diff --git a/.github/workflows/ministack.yml b/.github/workflows/ministack.yml index b4edf6f35e..1bfd47c7e5 100644 --- a/.github/workflows/ministack.yml +++ b/.github/workflows/ministack.yml @@ -32,7 +32,7 @@ env: AWS_ACCESS_KEY_ID: "000000000000" AWS_DEFAULT_REGION: eu-west-1 AWS_EC2_METADATA_DISABLED: "true" - AWS_ENDPOINT_URL: http://127.0.0.1:4566 + AWS_ENDPOINT_URL: http://localhost:4566 AWS_REGION: eu-west-1 AWS_SECRET_ACCESS_KEY: test-only TF_IN_AUTOMATION: "true" @@ -45,7 +45,6 @@ jobs: timeout-minutes: 30 strategy: fail-fast: false - max-parallel: 4 matrix: example: - base @@ -53,6 +52,7 @@ jobs: - default - ephemeral - multi-runner + - multi-runner-v2 - termination-watcher terraform: - "1.4.0" diff --git a/.github/workflows/terraform.yml b/.github/workflows/terraform.yml index 6d91e10c66..f89bdfe742 100644 --- a/.github/workflows/terraform.yml +++ b/.github/workflows/terraform.yml @@ -85,6 +85,9 @@ jobs: "download-lambda", "lambda", "multi-runner", + "compute-providers/aws/microvm", + "compute-providers/aws/microvm/trust-policy", + "microvm-foundation", "runner-binaries-syncer", "runners", "setup-iam-permissions", @@ -155,7 +158,9 @@ jobs: "ephemeral", "termination-watcher", "multi-runner", - "external-managed-ssm-secrets" + "multi-runner-v2", + "external-managed-ssm-secrets", + "microvm-foundation" ] defaults: run: @@ -215,6 +220,8 @@ jobs: module: - modules/runners - modules/multi-runner + - modules/compute-providers/aws/microvm + - modules/compute-providers/aws/microvm/trust-policy defaults: run: working-directory: ${{ matrix.module }} diff --git a/docs/adr/002-runner-orchestration-provider-boundary.md b/docs/adr/002-runner-orchestration-provider-boundary.md index 3d77e2f3cd..06dc16a875 100644 --- a/docs/adr/002-runner-orchestration-provider-boundary.md +++ b/docs/adr/002-runner-orchestration-provider-boundary.md @@ -229,6 +229,36 @@ not below `modules/runner-config`. This keeps the common composition module small and prevents provider-owned resources from becoming part of the common contract. +### `runner-config` is the provider-neutral composition boundary + +`modules/runner-config` is an internal composition module selected by +`multi-runner`; it is not a standalone public entry point. It receives one +resolved runner configuration and owns the common runner identity, IAM role, +runner bootstrap parameters, SSM housekeeper composition, and the capability +connections between the selected providers. + +`runner-config` dispatches exactly one typed orchestration provider and one +typed compute provider. Provider selection is made from the plan-known typed +wrappers, not from a string discriminator or runtime fallback. The selected +provider receives the resolved common runner settings and returns only the +provider-specific resources, environment variables, IAM fragments, and +outputs required by the orchestration provider. + +Webhook queues, Lambda functions, schedules, and retry behavior remain owned +by the webhook orchestration provider. EC2 instances, Lambda MicroVM capacity, +image publication, and provider-specific bootstrap behavior remain owned by +their compute providers. `runner-config` connects these capabilities but does +not absorb either provider's implementation. + +For Lambda MicroVM runners, the image is an immutable runtime artifact. The +runner configuration and its sensitive, short-lived bootstrap value are +published through the runner-config SSM contract and retrieved when the +MicroVM starts. Tenant-specific runner configuration, registration tokens, and +JIT payloads must not be baked into the image or its Terraform configuration. +The image therefore supplies the runner and lifecycle-hook runtime, while the +selected compute provider supplies the lane-specific SSM path and execution +permissions. + ```mermaid flowchart TD Multi["multi-runner: translate and resolve"] --> Config["runner-config: compose one runner config"] diff --git a/docs/examples/index.md b/docs/examples/index.md index aee1d868b0..b7bdf60811 100644 --- a/docs/examples/index.md +++ b/docs/examples/index.md @@ -5,8 +5,11 @@ Examples are located in the [examples](https://github.com/github-aws-runners/ter - _[Default](default.md)_: The default example of the module - _[Ephemeral](ephemeral.md)_: Example usages of ephemeral runners based on the default example. - _[Multi Runner](multi-runner.md)_ : Example usage of creating a multi runner which creates multiple runners/ configurations with a single deployment. The examples including: "arm64", "windows", and "ubuntu" runners. +- _[Multi Runner v2](multi-runner-v2.md)_ : Example usage of the experimental v2 multi-runner configuration interface with shared defaults and per-lane overrides. - _[Permissions boundary](permissions-boundary.md)_: Example usages of permissions boundaries. - _[Prebuilt Images](prebuilt.md)_: Example usages of deploying runners with a custom prebuilt image. - _[Termination watcher](termination-watcher.md)_: Example usages of termination watcher. - _[Dedicated Mac Hosts](dedicated-mac-hosts.md)_: Example usage of setting up dedicated hosts for macOS runners. - _[Externally managed SSM secrets](external-managed-ssm-secrets.md)_: Example usage of externally managed SSM secrets for the GitHub App credentials. +- _[MicroVM foundation](microvm-foundation.md)_: Example usage of the regional Lambda MicroVM image-build and Network Connector prerequisites. +- _[Lambda MicroVM](microvm.md)_: Example usage of Linux ARM64 ephemeral runners backed by Lambda MicroVM images. diff --git a/docs/examples/microvm-foundation.md b/docs/examples/microvm-foundation.md new file mode 100644 index 0000000000..b92a148a9c --- /dev/null +++ b/docs/examples/microvm-foundation.md @@ -0,0 +1,3 @@ +# Lambda MicroVM foundation + +--8<-- "examples/microvm-foundation/README.md" diff --git a/docs/examples/multi-runner-v2.md b/docs/examples/multi-runner-v2.md new file mode 100644 index 0000000000..565b601ecb --- /dev/null +++ b/docs/examples/multi-runner-v2.md @@ -0,0 +1 @@ +--8<-- "examples/multi-runner-v2/README.md" diff --git a/docs/modules/public/microvm-foundation.md b/docs/modules/public/microvm-foundation.md new file mode 100644 index 0000000000..17129c131e --- /dev/null +++ b/docs/modules/public/microvm-foundation.md @@ -0,0 +1,3 @@ +# Lambda MicroVM regional foundation + +--8<-- "modules/microvm-foundation/README.md" diff --git a/examples/microvm-foundation/.terraform.lock.hcl b/examples/microvm-foundation/.terraform.lock.hcl new