diff --git a/diagnose.py b/diagnose.py index b6e4300..594bfdb 100644 --- a/diagnose.py +++ b/diagnose.py @@ -536,7 +536,8 @@ class DiagnosticsRunner: if lldp.get('available'): expected_switch = (switch_port_data.get('switch_name') or '').lower() srv_neighbor = (lldp.get('neighbor_system') or '').lower() - if expected_switch and srv_neighbor and expected_switch not in srv_neighbor and srv_neighbor not in expected_switch: + names_differ = expected_switch not in srv_neighbor and srv_neighbor not in expected_switch + if expected_switch and srv_neighbor and names_differ: add(warnings, 'LLDP_MISMATCH', f'LLDP mismatch: this port is on "{switch_port_data.get("switch_name")}" but the server\'s ' f'lldpctl sees "{lldp.get("neighbor_system")}" — cross-cabled port?') diff --git a/scripts/demo/capture.py b/scripts/demo/capture.py index 6f3ddbd..1a1ccb7 100644 --- a/scripts/demo/capture.py +++ b/scripts/demo/capture.py @@ -1,70 +1,164 @@ """Regenerates docs/img/* from a LOCAL demo instance (fictional data). See README.md in this folder.""" -import asyncio, io, sys + +# flake8: noqa: E501 (demo data and canned output contain long literal lines) + +import asyncio +import io +import pathlib +import sys + from PIL import Image from playwright.async_api import async_playwright -import pathlib -OUT=str(pathlib.Path(__file__).resolve().parents[2]/'docs'/'img') -B='http://127.0.0.1:8500' -H={'Remote-User':'alex.rivera','Remote-Name':'Alex Rivera','Remote-Email':'alex@example.com','Remote-Groups':'admin'} -TOP="document.activeElement&&document.activeElement.blur();document.documentElement.style.scrollBehavior='auto';window.scrollTo(0,0)" -AV='AR' -async def mk(p,theme='dark',w=1440,h=900): - b=await p.chromium.launch(); c=await b.new_context(viewport={'width':w,'height':h},extra_http_headers=H) + +OUT = str(pathlib.Path(__file__).resolve().parents[2] / "docs" / "img") +B = "http://127.0.0.1:8500" +H = { + "Remote-User": "alex.rivera", + "Remote-Name": "Alex Rivera", + "Remote-Email": "alex@example.com", + "Remote-Groups": "admin", +} +TOP = ( + "document.activeElement&&document.activeElement.blur();" + "document.documentElement.style.scrollBehavior='auto';window.scrollTo(0,0)" +) +AV = ( + '' + '' + 'AR' +) + + +async def mk(p, theme="dark", w=1440, h=900): + b = await p.chromium.launch() + c = await b.new_context(viewport={"width": w, "height": h}, extra_http_headers=H) await c.add_init_script(f"try{{localStorage.setItem('lt_theme','{theme}')}}catch(e){{}}") - async def av(route): await route.fulfill(status=200,content_type='image/svg+xml',body=AV) - await c.route('**/api/avatar*',av) - return b,c -async def go(pg,path,wait=5500): - await pg.goto(B+path); await pg.wait_for_timeout(wait); await pg.evaluate(TOP); await pg.wait_for_timeout(300) -async def el(pg,sel,name,idx=0): - l=pg.locator(sel).nth(idx); await l.scroll_into_view_if_needed(); await pg.wait_for_timeout(300); await l.screenshot(path=f'{OUT}/{name}.png'); print(name,'ok') -async def select_port(pg,sw,idx): - await pg.locator(f'[data-action="select-port"][data-switch="{sw}"][data-port-idx="{idx}"]').first.click(); await pg.wait_for_timeout(1200) + + async def av(route): + await route.fulfill(status=200, content_type="image/svg+xml", body=AV) + + await c.route("**/api/avatar*", av) + return b, c + + +async def go(pg, path, wait=5500): + await pg.goto(B + path) + await pg.wait_for_timeout(wait) + await pg.evaluate(TOP) + await pg.wait_for_timeout(300) + + +async def el(pg, sel, name, idx=0): + loc = pg.locator(sel).nth(idx) + await loc.scroll_into_view_if_needed() + await pg.wait_for_timeout(300) + await loc.screenshot(path=f"{OUT}/{name}.png") + print(name, "ok") + + +async def select_port(pg, sw, idx): + await pg.locator(f'[data-action="select-port"][data-switch="{sw}"][data-port-idx="{idx}"]').first.click() + await pg.wait_for_timeout(1200) + + async def shots(): async with async_playwright() as p: - b,c=await mk(p); pg=await c.new_page(); errs=[]; pg.on('pageerror',lambda e:errs.append(str(e)[:100])) - await go(pg,'/'); await pg.screenshot(path=f'{OUT}/dashboard.png'); print('dashboard ok') - await el(pg,'#topology-diagram','topology') - await