feat(o11y): add o11y terraform module for VM

.trivyignore.yaml

@@ -14,6 +14,8 @@ misconfigurations:
       - docker/osv-scanner/Dockerfile
       - docker/semgrep/Dockerfile
       - docker/trivy/Dockerfile
+      # Container runs as non-root (user 65532) via the ECS task definition; the image is a thin version-pin for dependabot.
+      - docker/victoriametrics/Dockerfile
       - docker/zap/Dockerfile
   - id: AVD-AWS-0053  # Public ALB intentional for nest.owasp.dev
     paths:

docker-compose/local/compose.o11y.yaml

@@ -35,7 +35,9 @@ services:
     command:
       - -retentionPeriod=5y
       - -storageDataPath=/data
-    image: victoriametrics/victoria-metrics:v1.145.0@sha256:c014fb5a711d38cb24fd0673197592cd1394bb903dbb16aea565620c9c8a3d70
+    build:
+      context: ../../docker/victoriametrics
+      dockerfile: Dockerfile
     healthcheck:
       interval: 5s
       retries: 5

docker/victoriametrics/Dockerfile

@@ -0,0 +1 @@
+FROM victoriametrics/victoria-metrics:v1.145.0@sha256:c014fb5a711d38cb24fd0673197592cd1394bb903dbb16aea565620c9c8a3d70

infrastructure/live/README.md

@@ -59,6 +59,7 @@ No providers.
 | <a name="module_frontend_build_cache"></a> [frontend\_build\_cache](#module\_frontend\_build\_cache) | ../modules/ecr-cache | n/a |
 | <a name="module_kms"></a> [kms](#module\_kms) | ../modules/kms | n/a |
 | <a name="module_networking"></a> [networking](#module\_networking) | ../modules/networking | n/a |
+| <a name="module_observability"></a> [observability](#module\_observability) | ../modules/observability | n/a |
 | <a name="module_parameters"></a> [parameters](#module\_parameters) | ../modules/parameters | n/a |
 | <a name="module_security"></a> [security](#module\_security) | ../modules/security | n/a |
 | <a name="module_storage"></a> [storage](#module\_storage) | ../modules/storage | n/a |
@@ -101,6 +102,7 @@ No resources.
 | <a name="input_enable_additional_parameters"></a> [enable\_additional\_parameters](#input\_enable\_additional\_parameters) | Whether to enable additional parameters (e.g. for production). | `bool` | `false` | no |
 | <a name="input_enable_cron_tasks"></a> [enable\_cron\_tasks](#input\_enable\_cron\_tasks) | Whether to enable scheduled cron tasks. | `bool` | n/a | yes |
 | <a name="input_enable_nat_gateway"></a> [enable\_nat\_gateway](#input\_enable\_nat\_gateway) | Whether to enable a NAT Gateway. | `bool` | `true` | no |
+| <a name="input_enable_observability"></a> [enable\_observability](#input\_enable\_observability) | Whether to create the observability stack. | `bool` | `false` | no |
 | <a name="input_enable_rds_proxy"></a> [enable\_rds\_proxy](#input\_enable\_rds\_proxy) | Whether to create an RDS proxy. | `bool` | `false` | no |
 | <a name="input_enable_vpc_cloudwatch_logs_endpoint"></a> [enable\_vpc\_cloudwatch\_logs\_endpoint](#input\_enable\_vpc\_cloudwatch\_logs\_endpoint) | Whether to create CloudWatch Logs VPC endpoint. | `bool` | `false` | no |
 | <a name="input_enable_vpc_ecr_api_endpoint"></a> [enable\_vpc\_ecr\_api\_endpoint](#input\_enable\_vpc\_ecr\_api\_endpoint) | Whether to create ECR API VPC endpoint. | `bool` | `false` | no |

infrastructure/live/main.tf

@@ -22,6 +22,10 @@ locals {
     Project     = var.project_name
   }
   fixtures_bucket_name = coalesce(var.fixtures_bucket_name, "${var.project_name}-${var.environment}-fixtures")
+  observability_vm_image = trimspace(trimprefix(
+    one([for line in split("\n", file("${path.root}/../../docker/victoriametrics/Dockerfile")) : line if startswith(line, "FROM ")]),
+    "FROM "
+  ))
 }
 
 module "alb" {
@@ -179,6 +183,26 @@ module "networking" {
   vpc_cidr                            = var.vpc_cidr
 }
 
+module "observability" {
+  count  = var.enable_observability ? 1 : 0
+  source = "../modules/observability"
+
+  app_security_group_ids = [
+    module.security.backend_sg_id,
+    module.security.frontend_sg_id,
+    module.security.tasks_sg_id,
+  ]
+  assign_public_ip = local.assign_public_ip
+  aws_region       = var.aws_region
+  common_tags      = local.common_tags
+  environment      = var.environment
+  kms_key_arn      = module.kms.key_arn
+  project_name     = var.project_name
+  subnet_ids       = var.enable_nat_gateway ? module.networking.private_subnet_ids : module.networking.public_subnet_ids
+  vm_image         = local.observability_vm_image
+  vpc_id           = module.networking.vpc_id
+}
+
 module "parameters" {
   source = "../modules/parameters"
 

infrastructure/live/variables.tf

@@ -193,6 +193,12 @@ variable "enable_nat_gateway" {
   default     = true
 }
 
+variable "enable_observability" {
+  description = "Whether to create the observability stack."
+  type        = bool
+  default     = false
+}
+
 variable "enable_rds_proxy" {
   description = "Whether to create an RDS proxy."
   type        = bool