file mode 100644 index 0000000000..78cf3de9bd --- /dev/null +++ b/examples/microvm-foundation/.terraform.lock.hcl @@ -0,0 +1,49 @@ +# This file is maintained automatically by "terraform init". +# Manual edits may be lost in future updates. + +provider "registry.terraform.io/hashicorp/aws" { + version = "6.63.0" + constraints = ">= 6.61.0" + hashes = [ + "h1:9cre7jh1lSs/9igpgAcENMUAUlYW3HCtkav3up4oit0=", + "h1:dRlYHkc+r6fgzF57WC7Zjcmb6sF/6TTGDEgwGK+LAZY=", + "zh:005d56736afd17d963998c405cee6f434dbc23a415109f9435ff1542879ae611", + "zh:026ef126321a86ad7080b5d858e2527f96f5289678cbcd8856296e229c43339d", + "zh:06e0b58b2d1eddb5137fc86bee7ad2d07953c0bc3f57cccfc5ae0d2456068a3a", + "zh:07221735d61ababed84734e5ffcfc5bd59d01f29f029166ba5f2175895dceed1", + "zh:1a72db00583112bdb8c19b213a78a3f5de754fffc08f07e061f4e326289fab7d", + "zh:32968e74a53b03e97a084dc7050c22ef661fb5b3ea8a44f5a63e47bc45ad0e7c", + "zh:4b357dfe4b820e3e4acd2881cff8288b2186491e63416751f0d12692ba478ceb", + "zh:81e30884d7de686265e7d87bb92527e802878c65a378470ede2a1e9f4e40ccc9", + "zh:82e137297f6a5a08b9ce2138f7aabea245ad99495d9d9eff502f752d6ca90dbd", + "zh:8eb83b67099f0ea9df238a979dff933ff50ce06a2e3ff05a48556a10f10dd204", + "zh:9b12af85486a96aedd8d7984b0ff811a4b42e3d88dad1a3fb4c0b580d04fa425", + "zh:d0ba30886cbe41850fee689f51ef9088578f323cfd21817bb409951d43c465eb", + "zh:dd48e7089784454bc03d713e9057f5ca0ea1613bd402125054a51894957b7925", + "zh:f250fa81e54cf60fcb0e9c0fc4ac043f1ecc2ac24967f628b3609364fcab3d04", + "zh:f38fc09fc25a8d2cf89a4d4cd6a5ef7cb1aad72798dbdcad58b8876b6a551a54", + "zh:f7c7380fdf126e1901f2084588dbfd724c76cb131ccfa795a541219111103c06", + ] +} + +provider "registry.terraform.io/hashicorp/time" { + version = "0.14.1" + constraints = ">= 0.13.0" + hashes = [ + "h1:GJig5pIwiKDsiF73KLs7vWvDs76/x6DeNSxKrfqlA40=", + "h1:r93SxP++6gUlwCHDQ5OkRmcU8B0yv6ZA9nF0Dh6NJmA=", + "zh:0837ca5b057e5cff94dff7de2fcccafb4abaa33c45de193fe2853e684818a267", + "zh:15a122f72d9e0f34fc5384cc7ec089319641fee5c319748a3aa02fc42f459969", + "zh:342fb83093a280ea7ee0654feae1f5867c62eb8eebc1ab46f9a7ab0b4c878a62", + "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3", + "zh:99f169834d3370b8341381c6a9c7a8b01fb26027531faa38e6fb49cc23916f68", + "zh:9f482917c7a28cf2436578be7aa9f04f8c811aba8b5949e0223ea987a2757a91", + "zh:ac6b5b8732826f2d1129a8a4a038ac7a7a9ca7b77d2a4608e5703be1a1e2bff0", + "zh:c54782a27d58ce04f6696c6fc0b2cf1e2fba6bed239fb520521a7bce7d7193cb", + "zh:c8d0ddc8f575ecb44f025d54edbfe118e26397fe328a67be62325766f31eb6e7", + "zh:d043b96f204edd2353bf6b2a34e645ffdee2e9634d9bb747331320444810a538", + "zh:e32c288501ca9a6c9d22b52e839dd391fc7083d54ee6b8dc296ce0e6bd3e57ef", + "zh:e47fcc7bb4e9ab5cc522c3b06e4fa9c0bf94b84be8210bc6b1655c44acb2addc", + "zh:f61bf218322bcbe0bd2d56bba738e7fa485e9b54244e13aa12de741b37d450c0", + ] +} diff --git a/examples/microvm-foundation/README.md b/examples/microvm-foundation/README.md new file mode 100644 index 0000000000..bdc531bc12 --- /dev/null +++ b/examples/microvm-foundation/README.md @@ -0,0 +1,77 @@ +# MicroVM foundation example + +This example creates the regional dependencies required by the Lambda MicroVM +image build and runner runtime using the reusable module in this repository. + +Set real VPC and subnet IDs in `terraform.tfvars` (copy +`terraform.tfvars.example`). The module validates that every selected subnet +belongs to its configured VPC. + +```bash +terraform init +terraform apply +terraform output +``` + +Apply this foundation before building an image with the direct Packer commands +documented in `../../images/microvm/README.md`. Use the outputs as the build inputs: + +- `artifact_bucket_name` -> `MICROVM_ARTIFACT_BUCKET` +- `build_role_arn` -> `MICROVM_BUILD_ROLE_ARN` +- `connector_arns.cicd` -> `MICROVM_EGRESS_NETWORK_CONNECTOR_ARN` +- `usage_policy_arn` -> attach to the control-plane role used by the runner example + +The foundation module owns regional storage, build IAM, Network Connectors, +and the reusable runtime policy. It does not publish an image or create the +runner control plane; those steps remain explicit and can be performed after +the foundation is available. + + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.4.0 | +| [aws](#requirement\_aws) | >= 6.61 | + +## Providers + +No providers. + +## Modules + +| Name | Source | Version | +|------|--------|---------| +| [microvm\_foundation](#module\_microvm\_foundation) | ../../modules/microvm-foundation | n/a | + +## Resources + +No resources. + +## Inputs + +| Name | Description | Type | Default | Required | +|------|-------------|------|---------|:--------:| +| [artifact\_bucket\_name](#input\_artifact\_bucket\_name) | Optional globally unique S3 bucket name. When null, AWS generates the bucket name. | `string` | `null` | no | +| [artifact\_retention\_days](#input\_artifact\_retention\_days) | Number of days to retain current and noncurrent build artifacts. | `number` | `30` | no | +| [aws\_profile](#input\_aws\_profile) | Optional local AWS CLI profile. Leave null when credentials are provided by the environment or role. | `string` | `null` | no | +| [aws\_region](#input\_aws\_region) | AWS region in which to create the MicroVM foundation. | `string` | `"eu-west-1"` | no | +| [build\_policy\_name\_prefix](#input\_build\_policy\_name\_prefix) | Name prefix for the Lambda MicroVM build policy. | `string` | `"github-actions-runner-microvm-build-policy-"` | no | +| [build\_role\_name\_prefix](#input\_build\_role\_name\_prefix) | Name prefix for the Lambda MicroVM build role. | `string` | `"github-actions-runner-microvm-build-"` | no | +| [ecr\_repository\_arns](#input\_ecr\_repository\_arns) | Optional private ECR repository ARNs used by the image build. | `set(string)` | `[]` | no | +| [image\_name\_prefix](#input\_image\_name\_prefix) | Reserved Lambda MicroVM image-name namespace used by the runtime policy. | `string` | `"github-actions-runner-ubuntu-arm64"` | no | +| [network\_connector\_operator\_role\_name\_prefix](#input\_network\_connector\_operator\_role\_name\_prefix) | Name prefix for the Lambda Network Connector operator role. | `string` | `"github-actions-microvm-net-operator-"` | no | +| [network\_connectors](#input\_network\_connectors) | VPC and subnet configuration for regional Lambda MicroVM egress connectors. |
map(object({
name = string
vpc_id = string
subnet_ids = set(string)
network_protocol = optional(string, "IPv4")
}))
| n/a | yes | +| [tags](#input\_tags) | Additional tags applied by the foundation module. | `map(string)` |
