mirrors/nebula
1
Fork 0
mirror of https://github.com/slackhq/nebula.git synced 2025-12-05 18:20:48 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add more metrics (#450)

Browse source 
* Add more metrics

This change adds the following counter metrics:

Metrics to track packets dropped at the firewall:

    firewall.dropped.local_ip
    firewall.dropped.remote_ip
    firewall.dropped.no_rule

Metrics to track handshakes attempts that have been initiated and ones
that have timed out (ones that have completed are tracked by the
existing "handshakes" histogram).

    handshake_manager.initiated
    handshake_manager.timed_out

Metrics to track when cached_packets are dropped because we run out of
buffer space, and how many are sent once the handshake completes.

    hostinfo.cached_packets.dropped
    hostinfo.cached_packets.sent

This change also notes how many cached packets we have when we log the
final "Handshake received" message for either stage1 for stage2.

* separate incoming/outgoing metrics

* remove "allowed" firewall metrics

We don't need this on the hotpath, they aren't worh it.

* don't need pointers here
This commit is contained in:
Wade Simmons 2021-04-27 22:23:18 -04:00 • committed by GitHub
parent db23fdf9bc
commit 44cb697552
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 69 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

11
hostmap.go
View file

@ -77,6 +77,11 @@ type cachedPacket struct {
type packetCallback func(t NebulaMessageType, st NebulaMessageSubType, h *HostInfo, p, nb, out []byte)
type cachedPacketMetrics struct {
sent metrics.Counter
dropped metrics.Counter
}
func NewHostMap(l *logrus.Logger, name string, vpnCIDR *net.IPNet, preferredRanges []*net.IPNet) *HostMap {
h := map[uint32]*HostInfo{}
i := map[uint32]*HostInfo{}
@ -435,7 +440,7 @@ func (i *HostInfo) TryPromoteBest(preferredRanges []*net.IPNet, ifce *Interface)
}
}
func (i *HostInfo) cachePacket(l *logrus.Logger, t NebulaMessageType, st NebulaMessageSubType, packet []byte, f packetCallback) {
func (i *HostInfo) cachePacket(l *logrus.Logger, t NebulaMessageType, st NebulaMessageSubType, packet []byte, f packetCallback, m *cachedPacketMetrics) {
//TODO: return the error so we can log with more context
if len(i.packetStore) < 100 {
tempPacket := make([]byte, len(packet))
@ -450,6 +455,7 @@ func (i *HostInfo) cachePacket(l *logrus.Logger, t NebulaMessageType, st NebulaM
}
} else if l.Level >= logrus.DebugLevel {
m.dropped.Inc(1)
i.logger(l).
WithField("length", len(i.packetStore)).
WithField("stored", false).
@ -458,7 +464,7 @@ func (i *HostInfo) cachePacket(l *logrus.Logger, t NebulaMessageType, st NebulaM
}
// handshakeComplete will set the connection as ready to communicate, as well as flush any stored packets
func (i *HostInfo) handshakeComplete(l *logrus.Logger) {
func (i *HostInfo) handshakeComplete(l *logrus.Logger, m *cachedPacketMetrics) {
//TODO: I'm not certain the distinction between handshake complete and ConnectionState being ready matters because:
//TODO: HandshakeComplete means send stored packets and ConnectionState.ready means we are ready to send
//TODO: if the transition from HandhsakeComplete to ConnectionState.ready happens all within this function they are identical
@ -479,6 +485,7 @@ func (i *HostInfo) handshakeComplete(l *logrus.Logger) {
for _, cp := range i.packetStore {
cp.callback(cp.messageType, cp.messageSubType, i, cp.packet, nb, out)
}
m.sent.Inc(int64(len(i.packetStore)))
}
i.remotes.ResetBlockedRemotes()