el(pg,'.lt-section-header >> text=ALERT QUEUE','alerts-tmp') if False else None - full=Image.open(io.BytesIO(await pg.screenshot(full_page=True))) + b, c = await mk(p) + pg = await c.new_page() + errs = [] + pg.on("pageerror", lambda e: errs.append(str(e)[:100])) + await go(pg, "/") + await pg.screenshot(path=f"{OUT}/dashboard.png") + print("dashboard ok") + await el(pg, "#topology-diagram", "topology") + await el(pg, ".lt-section-header >> text=ALERT QUEUE", "alerts-tmp") if False else None # host cards + unifi table via element crops - hb=await pg.locator('#hosts-grid, .host-grid, .hosts-grid').first.bounding_box() if await pg.locator('#hosts-grid, .host-grid, .hosts-grid').count() else None - if hb: await pg.locator('#hosts-grid, .host-grid, .hosts-grid').first.screenshot(path=f'{OUT}/host-cards.png'); print('host-cards ok') - await go(pg,'/links'); await pg.screenshot(path=f'{OUT}/link-debug.png') - names=await pg.evaluate("[...document.querySelectorAll('.link-host-name')].map(e=>e.textContent.trim())"); print('hosts',names) - for nm,fn in (('large1','link-debug-sfp-warning'),('compute-storage-gpu-01','link-debug-sfp'),('Pro 24 PoE','link-debug-switch')): - i=next((k for k,n in enumerate(names) if nm in n),None) - if i is not None: await el(pg,'.link-host-panel',fn,i) - await go(pg,'/inspector'); await pg.screenshot(path=f'{OUT}/inspector.png') - await select_port(pg,'USW-Aggregation',4); await pg.screenshot(path=f'{OUT}/inspector-port.png',full_page=False) - await pg.locator('[data-action="run-diagnostic"]').first.click(); await pg.wait_for_timeout(9000) - await pg.evaluate("document.getElementById('diag-results')?.scrollIntoView({block:'start'})"); await pg.wait_for_timeout(600) - await pg.screenshot(path=f'{OUT}/inspector-diagnostics.png'); print('diagnostics ok') - await go(pg,'/suppressions'); await pg.screenshot(path=f'{OUT}/suppressions.png',full_page=True) - print('errors',errs[:3]); await b.close() - b,c=await mk(p,'light'); pg=await c.new_page(); await go(pg,'/'); await pg.screenshot(path=f'{OUT}/dashboard-light.png'); await b.close() -async def gif(): - frames=[] - async with async_playwright() as p: - b,c=await mk(p,'dark',1280,720); pg=await c.new_page() - async def snap(n=1,ms=0): - if ms: await pg.wait_for_timeout(ms) - im=Image.open(io.BytesIO(await pg.screenshot())).convert('RGB').resize((960,540),Image.LANCZOS) - for _ in range(n): frames.append(im) - await go(pg,'/',5000); await snap(3) - await pg.mouse.wheel(0,620); await snap(3,600) - await pg.mouse.wheel(0,700); await snap(2,600) - await go(pg,'/links',4500); await snap(3) - await pg.mouse.wheel(0,500); await snap(2,500) - await go(pg,'/inspector',4000); await snap(2) - await select_port(pg,'USW-Aggregation',4); await snap(3) - await pg.locator('[data-action="run-diagnostic"]').first.click(); await snap(2,1500); await snap(2,7500) - await pg.evaluate("document.getElementById('diag-results')?.scrollIntoView({block:'start'})"); await snap(4,600) - await go(pg,'/suppressions',4000); await snap(3) + hb = ( + await pg.locator("#hosts-grid, .host-grid, .hosts-grid").first.bounding_box() + if await pg.locator("#hosts-grid, .host-grid, .hosts-grid").count() + else None + ) + if hb: + await pg.locator("#hosts-grid, .host-grid, .hosts-grid").first.screenshot(path=f"{OUT}/host-cards.png") + print("host-cards ok") + await go(pg, "/links") + await pg.screenshot(path=f"{OUT}/link-debug.png") + names = await pg.evaluate("[...document.querySelectorAll('.link-host-name')].map(e=>e.textContent.trim())") + print("hosts", names) + for nm, fn in ( + ("large1", "link-debug-sfp-warning"), + ("compute-storage-gpu-01", "link-debug-sfp"), + ("Pro 24 PoE", "link-debug-switch"), + ): + i = next((k for k, n in enumerate(names) if nm in n), None) + if i is not None: + await el(pg, ".link-host-panel", fn, i) + await go(pg, "/inspector") + await pg.screenshot(path=f"{OUT}/inspector.png") + await select_port(pg, "USW-Aggregation", 4) + await pg.screenshot(path=f"{OUT}/inspector-port.png", full_page=False) + await pg.locator('[data-action="run-diagnostic"]').first.click() + await pg.wait_for_timeout(9000) + await