{
"Component": "microvm-foundation"
}
| no | +| [usage\_policy\_name\_prefix](#input\_usage\_policy\_name\_prefix) | Name prefix for the Lambda MicroVM runtime usage policy. | `string` | `"github-actions-runner-microvm-runtime-usage-policy-"` | no | + +## Outputs + +| Name | Description | +|------|-------------| +| [artifact\_bucket\_name](#output\_artifact\_bucket\_name) | S3 bucket to pass to the MicroVM image build. | +| [artifact\_prefix](#output\_artifact\_prefix) | S3 prefix used for MicroVM build artifacts. | +| [build\_role\_arn](#output\_build\_role\_arn) | Lambda build role ARN to pass to the image build. | +| [connector\_arns](#output\_connector\_arns) | Regional Network Connector ARNs keyed by configuration name. | +| [usage\_policy\_arn](#output\_usage\_policy\_arn) | Unattached runtime usage policy for the runner control-plane role. | + diff --git a/examples/microvm-foundation/main.tf b/examples/microvm-foundation/main.tf new file mode 100644 index 0000000000..27ed22c816 --- /dev/null +++ b/examples/microvm-foundation/main.tf @@ -0,0 +1,15 @@ +module "microvm_foundation" { + source = "../../modules/microvm-foundation" + + aws_region = var.aws_region + tags = var.tags + build_policy_name_prefix = var.build_policy_name_prefix + build_role_name_prefix = var.build_role_name_prefix + network_connector_operator_role_name_prefix = var.network_connector_operator_role_name_prefix + usage_policy_name_prefix = var.usage_policy_name_prefix + artifact_bucket_name = var.artifact_bucket_name + artifact_retention_days = var.artifact_retention_days + image_name_prefix = var.image_name_prefix + ecr_repository_arns = var.ecr_repository_arns + network_connectors = var.network_connectors +} diff --git a/examples/microvm-foundation/outputs.tf b/examples/microvm-foundation/outputs.tf new file mode 100644 index 0000000000..709d43f933 --- /dev/null +++ b/examples/microvm-foundation/outputs.tf @@ -0,0 +1,24 @@ +output "artifact_bucket_name" { + description = "S3 bucket to pass to the MicroVM image build." + value = module.microvm_foundation.artifact_bucket_name +} + +output "artifact_prefix" { + description = "S3 prefix used for MicroVM build artifacts." + value = module.microvm_foundation.artifact_prefix +} + +output "build_role_arn" { + description = "Lambda build role ARN to pass to the image build." + value = module.microvm_foundation.build_role_arn +} + +output "connector_arns" { + description = "Regional Network Connector ARNs keyed by configuration name." + value = module.microvm_foundation.connector_arns +} + +output "usage_policy_arn" { + description = "Unattached runtime usage policy for the runner control-plane role." + value = module.microvm_foundation.usage_policy_arn +} diff --git a/examples/microvm-foundation/providers.tf b/examples/microvm-foundation/providers.tf new file mode 100644 index 0000000000..9e8a8a7627 --- /dev/null +++ b/examples/microvm-foundation/providers.tf @@ -0,0 +1,4 @@ +provider "aws" { + region = var.aws_region + profile = var.aws_profile +} diff --git a/examples/microvm-foundation/terraform.tfvars.example b/examples/microvm-foundation/terraform.tfvars.example new file mode 100644 index 0000000000..ef864c384c --- /dev/null +++ b/examples/microvm-foundation/terraform.tfvars.example @@ -0,0 +1,15 @@ +aws_region = "eu-west-1" + +network_connectors = { + cicd = { + name = "github-actions-runner-egress" + vpc_id = "vpc-0123456789abcdef0" + subnet_ids = ["subnet-0123456789abcdef0", "subnet-0fedcba9876543210"] + } +} + +# Add the private ECR repository that contains the regional Ubuntu base image +# when the image build pulls from ECR. +# ecr_repository_arns = [ +# "arn:aws:ecr:eu-west-1:123456789012:repository/actions-runner-base-image", +# ] diff --git a/examples/microvm-foundation/variables.tf b/examples/microvm-foundation/variables.tf new file mode 100644 index 0000000000..aa8d9fb002 --- /dev/null +++ b/examples/microvm-foundation/variables.tf @@ -0,0 +1,79 @@ +variable "aws_profile" { + type = string + description = "Optional local AWS CLI profile. Leave null when credentials are provided by the environment or role." + default = null + nullable = true +} + +variable "aws_region" { + type = string + description = "AWS region in which to create the MicroVM foundation." + default = "eu-west-1" +} + +variable "tags" { + type = map(string) + description = "Additional tags applied by the foundation module." + default = { + Component = "microvm-foundation" + } +} + +variable "build_policy_name_prefix" { + type = string + description = "Name prefix for the Lambda MicroVM build policy." + default = "github-actions-runner-microvm-build-policy-" +} + +variable "usage_policy_name_prefix" { + type = string + description = "Name prefix for the Lambda MicroVM runtime usage policy." + default = "github-actions-runner-microvm-runtime-usage-policy-" +} + +variable "build_role_name_prefix" { + type = string + description = "Name prefix for the Lambda MicroVM build role." + default = "github-actions-runner-microvm-build-" +} + +variable "network_connector_operator_role_name_prefix" { + type = string + description = "Name prefix for the Lambda Network Connector operator role." + default = "github-actions-microvm-net-operator-" +} + +variable "artifact_bucket_name" { + type = string + description = "Optional globally unique S3 bucket name. When null, AWS generates the bucket name." + default = null + nullable = true +} + +variable "artifact_retention_days" { + type = number + description = "Number of days to retain current and noncurrent build artifacts." + default = 30 +} + +variable "image_name_prefix" { + type = string + description = "Reserved Lambda MicroVM image-name namespace used by the runtime policy." + default = "github-actions-runner-ubuntu-arm64" +} + +variable "ecr_repository_arns" { + type = set(string) + description = "Optional private ECR repository ARNs used by the image build." + default = [] +} + +variable "network_connectors" { + type = map(object({ + name = string + vpc_id = string + subnet_ids = set(string) + network_protocol = optional(string, "IPv4") + })) + description = "VPC and subnet configuration for regional Lambda MicroVM egress connectors." +} diff --git a/examples/microvm-foundation/versions.tf b/examples/microvm-foundation/versions.tf new file mode 100644 index 0000000000..e72a26b153 --- /dev/null +++ b/examples/microvm-foundation/versions.tf @@ -0,0 +1,10 @@ +terraform { + required_version = ">= 1.4.0" + + required_providers { + aws = { + source = "hashicorp/aws" + version = ">= 6.61" + } + } +} diff --git a/examples/multi-runner-v2/.terraform.lock.hcl b/examples/multi-runner-v2/.terraform.lock.hcl new file mode 100644 index 0000000000..c96d2b19bf --- /dev/null +++ b/examples/multi-runner-v2/.terraform.lock.hcl @@ -0,0 +1,93 @@ +# This file is maintained automatically by "terraform init". +# Manual edits may be lost in future updates. + +provider "registry.terraform.io/hashicorp/aws" { + version = "6.63.0" + constraints = ">= 5.0.0, >= 6.21.0, >= 6.33.0" + hashes = [ + "h1:9cre7jh1lSs/9igpgAcENMUAUlYW3HCtkav3up4oit0=", + "h1:dRlYHkc+r6fgzF57WC7Zjcmb6sF/6TTGDEgwGK+LAZY=", + "zh:005d56736afd17d963998c405cee6f434dbc23a415109f9435ff1542879ae611", + "zh:026ef126321a86ad7080b5d858e2527f96f5289678cbcd8856296e229c43339d", + "zh:06e0b58b2d1eddb5137fc86bee7ad2d07953c0bc3f57cccfc5ae0d2456068a3a", + "zh:07221735d61ababed84734e5ffcfc5bd59d01f29f029166ba5f2175895dceed1", + "zh:1a72db00583112bdb8c19b213a78a3f5de754fffc08f07e061f4e326289fab7d", + "zh:32968e74a53b03e97a084dc7050c22ef661fb5b3ea8a44f5a63e47bc45ad0e7c", + "zh:4b357dfe4b820e3e4acd2881cff8288b2186491e63416751f0d12692ba478ceb", + "zh:81e30884d7de686265e7d87bb92527e802878c65a378470ede2a1e9f4e40ccc9", + "zh:82e137297f6a5a08b9ce2138f7aabea245ad99495d9d9eff502f752d6ca90dbd", + "zh:8eb83b67099f0ea9df238a979dff933ff50ce06a2e3ff05a48556a10f10dd204", + "zh:9b12af85486a96aedd8d7984b0ff811a4b42e3d88dad1a3fb4c0b580d04fa425", + "zh:d0ba30886cbe41850fee689f51ef9088578f323cfd21817bb409951d43c465eb", + "zh:dd48e7089784454bc03d713e9057f5ca0ea1613bd402125054a51894957b7925", + "zh:f250fa81e54cf60fcb0e9c0fc4ac043f1ecc2ac24967f628b3609364fcab3d04", + "zh:f38fc09fc25a8d2cf89a4d4cd6a5ef7cb1aad72798dbdcad58b8876b6a551a54", + "zh:f7c7380fdf126e1901f2084588dbfd724c76cb131ccfa795a541219111103c06", + ] +} + +provider "registry.terraform.io/hashicorp/local" { + version = "2.9.0" + constraints = "~> 2.0" + hashes = [ + "h1:9rBZCMNpxKwMlRbWH2QpwD3kqUCAejdOZQ/aiiDObXQ=", + "h1:m24fjcInWvTVZ1XSo2MaNuKPe+X/gfG8SIi09rA7a7M=", + "zh:0baa4566cf77f1ff52f4293d1c8536202dd23edc197c3196413a28343c3ac3a0", + "zh:16b5559c3c07088ddad11a9bb9e9c0799999363c2958e9a5be2bcbbf2cd9ca64", + "zh:197c79015a10d1cce904a8ea722cbc750c42aeae2da53f44a6a0751d9fd1aa90", + "zh:29d0b03e5343a80677ebfeb2e2c31cbe4b1f65e736e53417454a4277fec2544c", + "zh:4896bfa6cf1d2fd562b47ef2e87f47862ae92a04f8ad5d764380f0c6653473b8", + "zh:531f8529cbca49f681883e57761a05a8398afaef6d1ab0d205d26bf12f4428e8", + "zh:6aaf5011d83161c86d2bfb80c0923ec934e578288758da2f37acb7aec129004b", + "zh:7430275253d3d3c40aa6179e0ec0d63212874dbbc06c5a51b9d07ec590f9756c", + "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3", + "zh:be17dc611e95e26cdf6cad79dfccf1064f0e32032a2efeb939a9bbe7fb1cbfe9", + "zh:f0e3b0aa644202e1d79d2000dca91f6019425da71e9800fa23f27e51c034f195", + "zh:f62bae4519e4ead49182ddc8afe8cf61e2a4c3ba3973b0fbba967736a2696aa3", + "zh:fcafa360a5b0b96244f26f4e3a6d642b716a376557142c2442ff2fb12d11da18", + ] +} + +provider "registry.terraform.io/hashicorp/null" { + version = "3.3.1" + constraints = "~> 3.0, ~> 3.2" + hashes = [ + "h1:TuxJq10DVnRP7c5HBZPyyvQGcckNVfijyU1eXEu5e4M=", + "h1:m5FqidbIgh+E9OigiZh8/xbkvpUQFSj3hZo/jqNLCLQ=", + "zh:08c59776542ea16e5a8545752787b17ff412922182b4cfabe16139197be8ac44", + "zh:123109cc7e5ed6d515787fbc212f2a3fd5e75647bb24ab7c801ccd4d4ed42451", + "zh:14b3fa4372754b54844b41d5dbd4671a292d8d6828b90169061feb4d7b15dd05", + "zh:56a4daaa3212f57b764bf3d1f333141c6610c5f21abb240e0111221f7c7fa4d4", + "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3", + "zh:7e888a026dbacd2474a42264227ae35f639780f0f0c613529d10a95cd61988b3", + "zh:85a53646267e87d600df7124e4767ffde9bba3b6356d45d961618bdd68131cc7", + "zh:8ffa0e9c7c39b2ab0905b472465d6e35ef0b776b3f6273bb34c150340b61bff1", + "zh:9846510a1841530d4403f4818e233f91e3b3bade7441047599fbf800742f65be", + "zh:afa98d44860875f037c6def0a7e6ff208e042712ba771f620482b143cd336891", + "zh:bdca130d9ef27488ae0b13bc8fd8019e8bbdd4f2ceff29da066bd333165d68c5", + "zh:cb3b94cbca88210dd0d1f11e2b8a89333f48c3857faf8f70f589072ce7c28610", + "zh:f0c0ba87925fe32f84b80f7513b1efb1b0866f51f899ba825e95ad59ff09b018", + ] +} + +provider "registry.terraform.io/hashicorp/random" { + version = "3.9.0" + constraints = "~> 3.0" + hashes = [ + "h1:OO+IuvQJSPmWdN8AyyIEvPJbLvDQpgX/zbktoa9KsJE=", + "h1:UlBuNVuCGJ39tTv2c5gz2NRZnQbXfbIWbTzWcth5o74=", + "zh:161ad0bd9a75768c82f53fb6e7172a9d8be2d4889b012645a34795031aaf1bf1", + "zh:19dc9a5b17729725ccfc4f45b0500af0ee5bc6b6b160c7adb8f2bf617d2c80ea", + "zh:269eda8fe42daa7974d5a34d166c3ba9defe80cde86c01e4dadcfdf2e1f05e5f", + "zh:373f7c65566f8f2cc7f45d698654feb9d988996957e1266a69ca00c52d6d16d0", + "zh:5599d16804c41c83009ec621b6d6b6f74e102f5827678a4750f8809055546b61", + "zh:583be0440469a22bff70dcfa56593b01566860b29607437264adb51060cf46fc", + "zh:5f211d8ec3f2e1f414870d9584bfe26e6995560ef81c748f8447a48164767398", + "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3", + "zh:7b547fd16216761ef86efc3ed516ac5ac0c5c42b7c7eb24a08cef2d93f69ed5e", + "zh:7e7c0679daf2a382151d05068c8c3f0dae6b7b7dccf818827b73dd08638df2ef", + "zh:8089dec888a8038b9b4fb23b3df7e1057293dbc5b60b42cc47ff690d69d4b61b", + "zh:c51f15a031edfd6f23ce8ced3446ca7f8d8d647e2499890d7d5d10d5016d7257", + "zh:c94784f005708890dc6895afd53636ec00ec1e430b15d41e5aebfb1d4b39bd04", + ] +} diff --git a/examples/multi-runner-v2/README.md b/examples/multi-runner-v2/README.md new file mode 100644 index 0000000000..f8cea507ec --- /dev/null +++ b/examples/multi-runner-v2/README.md @@ -0,0 +1,74 @@ +# Multi-runner v2 example + +This example demonstrates the experimental multi-runner v2 interface. Shared +defaults are configured with `global_config*` variables, while +each runner lane uses `multi_runner_config` for its matcher, +runner lifecycle, and compute-provider settings. + +The example creates three lanes from one deployment: + +- Linux ARM64 Amazon Linux runners. +- Ephemeral Linux x64 Amazon Linux runners with job retry enabled. +- Windows x64 Server Core 2022 runners. + +The v2 interface keeps provider-owned settings inside the selected provider +configuration. For example, VPC and subnet settings are under +`global_config_compute_provider.aws.ec2`, while the per-lane +instance types and AMI filter are under each lane's compute provider block. + +Configure the GitHub App variables before applying: + +```bash +terraform init +terraform apply \ + -var='github_app={id="123456",key_base64="..."