infrastructure/modules/observability/README.md

@@ -0,0 +1,69 @@
+<!-- BEGIN_TF_DOCS -->
+## Requirements
+
+| Name | Version |
+| ---- | ------- |
+| <a name="requirement_terraform"></a> [terraform](#requirement\_terraform) | ~> 1.15.0 |
+| <a name="requirement_aws"></a> [aws](#requirement\_aws) | ~> 6.53.0 |
+
+## Providers
+
+| Name | Version |
+| ---- | ------- |
+| <a name="provider_aws"></a> [aws](#provider\_aws) | 6.53.0 |
+
+## Modules
+
+No modules.
+
+## Resources
+
+| Name | Type |
+| ---- | ---- |
+| [aws_cloudwatch_log_group.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/cloudwatch_log_group) | resource |
+| [aws_ecs_cluster.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ecs_cluster) | resource |
+| [aws_ecs_cluster_capacity_providers.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ecs_cluster_capacity_providers) | resource |
+| [aws_ecs_service.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ecs_service) | resource |
+| [aws_ecs_task_definition.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ecs_task_definition) | resource |
+| [aws_efs_access_point.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/efs_access_point) | resource |
+| [aws_efs_file_system.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/efs_file_system) | resource |
+| [aws_efs_mount_target.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/efs_mount_target) | resource |
+| [aws_iam_policy.ecs_task_execution_policy](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_policy) | resource |
+| [aws_iam_role.ecs_task_execution_role](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role) | resource |
+| [aws_iam_role_policy_attachment.ecs_task_execution_policy_attachment](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy_attachment) | resource |
+| [aws_security_group.efs](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/security_group) | resource |
+| [aws_security_group.vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/security_group) | resource |
+| [aws_security_group_rule.efs_from_vm](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/security_group_rule) | resource |
+| [aws_security_group_rule.vm_egress_https](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/security_group_rule) | resource |
+| [aws_security_group_rule.vm_ingest_from_apps](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/security_group_rule) | resource |
+| [aws_security_group_rule.vm_to_efs](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/security_group_rule) | resource |
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+| ---- | ----------- | ---- | ------- | :------: |
+| <a name="input_app_security_group_ids"></a> [app\_security\_group\_ids](#input\_app\_security\_group\_ids) | Security group IDs of the application tasks allowed to send metrics to VictoriaMetrics. | `list(string)` | n/a | yes |
+| <a name="input_assign_public_ip"></a> [assign\_public\_ip](#input\_assign\_public\_ip) | Whether to assign a public IP to the VictoriaMetrics task. | `bool` | `false` | no |
+| <a name="input_aws_region"></a> [aws\_region](#input\_aws\_region) | The AWS region where the module is deployed. | `string` | n/a | yes |
+| <a name="input_common_tags"></a> [common\_tags](#input\_common\_tags) | A map of common tags to apply to all resources. | `map(string)` | `{}` | no |
+| <a name="input_environment"></a> [environment](#input\_environment) | The environment (e.g., staging, production). | `string` | n/a | yes |
+| <a name="input_kms_key_arn"></a> [kms\_key\_arn](#input\_kms\_key\_arn) | The ARN of the KMS key used to encrypt the EFS file system. | `string` | n/a | yes |
+| <a name="input_log_retention_in_days"></a> [log\_retention\_in\_days](#input\_log\_retention\_in\_days) | The number of days to retain VictoriaMetrics container logs. | `number` | `90` | no |
+| <a name="input_project_name"></a> [project\_name](#input\_project\_name) | The name of the project. | `string` | n/a | yes |
+| <a name="input_subnet_ids"></a> [subnet\_ids](#input\_subnet\_ids) | The private subnet IDs for the EFS mount targets and the VictoriaMetrics task. | `list(string)` | n/a | yes |
+| <a name="input_vm_cpu"></a> [vm\_cpu](#input\_vm\_cpu) | The CPU units for the VictoriaMetrics Fargate task. | `number` | `512` | no |
+| <a name="input_vm_desired_count"></a> [vm\_desired\_count](#input\_vm\_desired\_count) | The number of VictoriaMetrics tasks to run (0 or 1; it is a single-node store). | `number` | `1` | no |
+| <a name="input_vm_image"></a> [vm\_image](#input\_vm\_image) | The VictoriaMetrics container image (including digest). | `string` | n/a | yes |
+| <a name="input_vm_memory"></a> [vm\_memory](#input\_vm\_memory) | The memory (in MiB) for the VictoriaMetrics Fargate task. | `number` | `1024` | no |
+| <a name="input_vm_port"></a> [vm\_port](#input\_vm\_port) | The port VictoriaMetrics listens on for ingest and queries. | `number` | `8428` | no |
+| <a name="input_vm_retention_period"></a> [vm\_retention\_period](#input\_vm\_retention\_period) | The VictoriaMetrics data retention period (e.g., 12, 5y). | `string` | `"12"` | no |
+| <a name="input_vpc_id"></a> [vpc\_id](#input\_vpc\_id) | The VPC ID where the VictoriaMetrics security group is created. | `string` | n/a | yes |
+
+## Outputs
+
+| Name | Description |
+| ---- | ----------- |
+| <a name="output_efs_file_system_id"></a> [efs\_file\_system\_id](#output\_efs\_file\_system\_id) | The ID of the EFS file system backing VictoriaMetrics storage. |
+| <a name="output_vm_cluster_name"></a> [vm\_cluster\_name](#output\_vm\_cluster\_name) | The name of the ECS cluster running VictoriaMetrics. |
+| <a name="output_vm_security_group_id"></a> [vm\_security\_group\_id](#output\_vm\_security\_group\_id) | The ID of the VictoriaMetrics security group. |
+<!-- END_TF_DOCS -->