mirror of
https://github.com/netbirdio/netbird.git
synced 2026-08-10 20:15:39 -04:00
[client] disambiguate the connection_type metric tag (#7043)
## Describe your changes `recordConnectionMetrics` mapped only `conntype.Relay` to `relay` and let a `default` branch record everything else as `ice`. That silently included `ICETurn` — an ICE connection through a TURN server, which [`conn.isRelayed`](https://github.com/netbirdio/netbird/blob/main/client/internal/peer/conn.go#L788-L795) itself counts as relayed — and `None`, the transient state set when the relay drops ([conn.go:632](https://github.com/netbirdio/netbird/blob/main/client/internal/peer/conn.go#L632)) or the peer state is reset ([conn.go:757](https://github.com/netbirdio/netbird/blob/main/client/internal/peer/conn.go#L757)). Both were reported as direct peer-to-peer, so the `ice` share overstated direct connections on every platform. The mapping now lists every priority explicitly and emits `ice_p2p`, `ice_turn`, `relay` or `unknown`. The new values deliberately do not reuse `ice` to avoid ambuguity. ## Issue ticket number and link No public issue. Found while reviewing the first production sample of client metrics: 38% of iOS connection events were tagged `ice` on a platform that forces relay by default, which traced back to the `default` branch at [client/internal/peer/conn.go#L963-L968](https://github.com/netbirdio/netbird/blob/main/client/internal/peer/conn.go#L963-L968). ## Stack <!-- branch-stack --> ### Checklist - [x] Is it a bug fix - [ ] Is a typo/documentation fix - [ ] Is a feature enhancement - [ ] It is a refactor - [x] Created tests that fail without the change (if possible) > By submitting this pull request, you confirm that you have read and agree to the terms of the [Contributor License Agreement](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT.md). ## Documentation Select exactly one: - [] I added/updated documentation for this change - [x] Documentation is **not needed** for this change (explain why) Internal metrics documentation only, in `client/internal/metrics/infra/README.md`: the four `connection_type` values with their derivation, and a note that pre-fix `ice` samples are not comparable with `ice_p2p`. No public API, CLI or configuration change, so no netbirdio/docs PR. ### Docs PR URL (required if "docs added" is checked) Paste the PR link from https://github.com/netbirdio/docs here: N/A <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit ## Summary by CodeRabbit * **New Features** * Connection metrics now distinguish direct peer-to-peer, TURN-assisted, relay, and unknown connection types. * Metrics include clearer connection and peer identification details. * **Documentation** * Updated connection timing metric values, traffic semantics, priority behavior, and historical data guidance. * **Bug Fixes** * Unset or unrecognized connection priorities are no longer incorrectly classified as peer-to-peer. * Unknown-transport metrics are skipped to prevent misleading connection data. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
This commit is contained in:
@@ -4,11 +4,17 @@ package metrics
|
||||
type ConnectionType string
|
||||
|
||||
const (
|
||||
// ConnectionTypeICE represents a direct peer-to-peer connection using ICE
|
||||
ConnectionTypeICE ConnectionType = "ice"
|
||||
// ConnectionTypeICEP2P represents a direct peer-to-peer connection using ICE
|
||||
ConnectionTypeICEP2P ConnectionType = "ice_p2p"
|
||||
|
||||
// ConnectionTypeICETurn represents an ICE connection through a TURN server
|
||||
ConnectionTypeICETurn ConnectionType = "ice_turn"
|
||||
|
||||
// ConnectionTypeRelay represents a relayed connection
|
||||
ConnectionTypeRelay ConnectionType = "relay"
|
||||
|
||||
// ConnectionTypeUnknown represents a connection with no active transport. It is not pushed.
|
||||
ConnectionTypeUnknown ConnectionType = "unknown"
|
||||
)
|
||||
|
||||
// String returns the string representation of the connection type
|
||||
|
||||
@@ -28,7 +28,7 @@ func TestInfluxDBMetrics_RecordAndExport(t *testing.T) {
|
||||
WgHandshakeSuccess: time.Now().Add(-1 * time.Second),
|
||||
}
|
||||
|
||||
m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICE, false, ts)
|
||||
m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICEP2P, false, ts)
|
||||
|
||||
var buf bytes.Buffer
|
||||
err := m.Export(&buf)
|
||||
@@ -60,7 +60,7 @@ func TestInfluxDBMetrics_ExportDeterministicFieldOrder(t *testing.T) {
|
||||
|
||||
// Record multiple times and verify consistent field order
|
||||
for i := 0; i < 10; i++ {
|
||||
m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICE, false, ts)
|
||||
m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICEP2P, false, ts)
|
||||
}
|
||||
|
||||
var buf bytes.Buffer
|
||||
|
||||
@@ -56,14 +56,33 @@ Measurement: `netbird_peer_connection`
|
||||
|
||||
Tags:
|
||||
- `deployment_type`: "cloud" | "selfhosted" | "unknown"
|
||||
- `connection_type`: "ice" | "relay"
|
||||
- `connection_type`: "ice_p2p" | "ice_turn" | "relay" (see below)
|
||||
- `attempt_type`: "initial" | "reconnection"
|
||||
- `version`: NetBird version string
|
||||
- `os`: Operating system (linux, darwin, windows, android, ios, etc.)
|
||||
- `arch`: CPU architecture (amd64, arm64, etc.)