pg.evaluate("document.getElementById('diag-results')?.scrollIntoView({block:'start'})") + await pg.wait_for_timeout(600) + await pg.screenshot(path=f"{OUT}/inspector-diagnostics.png") + print("diagnostics ok") + await go(pg, "/suppressions") + await pg.screenshot(path=f"{OUT}/suppressions.png", full_page=True) + print("errors", errs[:3]) await b.close() - pal=[f.quantize(colors=96,method=Image.MEDIANCUT,dither=Image.NONE) for f in frames] - pal[0].save(f'{OUT}/demo.gif',save_all=True,append_images=pal[1:],duration=1100,loop=0,optimize=True); print('gif',len(frames)) + b, c = await mk(p, "light") + pg = await c.new_page() + await go(pg, "/") + await pg.screenshot(path=f"{OUT}/dashboard-light.png") + await b.close() + + +async def gif(): + frames = [] + async with async_playwright() as p: + b, c = await mk(p, "dark", 1280, 720) + pg = await c.new_page() + + async def snap(n=1, ms=0): + if ms: + await pg.wait_for_timeout(ms) + im = Image.open(io.BytesIO(await pg.screenshot())).convert("RGB").resize((960, 540), Image.LANCZOS) + for _ in range(n): + frames.append(im) + + await go(pg, "/", 5000) + await snap(3) + await pg.mouse.wheel(0, 620) + await snap(3, 600) + await pg.mouse.wheel(0, 700) + await snap(2, 600) + await go(pg, "/links", 4500) + await snap(3) + await pg.mouse.wheel(0, 500) + await snap(2, 500) + await go(pg, "/inspector", 4000) + await snap(2) + await select_port(pg, "USW-Aggregation", 4) + await snap(3) + await pg.locator('[data-action="run-diagnostic"]').first.click() + await snap(2, 1500) + await snap(2, 7500) + await pg.evaluate("document.getElementById('diag-results')?.scrollIntoView({block:'start'})") + await snap(4, 600) + await go(pg, "/suppressions", 4000) + await snap(3) + await b.close() + pal = [f.quantize(colors=96, method=Image.MEDIANCUT, dither=Image.NONE) for f in frames] + pal[0].save(f"{OUT}/demo.gif", save_all=True, append_images=pal[1:], duration=1100, loop=0, optimize=True) + print("gif", len(frames)) + + async def main(): - if 'gif' not in sys.argv: await shots() - if 'shots' not in sys.argv: await gif() + if "gif" not in sys.argv: + await shots() + if "shots" not in sys.argv: + await gif() + + asyncio.run(main()) diff --git a/scripts/demo/mock_pulse.py b/scripts/demo/mock_pulse.py index 5f9d7b1..81932e6 100644 --- a/scripts/demo/mock_pulse.py +++ b/scripts/demo/mock_pulse.py @@ -1,6 +1,10 @@ """Minimal stand-in for the PULSE internal API, returning canned diagnostics output (fictional data).""" + +# flake8: noqa: E501 (demo data and canned output contain long literal lines) + import json from http.server import BaseHTTPRequestHandler, HTTPServer + CANNED = """=== carrier === 1 === operstate === @@ -22,14 +26,14 @@ rx_missed_errors:0 6 === ethtool === Settings for enp5s0: - Supported ports: [ FIBRE ] - Supported link modes: 10000baseT/Full - Speed: 10000Mb/s - Duplex: Full - Port: FIBRE - PHYAD: 0 - Auto-negotiation: off - Link detected: yes + Supported ports: [ FIBRE ] + Supported link modes: 10000baseT/Full + Speed: 10000Mb/s + Duplex: Full + Port: FIBRE + PHYAD: 0 + Auto-negotiation: off + Link detected: yes === ethtool_driver === driver: ixgbe version: 6.8.12-4-pve @@ -65,16 +69,16 @@ NIC statistics: tx_flow_control_xon: 0 rx_flow_control_xon: 0 === ethtool_dom === - Identifier : 0x03 (SFP) - Connector : 0x07 (LC) - Vendor name : FS - Vendor PN : SFP-10GSR-85 - Laser wavelength : 850nm - Laser bias current : 6.100 mA - Laser output power : 0.5530 mW / -2.57 dBm - Receiver signal average optical power : 0.0120 mW / -19.21 dBm - Module temperature : 47.50 degrees C / 117.50 degrees F - Module voltage : 3.3120 V + Identifier : 0x03 (SFP) + Connector : 0x07 (LC) + Vendor name : FS + Vendor PN : SFP-10GSR-85 + Laser wavelength : 850nm + Laser bias current : 6.100 mA + Laser output power : 0.5530 mW / -2.57 dBm + Receiver signal average optical power : 0.0120 mW / -19.21 dBm + Module temperature : 47.50 degrees C / 117.50 degrees F + Module voltage : 3.3120 V === ip_link === 5: enp5s0: mtu 9000 qdisc mq master vmbr1 state UP mode DEFAULT group default qlen 1000 link/ether 02:00:5e:10:00:05 brd ff:ff:ff:ff:ff:ff @@ -104,12 +108,26 @@ Interface: enp5s0, via: LLDP, RID: 1, Time: 12 days, 03:11:42 