Onboard CAS test scenario with 200 nodes and 200 pods

pipelines/perf-eval/Autoscale Benchmark/cluster-autoscaler-benchmark-nodes200-pods200.yml

@@ -0,0 +1,67 @@
+trigger: none
+schedules:
+  - cron: "0 16 * * *"
+    displayName: "Every day at 4:00 PM"
+    branches:
+      include:
+        - main
+    always: true
+
+variables:
+  SCENARIO_TYPE: perf-eval
+  SCENARIO_NAME: cas-c2n200p200
+  SCENARIO_VERSION: main
+
+stages:
+  - stage: azure_eastus2
+    dependsOn: []
+    jobs:
+      - template: /jobs/competitive-test.yml
+        parameters:
+          cloud: azure
+          regions:
+            - eastus2
+          engine: clusterloader2
+          engine_input:
+            image: "ghcr.io/azure/clusterloader2:v20241002"
+          topology: cluster-autoscaler
+          matrix:
+            c2-n200-p200:
+              cpu_per_node: 2
+              node_count: 200
+              pod_count: 200
+              scale_up_timeout: "15m"
+              scale_down_timeout: "15m"
+              node_label_selector: "cas = dedicated"
+              node_selector: "{cas: dedicated}"
+              loop_count: 1
+          max_parallel: 1
+          timeout_in_minutes: 180
+          credential_type: service_connection
+          ssh_key_enabled: false
+  - stage: aws_eastus2
+    dependsOn: []
+    jobs:
+      - template: /jobs/competitive-test.yml
+        parameters:
+          cloud: aws
+          regions:
+            - us-east-2
+          engine: clusterloader2
+          engine_input:
+            image: "ghcr.io/azure/clusterloader2:v20241002"
+          topology: cluster-autoscaler
+          matrix:
+            c2-n200-p200:
+              cpu_per_node: 2
+              node_count: 200
+              pod_count: 200
+              scale_up_timeout: "15m"
+              scale_down_timeout: "15m"
+              node_label_selector: "cas = dedicated"
+              node_selector: "{cas: dedicated}"
+              loop_count: 1
+          max_parallel: 1
+          timeout_in_minutes: 180
+          credential_type: service_connection
+          ssh_key_enabled: false

scenarios/perf-eval/cas-c2n200p200/terraform-inputs/aws.tfvars

@@ -0,0 +1,103 @@
+scenario_type  = "perf-eval"
+scenario_name  = "cas-c2n200p200"
+deletion_delay = "2h"
+owner          = "aks"
+
+network_config_list = [
+  {
+    role           = "cas"
+    vpc_name       = "cas-vpc"
+    vpc_cidr_block = "10.0.0.0/16"
+    subnet = [
+      {
+        name                    = "cas-subnet"
+        cidr_block              = "10.0.32.0/19"
+        zone_suffix             = "a"
+        map_public_ip_on_launch = true
+      },
+      {
+        name                    = "cas-subnet-2"
+        cidr_block              = "10.0.64.0/19"
+        zone_suffix             = "b"
+        map_public_ip_on_launch = true
+      },
+      {
+        name                    = "cas-subnet-3"
+        cidr_block              = "10.0.96.0/19"
+        zone_suffix             = "c"
+        map_public_ip_on_launch = true
+      }
+    ]
+    security_group_name = "cas-sg"
+    route_tables = [
+      {
+        name       = "internet-rt"
+        cidr_block = "0.0.0.0/0"
+      }
+    ],
+    route_table_associations = [
+      {
+        name             = "cas-subnet-rt-assoc"
+        subnet_name      = "cas-subnet"
+        route_table_name = "internet-rt"
+      },
+      {
+        name             = "cas-subnet-rt-assoc-2"
+        subnet_name      = "cas-subnet-2"
+        route_table_name = "internet-rt"
+      },
+      {
+        name             = "cas-subnet-rt-assoc-3"
+        subnet_name      = "cas-subnet-3"
+        route_table_name = "internet-rt"
+      }
+    ]
+    sg_rules = {
+      ingress = []
+      egress = [
+        {
+          from_port  = 0
+          to_port    = 0
+          protocol   = "-1"
+          cidr_block = "0.0.0.0/0"
+        }
+      ]
+    }
+  }
+]
+
+eks_config_list = [{
+  role                      = "cas"
+  eks_name                  = "cas-c2n200p200"
+  enable_cluster_autoscaler = true
+  vpc_name                  = "cas-vpc"
+  policy_arns               = ["AmazonEKSClusterPolicy", "AmazonEKSVPCResourceController", "AmazonEKSWorkerNodePolicy", "AmazonEKS_CNI_Policy", "AmazonEC2ContainerRegistryReadOnly", "AmazonSSMManagedInstanceCore"]
+  eks_managed_node_groups = [
+    {
+      name           = "default"
+      ami_type       = "AL2_x86_64"
+      instance_types = ["m4.large"]
+      min_size       = 5
+      max_size       = 5
+      desired_size   = 5
+      capacity_type  = "ON_DEMAND"
+    },
+    {
+      name           = "userpool"
+      ami_type       = "AL2_x86_64"
+      instance_types = ["m6i.large"]
+      min_size       = 0
+      max_size       = 200
+      desired_size   = 0
+      capacity_type  = "ON_DEMAND"
+      labels         = { "cas" = "dedicated" }
+      taints         = []
+    }
+  ]
+  eks_addons         = []
+  kubernetes_version = "1.31"
+  auto_scaler_profile = {
+    scale_down_delay_after_add = "0m"
+    scale_down_unneeded        = "0m"
+  }
+}]

scenarios/perf-eval/cas-c2n200p200/terraform-inputs/azure.tfvars

@@ -0,0 +1,44 @@
+scenario_type  = "perf-eval"
+scenario_name  = "cas-c2n200p200"
+deletion_delay = "2h"
+owner          = "aks"
+
+aks_config_list = [
+  {
+    role        = "cas"
+    aks_name    = "cas-c2n200p200"
+    dns_prefix  = "cas"
+    subnet_name = "aks-network"
+    sku_tier    = "Standard"
+    network_profile = {
+      network_plugin      = "azure"
+      network_plugin_mode = "overlay"
+    }
+    default_node_pool = {
+      name                         = "default"
+      node_count                   = 5
+      auto_scaling_enabled         = false
+      vm_size                      = "Standard_D4_v3"
+      os_disk_type                 = "Managed"
+      only_critical_addons_enabled = false
+      temporary_name_for_rotation  = "defaulttmp"
+    }
+    extra_node_pool = [
+      {
+        name                 = "userpool"
+        node_count           = 0
+        min_count            = 0
+        max_count            = 200
+        auto_scaling_enabled = true
+        vm_size              = "Standard_D2_v5"
+        max_pods             = 110
+        node_labels          = { "cas" = "dedicated" }
+      }
+    ]
+    kubernetes_version = "1.31"
+    auto_scaler_profile = {
+      scale_down_delay_after_add = "0m"
+      scale_down_unneeded        = "0m"
+    }
+  }
+]

scenarios/perf-eval/cas-c2n200p200/terraform-test-inputs/aws.json

@@ -0,0 +1,4 @@
+{
+    "run_id"                           : "123456789",
+    "region"                           : "us-east-2"
+}

scenarios/perf-eval/cas-c2n200p200/terraform-test-inputs/azure.json

@@ -0,0 +1,4 @@
+{
+    "run_id"                           : "123456789",
+    "region"                           : "eastus2"
+}