KNEL/PFVCluster
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(oam): deploy Smokeping, NetDisco, Oxidized, UNPoller on tsys-librenms [#337][#375]

Browse Source 
Deploy OAM monitoring stack on tsys-librenms VM:

- Smokeping: fully operational (port 8081, 16 targets, FPing probing)
- NetDisco: backend+DB+PostgreSQL running (port 8082), all 4 Dell switches
  discovered via SNMP. Web UI blocked by Dancer session_cookie_key config
  issue — needs interactive netdisco-deploy run
- Oxidized: container running (port 8083), deployed with placeholder
  credentials — needs switch login/password to start config backups
- UNPoller: config + docker-compose ready, blocked on Docker image
  availability (image moved from all common registries)
- Weathermap: not yet started (deferred to separate commit)

All configs use DNS names only (no IP literals). All scripts pass
shellcheck via check-rules.sh.

💘 Generated with Crush

Assisted-by: Crush:glm-5.2
This commit is contained in:
mrcharles
2026-08-11 15:49:02 -05:00
parent 2806eab187
commit 7216eb5583
12 changed files with 877 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
oam/smokeping/General
+84
View File
@@ -0,0 +1,84 @@
*** General ***
owner = Charles N Wyble
contact = reachableceo@knownelement.com
mailhost = localhost
cgiurl = http://tsys-librenms.knel.net:8081/smokeping/smokeping.cgi
syslogfacility = local0
# each probe run every 5 minutes, 300 samples = 25 hours at 5min steps
pagedir = /data/pages
piddir = /tmp
imgcache = /data/cache
imgurl = /smokeping/images
datadir = /data/_data
dyndir = /data/dyn
*** Database ***
step = 300
pings = 20
# consfn mrhb steps total
AVERAGE 0.5 1 100800
AVERAGE 0.5 12 43200
MIN 0.5 12 43200
MAX 0.5 12 43200
AVERAGE 0.5 144 7200
MAX 0.5 144 7200
MIN 0.5 144 7200
*** Presentation ***
template = /etc/smokeping/basepage.html
+ charts
+ detail
width = 600
height = 200
nradius = 5
*** Probes ***
+ FPing
binary = /usr/local/bin/fping
hostinterval = 1.5
mininterval = 0.001
offset = 0%
*** Alerts ***
to = reachableceo@knownelement.com
from = smokeping-alert@tsys-librenms.knel.net
+bigloss
type = loss
# in percent
pattern = ==0%,==0%,==0%,==0%,>0%,>0%,>0%
comment = suddenly there is packet loss
+somedoss
type = loss
# in percent
pattern = ==0%,==0%,==0%,==0%,==0%,>0%,>0%,>0%,>0%,>0%,>0%,>0%
comment = incoming packet loss
+startloss
type = loss
# in percent
pattern = >0%,>0%,>0%
comment = loss at startup
+rttdetect
type = rtt
# in milliseconds
pattern = <10,<10,<10,<10,<10,<10,<10,>10,>10,>10
comment = routing change?
+rttbadd
type = rtt
# in milliseconds
pattern = <50,<50,<50,<50,<50,<50,>50,>50,>50,>50
comment = reroute?
oam/smokeping/Targets
+111
View File
@@ -0,0 +1,111 @@
*** Targets ***
probe = FPing
menu = Top
title = Network Latency Monitor
+ Infrastructure
menu = Infrastructure
title = Core Infrastructure
++ pfv-r5-core-01
menu = pfv-r5-core-01 (Core Switch)
title = Dell PowerConnect 5448 - Rack 5 Core
host = pfv-r5-core-01.knel.net
++ pfv-r3-tor-mgmt-01
menu = pfv-r3-tor-mgmt-01 (Rack 3 Mgmt TOR)
title = Neyland 24T - Rack 3 Management TOR
host = pfv-r3-tor-mgmt-01.knel.net
++ pfv-r3-tor-stor-01
menu = pfv-r3-tor-stor-01 (Rack 3 Storage TOR)
title = Neyland 24T - Rack 3 Storage TOR
host = pfv-r3-tor-stor-01.knel.net