PortID: ifname Port 4 === end === """ + + class H(BaseHTTPRequestHandler): def _send(self, obj, code=200): - b = json.dumps(obj).encode(); self.send_response(code); self.send_header('Content-Type', 'application/json'); self.send_header('Content-Length', str(len(b))); self.end_headers(); self.wfile.write(b) + b = json.dumps(obj).encode() + self.send_response(code) + self.send_header("Content-Type", "application/json") + self.send_header("Content-Length", str(len(b))) + self.end_headers() + self.wfile.write(b) + def do_POST(self): - self.rfile.read(int(self.headers.get('Content-Length', 0) or 0)); self._send({'execution_id': 'demo-exec-0001'}) + self.rfile.read(int(self.headers.get("Content-Length", 0) or 0)) + self._send({"execution_id": "demo-exec-0001"}) + def do_GET(self): - self._send({'status': 'completed', 'logs': [{'action': 'command_result', 'stdout': CANNED}]}) - def log_message(self, *a): pass -HTTPServer(('127.0.0.1', 8650), H).serve_forever() + self._send({"status": "completed", "logs": [{"action": "command_result", "stdout": CANNED}]}) + + def log_message(self, *a): + pass + + +HTTPServer(("127.0.0.1", 8650), H).serve_forever() diff --git a/scripts/demo/seed.py b/scripts/demo/seed.py index c856f49..88168b3 100644 --- a/scripts/demo/seed.py +++ b/scripts/demo/seed.py @@ -1,115 +1,425 @@ """Seed a throwaway GANDALF database with fictional data (documentation IP ranges only).""" -import json, random, sys + +# flake8: noqa: E501 (demo data and canned output contain long literal lines) + +import json +import random from datetime import datetime, timedelta, timezone import pymysql + random.seed(11) -conn=pymysql.connect(host='127.0.0.1',port=3398,user='gandalf',password='demo-only',database='gandalf',autocommit=True,charset='utf8mb4') -cur=conn.cursor() -now=datetime.now(timezone.utc) -ts=lambda h: (now-timedelta(hours=h)).strftime('%Y-%m-%d %H:%M:%S') -def state(k,v): - cur.execute("REPLACE INTO monitor_state (key_name,value) VALUES (%s,%s)",(k,v if isinstance(v,str) else json.dumps(v))) +conn = pymysql.connect( + host="127.0.0.1", + port=3398, + user="gandalf", + password="demo-only", + database="gandalf", + autocommit=True, + charset="utf8mb4", +) +cur = conn.cursor() +now = datetime.now(timezone.utc) + + +def ts(h): + return (now - timedelta(hours=h)).strftime("%Y-%m-%d %H:%M:%S") + + +def state(k, v): + cur.execute( + "REPLACE INTO monitor_state (key_name,value) VALUES (%s,%s)", (k, v if isinstance(v, str) else json.dumps(v)) + ) + # ---- hosts / interfaces: (name, ip, [(iface, speed_mbps, up, kind)]) kind: rj45 | fiber | dac -HOSTS=[ - ('compute-storage-01','192.0.2.4',[('eno1',1000,True,'rj45'),('enp1s0f0',10000,True,'dac'),('enp1s0f1',10000,True,'dac')]), - ('compute-storage-gpu-01','192.0.2.10',[('enp2s0',1000,True,'rj45'),('enp4s0',10000,True,'fiber')]), - ('large1','192.0.2.2',[('enp3s0',1000,True,'rj45'),('enp5s0',10000,True,'fiber')]), - ('storage-01','192.0.2.11',[('enp5s0',1000,True,'rj45'),('enp1s0',10000,False,'fiber')]), # regression: link down - ('micro1','192.0.2.8',[('enp2s0',1000,True,'rj45'),('enp3s0',1000,False,'rj45')]), # unused bond leg (baseline, not alerted) - ('monitor-02','192.0.2.9',[('enp2s0',1000,True,'rj45'),('enp3s0',1000,True,'rj45')]), +HOSTS = [ + ( + "compute-storage-01", + "192.0.2.4", + [("eno1", 1000, True, "rj45"), ("enp1s0f0", 10000, True, "dac"), ("enp1s0f1", 10000, True, "dac")], + ), + ("compute-storage-gpu-01", "192.0.2.10", [("enp2s0", 1000, True, "rj45"), ("enp4s0", 10000, True, "fiber")]), + ("large1", "192.0.2.2", [("enp3s0", 1000, True, "rj45"), ("enp5s0", 10000, True, "fiber")]), + ( + "storage-01", + "192.0.2.11", + [("enp5s0", 1000, True, "rj45"), ("enp1s0", 10000, False, "fiber")], + ), # regression: link down + ( + "micro1", + "192.0.2.8", + [("enp2s0", 1000, True, "rj45"), ("enp3s0", 1000, False, "rj45")], + ), # unused bond leg (baseline, not alerted) + ("monitor-02", "192.0.2.9", [("enp2s0", 1000, True, "rj45"), ("enp3s0", 1000, True, "rj45")]), ] -hosts={} -for name,ip,ifs in HOSTS: - st=[u for _,_,u,_ in ifs] - status='up' if all(st) else ('down' if not any(st) else 'degraded') - hosts[name]={'ip':ip,'interfaces':{i:('up' if