feat: unified fleet telemetry — canonical format, GPS/IP geo, WAN health dashboard

- Rewrite telemetry-synology.sh: canonical GL format (modem_0001/wan keys),
  self-contained metrics (no aiwanbal), Eyeride GPS with IP geo fallback
- Add /api/fleet-telemetry to hub: joins tunnel status with fleet Postgres
- Update dashboard.html: per-device WAN health bars, GPS, signal strength
- Fix hub/ingest.sh normalisation: remap old wan1/wan2 → modem_0001/wan
- Bump SPK version: 0.1-0001 → 0.5.0-0001 for GL parity

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-23 01:47:02 +00:00
parent d86a7e49b5
commit db04341f7c
6 changed files with 596 additions and 220 deletions
+107 -10
View File
@@ -23,18 +23,36 @@ body { font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
.stat-card .lbl { font-size: 10px; color: var(--dim); text-transform: uppercase; margin-top: 2px; } .stat-card .lbl { font-size: 10px; color: var(--dim); text-transform: uppercase; margin-top: 2px; }
.stat-card .num.online { color: var(--green); } .stat-card .num.online { color: var(--green); }
.stat-card .num.offline { color: var(--red); } .stat-card .num.offline { color: var(--red); }
.grid { display: grid; grid-template-columns: repeat(auto-fill, minmax(400px, 1fr)); gap: 16px; } .grid { display: grid; grid-template-columns: repeat(auto-fill, minmax(420px, 1fr)); gap: 16px; }
.card { background: var(--card); border: 1px solid var(--border); border-radius: 8px; padding: 16px; } .card { background: var(--card); border: 1px solid var(--border); border-radius: 8px; padding: 16px; }
.card h2 { font-size: 16px; margin-bottom: 12px; display: flex; justify-content: space-between; align-items: center; } .card h2 { font-size: 16px; margin-bottom: 8px; display: flex; justify-content: space-between; align-items: center; }
.badge { font-size: 11px; padding: 2px 8px; border-radius: 12px; font-weight: 600; } .badge { font-size: 11px; padding: 2px 8px; border-radius: 12px; font-weight: 600; }
.badge-gl { background: rgba(88,166,255,0.15); color: var(--blue); } .badge-gl { background: rgba(88,166,255,0.15); color: var(--blue); }
.badge-synology { background: rgba(210,153,34,0.15); color: var(--amber); } .badge-synology { background: rgba(210,153,34,0.15); color: var(--amber); }
.badge-ver { background: rgba(139,148,158,0.15); color: var(--dim); font-size: 10px; }
.dot { display: inline-block; width: 8px; height: 8px; border-radius: 50%; margin-right: 4px; } .dot { display: inline-block; width: 8px; height: 8px; border-radius: 50%; margin-right: 4px; }
.dot-up { background: var(--green); } .dot-up { background: var(--green); }
.dot-down { background: var(--red); } .dot-down { background: var(--red); }
.row { display: flex; justify-content: space-between; padding: 5px 0; font-size: 13px; border-bottom: 1px solid rgba(255,255,255,0.04); } .row { display: flex; justify-content: space-between; padding: 4px 0; font-size: 13px; border-bottom: 1px solid rgba(255,255,255,0.04); }
.row .label { color: var(--dim); } .row .label { color: var(--dim); }
.row .val { font-family: monospace; font-size: 12px; } .row .val { font-family: monospace; font-size: 12px; }
.wan-section { margin-top: 8px; padding-top: 8px; border-top: 1px solid var(--border); }
.wan-section .title { font-size: 11px; color: var(--dim); text-transform: uppercase; letter-spacing: 1px; margin-bottom: 6px; }
.wan-bar { display: flex; align-items: center; gap: 8px; margin-bottom: 4px; font-size: 12px; }
.wan-bar .member { font-family: monospace; min-width: 90px; font-size: 11px; }
.wan-bar .score { font-weight: 700; min-width: 32px; text-align: right; }
.wan-bar .score.good { color: var(--green); }
.wan-bar .score.warn { color: var(--amber); }
.wan-bar .score.bad { color: var(--red); }
.wan-bar .metric { color: var(--dim); font-size: 11px; }
.wan-bar .signal { font-size: 10px; }
.wan-bar .signal.good { color: var(--green); }
.wan-bar .signal.warn { color: var(--amber); }
.wan-bar .signal.bad { color: var(--red); }
.active-dot { display: inline-block; width: 6px; height: 6px; border-radius: 50%; background: var(--green); margin-right: 4px; flex-shrink: 0; }
.gps-line { font-size: 11px; color: var(--dim); margin-top: 4px; }
.gps-line a { color: var(--blue); text-decoration: none; }
.gps-line a:hover { text-decoration: underline; }
.access { margin-top: 12px; padding-top: 12px; border-top: 1px solid var(--border); } .access { margin-top: 12px; padding-top: 12px; border-top: 1px solid var(--border); }
.access .title { font-size: 11px; color: var(--dim); text-transform: uppercase; letter-spacing: 1px; margin-bottom: 8px; } .access .title { font-size: 11px; color: var(--dim); text-transform: uppercase; letter-spacing: 1px; margin-bottom: 8px; }
.cmd { background: #0d1117; padding: 6px 10px; border-radius: 4px; font-family: monospace; .cmd { background: #0d1117; padding: 6px 10px; border-radius: 4px; font-family: monospace;
@@ -43,6 +61,7 @@ body { font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
.cmd a:hover { text-decoration: underline; } .cmd a:hover { text-decoration: underline; }
.empty { color: var(--dim); text-align: center; padding: 60px 20px; font-size: 14px; } .empty { color: var(--dim); text-align: center; padding: 60px 20px; font-size: 14px; }
.refresh { color: var(--dim); font-size: 11px; text-align: right; margin-top: 20px; } .refresh { color: var(--dim); font-size: 11px; text-align: right; margin-top: 20px; }
.telem-warn { font-size: 10px; color: var(--amber); margin-left: 8px; }
</style> </style>
</head> </head>
<body> <body>
@@ -59,8 +78,8 @@ body { font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
var HUB = window.location.origin; var HUB = window.location.origin;
function loadFleet() { function loadFleet() {
fetch(HUB + '/api/fleet') fetch(HUB + '/api/fleet-telemetry')
.then(function(r) { return r.ok ? r.json() : Promise.reject(r.status); }) .then(function(r) { return r.ok ? r.json() : fetch(HUB + '/api/fleet').then(function(r2) { return r2.json(); }); })
.then(function(data) { render(data); }) .then(function(data) { render(data); })
.catch(function(e) { .catch(function(e) {
document.getElementById('fleet').innerHTML = document.getElementById('fleet').innerHTML =
@@ -69,18 +88,55 @@ function loadFleet() {
document.getElementById('refresh').textContent = 'Last updated: ' + new Date().toLocaleTimeString(); document.getElementById('refresh').textContent = 'Last updated: ' + new Date().toLocaleTimeString();
} }
function scoreClass(s) {
if (s == null) return '';