}' +``` + +The `github_app` value is sensitive and should be supplied through a secure +variable source in real deployments rather than committed to configuration. + + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.4.0 | +| [aws](#requirement\_aws) | >= 6.33 | +| [local](#requirement\_local) | ~> 2.0 | +| [random](#requirement\_random) | ~> 3.0 | + +## Providers + +| Name | Version | +|------|---------| +| [random](#provider\_random) | 3.9.0 | + +## Modules + +| Name | Source | Version | +|------|--------|---------| +| [base](#module\_base) | ../base | n/a | +| [runners](#module\_runners) | ../../modules/multi-runner | n/a | +| [webhook\_github\_app](#module\_webhook\_github\_app) | ../../modules/webhook-github-app | n/a | + +## Resources + +| Name | Type | +|------|------| +| [random_id.random](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/id) | resource | + +## Inputs + +| Name | Description | Type | Default | Required | +|------|-------------|------|---------|:--------:| +| [aws\_region](#input\_aws\_region) | AWS region to deploy to. | `string` | `"eu-west-1"` | no | +| [environment](#input\_environment) | Environment name, used as prefix. | `string` | `null` | no | +| [github\_app](#input\_github\_app) | GitHub App ID and base64-encoded private key. |
object({
id = string
key_base64 = string
})
| n/a | yes | + +## Outputs + +| Name | Description | +|------|-------------| +| [webhook\_endpoint](#output\_webhook\_endpoint) | n/a | +| [webhook\_secret](#output\_webhook\_secret) | n/a | + diff --git a/examples/multi-runner-v2/main.tf b/examples/multi-runner-v2/main.tf new file mode 100644 index 0000000000..ca740ca078 --- /dev/null +++ b/examples/multi-runner-v2/main.tf @@ -0,0 +1,173 @@ +locals { + environment = var.environment != null ? var.environment : "multi-runner-v2" + aws_region = var.aws_region +} + +resource "random_id" "random" { + byte_length = 20 +} + +module "base" { + source = "../base" + + prefix = local.environment + aws_region = local.aws_region +} + +module "runners" { + source = "../../modules/multi-runner" + + prefix = local.environment + aws_region = local.aws_region + + global_config = { + tags = { + Example = local.environment + Project = "ProjectX" + } + runner = { + os = "linux" + architecture = "x64" + extra_labels = ["v2"] + } + } + + global_config_github = { + app = { + key_base64 = var.github_app.key_base64 + id = var.github_app.id + webhook_secret = random_id.random.hex + } + } + + global_config_lambda = { + architecture = "arm64" + } + + global_config_orchestration_provider = { + webhook = { + eventbridge = { + enabled = true + accept_events = ["workflow_job"] + } + } + } + + global_config_compute_provider = { + aws = { + ec2 = { + vpc_id = module.base.vpc.vpc_id + subnet_ids = module.base.vpc.private_subnets + ssm_enabled = true + runner_binaries = { + enabled = true + } + } + } + } + + multi_runner_config = { + linux-arm64 = { + runner = { + architecture = "arm64" + name_prefix = "amazon-arm64-" + extra_labels = ["amazon"] + } + orchestration_provider = { + webhook = { + runner = { + maximum_count = 1 + } + matcherConfig = { + exactMatch = true + labelMatchers = [["self-hosted", "linux", "arm64", "amazon"]] + } + } + } + compute_provider = { + aws = { + ec2 = { + instance_types = ["t4g.large", "c6g.large"] + } + } + } + } + + linux-x64 = { + runner = { + name_prefix = "amazon-x64-" + extra_labels = ["amazon"] + } + orchestration_provider = { + webhook = { + runner = { + ephemeral = true + maximum_count = 1 + } + matcherConfig = { + labelMatchers = [["self-hosted", "linux", "x64", "amazon"]] + exactMatch = false + priority = 1 + } + queue = { + delay_webhook_event = 0 + } + job_retry = { + enabled = true + } + } + } + compute_provider = { + aws = { + ec2 = { + instance_types = ["m5a.large", "m5ad.large"] + } + } + } + } + + windows-x64 = { + runner = { + os = "windows" + name_prefix = "windows-x64-" + } + orchestration_provider = { + webhook = { + runner = { + boot_time_in_minutes = 20 + maximum_count = 1 + } + matcherConfig = { + exactMatch = true + labelMatchers = [["self-hosted", "windows", "x64", "servercore-2022"]] + } + } + } + compute_provider = { + aws = { + ec2 = { + instance_types = ["m5.large", "c5.large"] + ami = { + filter = { + name = ["Windows_Server-2022-English-Full-ECS_Optimized-*"] + state = ["available"] + } + } + } + } + } + } + } +} + +module "webhook_github_app" { + source = "../../modules/webhook-github-app" + depends_on = [module.runners] + + github_app = { + key_base64 = var.github_app.key_base64 + id = var.github_app.id + webhook_secret = random_id.random.hex + } + webhook_endpoint = module.runners.webhook.endpoint +} diff --git a/examples/multi-runner-v2/outputs.tf b/examples/multi-runner-v2/outputs.tf new file mode 100644 index 0000000000..1feaf2e671 --- /dev/null +++ b/examples/multi-runner-v2/outputs.tf @@ -0,0 +1,8 @@ +output "webhook_endpoint" { + value = module.runners.webhook.endpoint +} + +output "webhook_secret" { + sensitive = true + value = random_id.random.hex +} diff --git a/examples/multi-runner-v2/providers.tf b/examples/multi-runner-v2/providers.tf new file mode 100644 index 0000000000..eca2fe96a7 --- /dev/null +++ b/examples/multi-runner-v2/providers.tf @@ -0,0 +1,9 @@ +provider "aws" { + region = local.aws_region + + default_tags { + tags = { + Example = local.environment + } + } +} diff --git a/examples/multi-runner-v2/variables.tf b/examples/multi-runner-v2/variables.tf new file mode 100644 index 0000000000..2a7f7eda54 --- /dev/null +++ b/examples/multi-runner-v2/variables.tf @@ -0,0 +1,23 @@ +variable "github_app" { + description = "GitHub App ID and base64-encoded private key." + + type = object({ + id = string + key_base64 = string + }) + sensitive = true +} + +variable "environment" { + description = "Environment name, used as prefix." + + type = string + default = null +} + +variable "aws_region" { + description = "AWS region to deploy to." + + type = string + default = "eu-west-1" +} diff --git a/examples/multi-runner-v2/versions.tf b/examples/multi-runner-v2/versions.tf new file mode 100644 index 0000000000..1dfb3e5774 --- /dev/null +++ b/examples/multi-runner-v2/versions.tf @@ -0,0 +1,17 @@ +terraform { + required_providers { + aws = { + source = "hashicorp/aws" + version = ">= 6.33" + } + local = { + source = "hashicorp/local" + version = "~> 2.0" + } + random = { + source = "hashicorp/random" + version = "~> 3.0" + } + } + required_version = ">= 1.4.0" +} diff --git a/examples/multi-runner/README.md