fix(monitoring): dashboard infra nodata — nftables pod CIDR + mountpoint

nftables.conf.j2 :
  - Ajoute 10.42.0.0/16 (CIDR pods k8s) pour port 9100 (node_exporter)
    et port 8080 (hermes webhook AlertManager)
  - Appliqué live sur storage-01 + persisté dans /etc/sysconfig/nftables.conf
  - storage-01 était up=0 (timeout) car pods Prometheus ne pouvaient pas
    l'atteindre malgré node_exporter actif

dashboard-infrastructure.yaml :
  - Corrige mountpoint /srv → /srv/data (RAID5 monté sur /srv/data)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
alkatrazz 2026-05-14 18:42:11 +02:00
parent f937c2589d
commit 0498d770f2
2 changed files with 5 additions and 5 deletions

View file

@ -32,11 +32,11 @@ table inet filter {
# Services données (accès cluster uniquement) # Services données (accès cluster uniquement)
tcp dport { 5432, 6333, 6334, 9000, 9001 } ip saddr 192.168.10.0/24 accept tcp dport { 5432, 6333, 6334, 9000, 9001 } ip saddr 192.168.10.0/24 accept
# Monitoring — node_exporter + alertmanager webhook (accès cluster) # Monitoring — node_exporter (scraping par Prometheus : nœuds cluster + pods 10.42/16)
tcp dport { 9100, 9093 } ip saddr 192.168.10.0/24 accept tcp dport 9100 ip saddr { 192.168.10.0/24, 10.42.0.0/16 } accept
# Hermes gateway (accès LAN domestique + cluster) # Hermes gateway (accès LAN domestique + cluster + pods k8s pour alertmanager webhook)
tcp dport 8080 ip saddr { 192.168.1.0/24, 192.168.10.0/24 } accept tcp dport 8080 ip saddr { 192.168.1.0/24, 192.168.10.0/24, 10.42.0.0/16 } accept
# Hermes dashboard (poste admin uniquement) # Hermes dashboard (poste admin uniquement)
tcp dport 9119 ip saddr {{ hermes_dashboard_allowed_ip }} accept tcp dport 9119 ip saddr {{ hermes_dashboard_allowed_ip }} accept

View file

@ -369,7 +369,7 @@ data:
"targets": [ "targets": [
{ {
"datasource": {"type": "prometheus", "uid": "${datasource}"}, "datasource": {"type": "prometheus", "uid": "${datasource}"},
"expr": "100 - (node_filesystem_avail_bytes{job=\"storage-01\",mountpoint=\"/srv\",fstype!=\"tmpfs\"} / node_filesystem_size_bytes{job=\"storage-01\",mountpoint=\"/srv\",fstype!=\"tmpfs\"} * 100)", "expr": "100 - (node_filesystem_avail_bytes{job=\"storage-01\",mountpoint=\"/srv/data\",fstype!=\"tmpfs\"} / node_filesystem_size_bytes{job=\"storage-01\",mountpoint=\"/srv/data\",fstype!=\"tmpfs\"} * 100)",
"legendFormat": "/srv", "legendFormat": "/srv",
"refId": "A" "refId": "A"
} }