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).
131 lines
3.0 KiB
Go
131 lines
3.0 KiB
Go
// Copyright (C) 2019 Storj Labs, Inc.
|
|
// See LICENSE for copying information.
|
|
|
|
package discovery
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
|
|
"github.com/zeebo/errs"
|
|
"go.uber.org/zap"
|
|
"golang.org/x/sync/errgroup"
|
|
monkit "gopkg.in/spacemonkeygo/monkit.v2"
|
|
|
|
"storj.io/storj/internal/sync2"
|
|
"storj.io/storj/satellite/contact"
|
|
"storj.io/storj/satellite/overlay"
|
|
)
|
|
|
|
var (
|
|
mon = monkit.Package()
|
|
|
|
// Error is a general error class of this package
|
|
Error = errs.Class("discovery error")
|
|
)
|
|
|
|
// Config loads on the configuration values for the cache
|
|
type Config struct {
|
|
RefreshInterval time.Duration `help:"the interval at which the cache refreshes itself in seconds" default:"1s"`
|
|
RefreshLimit int `help:"the amount of nodes read from the overlay in a single pagination call" default:"100"`
|
|
RefreshConcurrency int `help:"the amount of nodes refreshed in parallel" default:"8"`
|
|
}
|
|
|
|
// Discovery struct loads on cache, kad
|
|
//
|
|
// architecture: Chore
|
|
type Discovery struct {
|
|
log *zap.Logger
|
|
cache *overlay.Service
|
|
contact *contact.Service
|
|
|
|
refreshLimit int
|
|
refreshConcurrency int
|
|
|
|
Refresh sync2.Cycle
|
|
}
|
|
|
|
// New returns a new discovery service.
|
|
func New(logger *zap.Logger, ol *overlay.Service, contact *contact.Service, config Config) *Discovery {
|
|
discovery := &Discovery{
|
|
log: logger,
|
|
cache: ol,
|
|
contact: contact,
|
|
refreshLimit: config.RefreshLimit,
|
|
refreshConcurrency: config.RefreshConcurrency,
|
|
}
|
|
|
|
discovery.Refresh.SetInterval(config.RefreshInterval)
|
|
return discovery
|
|
}
|
|
|
|
// Close closes resources
|
|
func (discovery *Discovery) Close() error {
|
|
discovery.Refresh.Close()
|
|
return nil
|
|
}
|
|
|
|
// Run runs the discovery service
|
|
func (discovery *Discovery) Run(ctx context.Context) (err error) {
|
|
defer mon.Task()(&ctx)(&err)
|
|
|
|
var group errgroup.Group
|
|
discovery.Refresh.Start(ctx, &group, func(ctx context.Context) error {
|
|
err := discovery.refresh(ctx)
|
|
if err != nil {
|
|
discovery.log.Error("error with cache refresh: ", zap.Error(err))
|
|
}
|
|
return nil
|
|
})
|
|
return group.Wait()
|
|
}
|
|
|
|
// refresh updates the cache db with the current DHT.
|
|
func (discovery *Discovery) refresh(ctx context.Context) (err error) {
|
|
defer mon.Task()(&ctx)(&err)
|
|
|
|
limiter := sync2.NewLimiter(discovery.refreshConcurrency)
|
|
|
|
var offset int64
|
|
|
|
for {
|
|
list, more, err := discovery.cache.PaginateQualified(ctx, offset, discovery.refreshLimit)
|
|
if err != nil {
|
|
return Error.Wrap(err)
|
|
}
|
|
|
|
if len(list) == 0 {
|
|
break
|
|
}
|
|
|
|
offset += int64(len(list))
|
|
|
|
for _, node := range list {
|
|
node := node
|
|
|
|
limiter.Go(ctx, func() {
|
|
info, err := discovery.contact.FetchInfo(ctx, *node)
|
|
if ctx.Err() != nil {
|
|
return
|
|
}
|
|
|
|
if err != nil {
|
|
discovery.log.Info("could not ping node", zap.Stringer("ID", node.Id), zap.Error(err))
|
|
return
|
|
}
|
|
|
|
if _, err = discovery.cache.UpdateNodeInfo(ctx, node.Id, info); err != nil {
|
|
discovery.log.Warn("could not update node info", zap.Stringer("ID", node.GetAddress()))
|
|
}
|
|
})
|
|
}
|
|
|
|
if !more {
|
|
break
|
|
}
|
|
}
|
|
|
|
limiter.Wait()
|
|
return nil
|
|
}
|