Add 25.9.0

Author: OguzPastirmaci

README.md

@@ -1,5 +1,5 @@
 # Running RDMA (remote direct memory access) GPU workloads on OKE
-Oracle Cloud Infrastructure Kubernetes Engine (OKE)[https://docs.oracle.com/en-us/iaas/Content/ContEng/Concepts/contengoverview.htm] is a fully-managed, scalable, and highly available service that you can use to deploy your containerized applications to the cloud.
+Oracle Cloud Infrastructure Kubernetes Engine (OKE) is a fully-managed, scalable, and highly available service that you can use to deploy your containerized applications to the cloud.
 
 ### Supported Operating Systems
 - Ubuntu 22.04

terraform/oci-bv.tf renamed to terraform/bv.tf

@@ -1,4 +1,4 @@
-# Copyright (c) 2024 Oracle Corporation and/or its affiliates.
+# Copyright (c) 2025 Oracle Corporation and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl
 
 resource "kubernetes_storage_class_v1" "oci_high_vpu_20" {

terraform/datasources.tf

@@ -0,0 +1,49 @@
+# Copyright (c) 2025 Oracle Corporation and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl
+
+data "kubernetes_service" "nginx_lb" {
+  count = alltrue([var.install_monitoring, var.install_node_problem_detector_kube_prometheus_stack, var.preferred_kubernetes_services == "public", local.deploy_from_local || local.deploy_from_orm]) ? 1 : 0
+
+  depends_on = [time_sleep.wait_for_nginx_lb]
+
+  metadata {
+    name      = format("%s-controller", one(helm_release.nginx.*.name))
+    namespace = one(helm_release.nginx.*.namespace)
+  }
+}
+
+data "oci_load_balancer_load_balancers" "lbs" {
+  count = alltrue([var.install_monitoring, var.install_node_problem_detector_kube_prometheus_stack, var.preferred_kubernetes_services == "public", local.deploy_from_operator]) ? 1 : 0
+
+  compartment_id = var.compartment_ocid
+
+  filter {
+    name   = "freeform_tags.state_id"
+    values = [local.state_id]
+  }
+
+  filter {
+    name   = "freeform_tags.application"
+    values = ["nginx"]
+  }
+
+  depends_on = [module.nginx]
+}
+
+data "oci_load_balancer_load_balancers" "internal_lbs" {
+  count = alltrue([var.install_monitoring, var.install_node_problem_detector_kube_prometheus_stack, var.preferred_kubernetes_services == "internal", local.deploy_from_operator]) ? 1 : 0
+
+  compartment_id = var.compartment_ocid
+
+  filter {
+    name   = "freeform_tags.state_id"
+    values = [local.state_id]
+  }
+
+  filter {
+    name   = "freeform_tags.application"
+    values = ["grafana"]
+  }
+
+  depends_on = [module.kube_prometheus_stack]
+}

terraform/files/.DS_Store

@@ -0,0 +1,20 @@
+---
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: le-clusterissuer
+spec:
+  acme:
+    # You must replace this email address with your own.
+    # Let's Encrypt will use this to contact you about expiring
+    # certificates, and issues related to your account.
+    email: [email protected]
+    server: https://acme-v02.api.letsencrypt.org/directory #https://acme-staging-v02.api.letsencrypt.org/directory
+    privateKeySecretRef:
+      # Secret resource that will be used to store the account's private key.
+      name: le-clusterissuer-secret
+    # Add a single challenge solver, HTTP01 using nginx
+    solvers:
+    - http01:
+        ingress:
+          ingressClassName: nginx

terraform/files/cert-manager/cluster-issuer.yaml

@@ -0,0 +1,20 @@
+apiVersion: 1
+contactPoints:
+  - orgId: 1
+    name: ons-webhook
+    receivers:
+    - uid: ons
+      type: webhook
+      settings:
+        url: http://oke-ons-webhook/grafana-webhook
+        httpMethod: POST
+policies:
+    - orgId: 1
+      receiver: ons-webhook
+      group_by:
+        - grafana_folder
+        - alertname
+        - hostname
+      group_wait: 30s
+      group_interval: 5m
+      repeat_interval: 12h

terraform/files/grafana/alerts/alert-rules.yaml

@@ -2,7 +2,7 @@ apiVersion: 1
 groups:
     - orgId: 1
       name: Node Problem Detector
-      folder: OKE
+      folder: Alerts
       interval: 1m
       rules:
         - uid: oke_npd_cpu_profile
@@ -54,3 +54,6 @@ groups:
           annotations: {}
           labels: {}
           isPaused: false
+          notification_settings:
+            receiver: ons-webhook
+            repeat_interval: 24h

terraform/files/grafana/alerts/cpu-profile.yaml

@@ -2,7 +2,7 @@ apiVersion: 1
 groups:
     - orgId: 1
       name: Node Problem Detector
-      folder: OKE
+      folder: Alerts
       interval: 1m
       rules:
         - uid: oke_npd_gpu_bad_pages
@@ -54,3 +54,6 @@ groups:
           annotations: {}
           labels: {}
           isPaused: false
+          notification_settings:
+            receiver: ons-webhook
+            repeat_interval: 24h

terraform/files/grafana/alerts/gpu-bad-pages.yaml

@@ -2,7 +2,7 @@ apiVersion: 1
 groups:
     - orgId: 1
       name: Node Problem Detector
-      folder: OKE
+      folder: Alerts
       interval: 1m
       rules:
         - uid: oke_npd_gpu_bus
@@ -54,3 +54,6 @@ groups:
           annotations: {}
           labels: {}
           isPaused: false
+          notification_settings:
+            receiver: ons-webhook
+            repeat_interval: 24h

terraform/files/grafana/alerts/gpu-bus.yaml

@@ -2,7 +2,7 @@ apiVersion: 1
 groups:
     - orgId: 1
       name: Node Problem Detector
-      folder: OKE
+      folder: Alerts
       interval: 1m
       rules:
         - uid: oke_npd_gpu_count
@@ -54,3 +54,6 @@ groups:
           annotations: {}
           labels: {}
           isPaused: false
+          notification_settings:
+            receiver: ons-webhook
+            repeat_interval: 24h