if (s >= 70) return 'good';
if (s >= 40) return 'warn';
return 'bad';
}
function signalClass(rsrp) {
if (rsrp == null) return '';
if (rsrp >= -85) return 'good';
if (rsrp >= -105) return 'warn';
return 'bad';
}
function signalBars(rsrp) {
if (rsrp == null) return '—';
if (rsrp >= -85) return '▂▄▆█';
if (rsrp >= -95) return '▂▄▆_';
if (rsrp >= -105) return '▂▄__';
if (rsrp >= -115) return '▂___';
return '____';
}
function fmtLatency(ms) { return ms != null ? ms + ' ms' : '—'; }
function fmtLoss(pct) { return pct != null ? pct + '%' : '—'; }
function fmtScore(s) { return s != null ? s : '—'; }
function fmtUptime(s) {
if (s == null) return '—';
var h = Math.floor(s / 3600);
var m = Math.floor((s % 3600) / 60);
if (h >= 24) { var d = Math.floor(h / 24); return d + 'd ' + (h % 24) + 'h'; }
return h + 'h ' + m + 'm';
}
function render(data) { function render(data) {
var devices = data.devices || []; var devices = data.devices || [];
var online = devices.filter(function(d) { return d.tunnel_up; }).length; var online = devices.filter(function(d) { return d.tunnel_up; }).length;
var telemOnline = data.telemetry_online || 0;
document.getElementById('stats').innerHTML = document.getElementById('stats').innerHTML =
'<div class="stat-card"><div class="num">' + devices.length + '<div class="stat-card"><div class="num">' + devices.length +
'</div><div class="lbl">Registered</div></div>' + '</div><div class="lbl">Registered</div></div>' +
'<div class="stat-card"><div class="num online">' + online + '<div class="stat-card"><div class="num online">' + online +
'</div><div class="lbl">Online</div></div>' + '</div><div class="lbl">Tunnel Online</div></div>' +
'<div class="stat-card"><div class="num offline">' + (devices.length - online) + '<div class="stat-card"><div class="num offline">' + (devices.length - online) +
'</div><div class="lbl">Offline</div></div>' + '</div><div class="lbl">Tunnel Offline</div></div>' +
'<div class="stat-card"><div class="num">' + (data.hub || '') + '<div class="stat-card"><div class="num" style="font-size:20px">' + telemOnline +
'</div><div class="lbl">Telemetry Active</div></div>' +
'<div class="stat-card"><div class="num" style="font-size:18px">' + (data.hub || '') +
'</div><div class="lbl">Hub</div></div>'; '</div><div class="lbl">Hub</div></div>';
var el = document.getElementById('fleet'); var el = document.getElementById('fleet');
@@ -90,21 +146,62 @@ function render(data) {
} }
el.innerHTML = devices.map(function(d) { el.innerHTML = devices.map(function(d) {
var isSynology = d.device_id.startsWith('x'); var isSynology = d.platform === 'synology' || d.device_id.startsWith('x');
var badge = isSynology var badge = isSynology
? '<span class="badge badge-synology">Synology</span>' ? '<span class="badge badge-synology">Synology</span>'
: '<span class="badge badge-gl">GL-XE3000</span>'; : '<span class="badge badge-gl">GL-XE3000</span>';
var verBadge = d.version ? '<span class="badge badge-ver">v' + esc(d.version) + '</span>' : '';
var status = d.tunnel_up var status = d.tunnel_up
? '<span><span class="dot dot-up"></span>ONLINE</span>' ? '<span><span class="dot dot-up"></span>ONLINE</span>'
: '<span><span class="dot dot-down"></span>OFFLINE</span>'; : '<span><span class="dot dot-down"></span>OFFLINE</span>';
var telemWarn = d.tunnel_up && !d.online_telemetry
? '<span class="telem-warn">(no telemetry)</span>' : '';
var ssh = 'ssh -p ' + d.tunnel_port + ' kitadmin@' + data.hub; var ssh = 'ssh -p ' + d.tunnel_port + ' kitadmin@' + data.hub;
var web = d.dashboard_url; var web = d.dashboard_url;
// WAN health bars
var wanHtml = '';
var wans = d.wan_summary || [];
if (wans.length) {
wanHtml = '<div class="wan-section"><div class="title">WAN Health</div>';
for (var i = 0; i < wans.length; i++) {
var w = wans[i];
var activeMarker = w.active ? '<span class="active-dot"></span>' : '<span style="display:inline-block;width:6px;margin-right:4px"></span>';
var bars = signalBars(w.rsrp_dbm);
wanHtml += '<div class="wan-bar">' +
activeMarker +
'<span class="member">' + esc(w.member) + '</span>' +
'<span class="score ' + scoreClass(w.score) + '">' + fmtScore(w.score) + '</span>' +
'<span class="metric">' + fmtLatency(w.latency_ms) + ' / ' + fmtLoss(w.loss_pct) + ' loss</span>' +
(w.rsrp_dbm != null
? '<span class="signal ' + signalClass(w.rsrp_dbm) + '" title="RSRP: ' + w.rsrp_dbm + ' dBm">' + bars + ' ' + w.rsrp_dbm + ' dBm</span>'
: '') +
(w.carrier ? '<span class="metric" style="margin-left:4px">' + esc(w.carrier) + '</span>' : '') +
(w.technology && w.technology !== 'unknown' ? '<span class="metric">' + esc(w.technology) + '</span>' : '') +
'</div>';
}
wanHtml += '</div>';
}
// GPS line
var gpsHtml = '';
if (d.gps && d.gps.lat != null && d.gps.lon != null) {
var fixLabel = d.gps.fix === 1 ? ' (IP approx)' : (d.gps.fix >= 2 ? ' (GPS)' : '');
gpsHtml = '<div class="gps-line">📍 ' +
Number(d.gps.lat).toFixed(4) + ', ' + Number(d.gps.lon).toFixed(4) + fixLabel +
' — <a href="https://maps.google.com/?q=' + d.gps.lat + ',' + d.gps.lon + '" target="_blank">Google Maps</a>' +
'</div>';
}
return '<div class="card">' + return '<div class="card">' +
'<h2>' + esc(d.device_id) + ' ' + badge + ' <span style="font-size:13px">' + status + '</span></h2>' + '<h2>' + esc(d.device_id) + ' ' + badge + verBadge + ' <span style="font-size:13px">' + status + telemWarn + '</span></h2>' +
'<div class="row"><span class="label">Tunnel Port</span><span class="val">' + d.tunnel_port + '</span></div>' + '<div class="row"><span class="label">Tunnel Port</span><span class="val">' + d.tunnel_port + '</span></div>' +
'<div class="row"><span class="label">Assigned</span><span class="val">' + (d.assigned || '--') + '</span></div>' + '<div class="row"><span class="label">Assigned</span><span class="val">' + (d.assigned || '--') + '</span></div>' +
(d.uptime_s ? '<div class="row"><span class="label">Uptime</span><span class="val">' + fmtUptime(d.uptime_s) + '</span></div>' : '') +
(d.autonomous != null ? '<div class="row"><span class="label">Autonomous</span><span class="val">' + (d.autonomous ? '✅ Enabled' : '❌ Disabled') + '</span></div>' : '') +
wanHtml +
gpsHtml +
(d.tunnel_up (d.tunnel_up
? '<div class="access">' + ? '<div class="access">' +
'<div class="title">Direct Access</div>' + '<div class="title">Direct Access</div>' +
+17 -9
View File
@@ -18,23 +18,31 @@ mkdir -p "$TELEM_DIR" "$BACKUP_DIR"
# ── Normalise telemetry ──────────────────────────────────────────── # ── Normalise telemetry ────────────────────────────────────────────