b/examples/multi-runner/README.md index 5bb10f7248..960030c099 100644 --- a/examples/multi-runner/README.md +++ b/examples/multi-runner/README.md @@ -56,7 +56,7 @@ terraform output -raw webhook_secret | Name | Version | |------|---------| -| [terraform](#requirement\_terraform) | >= 1.3.0 | +| [terraform](#requirement\_terraform) | >= 1.4.0 | | [aws](#requirement\_aws) | >= 6.33 | | [local](#requirement\_local) | ~> 2.0 | | [random](#requirement\_random) | ~> 3.0 | diff --git a/examples/multi-runner/versions.tf b/examples/multi-runner/versions.tf index 666b978aac..1dfb3e5774 100644 --- a/examples/multi-runner/versions.tf +++ b/examples/multi-runner/versions.tf @@ -13,5 +13,5 @@ terraform { version = "~> 3.0" } } - required_version = ">= 1.3.0" + required_version = ">= 1.4.0" } diff --git a/mkdocs.yaml b/mkdocs.yaml index 849b9a53dc..0188c772eb 100644 --- a/mkdocs.yaml +++ b/mkdocs.yaml @@ -67,6 +67,7 @@ nav: - AMI Housekeeper: modules/public/ami-housekeeper.md - Lambda Downloader: modules/public/download-lambda.md - Setup IAM permissions: modules/public/setup-iam-permissions.md + - MicroVM foundation: modules/public/microvm-foundation.md - Submodules (internal): - Runners: modules/internal/runners.md - Syncer: modules/internal/runner-binaries-syncer.md @@ -77,6 +78,7 @@ nav: - Overview: examples/index.md - Default: examples/default.md - Multi Runner: examples/multi-runner.md + - Multi Runner v2: examples/multi-runner-v2.md - Ephemeral: examples/ephemeral.md - External managed secrets: examples/external-managed-ssm-secrets.md - Custom AMI: examples/prebuilt.md diff --git a/modules/compute-providers/aws/microvm/README.md b/modules/compute-providers/aws/microvm/README.md new file mode 100644 index 0000000000..07ecf5d50f --- /dev/null +++ b/modules/compute-providers/aws/microvm/README.md @@ -0,0 +1,70 @@ +# AWS Lambda MicroVM runner provider + +This internal module implements the AWS Lambda MicroVM compute provider used by `runner-config`. It returns provider-specific Lambda environment variables, control-plane IAM policy fragments, selected image metadata, native runtime and optional CloudWatch-agent log groups, and collected-file definitions through the common provider contract; the parent owns the runner role, Lambda resources, queues, schedules, and Parameter Store lifecycle. + +Select it with the `compute_provider.aws.microvm` leaf. The Terraform dispatch key is `aws_microvm`, while the runtime `COMPUTE_PROVIDER_TYPE` remains `microvm` for compatibility with the control-plane Lambda. MicroVM lanes require Linux on ARM64 and ephemeral webhook orchestration with just-in-time configuration enabled. + +MicroVM runners use the provider's fixed 28,800-second (8-hour) lifetime; this is not a Terraform input. + +The resolved provider-neutral `runner.iam.role` is passed to Lambda as the MicroVM execution role. The provider creates `/github-self-hosted-runners//microvm` with the common observability lifecycle and derives a metadata prefix at `//microvm-metadata`. Scale-up, scale-down, and pool use that non-secret prefix for MicroVM ownership and lifecycle state; the runner role can read only the lane's `*.tags` metadata records, the CloudWatch enablement parameter, and its lane-scoped one-time JIT parameter. It can also delete that JIT parameter and write to the provider-managed log groups. MicroVMs sharing the execution role can read the tag records for that lane, but not the ownership and cleanup records. When the runner role is supplied externally, its Lambda trust and these permissions remain caller-owned. + + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.4.0 | +| [aws](#requirement\_aws) | >= 6.33 | + +## Providers + +| Name | Version | +|------|---------| +| [aws](#provider\_aws) | >= 6.33 | +| [terraform](#provider\_terraform) | n/a | + +## Modules + +No modules. + +## Resources + +| Name | Type | +|------|------| +| [aws_cloudwatch_log_group.gh_runners](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/cloudwatch_log_group) | resource | +| [aws_cloudwatch_log_group.runtime](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/cloudwatch_log_group) | resource | +| [aws_ssm_parameter.cloudwatch_agent_config_runner](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ssm_parameter) | resource | +| [aws_ssm_parameter.runner_enable_cloudwatch](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ssm_parameter) | resource | +| [terraform_data.validate_config](https://registry.terraform.io/providers/hashicorp/terraform/latest/docs/resources/data) | resource | +| [terraform_data.validate_runner](https://registry.terraform.io/providers/hashicorp/terraform/latest/docs/resources/data) | resource | +| [aws_caller_identity.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/caller_identity) | data source | +| [aws_iam_policy_document.runner_cloudwatch](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.runner_metadata](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.runner_runtime_logs](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.runner_ssm_jit](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.scale_down](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.scale_up](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | + +## Inputs + +| Name | Description | Type | Default | Required | +|------|-------------|------|---------|:--------:| +| [aws\_partition](#input\_aws\_partition) | AWS partition used to construct IAM ARNs. | `string` | `"aws"` | no | +| [aws\_region](#input\_aws\_region) | AWS region used by compute-provider resources and policy documents. | `string` | n/a | yes | +| [config](#input\_config) | Lambda MicroVM compute-provider configuration. Paths match `compute_provider.aws.microvm` in runner-config.

- `image_arn`: ARN of the MicroVM image used to run GitHub runners.
- `image_version`: Optional MicroVM image version.
- `ingress_network_connectors`: Up to 10 Lambda network-connector ARNs passed to RunMicrovm.
- `egress_network_connectors`: Up to 10 Lambda network-connector ARNs passed to RunMicrovm.
- `cloudwatch_agent.enabled`: Enables the image CloudWatch agent through the shared runner configuration path.
- `cloudwatch_agent.config`: Optional complete CloudWatch agent configuration. Null renders the provider default from `log_files`. Custom log destinations must also be declared in `log_files` so Terraform creates their groups and IAM permissions.
- `log_files`: Optional files collected by the CloudWatch agent. Null uses the MicroVM defaults.