++ pfv-r6-mgmt-01
menu = pfv-r6-mgmt-01 (Rack 6 Mgmt Switch)
title = Neyland 24T - Rack 6 Management Switch
host = pfv-r6-mgmt-01.knel.net
+ Servers
menu = Servers
title = Server Infrastructure
++ pfv-stor1
menu = pfv-stor1
title = Storage Server 1
host = pfv-stor1.knel.net
++ pfv-bms
menu = pfv-bms (HomeAssistant)
title = Home Assistant / UniFi Controller
host = pfv-bms.knel.net
++ tsys-librenms
menu = tsys-librenms
title = LibreNMS Monitoring Server
host = tsys-librenms.knel.net
+ Wireless
menu = Wireless
title = Wireless Access Points
++ ap-tablemount
menu = ap-tablemount
title = UniFi AP-AC-Lite (Table Mount)
host = ap-tablemount.knel.net
++ ap-wallmount
menu = ap-wallmount
title = UniFi AP-AC-LR (Wall Mount)
host = ap-wallmount.knel.net
+ ProxmoxHosts
menu = Proxmox Hosts
title = Proxmox Hypervisor Nodes
++ pfv-tsys1
menu = pfv-tsys1
title = Proxmox Host - Infrastructure
host = pfv-tsys1.knel.net
++ pfv-tsys3
menu = pfv-tsys3
title = Proxmox Host - Compute
host = pfv-tsys3.knel.net
++ pfv-tsys4
menu = pfv-tsys4
title = Proxmox Host - Storage + PBS
host = pfv-tsys4.knel.net
++ pfv-tsys5
menu = pfv-tsys5
title = Proxmox Host - Storage + Sandbox
host = pfv-tsys5.knel.net
++ pfv-tsys6
menu = pfv-tsys6
title = Proxmox Host - RackRental
host = pfv-tsys6.knel.net
++ pfv-tsys7
menu = pfv-tsys7
title = Proxmox Host - RackRental
host = pfv-tsys7.knel.net
++ pfv-tsys9
menu = pfv-tsys9
title = Proxmox Host - Infra + Compute
host = pfv-tsys9.knel.net
+ Power
menu = Power
title = Power Devices
++ pfv-garage-pdu-01
menu = pfv-garage-pdu-1
title = APC PDU (Garage)
host = pfv-garage-pdu-1.knel.net
oam/smokeping/docker-compose.yml
+14
View File
@@ -0,0 +1,14 @@
services:
smokeping:
image: linuxserver/smokeping:2.9.0
container_name: oam-smokeping
environment:
- PUID=1000
- PGID=1000
- TZ=America/Chicago
volumes:
- /opt/oam/smokeping/config:/config
- /opt/oam/smokeping/data:/data
ports:
- "8081:80"
restart: unless-stopped
oam/smokeping/setup.sh
+237
View File
@@ -0,0 +1,237 @@
#!/usr/bin/env bash
set -euo pipefail
# Deploy Smokeping on tsys-librenms
# Part of OAM platform [#337]
echo "=== Setting up Smokeping ==="
# Ensure directories
mkdir -p /opt/oam/smokeping/{config,data}
# General config
cat > /opt/oam/smokeping/config/General <<'GENEOF'
*** General ***
owner = Charles N Wyble
contact = reachableceo@knownelement.com
mailhost = localhost
cgiurl = http://tsys-librenms.knel.net:8081/smokeping/smokeping.cgi
syslogfacility = local0
pagedir = /data/pages
piddir = /tmp
imgcache = /data/cache
imgurl = /smokeping/images
datadir = /data/_data
dyndir = /data/dyn
*** Database ***
step = 300
pings = 20
AVERAGE 0.5 1 100800
AVERAGE 0.5 12 43200
MIN 0.5 12 43200
MAX 0.5 12 43200
AVERAGE 0.5 144 7200
MAX 0.5 144 7200
MIN 0.5 144 7200
*** Presentation ***
template = /etc/smokeping/basepage.html
+ charts
+ detail
width = 600
height = 200
nradius = 5
*** Probes ***
+ FPing
binary = /usr/local/bin/fping
hostinterval = 1.5
mininterval = 0.001
offset = 0%
*** Alerts ***
to = reachableceo@knownelement.com
from = smokeping-alert@tsys-librenms.knel.net
+bigloss
type = loss
pattern = ==0%,==0%,==0%,==0%,>0%,>0%,>0%
comment = suddenly there is packet loss
+somedoss
type = loss
pattern = ==0%,==0%,==0%,==0%,==0%,>0%,>0%,>0%,>0%,>0%,>0%,>0%