# Both platforms POST to /api/telemetry. # Both platforms POST to /api/telemetry.
# GL uses: modem_0001/wan keys, no "platform" field # Canonical format uses modem_0001/wan keys (matching GL standard).
# Synology uses: wan1/wan2 keys, "platform":"synology" # Handles three variants:
# Output: unified schema with platform field + wan1/wan2 keys # - GL (no platform field): add platform="openwrt", pass through
# - GL (platform="openwrt"): already canonical, pass through
# - Old Synology (platform="synology" + wan1/wan2): remap to modem_0001/wan
# - New unified Synology (platform="synology" + modem_0001/wan): pass through
normalise_telemetry() { normalise_telemetry() {
local json="$1" json="$1"
local platform="" platform=""
platform=$(echo "$json" | grep -o '"platform":"[^"]*"' | cut -d'"' -f4) platform=$(echo "$json" | grep -o '"platform":"[^"]*"' | cut -d'"' -f4)
if [ -z "$platform" ]; then if [ -z "$platform" ]; then
# Pre-unified GL telemetry — add platform, remap keys # Pre-unified GL telemetry — add platform field, keys already canonical
platform="openwrt" platform="openwrt"
json=$(echo "$json" | sed \ json=$(echo "$json" | sed \
-e 's/"modem_0001"/"wan1"/g' \ -e 's/^{/{"platform":"'"$platform"'",/')
-e 's/"platform":"openwrt"/"platform":"'"$platform"'"/') fi
# Remap old Synology wan1/wan2 keys to canonical modem_0001/wan
if echo "$json" | grep -q '"wan1"'; then
json=$(echo "$json" | sed \
-e 's/"wan1"/"modem_0001"/g' \
-e 's/"wan2"/"wan"/g')
fi fi
# Ensure both wan1 and wan2 keys exist (Synology uses wan1/wan2 natively)
echo "$json" echo "$json"
} }
+184 -1
View File
@@ -7,6 +7,8 @@ Listens on :8080. Routes:
GET /api/register/<DEVICE_ID> — assign tunnel port, return JSON GET /api/register/<DEVICE_ID> — assign tunnel port, return JSON
GET /api/fleet — all registered devices with GET /api/fleet — all registered devices with
tunnel status + access links tunnel status + access links
GET /api/fleet-telemetry — fleet status enriched with telemetry
from fleet Postgres (WAN health, GPS)
POST /api/authorize-key — authorize device tunnel key POST /api/authorize-key — authorize device tunnel key
""" """
@@ -22,6 +24,13 @@ REGISTRY = "/opt/busfleet-hub/port-registry.json"
DASHBOARD = "/opt/busfleet-hub/dashboard.html" DASHBOARD = "/opt/busfleet-hub/dashboard.html"
HUB_IP = "162.243.83.36" HUB_IP = "162.243.83.36"
# Fleet Postgres connection (for telemetry enrichment)
FLEET_DB_HOST = os.environ.get("FLEET_DB_HOST", "167.172.237.162")
FLEET_DB_PORT = os.environ.get("FLEET_DB_PORT", "5432")
FLEET_DB_NAME = os.environ.get("FLEET_DB_NAME", "fleet")
FLEET_DB_USER = os.environ.get("FLEET_DB_USER", "fleet")
FLEET_DB_PASS = os.environ.get("FLEET_DB_PASS", "")
# ── Helper: check if a TCP port is open (tunnel active) ────────── # ── Helper: check if a TCP port is open (tunnel active) ──────────
def _port_is_open(port): def _port_is_open(port):
@@ -33,6 +42,84 @@ def _port_is_open(port):
return False return False
# ── Helper: query fleet Postgres for latest device_status ─────────
def _query_fleet_telemetry():
"""Query fleet Postgres for the latest telemetry data for all devices.
Returns a dict keyed by device_id, or empty dict if DB unreachable."""
try:
import psycopg2
conn = psycopg2.connect(
host=FLEET_DB_HOST,
port=FLEET_DB_PORT,
dbname=FLEET_DB_NAME,
user=FLEET_DB_USER,
password=FLEET_DB_PASS,
connect_timeout=5,
)
cur = conn.cursor()
cur.execute("""
SELECT d.device_id, d.vendor, d.model,
st.online, st.ts, st.version, st.uptime_s,
st.primary_member, st.active_wan,
st.gps_lat, st.gps_lon, st.gps_fix,
st.wan, st.starlink, st.state
FROM devices d
LEFT JOIN device_status st ON st.device_id = d.device_id
ORDER BY d.device_id
""")
rows = cur.fetchall()
cur.close()
conn.close()
result = {}
for row in rows:
device_id = row[0]
wan_data = row[12] if row[12] else {}
# psycopg2 returns JSONB as dict
if isinstance(wan_data, str):
try:
wan_data = json.loads(wan_data)
except (json.JSONDecodeError, TypeError):
wan_data = {}
starlink_data = row[13] if row[13] else {}
if isinstance(starlink_data, str):
try:
starlink_data = json.loads(starlink_data)
except (json.JSONDecodeError, TypeError):
starlink_data = {}
state_data = row[14] if row[14] else {}
if isinstance(state_data, str):
try:
state_data = json.loads(state_data)
except (json.JSONDecodeError, TypeError):
state_data = {}
result[device_id] = {
"vendor": row[1],
"model": row[2],
"online": row[3] if row[3] is not None else False,
"ts": str(row[4]) if row[4] else None,
"version": row[5],
"uptime_s": row[6],
"primary_member": row[7],
"active_wan": row[8],
"gps": {
"lat": float(row[9]) if row[9] is not None else None,
"lon": float(row[10]) if row[10] is not None else None,
"fix": row[11],
},
"wan": wan_data,
"starlink": starlink_data,
"state": state_data,
}
return result
except Exception as e:
print(f"[hub] fleet telemetry query failed: {e}", file=sys.stderr)
return {}
class HubHandler(BaseHTTPRequestHandler): class HubHandler(BaseHTTPRequestHandler):
"""Handle hub registration, fleet status, and dashboard requests.""" """Handle hub registration, fleet status, and dashboard requests."""
@@ -56,11 +143,16 @@ class HubHandler(BaseHTTPRequestHandler):
self.call_register_script(device_id) self.call_register_script(device_id)
return return
# Fleet status — all registered devices # Fleet status — basic tunnel-only (original endpoint)
if self.path == "/api/fleet": if self.path == "/api/fleet":
self.serve_fleet_status() self.serve_fleet_status()
return return
# Fleet status — enriched with telemetry from fleet DB
if self.path == "/api/fleet-telemetry":
self.serve_fleet_telemetry()
return
self.send_json_error(404, "Not found") self.send_json_error(404, "Not found")
def do_POST(self): def do_POST(self):
@@ -161,6 +253,73 @@ class HubHandler(BaseHTTPRequestHandler):
"devices": devices, "devices": devices,
})) }))
def serve_fleet_telemetry(self):
"""Build enriched fleet status: tunnel status + telemetry from fleet DB."""
# Read port registry (tunnel info)
try:
with open(REGISTRY) as f:
registry = json.load(f)
except Exception:
registry = {}
# Query fleet Postgres for telemetry
fleet_data = _query_fleet_telemetry()
devices = []
for dev_id, entry in registry.items():
port = entry.get("tunnel_port", 0)
tunnel_up = _port_is_open(port) if port else False
# Enrich with fleet telemetry
telem = fleet_data.get(dev_id, {})
# Derive platform from vendor or device_id prefix
vendor = telem.get("vendor", "")
if vendor == "synology" or dev_id.startswith("x"):
platform = "synology"
elif vendor == "glinet" or dev_id.startswith(("B", "C")):
platform = "openwrt"
else:
platform = telem.get("vendor", "unknown")
# Format WAN summary for dashboard
wan_summary = _format_wan_summary(telem.get("wan", {}), telem.get("primary_member"))
devices.append({
"device_id": dev_id,
"tunnel_port": port,
"assigned": entry.get("assigned", ""),
"tunnel_up": tunnel_up,
"ssh_command": f"ssh -p {port} kitadmin@{HUB_IP}",
"dashboard_url": f"http://{HUB_IP}:{port}" if tunnel_up else None,
# Telemetry enrichment
"platform": platform,
"version": telem.get("version"),
"uptime_s": telem.get("uptime_s"),
"online_telemetry": telem.get("online", False),
"primary_member": telem.get("primary_member"),
"active_wan": telem.get("active_wan"),
"gps": telem.get("gps", {}),
"wan_summary": wan_summary,
"starlink": telem.get("starlink"),
"autonomous": telem.get("state", {}).get("autonomous"),
})
# Sort: tunnel_up first, then by device_id
devices.sort(key=lambda d: (not d["tunnel_up"], d["device_id"]))
# Summary stats
online = sum(1 for d in devices if d["tunnel_up"])
telemetry_online = sum(1 for d in devices if d.get("online_telemetry"))
self.send_json(200, json.dumps({
"hub": HUB_IP,
"device_count": len(devices),
"online": online,
"telemetry_online": telemetry_online,
"devices": devices,
}))
def send_json(self, status, body): def send_json(self, status, body):
"""Send a JSON response.""" """Send a JSON response."""
