infra/stacks/monitoring/modules/monitoring/idrac.tf
Viktor Barzin 5c59429182 fix: HA Sofia REST sensors + PVC drift safety
Two real issues found while triaging HomeAssistantCriticalSensorUnavailable
alerts and the prometheus + technitium PVC Terminating-but-in-use
state from the earlier session.

1. idrac-redfish-exporter + snmp-exporter ingresses: auth=required →
   auth=none. HA Sofia REST sensors scrape these endpoints
   programmatically; with Authentik forward-auth in front, every
   request got a 302 to authentik.viktorbarzin.me and the REST
   sensors parsed the HTML login page instead of metrics — leaving
   the R730, UPS, and ~20 other sensors permanently unavailable.
   The allow_local_access_only IP allowlist (192.168.0.0/16 +
   10.0.0.0/8) already gates external access, so authentik on top
   was breaking machine-to-machine traffic for no security gain.

2. prometheus_server_pvc + technitium primary_config_encrypted:
   add lifecycle.ignore_changes = [spec[0].resources[0].requests].
   The autoresizer expands these PVCs; PVCs can't shrink. Without
   the ignore, every TF apply tried to revert the live size back
   to the TF spec value, hit K8s's shrink-forbidden rule, and
   force-replaced the PVC. Because the pod still mounted it, the
   PVC went into Terminating-but-protected limbo — fine until a
   pod restart would have orphaned the volume. Root cause of the
   2026-05-10 PVC Terminating incident.

Bonus: prometheus_server_pvc threshold was the inverted "90%" (the
same bug the bulk fecfa211 sweep fixed elsewhere; my regex only
matched "80%" so this one slipped through). Now "10%".

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-10 21:48:29 +00:00

142 lines
3.9 KiB
HCL

resource "kubernetes_config_map" "redfish-config" {
metadata {
name = "redfish-exporter-config"
namespace = kubernetes_namespace.monitoring.metadata[0].name
annotations = {
"reloader.stakater.com/match" = "true"
}
}
data = {
"config.yml" = <<-EOF
address: 0.0.0.0
port: 9610
hosts:
${var.idrac_host}:
username: ${var.idrac_username}
password: ${var.idrac_password}
default:
username: root
password: calvin
metrics:
all: true
# system: true
# sensors: true
# power: true
# sel: false # Disable SEL - often slow
# storage: true # Disable storage - slowest endpoint
# memory: true
# network: false # Disable network adapters
# firmware: false # Don't need this frequently
EOF
}
}
resource "kubernetes_deployment" "idrac-redfish" {
metadata {
name = "idrac-redfish-exporter"
namespace = kubernetes_namespace.monitoring.metadata[0].name
labels = {
app = "idrac-redfish-exporter"
tier = var.tier
}
annotations = {
"reloader.stakater.com/search" = "true"
}
}
spec {
replicas = 1
selector {
match_labels = {
app = "idrac-redfish-exporter"
}
}
template {
metadata {
labels = {
app = "idrac-redfish-exporter"
}
}
spec {
priority_class_name = "tier-1-cluster"
container {
# https://github.com/mrlhansen/idrac_exporter?tab=readme-ov-file
# Patched v2.4.1 - restored missing idrac_power_supply_input_voltage metric
# See: https://github.com/mrlhansen/idrac_exporter/issues/176
image = "viktorbarzin/idrac-redfish-exporter:2.4.1-voltage-fix"
name = "redfish-exporter"
port {
container_port = 9610
}
volume_mount {
name = "redfish-exporter-config"
mount_path = "/etc/prometheus/idrac.yml"
sub_path = "config.yml"
}
}
volume {
name = "redfish-exporter-config"
config_map {
name = "redfish-exporter-config"
}
}
dns_config {
option {
name = "ndots"
value = "2"
}
}
}
}
}
lifecycle {
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
ignore_changes = [spec[0].template[0].spec[0].dns_config]
}
}
resource "kubernetes_service" "idrac-redfish-exporter" {
metadata {
name = "idrac-redfish-exporter"
namespace = kubernetes_namespace.monitoring.metadata[0].name
labels = {
"app" = "idrac-redfish-exporter"
}
# annotations = {
# "prometheus.io/scrape" = "true"
# "prometheus.io/path" = "/metrics"
# "prometheus.io/port" = "9090"
# }
}
spec {
selector = {
"app" = "idrac-redfish-exporter"
}
port {
name = "http"
port = "9090"
target_port = "9610"
}
}
}
module "idrac-redfish-exporter-ingress" {
source = "../../../../modules/kubernetes/ingress_factory"
# Auth disabled: HA Sofia + Prometheus scrape this endpoint
# programmatically (no browser, no SSO cookie). The
# allow_local_access_only middleware (192.168.0.0/16 + 10.0.0.0/8)
# already gates external access, so layering Authentik on top only
# breaks the REST sensor in HA Sofia (it gets a 302 to authentik.viktorbarzin.me
# and parses HTML instead of metrics).
auth = "none"
namespace = kubernetes_namespace.monitoring.metadata[0].name
name = "idrac-redfish-exporter"
root_domain = "viktorbarzin.lan"
tls_secret_name = var.tls_secret_name
allow_local_access_only = true
ssl_redirect = false
port = 9090
}