storj/storagenode/inspector/inspector.go

129 lines
3.5 KiB
Go
Raw Normal View History

// Copyright (C) 2019 Storj Labs, Inc.
// See LICENSE for copying information.
package inspector
import (
"context"
"net"
"time"
"github.com/golang/protobuf/ptypes"
"github.com/spacemonkeygo/monkit/v3"
"github.com/zeebo/errs"
"go.uber.org/zap"
"storj.io/common/pb"
"storj.io/common/rpc/rpcstatus"
"storj.io/storj/storagenode/bandwidth"
"storj.io/storj/storagenode/contact"
"storj.io/storj/storagenode/pieces"
2019-04-26 06:17:18 +01:00
"storj.io/storj/storagenode/piecestore"
)
var (
mon = monkit.Package()
// Error is the default error class for piecestore monitor errors
Error = errs.Class("piecestore inspector")
)
// Endpoint does inspectory things
2019-09-10 14:24:16 +01:00
//
// architecture: Endpoint
type Endpoint struct {
log *zap.Logger
pieceStore *pieces.Store
Remove Kademlia dependencies from Satellite and Storagenode (#2966) 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).
2019-09-19 20:56:34 +01:00
contact *contact.Service
pingStats *contact.PingStats
usageDB bandwidth.DB
startTime time.Time
pieceStoreConfig piecestore.OldConfig
dashboardAddress net.Addr
Remove Kademlia dependencies from Satellite and Storagenode (#2966) 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).
2019-09-19 20:56:34 +01:00
externalAddress string
}
// NewEndpoint creates piecestore inspector instance
func NewEndpoint(
log *zap.Logger,
pieceStore *pieces.Store,
Remove Kademlia dependencies from Satellite and Storagenode (#2966) 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).
2019-09-19 20:56:34 +01:00
contact *contact.Service,
pingStats *contact.PingStats,
usageDB bandwidth.DB,
pieceStoreConfig piecestore.OldConfig,
dashboardAddress net.Addr,
Remove Kademlia dependencies from Satellite and Storagenode (#2966) 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).
2019-09-19 20:56:34 +01:00
externalAddress string) *Endpoint {
return &Endpoint{
log: log,
pieceStore: pieceStore,
Remove Kademlia dependencies from Satellite and Storagenode (#2966) 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).
2019-09-19 20:56:34 +01:00
contact: contact,
pingStats: pingStats,
usageDB: usageDB,
pieceStoreConfig: pieceStoreConfig,
dashboardAddress: dashboardAddress,
startTime: time.Now(),
Remove Kademlia dependencies from Satellite and Storagenode (#2966) 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).
2019-09-19 20:56:34 +01:00
externalAddress: externalAddress,
}
}
// Stats returns current statistics about the storage node
func (inspector *Endpoint) Stats(ctx context.Context, in *pb.StatsRequest) (out *pb.StatSummaryResponse, err error) {
defer mon.Task()(&ctx)(&err)
return inspector.retrieveStats(ctx)
}
func (inspector *Endpoint) retrieveStats(ctx context.Context) (_ *pb.StatSummaryResponse, err error) {
defer mon.Task()(&ctx)(&err)
// Space Usage
_, piecesContentSize, err := inspector.pieceStore.SpaceUsedForPieces(ctx)
if err != nil {
return nil, rpcstatus.Error(rpcstatus.Internal, err.Error())
}
usage, err := bandwidth.TotalMonthlySummary(ctx, inspector.usageDB)
if err != nil {
return nil, rpcstatus.Error(rpcstatus.Internal, err.Error())
}
ingress := usage.Put + usage.PutRepair
egress := usage.Get + usage.GetAudit + usage.GetRepair
totalUsedBandwidth := usage.Total()
return &pb.StatSummaryResponse{
UsedSpace: piecesContentSize,
AvailableSpace: inspector.pieceStoreConfig.AllocatedDiskSpace.Int64() - piecesContentSize,
UsedIngress: ingress,
UsedEgress: egress,
UsedBandwidth: totalUsedBandwidth,
}, nil
}
// Dashboard returns dashboard information
func (inspector *Endpoint) Dashboard(ctx context.Context, in *pb.DashboardRequest) (out *pb.DashboardResponse, err error) {
defer mon.Task()(&ctx)(&err)
return inspector.getDashboardData(ctx)
}
func (inspector *Endpoint) getDashboardData(ctx context.Context) (_ *pb.DashboardResponse, err error) {
defer mon.Task()(&ctx)(&err)
statsSummary, err := inspector.retrieveStats(ctx)
if err != nil {
return nil, rpcstatus.Error(rpcstatus.Internal, err.Error())
}
lastPingedAt := inspector.pingStats.WhenLastPinged()
return &pb.DashboardResponse{
NodeId: inspector.contact.Local().Id,
InternalAddress: "",
ExternalAddress: inspector.contact.Local().Address.Address,
LastPinged: lastPingedAt,
DashboardAddress: inspector.dashboardAddress.String(),
Uptime: ptypes.DurationProto(time.Since(inspector.startTime)),
Stats: statsSummary,
}, nil
}