self.send_response(status) self.send_response(status)
@@ -177,6 +336,30 @@ class HubHandler(BaseHTTPRequestHandler):
print(f"[hub] {args[0]}", file=sys.stderr) print(f"[hub] {args[0]}", file=sys.stderr)
def _format_wan_summary(wan, primary_member):
"""Format WAN data into a concise summary for the dashboard."""
if not wan or not isinstance(wan, dict):
return []
summary = []
for member, metrics in wan.items():
if not isinstance(metrics, dict):
continue
entry = {
"member": member,
"active": member == primary_member,
"score": metrics.get("score"),
"latency_ms": metrics.get("latency_ms"),
"loss_pct": metrics.get("loss_pct"),
"rsrp_dbm": metrics.get("rsrp_dbm"),
"carrier": metrics.get("carrier"),
"technology": metrics.get("technology"),
}
summary.append(entry)
# Sort: active first, then by score descending
summary.sort(key=lambda x: (not x["active"], -(x["score"] or 0)))
return summary
def main(): def main():
port = int(sys.argv[1]) if len(sys.argv) > 1 else 8080 port = int(sys.argv[1]) if len(sys.argv) > 1 else 8080
server = HTTPServer(("0.0.0.0", port), HubHandler) server = HTTPServer(("0.0.0.0", port), HubHandler)
+1 -1
View File
@@ -1,5 +1,5 @@
package="kit-connect" package="kit-connect"
version="0.1-0001" version="0.5.0-0001"
description="Unified management connectivity for Pioneer bus fleet routers. Single SPK — deploys Tailscale + reverse SSH tunnel. Hub auto-assigns ports on install. One package, all routers. Compatible: RT2600ac, RT6600ax." description="Unified management connectivity for Pioneer bus fleet routers. Single SPK — deploys Tailscale + reverse SSH tunnel. Hub auto-assigns ports on install. One package, all routers. Compatible: RT2600ac, RT6600ax."
displayname="KIT Bus Router Connect" displayname="KIT Bus Router Connect"
maintainer="Keylink IT" maintainer="Keylink IT"
+1 -1
View File
@@ -19,7 +19,7 @@ SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
cd "$SCRIPT_DIR" cd "$SCRIPT_DIR"
PKG_NAME="kit-connect" PKG_NAME="kit-connect"
VERSION="0.1-0001" VERSION="0.5.0-0001"
OUTPUT="${PKG_NAME}-${VERSION}.spk" OUTPUT="${PKG_NAME}-${VERSION}.spk"
BUILD_DIR="/tmp/kit-connect-build-$$" BUILD_DIR="/tmp/kit-connect-build-$$"
@@ -1,64 +1,77 @@
#!/bin/sh #!/bin/sh
# telemetry-synology.sh — Synology SRM telemetry payload builder for fleet hub. # telemetry-synology.sh — Self-contained telemetry for Synology SRM routers.
# #
# Reads aiwanbal state files from /tmp/aiwanbal/ and optionally queries the # Synology RT2600ac routers have NO built-in 5G modem or GPS. Cellular comes
# Eyeride Eyenet (OpenWrt ubus) for GPS position. Posts JSON to the fleet hub # from an external Eyeride device (192.168.10.1:8080) which provides GPS and
# over Tailscale with disk-buffered retry on failure. # signal metrics via OpenWrt ubus JSON-RPC.
# #
# Config (environment variables): # GPS fallback chain:
# 1. Eyeride ubus JSON-RPC (gps / location service) → fix=2 or 3
# 2. ip-api.com geolocation by external IP → fix=1 (approximate)
#
# WAN mapping (canonical GL format):
# WAN1 (Ethernet/primary uplink) → modem_0001
# WAN2 (Eyeride cellular) → wan (with rsrp_dbm/rsrq_db/sinr_db)
#
# Self-collected metrics (no aiwanbal dependency):
# - Ping latency/loss per interface (using -I <iface>)
# - Throughput from /sys/class/net/<iface>/statistics/ (bytes delta between cycles)
# - Score computed from latency + loss (simple heuristic)
# - Eyeride cellular signal via ubus (if available)
#
# Config (/etc/busrouter/telemetry.conf, sourced as shell):
# TELEMETRY_HUB POST endpoint (default: http://10.88.0.1:8080/api/telemetry) # TELEMETRY_HUB POST endpoint (default: http://10.88.0.1:8080/api/telemetry)
# TELEMETRY_BUFFER_DIR disk buffer for failed POSTs (default: /tmp/busrouter/telemetry-buf) # TELEMETRY_BUFFER_DIR disk buffer for failed POSTs (default: /tmp/busrouter/telemetry-buf)
# AIWANBAL_STATE_DIR aiwanbal runtime state (default: /tmp/aiwanbal) # EYERIDE_IP Eyeride OpenWrt IP (default: 192.168.10.1)
# EYERIDE_IP Eyeride OpenWrt IP for GPS (default: 192.168.10.1)
# EYERIDE_PORT Eyeride ubus port (default: 8080) # EYERIDE_PORT Eyeride ubus port (default: 8080)
# EYERIDE_USER Eyeride SSH/ubus username (default: root) # EYERIDE_USER Eyeride ubus username (default: benmashborn)
# EYERIDE_PASSWORD Eyeride password (required for GPS) # EYERIDE_PASSWORD Eyeride password (required for GPS + signal)
# WAN1_IFACE Primary WAN interface (default: eth0)
# WAN2_IFACE Secondary/cellular WAN interface (default: eth2)
# PING_TARGET Host to ping for latency/loss (default: 8.8.8.8)
# STATE_DIR Runtime state directory (default: /tmp/busrouter)
# #
# Public API: # Public API:
# eyeride_gps query GPS from Eyeride ubus; echo 'lat lon fix'; # eyeride_gps echo 'lat lon fix'; exit 1 on failure
# exit 1 if unavailable # ipgeo_gps echo 'lat lon fix'; exit 1 on failure
# telemetry_synology_collect emit JSON payload to stdout from aiwanbal state files # gps_fix try eyeride_gps, fall back to ipgeo_gps
# telemetry_synology_flush retry all buffered payloads; return 1 if hub still down # telemetry_collect emit JSON payload to stdout (canonical GL format)
# telemetry_synology_send collect + flush + post; buffer on failure # telemetry_flush retry all buffered payloads; return 1 if hub still down
# telemetry_send collect + flush + post; buffer on failure
# #
# Cron mode: runs telemetry_synology_send when executed directly. # Cron mode: runs telemetry_send when executed directly.
LIB_DIR="${LIB_DIR:-/usr/lib/busrouter}" # ── Configuration ──────────────────────────────────────────────────────────
: "${TELEMETRY_HUB:=http://10.88.0.1:8080/api/telemetry}" : "${TELEMETRY_HUB:=http://10.88.0.1:8080/api/telemetry}"
: "${TELEMETRY_BUFFER_DIR:=/tmp/busrouter/telemetry-buf}" : "${TELEMETRY_BUFFER_DIR:=/tmp/busrouter/telemetry-buf}"
: "${AIWANBAL_STATE_DIR:=/tmp/aiwanbal}"
: "${EYERIDE_IP:=192.168.10.1}" : "${EYERIDE_IP:=192.168.10.1}"
: "${EYERIDE_PORT:=8080}" : "${EYERIDE_PORT:=8080}"
: "${EYERIDE_USER:=root}" : "${EYERIDE_USER:=benmashborn}"
: "${WAN1_IFACE:=eth0}"
: "${WAN2_IFACE:=eth2}"
: "${PING_TARGET:=8.8.8.8}"
: "${STATE_DIR:=/tmp/busrouter}"
# Source per-device overrides if present
[ -f /etc/busrouter/telemetry.conf ] && . /etc/busrouter/telemetry.conf
_TELEM_SEQ=0 _TELEM_SEQ=0
# ── Helpers ───────────────────────────────────────────────────────────────────── # ── Helpers ────────────────────────────────────────────────────────────────
# Escape a string value for JSON (backslash and double-quote only). # Escape a string for JSON (backslash + double-quote only).