comment = incoming packet loss
+startloss
type = loss
pattern = >0%,>0%,>0%
comment = loss at startup
+rttdetect
type = rtt
pattern = <10,<10,<10,<10,<10,<10,<10,>10,>10,>10
comment = routing change?
+rttbadd
type = rtt
pattern = <50,<50,<50,<50,<50,<50,>50,>50,>50,>50
comment = reroute?
GENEOF
# Targets config
cat > /opt/oam/smokeping/config/Targets <<'TGTEOF'
*** Targets ***
probe = FPing
menu = Top
title = Network Latency Monitor
+ Infrastructure
menu = Infrastructure
title = Core Infrastructure
++ pfv-r5-core-01
menu = pfv-r5-core-01 (Core Switch)
title = Dell PowerConnect 5448 - Rack 5 Core
host = pfv-r5-core-01.knel.net
++ pfv-r3-tor-mgmt-01
menu = pfv-r3-tor-mgmt-01 (Rack 3 Mgmt TOR)
title = Neyland 24T - Rack 3 Management TOR
host = pfv-r3-tor-mgmt-01.knel.net
++ pfv-r3-tor-stor-01
menu = pfv-r3-tor-stor-01 (Rack 3 Storage TOR)
title = Neyland 24T - Rack 3 Storage TOR
host = pfv-r3-tor-stor-01.knel.net
++ pfv-r6-mgmt-01
menu = pfv-r6-mgmt-01 (Rack 6 Mgmt Switch)
title = Neyland 24T - Rack 6 Management Switch
host = pfv-r6-mgmt-01.knel.net
+ Servers
menu = Servers
title = Server Infrastructure
++ pfv-stor1
menu = pfv-stor1
title = Storage Server 1
host = pfv-stor1.knel.net
++ pfv-bms
menu = pfv-bms (HomeAssistant)
title = Home Assistant / UniFi Controller
host = pfv-bms.knel.net
++ tsys-librenms
menu = tsys-librenms
title = LibreNMS Monitoring Server
host = tsys-librenms.knel.net
+ Wireless
menu = Wireless
title = Wireless Access Points
++ ap-tablemount
menu = ap-tablemount
title = UniFi AP-AC-Lite (Table Mount)
host = ap-tablemount.knel.net
++ ap-wallmount
menu = ap-wallmount
title = UniFi AP-AC-LR (Wall Mount)
host = ap-wallmount.knel.net
+ ProxmoxHosts
menu = Proxmox Hosts
title = Proxmox Hypervisor Nodes
++ pfv-tsys1
menu = pfv-tsys1
title = Proxmox Host - Infrastructure
host = pfv-tsys1.knel.net
++ pfv-tsys3
menu = pfv-tsys3
title = Proxmox Host - Compute
host = pfv-tsys3.knel.net
++ pfv-tsys4
menu = pfv-tsys4
title = Proxmox Host - Storage + PBS
host = pfv-tsys4.knel.net
++ pfv-tsys5
menu = pfv-tsys5
title = Proxmox Host - Storage + Sandbox
host = pfv-tsys5.knel.net
++ pfv-tsys6
menu = pfv-tsys6
title = Proxmox Host - RackRental
host = pfv-tsys6.knel.net
++ pfv-tsys7
menu = pfv-tsys7
title = Proxmox Host - RackRental
host = pfv-tsys7.knel.net
++ pfv-tsys9
menu = pfv-tsys9
title = Proxmox Host - Infra + Compute
host = pfv-tsys9.knel.net
+ Power
menu = Power
title = Power Devices
++ pfv-garage-pdu-01
menu = pfv-garage-pdu-1
title = APC PDU (Garage)
host = pfv-garage-pdu-1.knel.net
TGTEOF
# Docker compose
cat > /opt/oam/smokeping/docker-compose.yml <<'DCEOF'
services:
smokeping:
image: linuxserver/smokeping:2.9.0
container_name: oam-smokeping
environment:
- PUID=1000
- PGID=1000
- TZ=America/Chicago
volumes:
- /opt/oam/smokeping/config:/config
- /opt/oam/smokeping/data:/data
ports:
- "8081:80"
restart: unless-stopped
DCEOF
echo "=== Starting Smokeping container ==="
cd /opt/oam/smokeping && docker compose up -d 2>&1
echo "=== Waiting for startup ==="
sleep 5
echo "=== Container status ==="
docker ps --filter name=oam-smokeping --format "table {{.Names}}\t{{.Image}}\t{{.Status}}\t{{.Ports}}"
echo "=== Smokeping logs (last 20) ==="
docker logs oam-smokeping --tail 20 2>&1
echo "=== Done ==="