Add AWS/EKS to sched performance comparison scenario.

Azure · Dec 9, 2024 · e78a9f2 · e78a9f2
1 parent 20674fa
commit e78a9f2
Show file tree

Hide file tree

Showing 3 changed files with 130 additions and 0 deletions.
diff --git a/pipelines/perf-eval/Scheduler Benchmark/cluster-churn-nodes1000-pods50k-sched.yml b/pipelines/perf-eval/Scheduler Benchmark/cluster-churn-nodes1000-pods50k-sched.yml
@@ -13,6 +13,32 @@ variables:
   SCENARIO_VERSION: main
 
 stages:
+  - stage: aws_eastus1_sched_baseline
+    dependsOn: []
+    jobs:
+      - template: /jobs/competitive-test.yml
+        parameters:
+          cloud: aws
+          regions:
+            - us-east-1
+          engine: clusterloader2
+          engine_input:
+            image: "ghcr.io/azure/clusterloader2:v20241022"
+          topology: slo
+          matrix:
+            aws_vpc_cni:
+              cpu_per_node: 4
+              node_count: 1000
+              node_per_step: 100
+              max_pods: 110
+              repeats: 1
+              scale_timeout: "30m"
+              cl2_config_file: cluster-scale-config.yaml
+              service_test: False
+          max_parallel: 1
+          timeout_in_minutes: 720
+          credential_type: service_connection
+          ssh_key_enabled: false
   - stage: azure_eastus2_sched_upstream_default
     dependsOn: []
     variables:

diff --git a/scenarios/perf-eval/cluster-churn-n1000p50k-sched/terraform-inputs/aws.tfvars b/scenarios/perf-eval/cluster-churn-n1000p50k-sched/terraform-inputs/aws.tfvars
@@ -0,0 +1,100 @@
+scenario_type  = "perf-eval"
+scenario_name  = "cluster-churn-n1000p50k-sched"
+deletion_delay = "12h"
+owner          = "aks"
+
+network_config_list = [
+  {
+    role                       = "slo"
+    vpc_name                   = "slo-vpc"
+    vpc_cidr_block             = "10.0.0.0/16"
+    secondary_ipv4_cidr_blocks = ["10.1.0.0/16"]
+    subnet = [
+      {
+        name                    = "slo-subnet-1"
+        cidr_block              = "10.0.0.0/16"
+        zone_suffix             = "a"
+        map_public_ip_on_launch = true
+      },
+      {
+        name                    = "slo-subnet-2"
+        cidr_block              = "10.1.0.0/17"
+        zone_suffix             = "b"
+        map_public_ip_on_launch = true
+      },
+      {
+        name                    = "slo-subnet-3"
+        cidr_block              = "10.1.128.0/17"
+        zone_suffix             = "c"
+        map_public_ip_on_launch = true
+      }
+    ]
+    security_group_name = "slo-sg"
+    route_tables = [
+      {
+        name       = "internet-rt"
+        cidr_block = "0.0.0.0/0"
+      }
+    ],
+    route_table_associations = [
+      {
+        name             = "slo-subnet-rt-assoc-1"
+        subnet_name      = "slo-subnet-1"
+        route_table_name = "internet-rt"
+      },
+      {
+        name             = "slo-subnet-rt-assoc-2"
+        subnet_name      = "slo-subnet-2"
+        route_table_name = "internet-rt"
+      },
+      {
+        name             = "slo-subnet-rt-assoc-3"
+        subnet_name      = "slo-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             = "slo"
+  eks_name         = "slo"
+  enable_karpenter = true
+  vpc_name         = "slo-vpc"
+  policy_arns      = ["AmazonEKSClusterPolicy", "AmazonEKSVPCResourceController", "AmazonEKSWorkerNodePolicy", "AmazonEKS_CNI_Policy", "AmazonEC2ContainerRegistryReadOnly"]
+  eks_managed_node_groups = [
+    {
+      name           = "default"
+      ami_type       = "AL2_x86_64"
+      instance_types = ["m4.4xlarge"]
+      min_size       = 5
+      max_size       = 5
+      desired_size   = 5
+      capacity_type  = "ON_DEMAND"
+    },
+    {
+      name           = "prompool"
+      ami_type       = "AL2_x86_64"
+      instance_types = ["m4.16xlarge"]
+      min_size       = 1
+      max_size       = 1
+      desired_size   = 1
+      capacity_type  = "ON_DEMAND"
+      labels         = { "prometheus" = "true" }
+    }
+  ]
+
+  eks_addons         = []
+  kubernetes_version = "1.30"
+}]
diff --git a/scenarios/perf-eval/cluster-churn-n1000p50k-sched/terraform-test-inputs/aws.json b/scenarios/perf-eval/cluster-churn-n1000p50k-sched/terraform-test-inputs/aws.json
@@ -0,0 +1,4 @@
+{
+    "run_id"                           : "123456789",
+    "region"                           : "us-east-1"
+}