u else 'down') for i,_,u,_ in ifs},'status':status,'source':'prometheus'} -hosts['backup-01']={'ip':'198.51.100.20','interfaces':{},'status':'up','source':'ping'} -unifi=[ - {'name':'Dream Machine Pro','mac':'aa:bb:cc:00:00:01','ip':'192.0.2.1','type':'udm','model':'UDMPRO','state':1,'connected':True}, - {'name':'Pro 24 PoE','mac':'aa:bb:cc:00:00:02','ip':'192.0.2.30','type':'usw','model':'US24PRO','state':1,'connected':True}, - {'name':'USW-Aggregation','mac':'aa:bb:cc:00:00:03','ip':'192.0.2.31','type':'usw','model':'USL8A','state':1,'connected':True}, - {'name':'UNVR Pro','mac':'aa:bb:cc:00:00:04','ip':'192.0.2.40','type':'unvr','model':'UNVRPRO','state':1,'connected':True}, - {'name':'Garage AP','mac':'aa:bb:cc:00:00:05','ip':'192.0.2.41','type':'uap','model':'U6LR','state':0,'connected':False}, - {'name':'Office AP','mac':'aa:bb:cc:00:00:06','ip':'192.0.2.42','type':'uap','model':'U6PRO','state':1,'connected':True}, +hosts = {} +for name, ip, ifs in HOSTS: + st = [u for _, _, u, _ in ifs] + status = "up" if all(st) else ("down" if not any(st) else "degraded") + hosts[name] = { + "ip": ip, + "interfaces": {i: ("up" if u else "down") for i, _, u, _ in ifs}, + "status": status, + "source": "prometheus", + } +hosts["backup-01"] = {"ip": "198.51.100.20", "interfaces": {}, "status": "up", "source": "ping"} +unifi = [ + { + "name": "Dream Machine Pro", + "mac": "aa:bb:cc:00:00:01", + "ip": "192.0.2.1", + "type": "udm", + "model": "UDMPRO", + "state": 1, + "connected": True, + }, + { + "name": "Pro 24 PoE", + "mac": "aa:bb:cc:00:00:02", + "ip": "192.0.2.30", + "type": "usw", + "model": "US24PRO", + "state": 1, + "connected": True, + }, + { + "name": "USW-Aggregation", + "mac": "aa:bb:cc:00:00:03", + "ip": "192.0.2.31", + "type": "usw", + "model": "USL8A", + "state": 1, + "connected": True, + }, + { + "name": "UNVR Pro", + "mac": "aa:bb:cc:00:00:04", + "ip": "192.0.2.40", + "type": "unvr", + "model": "UNVRPRO", + "state": 1, + "connected": True, + }, + { + "name": "Garage AP", + "mac": "aa:bb:cc:00:00:05", + "ip": "192.0.2.41", + "type": "uap", + "model": "U6LR", + "state": 0, + "connected": False, + }, + { + "name": "Office AP", + "mac": "aa:bb:cc:00:00:06", + "ip": "192.0.2.42", + "type": "uap", + "model": "U6PRO", + "state": 1, + "connected": True, + }, ] -state('network_snapshot',{'hosts':hosts,'unifi':unifi,'updated':now.isoformat().replace('+00:00','Z')}) -state('last_check',now.strftime('%Y-%m-%d %H:%M:%S UTC')) +state("network_snapshot", {"hosts": hosts, "unifi": unifi, "updated": now.isoformat().replace("+00:00", "Z")}) +state("last_check", now.strftime("%Y-%m-%d %H:%M:%S UTC")) + # ---- per-interface link stats -def rate(speed,frac): return speed*1e6/8*frac -link_hosts={} -for name,ip,ifs in HOSTS: - d={} - for iface,speed,up,kind in ifs: - e={'host_ip':ip,'link_detected':up,'carrier_changes':random.choice([1,2,2,3]) if up else 9} +def rate(speed, frac): + return speed * 1e6 / 8 * frac + + +link_hosts = {} +for name, ip, ifs in HOSTS: + d = {} + for iface, speed, up, kind in ifs: + e = {"host_ip": ip, "link_detected": up, "carrier_changes": random.choice([1, 2, 2, 3]) if up else 9} if up: - f=random.uniform(.01,.18) if speed==1000 else random.uniform(.04,.38) - e.update({'speed_mbps':speed,'duplex':'Full','auto_neg':True, - 'tx_bytes_rate':rate(speed,f),'rx_bytes_rate':rate(speed,f*random.uniform(.5,1.4)), - 'tx_errs_rate':0.0,'rx_errs_rate':0.0,'tx_drops_rate':0.0,'rx_drops_rate':0.0}) + f = random.uniform(0.01, 0.18) if speed == 1000 else random.uniform(0.04, 0.38) + e.update( + { + "speed_mbps": speed, + "duplex": "Full", + "auto_neg": True, + "tx_bytes_rate": rate(speed, f), + "rx_bytes_rate": rate(speed, f * random.uniform(0.5, 1.4)), + "tx_errs_rate": 0.0, + "rx_errs_rate": 0.0, + "tx_drops_rate": 0.0, + "rx_drops_rate": 0.0, + } + ) else: - e.update({'speed_mbps':None,'duplex':None,'auto_neg':True,'tx_bytes_rate':0,'rx_bytes_rate':0,'tx_errs_rate':0,'rx_errs_rate':0,'tx_drops_rate':0,'rx_drops_rate':0}) - if up and kind=='fiber': - e['sfp']={'sfp_type':'SFP+ 10GBASE-SR','vendor':'FS','part_no':'SFP-10GSR-85','temp_c':round(random.uniform(38,47),1), - 