Skip to content
Open
Show file tree
Hide file tree
Changes from 33 commits
Commits
Show all changes
41 commits
Select commit Hold shift + click to select a range
137b0e1
Add new EFA metrics to EFA integ test
the-mann Nov 19, 2025
6d91312
temp: only run efa test
the-mann Nov 19, 2025
7dd5008
helm v3 provider `kubernetes` block is now a single nested object att…
the-mann Nov 19, 2025
5a84f9a
undo helm v3 provider `kubernetes` block is now a single nested objec…
the-mann Nov 19, 2025
10ee4d1
redo helm v3 provider `kubernetes` block is now a single nested objec…
the-mann Nov 19, 2025
f014512
set instance type
the-mann Nov 19, 2025
fdda2dc
Convert EFA test to use terraform-aws-modules/eks v21.0 with CloudWat…
the-mann Nov 19, 2025
6c48320
shorten eks cluster name
the-mann Nov 19, 2025
4fbf9a1
don't create kms key
the-mann Nov 19, 2025
2e6f4df
Revert "don't create kms key"
the-mann Nov 19, 2025
030e920
Fix nodeadm bootstrap issues by switching to AL2_x86_64_GPU AMI and d…
the-mann Nov 19, 2025
1fb3655
Add public IP assignment to EKS node group
the-mann Nov 19, 2025
b70b1df
Add dedicated VPC with private subnets and NAT Gateway for EFA test
the-mann Nov 19, 2025
ec5e4ab
add other required addons
the-mann Nov 20, 2025
230d985
Fix EKS version and AMI type for GPU support
the-mann Nov 20, 2025
2e7a4c7
Add validator and enable public API access
the-mann Nov 20, 2025
b4083b0
fail faster
the-mann Nov 20, 2025
c8c9e1b
cluster_endpoint_public_access -> endpoint_public_access
the-mann Nov 20, 2025
f4ef8dc
Configure Pod Identity for CloudWatch Observability addon
the-mann Nov 20, 2025
6380e31
add pod identity associations
the-mann Nov 20, 2025
c48cefa
add pod identity associations
the-mann Nov 20, 2025
4ef5614
update image, add busy box
the-mann Nov 20, 2025
80d90d2
update kubernetes provider
the-mann Nov 20, 2025
0e8fcc4
update kubernetes provider
the-mann Nov 20, 2025
4d626b7
update kubernetes provider
the-mann Nov 20, 2025
2d2d413
give cluster creator admin permissions
the-mann Nov 20, 2025
0d6d94d
update instance type, add nvidia device plugin + efa device plugin
the-mann Nov 20, 2025
9c4a732
add providers
the-mann Nov 20, 2025
f94eb4e
add providers
the-mann Nov 20, 2025
91b49b8
re-enable efa metric tests
the-mann Nov 20, 2025
3cd4183
update dimensions to test
the-mann Nov 20, 2025
22f8988
remove duplicate training job
the-mann Nov 20, 2025
7c75b77
Revert "temp: only run efa test"
the-mann Nov 20, 2025
1831ae8
Address PR feedback: use k8s_version variable, ami_type variable, and…
the-mann Nov 21, 2025
494d32c
Reapply "temp: only run efa test"
the-mann Nov 21, 2025
d576942
use al2023
the-mann Nov 21, 2025
b66bf06
Fix terraform provider crash: add AWS provider config and downgrade t…
the-mann Nov 21, 2025
53da66a
exclude faulty 6.22.0 version
the-mann Nov 21, 2025
8cbec46
enable public endpoint access
the-mann Nov 21, 2025
f793966
Revert "Reapply "temp: only run efa test""
the-mann Nov 24, 2025
a78b5a2
fix formatting
the-mann Nov 24, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions generator/test_case_generator.go
Original file line number Diff line number Diff line change
Expand Up @@ -368,11 +368,11 @@ var testTypeToTestConfig = map[string][]testConfig{
testDir: "./test/entity", terraformDir: "terraform/eks/daemon/entity",
targets: map[string]map[string]struct{}{"arc": {"amd64": {}}},
},
//Skipping test until efa team implements fix
//{
// testDir: "./test/efa", terraformDir: "terraform/eks/daemon/efa",
// targets: map[string]map[string]struct{}{"arc": {"amd64": {}}},
//},
{
testDir: "./test/efa", terraformDir: "terraform/eks/daemon/efa",
targets: map[string]map[string]struct{}{"arc": {"amd64": {}}},
instanceType: "c6in.32xlarge",
},
{
testDir: "./test/metric_value_benchmark", terraformDir: "terraform/eks/daemon/credentials/pod_identity",
targets: map[string]map[string]struct{}{"arc": {"amd64": {}}},
Expand Down
60 changes: 60 additions & 0 deletions terraform/eks/daemon/efa/cloudwatch-pod-identity.tf
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: MIT

# IAM role for CloudWatch Observability addon
resource "aws_iam_role" "cloudwatch_observability" {
name = "cloudwatch-observability-${module.common.testing_id}"

assume_role_policy = jsonencode({
Version = "2012-10-17"
Statement = [
{
Effect = "Allow"
Principal = {
Service = "pods.eks.amazonaws.com"
}
Action = [
"sts:AssumeRole",
"sts:TagSession"
]
}
]
})

tags = {
Name = "cloudwatch-observability-${module.common.testing_id}"
Owner = "default"
}
}

# Attach CloudWatch policies
resource "aws_iam_role_policy_attachment" "cloudwatch_observability_server" {
policy_arn = "arn:aws:iam::aws:policy/CloudWatchAgentServerPolicy"
role = aws_iam_role.cloudwatch_observability.name
}

# Pod Identity association for CloudWatch agent
resource "aws_eks_pod_identity_association" "cloudwatch_agent" {
cluster_name = module.eks.cluster_name
namespace = "amazon-cloudwatch"
service_account = "cloudwatch-agent"
role_arn = aws_iam_role.cloudwatch_observability.arn

tags = {
Name = "cloudwatch-agent-${module.common.testing_id}"
Owner = "default"
}
}

# Pod Identity association for Fluent Bit
resource "aws_eks_pod_identity_association" "fluent_bit" {
cluster_name = module.eks.cluster_name
namespace = "amazon-cloudwatch"
service_account = "fluent-bit"
role_arn = aws_iam_role.cloudwatch_observability.arn

tags = {
Name = "fluent-bit-${module.common.testing_id}"
Owner = "default"
}
}
Loading
Loading