- `log_files[].log_group_name`: CloudWatch log-group name before optional prefixing.
- `log_files[].prefix_log_group`: Prefixes the log-group name with the runner configuration path.
- `log_files[].file_path`: File or glob read by the CloudWatch agent.
- `log_files[].log_stream_name`: Log-stream template. The image replaces `{microvm_id}` with the current MicroVM identifier.
- `log_files[].log_class`: CloudWatch log-group class for the collected file.
- `environment_variables`: Additional provider-specific Lambda environment variables merged into scale-up, scale-down, and pool.
- `iam.resource_arns.images`: Optional MicroVM image ARN allowlist for RunMicrovm and TerminateMicrovm. Null restricts both actions to `image_arn`; set an explicit list when dynamic image overrides are enabled. Provider-required list and connector permissions remain separately scoped to `*`.
- `iam.additional_policy_json.scale_up`: Optional additional provider policy attached separately to the scale-up Lambda role.
- `iam.managed_policies.scale_up`: Optional managed-policy wrapper attached to the scale-up Lambda role. Wrapper presence controls resource creation during planning.
- `iam.managed_policies.scale_up.arn`: ARN of the scale-up managed policy. The ARN may remain unknown until apply.
- `iam.managed_policies.pool`: Optional managed-policy wrapper attached to the pool Lambda role. Wrapper presence controls resource creation during planning.
- `iam.managed_policies.pool.arn`: ARN of the pool managed policy. The ARN may remain unknown until apply. |
object({
image_arn = string
image_version = optional(string, null)
ingress_network_connectors = optional(list(string), [])
egress_network_connectors = optional(list(string), [])
cloudwatch_agent = optional(object({
enabled = optional(bool, true)
config = optional(string, null)
}), {})
log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
environment_variables = optional(map(string), {})
iam = optional(object({
resource_arns = optional(object({
images = optional(list(string), null)
}), {})
additional_policy_json = optional(object({
scale_up = optional(string, null)
}), {})
managed_policies = optional(object({
scale_up = optional(object({
arn = string
}), null)
pool = optional(object({
arn = string
}), null)
}), {})
}), {})
})
| n/a | yes | +| [github](#input\_github) | GitHub Enterprise Server settings available to compute-provider bootstrap data.

- `enterprise_server.url`: Optional GitHub Enterprise Server base URL. Null selects GitHub.com.
- `enterprise_server.ssl_verify`: Enables TLS certificate verification for GitHub Enterprise Server. |
object({
enterprise_server = optional(object({
url = optional(string, null)
ssl_verify = optional(bool, true)
}), {})
})
| `{}` | no | +| [observability](#input\_observability) | Provider-neutral observability settings applied to the provider-managed MicroVM runtime log group.

- `logs.retention_in_days`: CloudWatch Logs retention period.
- `logs.kms_key_id`: Optional KMS key ID or ARN used to encrypt the log group.
- `logs.class`: CloudWatch log-group class.
- `logs.tags`: Tags merged after module-level tags on the log group. |
object({
logs = optional(object({
retention_in_days = optional(number, 180)
kms_key_id = optional(string, null)
class = optional(string, "STANDARD")
tags = optional(map(string), {})
}), {})
})
| `{}` | no | +| [prefix](#input\_prefix) | Prefix used to identify resources created for the runner configuration. | `string` | `"github-actions"` | no | +| [runner](#input\_runner) | Resolved runner settings consumed by the Lambda MicroVM compute provider.

- `os`: Runner operating system. Lambda MicroVM requires `linux`.
- `architecture`: Runner distribution architecture. Lambda MicroVM requires `arm64`.
- `name_prefix`: Prefix added to registered runner names.
- `run_as_root`: Runs the runner service as root.
- `run_as`: Operating-system user used when `run_as_root` is false.
- `hooks.job_started`: Script installed as the runner job-started hook.
- `hooks.job_completed`: Script installed as the runner job-completed hook.
- `iam.role.arn`: Resolved runner-role ARN used as the MicroVM execution role and referenced by provider policies.
- `iam.role.name`: Resolved runner-role name used by provider resources.
- `iam.role.managed`: Whether runner-config manages the resolved runner role. Callers own an external role and must grant it `ssm:GetParameter` on the lane's `microvm-metadata/*.tags` and `enable_cloudwatch` parameters, `ssm:GetParameter` and `ssm:DeleteParameter` on the lane token path, plus `logs:CreateLogStream` and `logs:PutLogEvents` on the provider-managed runtime log group. When the CloudWatch agent is enabled, it also needs `ssm:GetParameter` on `cloudwatch_agent_config_runner` and stream access to the configured runner log groups.
- `iam.managed_policy_arns`: Common managed-policy ARNs returned with the provider-specific runner policies for attachment by runner-config.
- `iam.path`: IAM path available to provider-managed IAM resources. Null derives the path from `prefix`. |
object({
os = optional(string, "linux")
architecture = optional(string, "arm64")
name_prefix = optional(string, "")
run_as_root = optional(bool, false)
run_as = optional(string, "ec2-user")
hooks = optional(object({
job_started = optional(string, "")
job_completed = optional(string, "")
}), {})
iam = object({
role = object({
arn = string
name = string
managed = optional(bool, true)
})
managed_policy_arns = optional(map(string), {})
path = optional(string, null)
})
})
| n/a | yes | +| [ssm](#input\_ssm) | Parameter Store paths and tag scopes available to compute-provider bootstrap resources.

- `paths.root`: Root Parameter Store path for the runner configuration.
- `paths.tokens`: Path segment used for registration tokens and just-in-time configuration.
- `paths.config`: Path segment used for persistent runner and provider configuration. MicroVM control-plane metadata is stored under its `microvm-metadata` child prefix.
- `tags`: Shared SSM tags that override module-level `tags`.