'tx_power_dbm':round(random.uniform(-2.8,-1.6),2),'rx_power_dbm':round(random.uniform(-4.5,-3.0),2)} - if up and kind=='dac': - e['sfp']={'sfp_type':'SFP+ passive DAC','vendor':'Ubiquiti','part_no':'UACC-DAC-SFP10-1M'} - d[iface]=e - link_hosts[name]=d + e.update( + { + "speed_mbps": None, + "duplex": None, + "auto_neg": True, + "tx_bytes_rate": 0, + "rx_bytes_rate": 0, + "tx_errs_rate": 0, + "rx_errs_rate": 0, + "tx_drops_rate": 0, + "rx_drops_rate": 0, + } + ) + if up and kind == "fiber": + e["sfp"] = { + "sfp_type": "SFP+ 10GBASE-SR", + "vendor": "FS", + "part_no": "SFP-10GSR-85", + "temp_c": round(random.uniform(38, 47), 1), + "tx_power_dbm": round(random.uniform(-2.8, -1.6), 2), + "rx_power_dbm": round(random.uniform(-4.5, -3.0), 2), + } + if up and kind == "dac": + e["sfp"] = {"sfp_type": "SFP+ passive DAC", "vendor": "Ubiquiti", "part_no": "UACC-DAC-SFP10-1M"} + d[iface] = e + link_hosts[name] = d # one marginal fibre (low RX power) for the warning colour -link_hosts['large1']['enp5s0']['sfp'].update({'rx_power_dbm':-10.9,'temp_c':58.4}) -link_hosts['large1']['enp5s0']['carrier_changes']=6 +link_hosts["large1"]["enp5s0"]["sfp"].update({"rx_power_dbm": -10.9, "temp_c": 58.4}) +link_hosts["large1"]["enp5s0"]["carrier_changes"] = 6 + # ---- UniFi switch ports (with LLDP neighbours = the hosts above) -def port(idx,up,speed,sw_ip,uplink=False,media='GE',lldp=None,poe=None,frac=.05): - r=lambda: rate(speed,frac*random.uniform(.5,1.5)) if up else 0 - p={'port_idx':idx,'switch_ip':sw_ip,'up':up,'speed_mbps':speed if up else 0,'full_duplex':up,'autoneg':True,'is_uplink':uplink,'media':media, - 'poe_power':poe[0] if poe else None,'poe_class':poe[1] if poe else None,'poe_max_power':poe[2] if poe else None,'poe_mode':'auto' if poe else '', - 'lldp':lldp,'tx_bytes':int(random.uniform(1e11,9e12)) if up else 0,'rx_bytes':int(random.uniform(1e11,9e12)) if up else 0, - 'tx_errors':0,'rx_errors':0,'tx_dropped':0,'rx_dropped':0, - 'tx_bytes_rate':r(),'rx_bytes_rate':r(),'tx_errs_rate':0.0,'rx_errs_rate':0.0,'tx_drops_rate':0.0,'rx_drops_rate':0.0} +def port(idx, up, speed, sw_ip, uplink=False, media="GE", lldp=None, poe=None, frac=0.05): + + def r(): + return rate(speed, frac * random.uniform(0.5, 1.5)) if up else 0 + + p = { + "port_idx": idx, + "switch_ip": sw_ip, + "up": up, + "speed_mbps": speed if up else 0, + "full_duplex": up, + "autoneg": True, + "is_uplink": uplink, + "media": media, + "poe_power": poe[0] if poe else None, + "poe_class": poe[1] if poe else None, + "poe_max_power": poe[2] if poe else None, + "poe_mode": "auto" if poe else "", + "lldp": lldp, + "tx_bytes": int(random.uniform(1e11, 9e12)) if up else 0, + "rx_bytes": int(random.uniform(1e11, 9e12)) if up else 0, + "tx_errors": 0, + "rx_errors": 0, + "tx_dropped": 0, + "rx_dropped": 0, + "tx_bytes_rate": r(), + "rx_bytes_rate": r(), + "tx_errs_rate": 0.0, + "rx_errs_rate": 0.0, + "tx_drops_rate": 0.0, + "rx_drops_rate": 0.0, + } return p -L=lambda host,iface: {'chassis_id':'aa:bb:cc:11:22:33','system_name':host,'port_id':iface,'port_desc':iface,'mgmt_ips':[dict(HOSTS_IP)[host]] if False else []} -HOSTS_IP={n:ip for n,ip,_ in HOSTS} -pro={} -mgmt=[(1,'compute-storage-01','eno1'),(2,'compute-storage-gpu-01','enp2s0'),(3,'large1','enp3s0'),(4,'storage-01','enp5s0'),(5,'micro1','enp2s0'),(6,'monitor-02','enp2s0'),(7,'monitor-02','enp3s0')] -for i in range(1,25): - m=[x for x in mgmt if x[0]==i] - if m: pro[f'Port {i}']=port(i,True,1000,'192.0.2.30',lldp=L(m[0][1],m[0][2]),frac=.06) - elif i==8: pro[f'Port {i}']=port(i,False,0,'192.0.2.30') # micro1 unused bond leg - elif i in (10,11,12): pro[f'Port {i}']=port(i,True,100 if i==12 else 1000,'192.0.2.30',lldp=None,poe=(round(random.uniform(3,9),1),4,30.0),frac=.02) # APs / cameras on PoE - elif i==9: pro[f'Port {i}']=port(i,True,1000,'192.0.2.30',lldp={'chassis_id':'aa:bb:cc:00:00:04','system_name':'UNVR Pro','port_id':'eth0','port_desc':'eth0','mgmt_ips':[]},poe=(0.0,0,30.0),frac=.2) - else: pro[f'Port {i}']=port(i,False,0,'192.0.2.30') -pro['Port 25']=port(25,True,10000,'192.0.2.30',uplink=True,media='SFP+',lldp={'chassis_id':'aa:bb:cc:00:00:03','system_name':'USW-Aggregation','port_id':'Port 