feat(monitoring): enable Alertmanager (null receiver, longhorn PVC, az-a) + fix forgejo-rules ns forgejo->cicd — alerting delivery was disabled; forgejo PrometheusRule targeted a nonexistent namespace

This commit is contained in:
Story Crater Bot
2026-08-13 07:10:03 -07:00
parent 2d7127b37e
commit 3a91c19b5c
13 changed files with 145 additions and 139 deletions
+24 -20
View File
@@ -22,26 +22,28 @@ resource "local_file" "controlplane_configs" {
filename = "${path.module}/../cluster-config/${each.key}.yaml"
content = templatefile("${path.module}/templates/controlplane.tftpl", {
version = "v1alpha1"
hostname = each.value.hostname
token = var.machine_token
ca_crt = var.machine_ca_crt
ca_key = var.machine_ca_key
lan_ip = each.value.lan_ip
lan_subnet = each.value.lan_subnet
lan_gateway = each.value.lan_gateway
kubelet_image = local.kubelet_image
cluster_dns_ip = local.cluster_dns_ip
install_disk = each.value.install_disk
factory_image = local.factory_image
talos_version = var.talos_version
longhorn_disks = each.value.longhorn_disks
dns_servers = var.cluster_config.dns_servers
forgejo_registry_ip = var.forgejo_registry_ip
forgejo_hostname = var.forgejo_hostname
zone = each.value.zone
allow_scheduling = each.value.allow_scheduling
coredns_corefile = file("${path.module}/files/coredns/Corefile")
version = "v1alpha1"
hostname = each.value.hostname
token = var.machine_token
ca_crt = var.machine_ca_crt
ca_key = var.machine_ca_key
lan_ip = each.value.lan_ip
lan_subnet = each.value.lan_subnet
lan_gateway = each.value.lan_gateway
kubelet_image = local.kubelet_image
cluster_dns_ip = local.cluster_dns_ip
install_disk = each.value.install_disk
factory_image = local.factory_image
talos_version = var.talos_version
longhorn_disks = each.value.longhorn_disks
dns_servers = var.cluster_config.dns_servers
forgejo_registry_ip = var.forgejo_registry_ip
forgejo_hostname = var.forgejo_hostname
zone = each.value.zone
allow_scheduling = each.value.allow_scheduling
coredns_corefile = file("${path.module}/files/coredns/Corefile")
cilium_lb_ippool = file("${path.module}/files/cilium/lb-ippool.yaml")
cilium_l2_announcement = file("${path.module}/files/cilium/l2-announcement.yaml")
# Cloudflare Tunnel cert SANs (talos :50000 and kube-apiserver :6443)
cloudflare_talos_sans = each.value.cloudflare_talos_sans
@@ -101,6 +103,8 @@ resource "local_file" "worker_configs" {
forgejo_hostname = var.forgejo_hostname
zone = each.value.zone
gpu_count = each.value.gpu_count
node_labels = each.value.node_labels
node_taints = each.value.node_taints
extra_disks = each.value.extra_disks
swap_size = each.value.swap_size
ephemeral_max_size = each.value.ephemeral_max_size