|
||||
- `peer_id`: anonymised peer identifier (truncated SHA-256 of the WireGuard public key)
|
||||
- `connection_pair_id`: deterministic identifier for the peer pair, identical on both sides
|
||||
|
||||
**Note:** `SignalingReceived` is set when the first offer or answer arrives from the remote peer (in both initial and reconnection paths). It excludes the potentially unbounded wait for the remote peer to come online.
|
||||
|
||||
#### `connection_type` values
|
||||
|
||||
Derived from the connection priority (`conntype.ConnPriority`) by `metricsConnType` in `client/internal/peer/conn.go`:
|
||||
|
||||
| Value | Priority | Traffic is |
|
||||
|-------|----------|------------|
|
||||
| `ice_p2p` | `ICEP2P` | direct peer-to-peer |
|
||||
| `ice_turn` | `ICETurn` | relayed, through a TURN server |
|
||||
| `relay` | `Relay` | relayed, through a NetBird relay |
|
||||
| `unknown` | `None` or unrecognised | no active transport — **the sample is not pushed** |
|
||||
|
||||
**Direct traffic is `ice_p2p` only.** `ice_turn` is relayed despite being negotiated by ICE, matching `Conn.isRelayed`.
|
||||
|
||||
`None` means no transport is active: not established yet, or reset after a relay drop or a peer-state reset. Such a sample cannot be attributed to a transport, so `recordConnectionMetrics` drops it instead of pushing it — `unknown` therefore never appears in the bucket. Connection counts are counts of connections whose transport was known at sampling time.
|
||||
|
||||
**Samples recorded before 0.77 used a single `ice` value** which covered `ICEP2P`, `ICETurn` *and* `None`, so historical `ice` samples overstate direct connections by an unknown amount and must not be compared with `ice_p2p`.
|
||||
|
||||
### Sync Duration
|
||||
|
||||
Measurement: `netbird_sync`
|
||||
|
||||
@@ -961,12 +961,9 @@ func (conn *Conn) recordConnectionMetrics() {
|
||||
priority := conn.currentConnPriority
|
||||
conn.mu.Unlock()
|
||||
|
||||
var connType metrics.ConnectionType
|
||||
switch priority {
|
||||
case conntype.Relay:
|
||||
connType = metrics.ConnectionTypeRelay
|
||||
default:
|
||||
connType = metrics.ConnectionTypeICE
|
||||
connType := metricsConnType(priority)
|
||||
if connType == metrics.ConnectionTypeUnknown {
|
||||
return
|
||||
}
|
||||
|
||||
// Record metrics with timestamps - duration calculation happens in metrics package
|
||||
@@ -1067,3 +1064,16 @@ func boolToConnStatus(connected bool) guard.ConnStatus {
|
||||
}
|
||||
return guard.ConnStatusDisconnected
|
||||
}
|
||||
|
||||
func metricsConnType(priority conntype.ConnPriority) metrics.ConnectionType {
|
||||
switch priority {
|
||||
case conntype.Relay:
|
||||
return metrics.ConnectionTypeRelay
|
||||
case conntype.ICETurn:
|
||||
return metrics.ConnectionTypeICETurn
|
||||
case conntype.ICEP2P:
|
||||
return metrics.ConnectionTypeICEP2P
|
||||
default:
|
||||
return metrics.ConnectionTypeUnknown
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,6 +11,8 @@ import (
|
||||
"github.com/stretchr/testify/assert"
|
||||
|
||||
"github.com/netbirdio/netbird/client/iface"
|
||||
"github.com/netbirdio/netbird/client/internal/metrics"
|
||||
"github.com/netbirdio/netbird/client/internal/peer/conntype"
|
||||
"github.com/netbirdio/netbird/client/internal/peer/dispatcher"
|
||||
"github.com/netbirdio/netbird/client/internal/peer/guard"
|
||||
"github.com/netbirdio/netbird/client/internal/peer/ice"
|
||||
@@ -386,3 +388,33 @@ func TestConn_onWGDisconnected_NoEscalationWithoutRosenpass(t *testing.T) {
|
||||
}
|
||||
assert.Empty(t, disconnected, "escalation must be limited to rosenpass connections")
|
||||
}
|
||||
|
||||
func TestMetricsConnType(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
priority conntype.ConnPriority
|
||||
expected metrics.ConnectionType
|
||||
}{
|
||||
{"relay", conntype.Relay, metrics.ConnectionTypeRelay},
|
||||
{"ice over turn is relayed, not p2p", conntype.ICETurn, metrics.ConnectionTypeICETurn},
|
||||
{"direct p2p", conntype.ICEP2P, metrics.ConnectionTypeICEP2P},
|
||||
{"unset priority is unknown, not p2p", conntype.None, metrics.ConnectionTypeUnknown},
|
||||
{"unrecognised priority is unknown", conntype.ConnPriority(99), metrics.ConnectionTypeUnknown},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
assert.Equal(t, tc.expected, metricsConnType(tc.priority))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestMetricsConnType_RelayedMatchesIsRelayed(t *testing.T) {
|
||||
for _, priority := range []conntype.ConnPriority{conntype.None, conntype.Relay, conntype.ICETurn, conntype.ICEP2P} {
|
||||
conn := &Conn{currentConnPriority: priority}
|
||||
tag := metricsConnType(priority)
|
||||
relayedTag := tag == metrics.ConnectionTypeRelay || tag == metrics.ConnectionTypeICETurn
|
||||
assert.Equal(t, conn.isRelayed(), relayedTag,
|
||||
"priority %s: isRelayed and the %q metric tag must agree", priority, tag)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user