netbird/management/server/updatechannel.go

178 lines
4.4 KiB
Go
Raw Normal View History

package server
import (
"context"
"sync"
"time"
log "github.com/sirupsen/logrus"
"github.com/netbirdio/netbird/management/proto"
"github.com/netbirdio/netbird/management/server/telemetry"
)
const channelBufferSize = 100
type UpdateMessage struct {
[management] Optimize network map updates (#2718) * Skip peer update on unchanged network map (#2236) * Enhance network updates by skipping unchanged messages Optimizes the network update process by skipping updates where no changes in the peer update message received. * Add unit tests * add locks * Improve concurrency and update peer message handling * Refactor account manager network update tests * fix test * Fix inverted network map update condition * Add default group and policy to test data * Run peer updates in a separate goroutine * Refactor * Refactor lock * Fix peers update by including NetworkMap and posture Checks * go mod tidy * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * [management] Skip account peers update if no changes affect peers (#2310) * Remove incrementing network serial and updating peers after group deletion * Update account peer if posture check is linked to policy * Remove account peers update on saving setup key * Refactor group link checking into re-usable functions * Add HasPeers function to group * Refactor group management * Optimize group change effects on account peers * Update account peers if ns group has peers * Refactor group changes * Optimize account peers update in DNS settings * Optimize update of account peers on jwt groups sync * Refactor peer account updates for efficiency * Optimize peer update on user deletion and changes * Remove condition check for network serial update * Optimize account peers updates on route changes * Remove UpdatePeerSSHKey method * Remove unused isPolicyRuleGroupsEmpty * Add tests for peer update behavior on posture check changes * Add tests for peer update behavior on policy changes * Add tests for peer update behavior on group changes * Add tests for peer update behavior on dns settings changes * Refactor * Add tests for peer update behavior on name server changes * Add tests for peer update behavior on user changes * Add tests for peer update behavior on route changes * fix tests * Add tests for peer update behavior on setup key changes * Add tests for peer update behavior on peers changes * fix merge * Fix tests * go mod tidy * Add NameServer and Route comparators * Update network map diff logic with custom comparators * Add tests * Refactor duplicate diff handling logic * fix linter * fix tests * Refactor policy group handling and update logic. Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Update route check by checking if group has peers Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Refactor posture check policy linking logic Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Simplify peer update condition in DNS management Refactor the condition for updating account peers to remove redundant checks Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add policy tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add posture checks tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix user and setup key tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix account and route tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix typo Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix nameserver tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix routes tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix group tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * upgrade diff package Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix nameserver tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * use generic differ for netip.Addr and netip.Prefix Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * go mod tidy Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add peer tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix management suite tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix postgres tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * enable diff nil structs comparison Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip the update only last sent the serial is larger Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * refactor peer and user Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip spell check for groupD Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Refactor group, ns group, policy and posture checks Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip spell check for GroupD Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * update account policy check before verifying policy status Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * add tests missing tests for dns setting groups Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add tests for posture checks changes Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add ns group and policy tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add route and group tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * increase Linux test timeout to 10 minutes Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Run diff for client posture checks only Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add panic recovery and detailed logging in peer update comparison Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Fix tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> --------- Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> --------- Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> Co-authored-by: Maycon Santos <mlsmaycon@gmail.com>
2024-10-23 12:05:02 +02:00
Update *proto.SyncResponse
NetworkMap *NetworkMap
}
type PeersUpdateManager struct {
// peerChannels is an update channel indexed by Peer.ID
peerChannels map[string]chan *UpdateMessage
// channelsMux keeps the mutex to access peerChannels
