grpc components encoding with optimisations

This commit is contained in:
crn4
2026-05-19 14:43:17 +02:00
parent 2de0283971
commit 4543780ef0
8 changed files with 4313 additions and 183 deletions
+11 -2
View File
@@ -13,8 +13,9 @@ import (
// Peer capability constants mirror the proto enum values.
const (
PeerCapabilitySourcePrefixes int32 = 1
PeerCapabilityIPv6Overlay int32 = 2
PeerCapabilitySourcePrefixes int32 = 1
PeerCapabilityIPv6Overlay int32 = 2
PeerCapabilityComponentNetworkMap int32 = 3
)
// Peer represents a machine connected to the network.
@@ -247,6 +248,14 @@ func (p *Peer) SupportsSourcePrefixes() bool {
return p.HasCapability(PeerCapabilitySourcePrefixes)
}
// SupportsComponentNetworkMap reports whether the peer assembles its
// NetworkMap from server-shipped components instead of consuming a fully
// expanded NetworkMap. Determines whether the network_map controller skips
// Calculate() server-side and emits the components envelope.
func (p *Peer) SupportsComponentNetworkMap() bool {
return p.HasCapability(PeerCapabilityComponentNetworkMap)
}
func capabilitiesEqual(a, b []int32) bool {
if len(a) != len(b) {
return false
+8
View File
@@ -45,6 +45,14 @@ type GroupPeer struct {
PeerID string `gorm:"primaryKey"`
}
// HasSeqID reports whether the group has been persisted long enough to have a
// per-account sequence id allocated. Wire encoders that key off AccountSeqID
// must skip groups that return false here — otherwise multiple unpersisted
// groups would collide on id 0.
func (g *Group) HasSeqID() bool {
return g != nil && g.AccountSeqID != 0
}
func (g *Group) LoadGroupPeers() {
g.Peers = make([]string, len(g.GroupPeers))
for i, peer := range g.GroupPeers {
@@ -0,0 +1,157 @@
package types_test
import (
"context"
"fmt"
"testing"
goproto "google.golang.org/protobuf/proto"
nbdns "github.com/netbirdio/netbird/dns"
"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller/cache"
mgmtgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
"github.com/netbirdio/netbird/management/server/types"
)
// wireBenchScales mirrors the scales used by networkmap_benchmark_test.go but
// trimmed: encoding+marshal are linear, so we don't need the 30k peer extreme
// to see the trend.
var wireBenchScales = []benchmarkScale{
{"100peers_5groups", 100, 5},
{"500peers_20groups", 500, 20},
{"1000peers_50groups", 1000, 50},
{"5000peers_100groups", 5000, 100},
}
// populateAccountSeqIDs assigns deterministic AccountSeqIDs to every group and
// policy in the account so that the component encoder can reference them. The
// scalableTestAccount fixture builds entities by struct literal and skips this
// step, but production paths populate the IDs via the store layer.
func populateAccountSeqIDs(account *types.Account) {
var nextGroupSeq uint32 = 1
for _, g := range account.Groups {
g.AccountSeqID = nextGroupSeq
nextGroupSeq++
}
var nextPolicySeq uint32 = 1
for _, p := range account.Policies {
p.AccountSeqID = nextPolicySeq
nextPolicySeq++
}
}
// BenchmarkNetworkMapWireEncode reports per-call ns and the marshaled wire
// size for both encoding paths. Run with:
//
// go test -run=^$ -bench=BenchmarkNetworkMapWireEncode -benchmem ./management/server/types/
func BenchmarkNetworkMapWireEncode(b *testing.B) {
skipCIBenchmark(b)
for _, scale := range wireBenchScales {
account, validatedPeers := scalableTestAccount(scale.peers, scale.groups)
populateAccountSeqIDs(account)
ctx := context.Background()
resourcePolicies := account.GetResourcePoliciesMap()
routers := account.GetResourceRoutersMap()
groupIDToUserIDs := account.GetActiveGroupUsers()
peerID := "peer-0"
peer := account.Peers[peerID]
networkMap := account.GetPeerNetworkMapFromComponents(ctx, peerID, nbdns.CustomZone{}, nil, validatedPeers, resourcePolicies, routers, nil, groupIDToUserIDs)
components := account.GetPeerNetworkMapComponents(ctx, peerID, nbdns.CustomZone{}, nil, validatedPeers, resourcePolicies, routers, groupIDToUserIDs)
dnsCache := &cache.DNSConfigCache{}
settings := &types.Settings{}
// Pre-encode once so the size metric is identical for every run inside
// the same scale; the b.Loop call only re-runs encode + Marshal.