_json_str() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g'; } _json_str() { printf '%s' "$1" | sed 's/\\/\\\\/g; s/"/\\"/g'; }
# Read an aiwanbal state file, return empty string if missing. # BusyBox-compatible float arithmetic via awk.
_aiwanbal_val() { _awk_float() { awk "BEGIN { printf \"%.1f\", $1 }" 2>/dev/null || echo "null"; }
local key="$1"
cat "${AIWANBAL_STATE_DIR}/${key}" 2>/dev/null || true
}
# ── Eyeride GPS (ubus JSON-RPC) ───────────────────────────────────────────────── # ── GPS: Eyeride ubus JSON-RPC ─────────────────────────────────────────────
#
# The Eyeride Eyenet is an OpenWrt device at 192.168.10.1:8080 with ubus
# JSON-RPC. GPS data may be available through:
# 1. ubus call gps status (if gps service is running)
# 2. ubus call location status (alternative service name)
# 3. /tmp/gps/last_fix on the Eyeride (mounted via NFS/SMB or scraped)
#
# This function tries option 1 first, then falls back gracefully.
# Authenticate to Eyeride ubus, return session token on stdout. # Authenticate to Eyeride ubus, return session token on stdout.
_eyeride_login() { _eyeride_login() {
local _pass="${EYERIDE_PASSWORD:-}" _pass="${EYERIDE_PASSWORD:-}"
[ -n "$_pass" ] || return 1 [ -n "$_pass" ] || return 1
local _login_body _login_resp _session
_login_body="{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"call\",\"params\":[\"00000000000000000000000000000000\",\"session\",\"login\",{\"username\":\"${EYERIDE_USER}\",\"password\":\"${_pass}\"}]}" _login_body="{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"call\",\"params\":[\"00000000000000000000000000000000\",\"session\",\"login\",{\"username\":\"${EYERIDE_USER}\",\"password\":\"${_pass}\"}]}"
_login_resp=$(curl -s --connect-timeout 5 -X POST \ _login_resp=$(curl -s --connect-timeout 5 -X POST \
-H 'Content-Type: application/json' \ -H 'Content-Type: application/json' \
@@ -76,10 +89,8 @@ _eyeride_login() {
} }
# Call a ubus method on the Eyeride with an active session token. # Call a ubus method on the Eyeride with an active session token.
# Usage: _eyeride_ubus_call <session> <service> <method> [params_json]
_eyeride_ubus_call() { _eyeride_ubus_call() {
local _session="$1" _svc="$2" _method="$3" _params="${4:-{}}" _session="$1" _svc="$2" _method="$3" _params="${4:-{}}"
local _body
_body="{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"call\",\"params\":[\"${_session}\",\"${_svc}\",\"${_method}\",${_params}]}" _body="{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"call\",\"params\":[\"${_session}\",\"${_svc}\",\"${_method}\",${_params}]}"
curl -s --connect-timeout 5 -X POST \ curl -s --connect-timeout 5 -X POST \
-H 'Content-Type: application/json' \ -H 'Content-Type: application/json' \
@@ -87,37 +98,36 @@ _eyeride_ubus_call() {
"http://${EYERIDE_IP}:${EYERIDE_PORT}/ubus" 2>/dev/null "http://${EYERIDE_IP}:${EYERIDE_PORT}/ubus" 2>/dev/null
} }
# Query GPS position from Eyeride. # Extract a numeric field from JSON (handles both integer and float).
# Emits 'lat lon fix_quality' on success; exit 1 on failure or no fix. _json_get_num() {
eyeride_gps() { echo "$1" | sed -n "s/.*\"$2\": *\(-\?[0-9.]*\).*/\1/p" | head -1
local _session _resp _lat _lon _fix }
# Extract a string field from JSON.
_json_get_str() {
echo "$1" | sed -n "s/.*\"$2\": *\"\([^\"]*\)\".*/\1/p" | head -1
}
# Query GPS from Eyeride ubus. Emits 'lat lon fix'; exit 1 on failure.
eyeride_gps() {
_session=$(_eyeride_login) || return 1 _session=$(_eyeride_login) || return 1
# Try 'gps' service first (common OpenWrt gpsd ubus binding) # Try 'gps' service first, then 'location' service
_resp=$(_eyeride_ubus_call "$_session" "gps" "status") 2>/dev/null _resp=$(_eyeride_ubus_call "$_session" "gps" "status") 2>/dev/null
if [ -z "$_resp" ] || echo "$_resp" | grep -q '"result":\[2\]'; then if [ -z "$_resp" ] || echo "$_resp" | grep -q '"result":\[2\]'; then
# gps service not found — try 'location' service
_resp=$(_eyeride_ubus_call "$_session" "location" "status") 2>/dev/null _resp=$(_eyeride_ubus_call "$_session" "location" "status") 2>/dev/null
fi fi
# Try to extract lat/lon from ubus response JSON # Extract lat/lon from various possible field names
_lat=$(echo "$_resp" | sed 's/.*"latitude":\([0-9.-]*\).*/\1/' 2>/dev/null) _lat=$(_json_get_num "$_resp" "latitude")
_lon=$(echo "$_resp" | sed 's/.*"longitude":\([0-9.-]*\).*/\1/' 2>/dev/null) _lon=$(_json_get_num "$_resp" "longitude")
# Also try snake_case variants [ -z "$_lat" ] && _lat=$(_json_get_num "$_resp" "lat")
[ "$_lat" = "$_resp" ] && _lat=$(echo "$_resp" | sed 's/.*"lat":\([0-9.-]*\).*/\1/' 2>/dev/null) [ -z "$_lon" ] && _lon=$(_json_get_num "$_resp" "lon")
[ "$_lon" = "$_resp" ] && _lon=$(echo "$_resp" | sed 's/.*"lon":\([0-9.-]*\).*/\1/' 2>/dev/null) [ -z "$_lat" ] && _lat=$(_json_get_num "$_resp" "lat_deg")
# Alt spelling [ -z "$_lon" ] && _lon=$(_json_get_num "$_resp" "lon_deg")
[ "$_lat" = "$_resp" ] && _lat=$(echo "$_resp" | sed 's/.*"lat_deg":\([0-9.-]*\).*/\1/' 2>/dev/null)
[ "$_lon" = "$_resp" ] && _lon=$(echo "$_resp" | sed 's/.*"lon_deg":\([0-9.-]*\).*/\1/' 2>/dev/null)
# Sanitize: if sed didn't match, the field equals the full response
[ "$_lat" = "$_resp" ] && _lat=""
[ "$_lon" = "$_resp" ] && _lon=""
if [ -n "$_lat" ] && [ -n "$_lon" ]; then if [ -n "$_lat" ] && [ -n "$_lon" ]; then
_fix=2 # assume 2D fix if we got coordinates _fix=2 # assume 2D fix from Eyeride
[ -n "$_fix" ] || _fix=2
logger -t busrouter -p daemon.debug "eyeride_gps: ${_lat} ${_lon} fix=${_fix}" logger -t busrouter -p daemon.debug "eyeride_gps: ${_lat} ${_lon} fix=${_fix}"
printf '%s %s %s\n' "$_lat" "$_lon" "$_fix" printf '%s %s %s\n' "$_lat" "$_lon" "$_fix"
return 0 return 0
@@ -127,154 +137,234 @@ eyeride_gps() {
return 1 return 1
} }
# ── Telemetry Collection ───────────────────────────────────────────────────────── # ── GPS: IP Geolocation Fallback ───────────────────────────────────────────
#
# State files read from AIWANBAL_STATE_DIR (written by aiwanbal daemon each cycle):
# wan1_score_avg, wan2_score_avg integer 0100
# wan1_latency, wan2_latency ms
# wan1_throughput, wan2_throughput B/s (converted to Mbps below)
# wan1_upload, wan2_upload B/s
# wan1_jitter, wan2_jitter ms
# wan1_packet_loss, wan2_packet_loss %
# wan1_rsrp, wan2_rsrp dBm (cellular signal)
# wan1_rsrq, wan2_rsrq dB
# wan1_sinr, wan2_sinr dB
# wan1_technology, wan2_technology e.g. "5G-NR", "LTE"
# wan1_modem_type, wan2_modem_type e.g. "eyeride", "peplink", "none"
# wan0_mode "active" or "failover"
# wan0_starlink_quality quality score (if Starlink connected)
# wan0_starlink_latency ms
# wan0_starlink_obstruction bool-ish
# wan0_starlink_outage bool-ish
# Read one WAN's metrics and emit a JSON object fragment. # Query ip-api.com for approximate location. Emits 'lat lon fix'; exit 1 on failure.
