
|
peerIDs overlay.PeerIdentities
|
|
transport transport.Client
|
|
}
|
|
|
|
// NewService creates a new contact service.
|
|
func NewService(log *zap.Logger, self *overlay.NodeDossier, overlay *overlay.Service, peerIDs overlay.PeerIdentities, transport transport.Client) *Service {
|
|
return &Service{
|
|
log: log,
|
|
self: self,
|
|
overlay: overlay,
|
|
peerIDs: peerIDs,
|
|
transport: transport,
|
|
}
|
|
}
|
|
|
|
// Local returns the satellite node dossier
|
|
func (service *Service) Local() overlay.NodeDossier {
|
|
service.mutex.Lock()
|
|
defer service.mutex.Unlock()
|
|
return *service.self
|
|
}
|
|
|
|
// FetchInfo connects to a node and returns its node info.
|
|
func (service *Service) FetchInfo(ctx context.Context, target pb.Node) (_ *pb.InfoResponse, err error) {
|
|
conn, err := service.dialNode(ctx, target)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
resp, err := conn.client.RequestInfo(ctx, &pb.InfoRequest{})
|
|
|
|
return resp, errs.Combine(err, conn.close())
|
|
}
|
|
|
|
// dialNode dials the specified node.
|
|
func (service *Service) dialNode(ctx context.Context, target pb.Node) (_ *Conn, err error) {
|
|
defer mon.Task()(&ctx)(&err)
|
|
grpcconn, err := service.transport.DialNode(ctx, &target)
|
|
return &Conn{
|
|
conn: grpcconn,
|
|
client: pb.NewNodesClient(grpcconn),
|
|
}, err
|
|
}
|
|
|
|
// close disconnects this connection.
|
|
func (conn *Conn) close() error {
|
|
return conn.conn.Close()
|
|
}
|
|
|
|
// Close closes resources
|
|
func (service *Service) Close() error { return nil }
|