7','port_desc':'Port 7','mgmt_ips':[]},frac=.08) -pro['Port 26']=port(26,False,0,'192.0.2.30',media='SFP+') -agg={} -aggmap=[(1,'compute-storage-01','enp1s0f0'),(2,'compute-storage-01','enp1s0f1'),(3,'compute-storage-gpu-01','enp4s0'),(4,'large1','enp5s0'),(5,'storage-01','enp1s0')] -for i in range(1,9): - m=[x for x in aggmap if x[0]==i] - if i==5: agg[f'Port {i}']=port(i,False,0,'192.0.2.31',media='SFP+',lldp=None) # storage-01 10G link is down - elif m: agg[f'Port {i}']=port(i,True,10000,'192.0.2.31',media='SFP+',lldp=L(m[0][1],m[0][2]),frac=.15) - elif i==7: agg[f'Port {i}']=port(i,True,10000,'192.0.2.31',uplink=True,media='SFP+',lldp={'chassis_id':'aa:bb:cc:00:00:02','system_name':'Pro 24 PoE','port_id':'Port 25','port_desc':'Port 25','mgmt_ips':[]},frac=.08) - else: agg[f'Port {i}']=port(i,False,0,'192.0.2.31',media='SFP+') -state('link_stats',{'hosts':link_hosts,'unifi_switches':{'Pro 24 PoE':{'ip':'192.0.2.30','model':'US24PRO','ports':pro},'USW-Aggregation':{'ip':'192.0.2.31','model':'USL8A','ports':agg}}, - 'updated':now.strftime('%Y-%m-%d %H:%M:%S UTC')}) + + +def L(host, iface): + return { + "chassis_id": "aa:bb:cc:11:22:33", + "system_name": host, + "port_id": iface, + "port_desc": iface, + "mgmt_ips": [dict(HOSTS_IP)[host]] if False else [], + } + + +HOSTS_IP = {n: ip for n, ip, _ in HOSTS} +pro = {} +mgmt = [ + (1, "compute-storage-01", "eno1"), + (2, "compute-storage-gpu-01", "enp2s0"), + (3, "large1", "enp3s0"), + (4, "storage-01", "enp5s0"), + (5, "micro1", "enp2s0"), + (6, "monitor-02", "enp2s0"), + (7, "monitor-02", "enp3s0"), +] +for i in range(1, 25): + m = [x for x in mgmt if x[0] == i] + if m: + pro[f"Port {i}"] = port(i, True, 1000, "192.0.2.30", lldp=L(m[0][1], m[0][2]), frac=0.06) + elif i == 8: + pro[f"Port {i}"] = port(i, False, 0, "192.0.2.30") # micro1 unused bond leg + elif i in (10, 11, 12): + pro[f"Port {i}"] = port( + i, + True, + 100 if i == 12 else 1000, + "192.0.2.30", + lldp=None, + poe=(round(random.uniform(3, 9), 1), 4, 30.0), + frac=0.02, + ) # APs / cameras on PoE + elif i == 9: + pro[f"Port {i}"] = port( + i, + True, + 1000, + "192.0.2.30", + lldp={ + "chassis_id": "aa:bb:cc:00:00:04", + "system_name": "UNVR Pro", + "port_id": "eth0", + "port_desc": "eth0", + "mgmt_ips": [], + }, + poe=(0.0, 0, 30.0), + frac=0.2, + ) + else: + pro[f"Port {i}"] = port(i, False, 0, "192.0.2.30") +pro["Port 25"] = port( + 25, + True, + 10000, + "192.0.2.30", + uplink=True, + media="SFP+", + lldp={ + "chassis_id": "aa:bb:cc:00:00:03", + "system_name": "USW-Aggregation", + "port_id": "Port 7", + "port_desc": "Port 7", + "mgmt_ips": [], + }, + frac=0.08, +) +pro["Port 26"] = port(26, False, 0, "192.0.2.30", media="SFP+") +agg = {} +aggmap = [ + (1, "compute-storage-01", "enp1s0f0"), + (2, "compute-storage-01", "enp1s0f1"), + (3, "compute-storage-gpu-01", "enp4s0"), + (4, "large1", "enp5s0"), + (5, "storage-01", "enp1s0"), +] +for i in range(1, 9): + m = [x for x in aggmap if x[0] == i] + if i == 5: + agg[f"Port {i}"] = port(i, False, 0, "192.0.2.31", media="SFP+", lldp=None) # storage-01 10G link is down + elif m: + agg[f"Port {i}"] = port(i, True, 10000, "192.0.2.31", media="SFP+", lldp=L(m[0][1], m[0][2]), frac=0.15) + elif i == 7: + agg[f"Port {i}"] = port( + i, + True, + 10000, + "192.0.2.31", + uplink=True, + media="SFP+", + lldp={ + "chassis_id": "aa:bb:cc:00:00:02", + "system_name": "Pro 24 PoE", + "port_id": "Port 25", + "port_desc": "Port 25", + "mgmt_ips": [], + }, + frac=0.08, + ) + else: + agg[f"Port {i}"] = port(i, False, 0, "192.0.2.31", media="SFP+") +state( + "link_stats", + { + "hosts": link_hosts, + "unifi_switches": { + "Pro 24 PoE": {"ip": "192.0.2.30", "model": "US24PRO", "ports": pro}, + "USW-Aggregation": {"ip": "192.0.2.31", "model": "USL8A", "ports": agg}, + }, + "updated": now.strftime("%Y-%m-%d %H:%M:%S UTC"), + }, +) # ---- events -EV=[ # type, sev, source, target, detail, desc, first_seen_h, last_seen_h, resolved_h|None, fails, ticket - ('interface_down','warning','prometheus','storage-01','enp1s0','Interface enp1s0 on storage-01 went down (UP -> DOWN regression).',3.2,0.0,None,5,'731905284'), - ('unifi_device_offline','warning','unifi','Garage