# Usage: _synology_wan_json <wan_num> ipgeo_gps() {
_synology_wan_json() { _resp=$(curl -s --connect-timeout 5 "http://ip-api.com/json/" 2>/dev/null) || return 1
local n="$1" [ -n "$_resp" ] || return 1
local score lat dl ul jitter loss rsrp rsrq sinr tech carrier modem
score=$(_aiwanbal_val "wan${n}_score_avg") _lat=$(_json_get_num "$_resp" "lat")
lat=$(_aiwanbal_val "wan${n}_latency") _lon=$(_json_get_num "$_resp" "lon")
local throughput_bytes
throughput_bytes=$(_aiwanbal_val "wan${n}_throughput")
dl=""
[ -n "$throughput_bytes" ] && dl=$(awk "BEGIN { printf \"%.1f\", ${throughput_bytes} / 125000 }" 2>/dev/null)
[ -z "$dl" ] && dl="0"
local upload_bytes
upload_bytes=$(_aiwanbal_val "wan${n}_upload")
ul=""
[ -n "$upload_bytes" ] && ul=$(awk "BEGIN { printf \"%.1f\", ${upload_bytes} / 125000 }" 2>/dev/null)
[ -z "$ul" ] && ul="0"
jitter=$(_aiwanbal_val "wan${n}_jitter")
loss=$(_aiwanbal_val "wan${n}_packet_loss")
rsrp=$(_aiwanbal_val "wan${n}_rsrp")
rsrq=$(_aiwanbal_val "wan${n}_rsrq")
sinr=$(_aiwanbal_val "wan${n}_sinr")
tech=$(_aiwanbal_val "wan${n}_technology")
modem=$(_aiwanbal_val "wan${n}_modem_type")
# Carrier is not tracked separately by aiwanbal — derive from modem type if [ -n "$_lat" ] && [ -n "$_lon" ]; then
carrier="" _fix=1 # approximate (IP-based)
case "$modem" in logger -t busrouter -p daemon.debug "ipgeo_gps: ${_lat} ${_lon} fix=${_fix} (IP geolocation)"
eyeride) carrier="Eyeride" ;; printf '%s %s %s\n' "$_lat" "$_lon" "$_fix"
peplink) carrier="Peplink" ;; return 0
zte) carrier="ZTE" ;; fi
mofi) carrier="Mofi" ;;
none|generic|"") carrier="" ;;
*) carrier="$modem" ;;
esac
local esc_tech esc_carrier logger -t busrouter "ipgeo_gps: geolocation failed"
esc_tech=$(_json_str "${tech:-unknown}") return 1
esc_carrier=$(_json_str "${carrier:-unknown}")
printf '{"score":%s,"latency_ms":%s,"dl_mbps":%s,"ul_mbps":%s,"jitter_ms":%s,"loss_pct":%s,"rsrp_dbm":%s,"rsrq_db":%s,"sinr_db":%s,"technology":"%s","carrier":"%s"}' \
"${score:-0}" \
"${lat:-null}" \
"${dl:-0}" \
"${ul:-0}" \
"${jitter:-null}" \
"${loss:-null}" \
"${rsrp:-null}" \
"${rsrq:-null}" \
"${sinr:-null}" \
"${esc_tech}" \
"${esc_carrier}"
} }
# Build the full telemetry JSON payload from aiwanbal state files. # GPS with fallback: try Eyeride first, then IP geolocation.
# Emits JSON on stdout; never fails — uses defaults for all missing fields. gps_fix() {
telemetry_synology_collect() { if eyeride_gps 2>/dev/null; then
local now device_id uptime_s version return 0
fi
ipgeo_gps
}
# ── Eyeride Cellular Signal ────────────────────────────────────────────────
# Query cellular signal from Eyeride ubus (network/wwan services).
# Returns: rsrp_dbm rsrq_db sinr_db technology carrier_str
_eyeride_signal() {
_session=$(_eyeride_login) 2>/dev/null || return 1
# Try network.wan status for modem info
_resp=$(_eyeride_ubus_call "$_session" "network" "status") 2>/dev/null
if [ -z "$_resp" ] || echo "$_resp" | grep -q '"result":\[2\]'; then
# Try alternative: wwan or modem service
_resp=$(_eyeride_ubus_call "$_session" "wwan" "status") 2>/dev/null
fi
_rsrp=$(_json_get_num "$_resp" "rsrp")
_rsrq=$(_json_get_num "$_resp" "rsrq")
_sinr=$(_json_get_num "$_resp" "sinr")
_tech=$(_json_get_str "$_resp" "technology")
_carrier=$(_json_get_str "$_resp" "operator")
# Also try signal-specific fields
[ -z "$_rsrp" ] && _rsrp=$(_json_get_num "$_resp" "signal")
[ -z "$_rsrp" ] && _rsrp=$(_json_get_num "$_resp" "rssi")
printf '%s %s %s %s %s\n' "${_rsrp:-null}" "${_rsrq:-null}" "${_sinr:-null}" "${_tech:-unknown}" "${_carrier:-Eyeride}"
return 0
}
# ── WAN Metric Collection ──────────────────────────────────────────────────
# Ping an interface to get latency and loss.
# On Synology SRM: ping requires root. When running from cron (as root), it works.
# When run manually as non-root, gracefully returns null.
# Usage: _ping_iface <iface> → "lat_ms loss_pct"
_ping_iface() {
_iface="$1"
# Try sudo ping (for Synology where ping needs root), fall back to direct ping
_out=$(sudo ping -I "$_iface" -c 3 -W 3 "$PING_TARGET" 2>/dev/null || ping -I "$_iface" -c 3 -W 3 "$PING_TARGET" 2>/dev/null)
if [ -z "$_out" ]; then
echo "null null"
return
fi
# Check for permission denied / other errors
if echo "$_out" | grep -qE "permission denied|not permitted|unknown host|Network is unreachable"; then
echo "null null"
