monitoring: expose Alloy OTLP for external log ingestion from RunPod pods
- Alloy config: route OTLP logs → Loki (was traces-only)
- Alloy config: fix River syntax (semicolons in rule{} blocks are invalid)
- Add alloy-otlp Service (ClusterIP:4318)
- Add alloy-otlp-auth Secret (bcrypt htpasswd for Traefik BasicAuth)
- Add alloy-otlp-basicauth-middleware Traefik Middleware
- Add alloy.neuralplatform.ai Ingress (TLS via cert-manager)
Auth: Authorization: Basic base64(pantheon:<push_token>)
Token stored in Vault at secret/alloy push_token
RunPod pods push OTLP logs to https://alloy.neuralplatform.ai/v1/logs
Alloy routes → Loki → queryable in Grafana
This commit is contained in:
@@ -147,6 +147,65 @@ resource "kubernetes_ingress_v1" "npm_registry" {
|
||||
depends_on = [helm_release.cert_manager]
|
||||
}
|
||||
|
||||
# Alloy OTLP HTTP ingress — external log/trace ingestion from RunPod pods
|
||||
# Auth: HTTP Basic Auth (username: pantheon, password: ALLOY_PUSH_TOKEN from Vault)
|
||||
# Pods set: Authorization: Basic base64(pantheon:<token>)
|
||||
# Traefik middleware strips auth before forwarding to Alloy.
|
||||
resource "kubernetes_manifest" "alloy_otlp_basicauth_middleware" {
|
||||
manifest = {
|
||||
apiVersion = "traefik.io/v1alpha1"
|
||||
kind = "Middleware"
|
||||
metadata = {
|
||||
name = "alloy-otlp-auth"
|
||||
namespace = "monitoring"
|
||||
}
|
||||
spec = {
|
||||
basicAuth = {
|
||||
secret = "alloy-otlp-auth"
|
||||
}
|
||||
}
|
||||
}
|
||||
depends_on = [kubernetes_secret.alloy_otlp_auth]
|
||||
}
|
||||
|
||||
resource "kubernetes_ingress_v1" "alloy_otlp" {
|
||||
metadata {
|
||||
name = "alloy-otlp"
|
||||
namespace = "monitoring"
|
||||
annotations = {
|
||||
"traefik.ingress.kubernetes.io/router.entrypoints" = "websecure"
|
||||
"traefik.ingress.kubernetes.io/router.middlewares" = "monitoring-alloy-otlp-auth@kubernetescrd"
|
||||
"cert-manager.io/cluster-issuer" = "letsencrypt-prod"
|
||||
}
|
||||
}
|
||||
spec {
|
||||
tls {
|
||||
hosts = ["alloy.${var.infra_domain}"]
|
||||
secret_name = "alloy-otlp-tls"
|
||||
}
|
||||
rule {
|
||||
host = "alloy.${var.infra_domain}"
|
||||
http {
|
||||
path {
|
||||
path = "/"
|
||||
path_type = "Prefix"
|
||||
backend {
|
||||
service {
|
||||
name = "alloy-otlp"
|
||||
port { number = 4318 }
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
depends_on = [
|
||||
kubernetes_manifest.alloy_otlp_basicauth_middleware,
|
||||
kubernetes_service.alloy_otlp,
|
||||
helm_release.cert_manager,
|
||||
]
|
||||
}
|
||||
|
||||
# PyPI registry — devpi (proxies pypi.org, caches locally)
|
||||
resource "kubernetes_ingress_v1" "pypi_registry" {
|
||||
metadata {
|
||||
|
||||
@@ -294,10 +294,22 @@ resource "helm_release" "alloy" {
|
||||
|
||||
discovery.relabel "pods" {
|
||||
targets = discovery.kubernetes.pods.targets
|
||||
rule { source_labels = ["__meta_kubernetes_namespace"]; target_label = "namespace" }
|
||||
rule { source_labels = ["__meta_kubernetes_pod_name"]; target_label = "pod" }
|
||||
rule { source_labels = ["__meta_kubernetes_pod_container_name"]; target_label = "container" }
|
||||
rule { source_labels = ["__meta_kubernetes_pod_label_app"]; target_label = "app" }
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_namespace"]
|
||||
target_label = "namespace"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_name"]
|
||||
target_label = "pod"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_container_name"]
|
||||
target_label = "container"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_label_app"]
|
||||
target_label = "app"
|
||||
}
|
||||
}
|
||||
|
||||
loki.source.kubernetes "pods" {
|
||||
@@ -317,6 +329,7 @@ resource "helm_release" "alloy" {
|
||||
http { endpoint = "0.0.0.0:4318" }
|
||||
output {
|
||||
traces = [otelcol.exporter.otlp.tempo.input]
|
||||
logs = [otelcol.exporter.loki.pantheon.input]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -326,8 +339,46 @@ resource "helm_release" "alloy" {
|
||||
tls { insecure = true }
|
||||
}
|
||||
}
|
||||
|
||||
otelcol.exporter.loki "pantheon" {
|
||||
forward_to = [loki.write.default.receiver]
|
||||
}
|
||||
EOT
|
||||
]
|
||||
|
||||
depends_on = [helm_release.loki, helm_release.tempo]
|
||||
}
|
||||
|
||||
# Expose Alloy's OTLP HTTP port (4318) for external log/trace ingestion from RunPod pods
|
||||
resource "kubernetes_service" "alloy_otlp" {
|
||||
metadata {
|
||||
name = "alloy-otlp"
|
||||
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
||||
labels = { app = "alloy-otlp" }
|
||||
}
|
||||
spec {
|
||||
selector = { "app.kubernetes.io/name" = "alloy" }
|
||||
port {
|
||||
name = "otlp-http"
|
||||
port = 4318
|
||||
target_port = 4318
|
||||
protocol = "TCP"
|
||||
}
|
||||
type = "ClusterIP"
|
||||
}
|
||||
depends_on = [helm_release.alloy]
|
||||
}
|
||||
|
||||
# BasicAuth secret for Traefik middleware — pods authenticate with
|
||||
# Authorization: Basic base64(pantheon:<ALLOY_PUSH_TOKEN>)
|
||||
resource "kubernetes_secret" "alloy_otlp_auth" {
|
||||
metadata {
|
||||
name = "alloy-otlp-auth"
|
||||
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
||||
}
|
||||
data = {
|
||||
# htpasswd entry — bcrypt hash of the push token, username "pantheon"
|
||||
users = "pantheon:${bcrypt(var.alloy_push_token)}"
|
||||
}
|
||||
depends_on = [kubernetes_namespace.monitoring]
|
||||
}
|
||||
|
||||
@@ -141,3 +141,9 @@ variable "gitea_runner_token" {
|
||||
type = string
|
||||
sensitive = true
|
||||
}
|
||||
|
||||
variable "alloy_push_token" {
|
||||
description = "Bearer token required to push OTLP logs/traces to alloy.neuralplatform.ai"
|
||||
type = string
|
||||
sensitive = true
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user