[management] Optimize network map updates (#2718) * Skip peer update on unchanged network map (#2236) * Enhance network updates by skipping unchanged messages Optimizes the network update process by skipping updates where no changes in the peer update message received. * Add unit tests * add locks * Improve concurrency and update peer message handling * Refactor account manager network update tests * fix test * Fix inverted network map update condition * Add default group and policy to test data * Run peer updates in a separate goroutine * Refactor * Refactor lock * Fix peers update by including NetworkMap and posture Checks * go mod tidy * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * [management] Skip account peers update if no changes affect peers (#2310) * Remove incrementing network serial and updating peers after group deletion * Update account peer if posture check is linked to policy * Remove account peers update on saving setup key * Refactor group link checking into re-usable functions * Add HasPeers function to group * Refactor group management * Optimize group change effects on account peers * Update account peers if ns group has peers * Refactor group changes * Optimize account peers update in DNS settings * Optimize update of account peers on jwt groups sync * Refactor peer account updates for efficiency * Optimize peer update on user deletion and changes * Remove condition check for network serial update * Optimize account peers updates on route changes * Remove UpdatePeerSSHKey method * Remove unused isPolicyRuleGroupsEmpty * Add tests for peer update behavior on posture check changes * Add tests for peer update behavior on policy changes * Add tests for peer update behavior on group changes * Add tests for peer update behavior on dns settings changes * Refactor * Add tests for peer update behavior on name server changes * Add tests for peer update behavior on user changes * Add tests for peer update behavior on route changes * fix tests * Add tests for peer update behavior on setup key changes * Add tests for peer update behavior on peers changes * fix merge * Fix tests * go mod tidy * Add NameServer and Route comparators * Update network map diff logic with custom comparators * Add tests * Refactor duplicate diff handling logic * fix linter * fix tests * Refactor policy group handling and update logic. Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Update route check by checking if group has peers Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Refactor posture check policy linking logic Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Simplify peer update condition in DNS management Refactor the condition for updating account peers to remove redundant checks Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add policy tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add posture checks tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix user and setup key tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix account and route tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix typo Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix nameserver tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix routes tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix group tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * upgrade diff package Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix nameserver tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * use generic differ for netip.Addr and netip.Prefix Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * go mod tidy Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add peer tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix management suite tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix postgres tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * enable diff nil structs comparison Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip the update only last sent the serial is larger Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * refactor peer and user Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip spell check for groupD Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Refactor group, ns group, policy and posture checks Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip spell check for GroupD Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * update account policy check before verifying policy status Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * add tests missing tests for dns setting groups Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add tests for posture checks changes Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add ns group and policy tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add route and group tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * increase Linux test timeout to 10 minutes Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Run diff for client posture checks only Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add panic recovery and detailed logging in peer update comparison Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Fix tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> --------- Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> --------- Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> Co-authored-by: Maycon Santos <mlsmaycon@gmail.com>
2024-10-23 12:05:02 +02:00
channelsMux *sync.RWMutex
// metrics provides method to collect application metrics
metrics telemetry.AppMetrics
}
// NewPeersUpdateManager returns a new instance of PeersUpdateManager
func NewPeersUpdateManager(metrics telemetry.AppMetrics) *PeersUpdateManager {
return &PeersUpdateManager{
peerChannels: make(map[string]chan *UpdateMessage),
channelsMux: &sync.RWMutex{},
metrics: metrics,
}
}
// SendUpdate sends update message to the peer's channel
func (p *PeersUpdateManager) SendUpdate(ctx context.Context, peerID string, update *UpdateMessage) {
start := time.Now()
var found, dropped bool
p.channelsMux.Lock()
[management] Optimize network map updates (#2718) * Skip peer update on unchanged network map (#2236) * Enhance network updates by skipping unchanged messages Optimizes the network update process by skipping updates where no changes in the peer update message received. * Add unit tests * add locks * Improve concurrency and update peer message handling * Refactor account manager network update tests * fix test * Fix inverted network map update condition * Add default group and policy to test data * Run peer updates in a separate goroutine * Refactor * Refactor lock * Fix peers update by including NetworkMap and posture Checks * go mod tidy * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * [management] Skip account peers update if no changes affect peers (#2310) * Remove incrementing network serial and updating peers after group deletion * Update account peer if posture check is linked to policy * Remove account peers update on saving setup key * Refactor group link checking into re-usable functions * Add HasPeers function to group * Refactor group management * Optimize group change effects on account peers * Update account peers if ns group has peers * Refactor group changes * Optimize account peers update in DNS settings * Optimize update of account peers on jwt groups sync * Refactor peer account updates for efficiency * Optimize peer update on user deletion and changes * Remove condition check for network serial update * Optimize account peers updates on route changes * Remove UpdatePeerSSHKey method * Remove unused isPolicyRuleGroupsEmpty * Add tests for peer update behavior on posture check changes * Add tests for peer update behavior on policy changes * Add tests for peer update behavior on group changes * Add tests for peer update behavior on dns settings changes * Refactor * Add tests for peer update behavior on name server changes * Add tests for peer update behavior on user changes * Add tests for peer update behavior on route changes * fix tests * Add tests for peer update behavior on setup key changes * Add tests for peer update behavior on peers changes * fix merge * Fix tests * go mod tidy * Add NameServer and Route comparators * Update network map diff logic with custom comparators * Add tests * Refactor duplicate diff handling logic * fix linter * fix tests * Refactor policy group handling and update logic. Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Update route check by checking if group has peers Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Refactor posture check policy linking logic Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Simplify peer update condition in DNS management Refactor the condition for updating account peers to remove redundant checks Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add policy tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add posture checks tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix user and setup key tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix account and route tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix typo Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix nameserver tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix routes tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix group tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * upgrade diff package Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix nameserver tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * use generic differ for netip.Addr and netip.Prefix Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * go mod tidy Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add peer tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix merge Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix management suite tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * fix postgres tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * enable diff nil structs comparison Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip the update only last sent the serial is larger Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * refactor peer and user Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip spell check for groupD Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Refactor group, ns group, policy and posture checks Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * skip spell check for GroupD Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * update account policy check before verifying policy status Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * Update management/server/route_test.go Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> * add tests missing tests for dns setting groups Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add tests for posture checks changes Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add ns group and policy tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add route and group tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * increase Linux test timeout to 10 minutes Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Run diff for client posture checks only Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * add panic recovery and detailed logging in peer update comparison Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> * Fix tests Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> --------- Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> Co-authored-by: Maycon Santos <mlsmaycon@gmail.com> --------- Signed-off-by: bcmmbaga <bethuelmbaga12@gmail.com> Co-authored-by: Maycon Santos <mlsmaycon@gmail.com>
2024-10-23 12:05:02 +02:00
defer func() {
p.channelsMux.Unlock()
if p.metrics != nil {
p.metrics.UpdateChannelMetrics().CountSendUpdateDuration(time.Since(start), found, dropped)
}
}()
if channel, ok := p.peerChannels[peerID]; ok {
found = true
select {
case channel <- update:
log.WithContext(ctx).Debugf("update was sent to channel for peer %s", peerID)
default:
dropped = true
2024-09-06 16:28:19 +02:00
log.WithContext(ctx).Warnf("channel for peer %s is %d full or closed", peerID, len(channel))
}
} else {
log.WithContext(ctx).Debugf("peer %s has no channel", peerID)
}
}
// CreateChannel creates a go channel for a given peer used to deliver updates relevant to the peer.
func (p *PeersUpdateManager) CreateChannel(ctx context.Context, peerID string) chan *UpdateMessage {
start := time.Now()
closed := false
p.channelsMux.Lock()
defer func() {
p.channelsMux.Unlock()
if p.metrics != nil {
p.metrics.UpdateChannelMetrics().CountCreateChannelDuration(time.Since(start), closed)
}
}()
if channel, ok := p.peerChannels[peerID]; ok {
closed = true
delete(p.peerChannels, peerID)
close(channel)
}
// mbragin: todo shouldn't it be more? or configurable?
channel := make(chan *UpdateMessage, channelBufferSize)
p.peerChannels[peerID] = channel
log.WithContext(ctx).Debugf("opened updates channel for a peer %s", peerID)
return channel
}
func (p *PeersUpdateManager) closeChannel(ctx context.Context, peerID string) {
if channel, ok := p.peerChannels[peerID]; ok {
delete(p.peerChannels, peerID)
close(channel)
log.WithContext(ctx).Debugf("closed updates channel of a peer %s", peerID)
return
}
log.WithContext(ctx).Debugf("closing updates channel: peer %s has no channel", peerID)
}
// CloseChannels closes updates channel for each given peer
func (p *PeersUpdateManager) CloseChannels(ctx context.Context, peerIDs []string) {
start := time.Now()
p.channelsMux.Lock()
defer func() {
p.channelsMux.Unlock()
if p.metrics != nil {
p.metrics.UpdateChannelMetrics().CountCloseChannelsDuration(time.Since(start), len(peerIDs))
}
}()
for _, id := range peerIDs {
p.closeChannel(ctx, id)
}
}
// CloseChannel closes updates channel of a given peer
func (p *PeersUpdateManager) CloseChannel(ctx context.Context, peerID string) {
start := time.Now()
p.channelsMux.Lock()
defer func() {
p.channelsMux.Unlock()
if p.metrics != nil {
p.metrics.UpdateChannelMetrics().CountCloseChannelDuration(time.Since(start))
}
}()
p.closeChannel(ctx, peerID)
}
// GetAllConnectedPeers returns a copy of the connected peers map
func (p *PeersUpdateManager) GetAllConnectedPeers() map[string]struct{} {
start := time.Now()
p.channelsMux.Lock()
m := make(map[string]struct{})
defer func() {
p.channelsMux.Unlock()
if p.metrics != nil {
p.metrics.UpdateChannelMetrics().CountGetAllConnectedPeersDuration(time.Since(start), len(m))
}
}()
for ID := range p.peerChannels {
m[ID] = struct{}{}
}
return m
}
// HasChannel returns true if peers has channel in update manager, otherwise false
func (p *PeersUpdateManager) HasChannel(peerID string) bool {
start := time.Now()
p.channelsMux.Lock()
defer func() {
p.channelsMux.Unlock()
if p.metrics != nil {
p.metrics.UpdateChannelMetrics().CountHasChannelDuration(time.Since(start))
}
}()
_, ok := p.peerChannels[peerID]
return ok
}