return
fi
# Extract avg rtt from last line.
# Standard ping: "rtt min/avg/max/mdev = 10.5/15.2/20.1/3.5 ms"
# BusyBox ping: "round-trip min/avg/max = 10.5/15.2/20.1 ms"
_avg=$(echo "$_out" | tail -1 | sed -n 's/.*=\ [0-9.]*\/\([0-9.]*\)\/.*/\1/p')
[ -z "$_avg" ] && _avg=$(echo "$_out" | tail -1 | sed -n 's/.*avg\/max.*=\ \([0-9.]*\)\/.*/\1/p')
[ -z "$_avg" ] && _avg="null"
# Extract loss percentage: "3 packets transmitted, 3 received, 0% packet loss"
_loss=$(echo "$_out" | sed -n 's/.* \([0-9]*\)% packet loss.*/\1/p')
[ -z "$_loss" ] && _loss="null"
echo "${_avg} ${_loss}"
}
# Compute simple WAN score from latency and loss (0-100, higher = better).
# Score = max(0, 100 - latency_ms/2 - loss_pct*5)
_compute_score() {
_lat="$1" _loss="$2"
if [ "$_lat" = "null" ] || [ "$_loss" = "null" ]; then
echo "0"
return
fi
_score=$(awk "BEGIN { s = 100 - ${_lat}/2 - ${_loss}*5; if (s < 0) s = 0; if (s > 100) s = 100; printf \"%d\", int(s) }" 2>/dev/null)
echo "${_score:-0}"
}
# Read bytes transferred from /sys/class/net/<iface>/statistics/.
# Returns delta from last reading stored in STATE_DIR.
_read_bytes_delta() {
_iface="$1" _direction="$2" # tx_bytes or rx_bytes
_stat_file="/sys/class/net/${_iface}/statistics/${_direction}"
_state_file="${STATE_DIR}/bytes_${_iface}_${_direction}"
[ -f "$_stat_file" ] || { echo "null"; return; }
mkdir -p "$STATE_DIR" 2>/dev/null
_current=$(cat "$_stat_file" 2>/dev/null)
_prev=$(cat "$_state_file" 2>/dev/null)
printf '%s\n' "$_current" > "$_state_file" 2>/dev/null || true
if [ -z "$_prev" ] || [ -z "$_current" ]; then
echo "null"; return
fi
_delta=$(( _current - _prev ))
if [ "$_delta" -lt 0 ]; then
_delta=0 # counter reset
fi
# Convert bytes to Mbps (bytes → Mb/s, assume ~60s interval)
_mbps=$(awk "BEGIN { printf \"%.1f\", ${_delta} * 8 / 60 / 1000000 }" 2>/dev/null)
echo "${_mbps:-0.0}"
}
# Collect metrics for one WAN interface.
# Usage: _collect_wan <iface> → JSON object fragment
_collect_wan() {
_iface="$1"
# Ping metrics
_ping_result=$(_ping_iface "$_iface")
_lat=$(echo "$_ping_result" | awk '{print $1}')
_loss=$(echo "$_ping_result" | awk '{print $2}')
# Throughput (delta since last cycle)
_dl=$(_read_bytes_delta "$_iface" "rx_bytes")
_ul=$(_read_bytes_delta "$_iface" "tx_bytes")
# Score
_score=$(_compute_score "$_lat" "$_loss")
# Jitter — rough estimate from ping variation (not true jitter, but indicative)
_jitter="null"
printf '{"score":%s,"latency_ms":%s,"dl_mbps":%s,"ul_mbps":%s,"jitter_ms":%s,"loss_pct":%s}' \
"${_score}" "${_lat}" "${_dl}" "${_ul}" "${_jitter}" "${_loss}"
}
# ── Telemetry Collection ───────────────────────────────────────────────────
# Build the full telemetry JSON payload (canonical GL format).
# Emits JSON to stdout; never fails — uses defaults for missing fields.
telemetry_collect() {
now=$(date +%s) now=$(date +%s)
device_id=$(cat /etc/busrouter/device-id 2>/dev/null || hostname) device_id=$(cat /etc/busrouter/device-id 2>/dev/null || hostname)
uptime_s=$(awk '{printf "%d", $1}' /proc/uptime 2>/dev/null) uptime_s=$(awk '{printf "%d", $1}' /proc/uptime 2>/dev/null)
version=$(cat /etc/busrouter/version 2>/dev/null || echo "dev") version=$(cat /etc/busrouter/version 2>/dev/null || echo "dev")
# GPS # GPS (Eyeride → IP geolocation fallback)
local gps_lat gps_lon gps_fix gps_lat="null" gps_lon="null" gps_fix="null"
if gps_out=$(eyeride_gps 2>/dev/null); then if gps_out=$(gps_fix 2>/dev/null); then
read -r gps_lat gps_lon gps_fix <<-EOF gps_lat=$(echo "$gps_out" | awk '{print $1}')
$gps_out gps_lon=$(echo "$gps_out" | awk '{print $2}')
EOF gps_fix=$(echo "$gps_out" | awk '{print $3}')
fi fi
# WAN 1 + WAN 2 # WAN1 (primary uplink, typically Ethernet → modem_0001 in canonical format)
local wan1_json wan2_json wan1_json=$(_collect_wan "$WAN1_IFACE")
wan1_json=$(_synology_wan_json 1)
wan2_json=$(_synology_wan_json 2)
# Active WAN — which one is currently carrying traffic # WAN2 (Eyeride cellular → wan in canonical format)
local mode sel_primary wan2_json=$(_collect_wan "$WAN2_IFACE")
mode=$(_aiwanbal_val "wan0_mode")
case "$mode" in # Eyeride cellular signal for WAN2 (try to enrich with rsrp/rsrq/sinr)
failover) eyeride_sig=$(_eyeride_signal 2>/dev/null)
# In failover, primary is the active one; check which is up _rsrp=$(echo "$eyeride_sig" | awk '{print $1}')
local wan1_state wan2_state _rsrq=$(echo "$eyeride_sig" | awk '{print $2}')
wan1_state=$(_aiwanbal_val "wan1_state") _sinr=$(echo "$eyeride_sig" | awk '{print $3}')
wan2_state=$(_aiwanbal_val "wan2_state") _tech=$(echo "$eyeride_sig" | awk '{print $4}')
if [ "$wan2_state" = "up" ]; then _carrier=$(echo "$eyeride_sig" | awk '{print $5}')
sel_primary="wan2"
else # Build WAN2 JSON with cellular signal if available
sel_primary="wan1" if [ "$_rsrp" != "null" ] && [ -n "$_rsrp" ]; then
# Replace closing brace with signal fields
wan2_json=$(printf '%s' "$wan2_json" | sed 's/}$//')
_esc_tech=$(_json_str "${_tech:-unknown}")
_esc_carrier=$(_json_str "${_carrier:-Eyeride}")
wan2_json="${wan2_json},\"rsrp_dbm\":${_rsrp},\"rsrq_db\":${_rsrq},\"sinr_db\":${_sinr},\"technology\":\"${_esc_tech}\",\"carrier\":\"${_esc_carrier}\"}"
fi fi
;;
*)
# Load-balance mode: both are active; wan1 is primary
sel_primary="wan1"
;;
esac
# Starlink (may be attached to one of the WANs) # Active WAN: determine from routing table (default route interface)
local sl_lat sl_dl sl_obs sl_outage sel_primary="modem_0001"
sl_lat=$(_aiwanbal_val "wan0_starlink_latency") default_iface=$(ip route show default 2>/dev/null | awk '{print $5}' | head -1)
sl_dl=$(_aiwanbal_val "wan0_starlink_quality") if [ "$default_iface" = "$WAN2_IFACE" ]; then
sl_obs=$(_aiwanbal_val "wan0_starlink_obstruction") sel_primary="wan"
sl_outage=$(_aiwanbal_val "wan0_starlink_outage") fi
# Convert Starlink quality to bps (quality is a score 0100, not bps) # Starlink — detect if present
# Store quality as-is; the hub can interpret it sl_lat="null" sl_dl="null" sl_obs="0" sl_outage="0"
local sl_quality # Starlink is typically on a USB ethernet adapter or separate VLAN
