feature: site_to_site holds any number of named site-to-site connections, which /site-to-site lists, adds, changes and removes.

debian-package/src/usr/lib/vpn-router/metrics

@@ -8,9 +8,10 @@ Every SAMPLE_SECONDS, on the minute, a sample is taken with psutil: the CPU util
 previous sample, the memory used and in total, the free and the total space of /, the bytes
 received and sent per second on the external and the internal interface, and the load averages;
 and the VPN clients of each enabled VPN system (vpnrouter_status): road-warrior (p2s) and
-OpenVPN clients, WireGuard peers with a recent handshake, and the site-to-site tunnel, 1 while it
-is up. The interfaces and the enabled systems are those vpn-router-setup resolved, read from
-/run/vpn-router/web.json.
+OpenVPN clients and WireGuard peers with a recent handshake; and of each site-to-site connection
+that is set up, whether it is up, the bytes and packets per second through its child SAs since
+the previous sample, and how long its IKE SA has been up. The interfaces, the enabled systems and
+the connections are those vpn-router-setup resolved, read from /run/vpn-router/web.json.
 
 The sample is written to the detail tables of vpnrouter_metrics. When the clock has passed into
 a new hour, day, month or year, the complete periods are summarized, and once a day, after the
@@ -105,9 +106,6 @@ def clients(state):
         counts['openvpn'] = vpnrouter_status.openvpn_clients()
     if state.get('wireguard'):
         counts['wireguard'] = vpnrouter_status.wireguard_connected()
-    if state.get('site_to_site'):
-        count = vpnrouter_status.established('remote-site')
-        counts['site_to_site'] = None if count is None else int(count > 0)
     return counts
 
 
@@ -121,6 +119,8 @@ def sample(previous):
     memory = psutil.virtual_memory()
     disk = psutil.disk_usage(MOUNTPOINT)
     load1, load5, load15 = os.getloadavg()
+    connections = state.get('site_to_site')
+    tunnels = vpnrouter_status.site_to_site_tunnels(connections) if isinstance(connections, list) and connections else {}
     now = time.time()
     current = {
         'time': now,
@@ -138,13 +138,26 @@ def sample(previous):
         'counters': {name: (counters[name].bytes_recv, counters[name].bytes_sent) for name in names if name in counters},
         'clients': clients(state),
         'rates': {},
+        'tunnels': tunnels or {},
+        'site_to_site': {},
     }
-    if previous is not None:
-        elapsed = current['monotonic'] - previous['monotonic']
+    elapsed = current['monotonic'] - previous['monotonic'] if previous is not None else 0
+    if elapsed > 0:
         for name, (received, sent) in current['counters'].items():
-            if name in previous['counters'] and elapsed > 0:
+            if name in previous['counters']:
                 before_received, before_sent = previous['counters'][name]
                 current['rates'][name] = (max(received - before_received, 0) / elapsed, max(sent - before_sent, 0) / elapsed)
+    # A connection's rates need its counters of the previous sample; a counter that went down was rekeyed and counts from zero.
+    for name, tunnel in current['tunnels'].items():
+        before = previous['tunnels'].get(name) if elapsed > 0 else None
+        values = {'up': tunnel['up'], 'uptime': tunnel['uptime']}
+        for value, counter in (('rx', 'bytes_in'), ('tx', 'bytes_out'), ('packets_rx', 'packets_in'), ('packets_tx', 'packets_out')):
+            if before is None:
+                values[value] = None
+            else:
+                count = tunnel[counter]
+                values[value] = (count - before[counter] if count >= before[counter] else count) / elapsed
+        current['site_to_site'][name] = values
     return current
 
 
@@ -162,7 +175,7 @@ def store(cfg, current, done):
     """
     now = periods(datetime.datetime.now(datetime.timezone.utc))
     with vpnrouter_metrics.database(cfg) as connection:
-        vpnrouter_metrics.write(connection, current['system'], current['rates'], current['clients'])
+        vpnrouter_metrics.write(connection, current['system'], current['rates'], current['clients'], current['site_to_site'])
         for level, _, _ in vpnrouter_metrics.LEVELS:
             if done.get(level) != now[level]:
                 vpnrouter_metrics.summarize(connection, level)
@@ -200,6 +213,17 @@ def otlp_request(current, started):
         gauge('system.cpu.load_average.5m', '{thread}', [(system['load5'], {})]),
         gauge('system.cpu.load_average.15m', '{thread}', [(system['load15'], {})]),
         gauge('vpn_router.clients', '{client}', [(count, {'kind': kind}) for kind, count in current['clients'].items()]),
+        gauge('vpn_router.site_to_site.up', '1', [(values['up'], {'connection': name})
+                                                 for name, values in current['site_to_site'].items()]),
+        gauge('vpn_router.site_to_site.uptime', 's', [(values['uptime'], {'connection': name})
+                                                     for name, values in current['site_to_site'].items()]),
+        gauge('vpn_router.site_to_site.io', 'By/s', [(values[value], {'connection': name, 'direction': direction})
+                                                    for name, values in current['site_to_site'].items()
+                                                    for value, direction in (('rx', 'receive'), ('tx', 'transmit'))]),
+        gauge('vpn_router.site_to_site.packets', '{packet}/s',
+              [(values[value], {'connection': name, 'direction': direction})
+               for name, values in current['site_to_site'].items()
+               for value, direction in (('packets_rx', 'receive'), ('packets_tx', 'transmit'))]),
         {'name': 'system.network.io', 'unit': 'By', 'sum': {
             'aggregationTemporality': 2, 'isMonotonic': True, 'dataPoints': [
                 {'startTimeUnixNano': start, 'timeUnixNano': stamp, 'asInt': str(value),
@@ -295,12 +319,30 @@ class Sample:
             network.add_metric([name, 'receive'], received)
             network.add_metric([name, 'transmit'], sent)
         yield network
-        vpn = GaugeMetricFamily('vpn_router_clients', 'Connected VPN clients; site_to_site is 1 while the tunnel is up',
-                                labels=['kind'])
+        vpn = GaugeMetricFamily('vpn_router_clients', 'Connected VPN clients', labels=['kind'])
         for kind, count in self.current['clients'].items():
             if count is not None:
                 vpn.add_metric([kind], count)
         yield vpn
+        tunnels = self.current['site_to_site']
+        up = GaugeMetricFamily('vpn_router_site_to_site_up', 'Whether the site-to-site connection is established, 1 or 0',
+                               labels=['connection'])
+        uptime = GaugeMetricFamily('vpn_router_site_to_site_uptime_seconds', 'Seconds the IKE SA of the site-to-site connection has been up',
+                                   labels=['connection'])
+        io = GaugeMetricFamily('vpn_router_site_to_site_io_bytes_per_second',
+                               'Bytes per second received and sent through the site-to-site connection', labels=['connection', 'direction'])
+        packets = GaugeMetricFamily('vpn_router_site_to_site_packets_per_second',
+                                    'Packets per second received and sent through the site-to-site connection',
+                                    labels=['connection', 'direction'])
+        for name, values in tunnels.items():
+            up.add_metric([name], values['up'])
+            if values['uptime'] is not None:
+                uptime.add_metric([name], values['uptime'])
+            for family, received, sent in ((io, 'rx', 'tx'), (packets, 'packets_rx', 'packets_tx')):
+                for value, direction in ((received, 'receive'), (sent, 'transmit')):
+                    if values[value] is not None:
+                        family.add_metric([name, direction], values[value])
+        yield from (up, uptime, io, packets)
 
 
 def authorized(header, account):