legacyResp := mgmtgrpc.ToSyncResponse(ctx, nil, nil, nil, peer, nil, nil, networkMap, "netbird.cloud", nil, dnsCache, settings, nil, nil, 0)
legacyBytes, err := goproto.Marshal(legacyResp.NetworkMap)
if err != nil {
b.Fatalf("marshal legacy networkmap: %v", err)
}
envelopeInput := mgmtgrpc.ComponentsEnvelopeInput{
Components: components,
PeerConfig: legacyResp.NetworkMap.PeerConfig,
DNSDomain: "netbird.cloud",
}
envelope := mgmtgrpc.EncodeNetworkMapEnvelope(envelopeInput)
envelopeBytes, err := goproto.Marshal(envelope)
if err != nil {
b.Fatalf("marshal envelope: %v", err)
}
b.Run(fmt.Sprintf("legacy/%s", scale.name), func(b *testing.B) {
b.ReportAllocs()
b.ReportMetric(float64(len(legacyBytes)), "bytes/msg")
b.ResetTimer()
for range b.N {
resp := mgmtgrpc.ToSyncResponse(ctx, nil, nil, nil, peer, nil, nil, networkMap, "netbird.cloud", nil, dnsCache, settings, nil, nil, 0)
if _, err := goproto.Marshal(resp.NetworkMap); err != nil {
b.Fatal(err)
}
}
})
b.Run(fmt.Sprintf("components/%s", scale.name), func(b *testing.B) {
b.ReportAllocs()
b.ReportMetric(float64(len(envelopeBytes)), "bytes/msg")
b.ResetTimer()
for range b.N {
env := mgmtgrpc.EncodeNetworkMapEnvelope(envelopeInput)
if _, err := goproto.Marshal(env); err != nil {
b.Fatal(err)
}
}
})
}
}
// BenchmarkNetworkMapWireSize is a fast snapshot of the wire size by scale
// without a tight encode loop. Run with -bench to see one ns/op + bytes per
// scale (treat the timing as informational; the sample is one Marshal per
// scale, not the full b.N loop).
func BenchmarkNetworkMapWireSize(b *testing.B) {
skipCIBenchmark(b)
for _, scale := range wireBenchScales {
account, validatedPeers := scalableTestAccount(scale.peers, scale.groups)
populateAccountSeqIDs(account)
ctx := context.Background()
resourcePolicies := account.GetResourcePoliciesMap()
routers := account.GetResourceRoutersMap()
groupIDToUserIDs := account.GetActiveGroupUsers()
peerID := "peer-0"
peer := account.Peers[peerID]
networkMap := account.GetPeerNetworkMapFromComponents(ctx, peerID, nbdns.CustomZone{}, nil, validatedPeers, resourcePolicies, routers, nil, groupIDToUserIDs)
components := account.GetPeerNetworkMapComponents(ctx, peerID, nbdns.CustomZone{}, nil, validatedPeers, resourcePolicies, routers, groupIDToUserIDs)
dnsCache := &cache.DNSConfigCache{}
settings := &types.Settings{}
legacyResp := mgmtgrpc.ToSyncResponse(ctx, nil, nil, nil, peer, nil, nil, networkMap, "netbird.cloud", nil, dnsCache, settings, nil, nil, 0)
legacyBytes, _ := goproto.Marshal(legacyResp.NetworkMap)
env := mgmtgrpc.EncodeNetworkMapEnvelope(mgmtgrpc.ComponentsEnvelopeInput{
Components: components,
PeerConfig: legacyResp.NetworkMap.PeerConfig,
DNSDomain: "netbird.cloud",
})
envBytes, _ := goproto.Marshal(env)
b.Run(fmt.Sprintf("size/%s", scale.name), func(b *testing.B) {
b.ReportMetric(float64(len(legacyBytes)), "legacy_bytes")
b.ReportMetric(float64(len(envBytes)), "components_bytes")
ratio := float64(len(envBytes)) / float64(len(legacyBytes))
b.ReportMetric(ratio, "components/legacy")
for range b.N {
}
})
}
}
+7
View File
@@ -79,6 +79,13 @@ type Policy struct {
SourcePostureChecks []string `gorm:"serializer:json"`
}
// HasSeqID reports whether the policy has been persisted long enough to have
// a per-account sequence id allocated. Wire encoders that key off
// AccountSeqID must skip policies that return false here.
func (p *Policy) HasSeqID() bool {
return p != nil && p.AccountSeqID != 0
}
// Copy returns a copy of the policy.
func (p *Policy) Copy() *Policy {
c := &Policy{