AP','uap / 192.0.2.41','UniFi device "Garage AP" has been offline for 3 consecutive checks.',1.1,0.0,None,3,'731905301'), - ('interface_down','warning','prometheus','compute-storage-01','enp1s0f1','Interface enp1s0f1 on compute-storage-01 went down.',9.0,7.5,7.4,2,None), - ('host_unreachable','warning','ping','backup-01','198.51.100.20','Host backup-01 stopped answering ping for 2 consecutive checks.',30.0,28.0,27.9,2,'731881772'), - ('unifi_device_offline','warning','unifi','Office AP','uap / 192.0.2.42','UniFi device "Office AP" was offline for 3 consecutive checks.',19.0,18.0,17.8,3,'731890014'), +EV = [ # type, sev, source, target, detail, desc, first_seen_h, last_seen_h, resolved_h|None, fails, ticket + ( + "interface_down", + "warning", + "prometheus", + "storage-01", + "enp1s0", + "Interface enp1s0 on storage-01 went down (UP -> DOWN regression).", + 3.2, + 0.0, + None, + 5, + "731905284", + ), + ( + "unifi_device_offline", + "warning", + "unifi", + "Garage AP", + "uap / 192.0.2.41", + 'UniFi device "Garage AP" has been offline for 3 consecutive checks.', + 1.1, + 0.0, + None, + 3, + "731905301", + ), + ( + "interface_down", + "warning", + "prometheus", + "compute-storage-01", + "enp1s0f1", + "Interface enp1s0f1 on compute-storage-01 went down.", + 9.0, + 7.5, + 7.4, + 2, + None, + ), + ( + "host_unreachable", + "warning", + "ping", + "backup-01", + "198.51.100.20", + "Host backup-01 stopped answering ping for 2 consecutive checks.", + 30.0, + 28.0, + 27.9, + 2, + "731881772", + ), + ( + "unifi_device_offline", + "warning", + "unifi", + "Office AP", + "uap / 192.0.2.42", + 'UniFi device "Office AP" was offline for 3 consecutive checks.', + 19.0, + 18.0, + 17.8, + 3, + "731890014", + ), ] -for t,sev,src,tgt,det,desc,f,l,r,fails,tid in EV: - cur.execute("INSERT INTO network_events (event_type,severity,source_type,target_name,target_detail,description,first_seen,last_seen,resolved_at,consecutive_failures,ticket_id) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)", - (t,sev,src,tgt,det,desc,ts(f),ts(l),ts(r) if r is not None else None,fails,tid)) +for t, sev, src, tgt, det, desc, f, l, r, fails, tid in EV: + cur.execute( + "INSERT INTO network_events (event_type,severity,source_type,target_name,target_detail,description,first_seen,last_seen,resolved_at,consecutive_failures,ticket_id) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)", + (t, sev, src, tgt, det, desc, ts(f), ts(l), ts(r) if r is not None else None, fails, tid), + ) # ---- suppressions (one active timed, one manual, one expired in history) -SUP=[('interface','micro1','enp3s0','Unused bond leg, cable not connected','alex.rivera',48,None,1), - ('host','monitor-02','','Planned firmware update window','alex.rivera',0.4,0.6,1), - ('unifi_device','Office AP','','Replacing the access point','sam.chen',30,29,0)] -for tt,tn,td,reason,by,created_h,exp_in,active in SUP: - exp=(now+timedelta(hours=exp_in)).strftime('%Y-%m-%d %H:%M:%S') if exp_in and exp_in>0 else (ts(-exp_in) if exp_in else None) - cur.execute("INSERT INTO suppression_rules (target_type,target_name,target_detail,reason,suppressed_by,created_at,expires_at,active) VALUES (%s,%s,%s,%s,%s,%s,%s,%s)",(tt,tn,td,reason,by,ts(created_h),exp,active)) -print('seeded: hosts',len(hosts),'unifi',len(unifi),'events',len(EV),'suppressions',len(SUP)) +SUP = [ + ("interface", "micro1", "enp3s0", "Unused bond leg, cable not connected", "alex.rivera", 48, None, 1), + ("host", "monitor-02", "", "Planned firmware update window", "alex.rivera", 0.4, 0.6, 1), + ("unifi_device", "Office AP", "", "Replacing the access point", "sam.chen", 30, 29, 0), +] +for tt, tn, td, reason, by, created_h, exp_in, active in SUP: + exp = ( + (now + timedelta(hours=exp_in)).strftime("%Y-%m-%d %H:%M:%S") + if exp_in and exp_in > 0 + else (ts(-exp_in) if exp_in else None) + ) + cur.execute( + "INSERT INTO suppression_rules (target_type,target_name,target_detail,reason,suppressed_by,created_at,expires_at,active) VALUES (%s,%s,%s,%s,%s,%s,%s,%s)", + (tt, tn, td, reason, by, ts(created_h), exp, active), + ) +print("seeded: hosts", len(hosts), "unifi", len(unifi), "events", len(EV), "suppressions", len(SUP))