sl_quality="${sl_dl:-0}" if ip link show 2>/dev/null | grep -qi starlink; then
# Basic Starlink check — if interface exists, try to get metrics
sl_iface=$(ip link show 2>/dev/null | grep -i starlink | head -1 | awk -F': ' '{print $2}' | awk '{print $1}')
if [ -n "$sl_iface" ]; then
sl_ping=$(_ping_iface "$sl_iface")
sl_lat=$(echo "$sl_ping" | awk '{print $1}')
sl_dl=$(_read_bytes_delta "$sl_iface" "rx_bytes")
fi
fi
# State — autonomous indicator (always true for fleet routers)
state='{"autonomous":true,"qos":{},"wanhealth":{}}'
local esc_id esc_ver esc_sel
esc_id=$(_json_str "$device_id") esc_id=$(_json_str "$device_id")
esc_ver=$(_json_str "$version") esc_ver=$(_json_str "$version")
esc_sel=$(_json_str "$sel_primary") esc_sel=$(_json_str "$sel_primary")
printf '{"device_id":"%s","timestamp":%d,"uptime":%d,"version":"%s","platform":"synology","sel_primary":"%s","gps":{"lat":%s,"lon":%s,"fix":%s},"wan":{"wan1":%s,"wan2":%s},"starlink":{"quality":%s,"latency_ms":%s,"obstructed":%s,"outage":%s}}\n' \ printf '{"device_id":"%s","timestamp":%d,"uptime":%d,"version":"%s","platform":"synology","sel_primary":"%s","active_wan":"%s","gps":{"lat":%s,"lon":%s,"fix":%s},"wan":{"modem_0001":%s,"wan":%s},"sim_slot":null,"starlink":{"latency_ms":%s,"dl_bps":%s,"obstructed":%s,"outage":%s},"state":%s}\n' \
"${esc_id}" "${now:-0}" "${uptime_s:-0}" "${esc_ver}" "${esc_sel}" \ "${esc_id}" "${now:-0}" "${uptime_s:-0}" "${esc_ver}" "${esc_sel}" "${esc_sel}" \
"${gps_lat:-null}" "${gps_lon:-null}" "${gps_fix:-null}" \ "${gps_lat}" "${gps_lon}" "${gps_fix}" \
"${wan1_json}" "${wan2_json}" \ "${wan1_json}" "${wan2_json}" \
"${sl_quality:-0}" "${sl_lat:-null}" "${sl_obs:-0}" "${sl_outage:-0}" "${sl_lat}" "${sl_dl}" "${sl_obs}" "${sl_outage}" \
"${state}"
} }
# ── Hub POST + Buffering ───────────────────────────────────────────────────────── # ── Hub POST + Buffering ───────────────────────────────────────────────────
# POST a JSON file to the hub. Returns 0 on HTTP 2xx, 1 on any failure. # POST a JSON file to the hub. Returns 0 on HTTP 2xx, 1 on any failure.
_telemetry_try_post() { _telemetry_try_post() {
local file="$1" file="$1"
local code
code=$(curl -sf -X POST -H "Content-Type: application/json" \ code=$(curl -sf -X POST -H "Content-Type: application/json" \
--data-binary @"$file" -o /dev/null -w "%{http_code}" \ --data-binary @"$file" -o /dev/null -w "%{http_code}" \
--max-time 10 "$TELEMETRY_HUB" 2>/dev/null) --max-time 10 "$TELEMETRY_HUB" 2>/dev/null)
@@ -283,16 +373,15 @@ _telemetry_try_post() {
# Retry all buffered payloads in timestamp order. # Retry all buffered payloads in timestamp order.
# Stops on first failure to avoid hammering a down hub. # Stops on first failure to avoid hammering a down hub.
telemetry_synology_flush() { telemetry_flush() {
[ -d "$TELEMETRY_BUFFER_DIR" ] || return 0 [ -d "$TELEMETRY_BUFFER_DIR" ] || return 0
local f
for f in "$TELEMETRY_BUFFER_DIR"/*.json; do for f in "$TELEMETRY_BUFFER_DIR"/*.json; do
[ -f "$f" ] || continue [ -f "$f" ] || continue
if _telemetry_try_post "$f"; then if _telemetry_try_post "$f"; then
rm -f "$f" rm -f "$f"
logger -t busrouter -p daemon.debug "telemetry_synology_flush: sent $(basename "$f")" logger -t busrouter -p daemon.debug "telemetry_flush: sent $(basename "$f")"
else else
logger -t busrouter "telemetry_synology_flush: hub unreachable, stopping" logger -t busrouter "telemetry_flush: hub unreachable, stopping"
return 1 return 1
fi fi
done done
@@ -301,20 +390,20 @@ telemetry_synology_flush() {
# Collect metrics, flush old buffer, POST current payload. # Collect metrics, flush old buffer, POST current payload.
# On POST failure: saves payload to TELEMETRY_BUFFER_DIR. # On POST failure: saves payload to TELEMETRY_BUFFER_DIR.
# Never blocks the caller on hub downtime. # Never blocks the caller on hub downtime.
telemetry_synology_send() { telemetry_send() {
local payload mkdir -p "$STATE_DIR" 2>/dev/null
payload=$(telemetry_synology_collect)
telemetry_synology_flush 2>/dev/null || true payload=$(telemetry_collect)
mkdir -p "$TELEMETRY_BUFFER_DIR" telemetry_flush 2>/dev/null || true
mkdir -p "$TELEMETRY_BUFFER_DIR" 2>/dev/null
_TELEM_SEQ=$(( _TELEM_SEQ + 1 )) _TELEM_SEQ=$(( _TELEM_SEQ + 1 ))
local tmpfile="${TELEMETRY_BUFFER_DIR}/$(date +%s)_$$_${_TELEM_SEQ}.json" tmpfile="${TELEMETRY_BUFFER_DIR}/$(date +%s)_$$_${_TELEM_SEQ}.json"
# Cap buffer to 60 files to protect tmpfs # Cap buffer to 60 files to protect tmpfs
local buf_count
buf_count=$(ls "$TELEMETRY_BUFFER_DIR"/*.json 2>/dev/null | wc -l) buf_count=$(ls "$TELEMETRY_BUFFER_DIR"/*.json 2>/dev/null | wc -l)
if [ "${buf_count:-0}" -ge 60 ]; then if [ "${buf_count:-0}" -ge 60 ]; then
local oldest
oldest=$(ls "$TELEMETRY_BUFFER_DIR"/*.json 2>/dev/null | sort | head -n 1) oldest=$(ls "$TELEMETRY_BUFFER_DIR"/*.json 2>/dev/null | sort | head -n 1)
[ -f "$oldest" ] && rm -f "$oldest" [ -f "$oldest" ] && rm -f "$oldest"
fi fi
@@ -322,16 +411,15 @@ telemetry_synology_send() {
if _telemetry_try_post "$tmpfile"; then if _telemetry_try_post "$tmpfile"; then
rm -f "$tmpfile" rm -f "$tmpfile"
logger -t busrouter -p daemon.debug "telemetry_synology_send: posted ok" logger -t busrouter -p daemon.debug "telemetry_send: posted ok"
else else
logger -t busrouter "telemetry_synology_send: hub unreachable, buffered $(basename "$tmpfile")" logger -t busrouter "telemetry_send: hub unreachable, buffered $(basename "$tmpfile")"
fi fi
} }
# ── Entry Point ────────────────────────────────────────────────────────────────── # ── Entry Point ────────────────────────────────────────────────────────────
# When executed directly (e.g. from cron), run a single telemetry cycle.
case "${0##*/}" in case "${0##*/}" in
telemetry-synology.sh|telemetry-synology) telemetry-synology.sh|telemetry-synology)
telemetry_synology_send telemetry_send
;; ;;
esac esac