- `parameters.tags`: Parameter-specific tags that override module-level and shared SSM tags. |
object({
paths = object({
root = string
tokens = string
config = string
})
tags = optional(map(string), {})
parameters = optional(object({
tags = optional(map(string), {})
}), {})
})
| n/a | yes | +| [tags](#input\_tags) | Base tags available to taggable compute-provider resources. Provider-specific tags override this map within their documented scopes. | `map(string)` | `{}` | no | + +## Outputs + +| Name | Description | +|------|-------------| +| [environment\_variables](#output\_environment\_variables) | Provider-specific Lambda environment variable fragments consumed by runner-config. | +| [policies](#output\_policies) | Provider-specific IAM policy fragments consumed by runner-config. | +| [provider](#output\_provider) | Nested Lambda MicroVM compute-provider contract consumed by runner-config. | +| [resources](#output\_resources) | Provider-specific MicroVM resources exposed by runner-config. | + diff --git a/modules/compute-providers/aws/microvm/control-plane.tf b/modules/compute-providers/aws/microvm/control-plane.tf new file mode 100644 index 0000000000..832a90df04 --- /dev/null +++ b/modules/compute-providers/aws/microvm/control-plane.tf @@ -0,0 +1,118 @@ +data "aws_iam_policy_document" "scale_up" { + statement { + effect = "Allow" + actions = [ + "lambda:ListMicrovms", + "lambda:PassNetworkConnector", + ] + resources = ["*"] + } + + statement { + effect = "Allow" + actions = [ + "lambda:RunMicrovm", + "lambda:TerminateMicrovm", + ] + resources = local.microvm_image_resource_arns + } + + statement { + effect = "Allow" + actions = [ + "ssm:AddTagsToResource", + "ssm:DeleteParameter", + "ssm:PutParameter", + ] + resources = [local.microvm_metadata_parameter_arn] + } + + statement { + effect = "Allow" + actions = ["ssm:GetParametersByPath"] + resources = [local.microvm_metadata_path_arn, local.microvm_metadata_parameter_arn] + } + + statement { + effect = "Allow" + actions = ["ssm:GetParameters"] + resources = [local.microvm_metadata_parameter_arn] + } + + statement { + effect = "Allow" + actions = ["iam:PassRole"] + resources = [var.runner.iam.role.arn] + } + + statement { + effect = "Allow" + actions = ["ssm:DeleteParameter"] + resources = [local.runner_token_path_arn] + } +} + +data "aws_iam_policy_document" "scale_down" { + statement { + effect = "Allow" + actions = ["lambda:ListMicrovms"] + resources = ["*"] + } + + statement { + effect = "Allow" + actions = ["lambda:TerminateMicrovm"] + resources = local.microvm_image_resource_arns + } + + statement { + effect = "Allow" + actions = [ + "ssm:DeleteParameter", + "ssm:PutParameter", + ] + resources = [local.microvm_metadata_parameter_arn] + } + + statement { + effect = "Allow" + actions = ["ssm:GetParametersByPath"] + resources = [local.microvm_metadata_path_arn, local.microvm_metadata_parameter_arn] + } + + statement { + effect = "Allow" + actions = ["ssm:DeleteParameter"] + resources = [local.runner_token_path_arn] + } +} + +locals { + microvm_metadata_ssm_path = "${local.ssm_config_ssm_path}/microvm-metadata" + microvm_metadata_path_arn = "${local.ssm_parameter_arn_prefix}${local.microvm_metadata_ssm_path}" + microvm_metadata_parameter_arn = "${local.microvm_metadata_path_arn}/*" + microvm_image_resource_arns = coalesce( + var.config.iam.resource_arns.images, + [var.config.image_arn], + ) + runner_jit_ssm_path = "/${trim(var.ssm.paths.root, "/")}/${trim(var.ssm.paths.tokens, "/")}" + + microvm_custom_environment_variables = { + for key, value in var.config.environment_variables : key => value + if !contains(["MICROVM_METADATA_TAGS", "MICROVM_RUNNER_CONFIG_SSM_ARN"], key) + } + microvm_environment_variables = merge(local.microvm_custom_environment_variables, { + MICROVM_EGRESS_NETWORK_CONNECTORS = length(var.config.egress_network_connectors) == 0 ? "" : jsonencode(var.config.egress_network_connectors) + MICROVM_EXECUTION_ROLE_ARN = var.runner.iam.role.arn + MICROVM_IMAGE_ARN = var.config.image_arn + MICROVM_IMAGE_VERSION = var.config.image_version == null ? "" : var.config.image_version + MICROVM_INGRESS_NETWORK_CONNECTORS = length(var.config.ingress_network_connectors) == 0 ? "" : jsonencode(var.config.ingress_network_connectors) + MICROVM_LOG_GROUP = aws_cloudwatch_log_group.runtime.name + MICROVM_METADATA_SSM_PATH = local.microvm_metadata_ssm_path + SSM_TOKEN_PATH = local.runner_jit_ssm_path + }) + + scale_up_environment_variables = local.microvm_environment_variables + scale_down_environment_variables = local.microvm_environment_variables + pool_environment_variables = local.microvm_environment_variables +} diff --git a/modules/compute-providers/aws/microvm/logging.tf b/modules/compute-providers/aws/microvm/logging.tf new file mode 100644 index 0000000000..18f87ffeed --- /dev/null +++ b/modules/compute-providers/aws/microvm/logging.tf @@ -0,0 +1,86 @@ +locals { + provider_tags = merge( + { + "Name" = format("%s-action-runner", var.prefix) + }, + var.tags, + ) + + log_group_tags = merge( + local.provider_tags, + var.observability.logs.tags, + ) + + ssm_config_ssm_path = "/${trim(var.ssm.paths.root, "/")}/${trim(var.ssm.paths.config, "/")}" + ssm_parameter_tags = merge( + local.provider_tags, + var.ssm.tags, + var.ssm.parameters.tags, + ) + + runner_log_files = var.config.log_files != null ? var.config.log_files : [ + { + log_group_name = "internal_service" + prefix_log_group = true + file_path = "/var/log/microvm/internal-services.log" + log_stream_name = "{microvm_id}" + log_class = "STANDARD" + }, + { + log_group_name = "run" + prefix_log_group = true + file_path = "/var/log/microvm/run.log" + log_stream_name = "{microvm_id}" + log_class = "STANDARD" + }, + { + log_group_name = "runner" + prefix_log_group = true + file_path = "/opt/actions-runner/_diag/Runner_**.log" + log_stream_name = "{microvm_id}" + log_class = "STANDARD" + }, + ] + + logfiles = var.config.cloudwatch_agent.enabled ? [for log_file in local.runner_log_files : { + log_group_name = log_file.prefix_log_group ? "/github-self-hosted-runners/${var.prefix}/${log_file.log_group_name}" : "/${log_file.log_group_name}" + log_stream_name = log_file.log_stream_name + file_path = log_file.file_path + log_group_class = log_file.log_class + }] : [] + runner_log_group_names = distinct([for log_file in local.logfiles : log_file.log_group_name]) + runner_log_group_classes = [for name in local.runner_log_group_names : [ + for log_file in local.logfiles : log_file.log_group_class + if log_file.log_group_name == name + ][0]] +} + +resource "aws_cloudwatch_log_group" "runtime" { + name = "/github-self-hosted-runners/${var.prefix}/microvm" + retention_in_days = var.observability.logs.retention_in_days + kms_key_id = var.observability.logs.kms_key_id + log_group_class = var.observability.logs.class + tags = local.log_group_tags +} + +resource "aws_ssm_parameter" "cloudwatch_agent_config_runner" { + count = var.config.cloudwatch_agent.enabled ? 1 : 0 + + name = "${local.ssm_config_ssm_path}/cloudwatch_agent_config_runner" + type = "String" + value = var.config.cloudwatch_agent.config != null ? var.config.cloudwatch_agent.config : templatefile( + "${path.module}/templates/cloudwatch_config.json", + { logfiles = jsonencode(local.logfiles) }, + ) + tags = local.ssm_parameter_tags +} + +resource "aws_cloudwatch_log_group" "gh_runners" { + count = length(local.runner_log_group_names) + + name = local.runner_log_group_names[count.index] + retention_in_days = var.observability.logs.retention_in_days + kms_key_id = var.observability.logs.kms_key_id + log_group_class = local.runner_log_group_classes[count.index] + tags = local.log_group_tags +} diff --git a/modules/compute-providers/aws/microvm/outputs.tf b/modules/compute-providers/aws/microvm/outputs.tf new file mode 100644 index 0000000000..6200a8f54e --- /dev/null +++ b/modules/compute-providers/aws/microvm/outputs.tf @@ -0,0 +1,23 @@ +output "environment_variables" { + description = "Provider-specific Lambda environment variable fragments consumed by runner-config." + value = local.provider_environment_variables +} + +output "policies" { + description = "Provider-specific IAM policy fragments consumed by runner-config." + value = local.provider_policies +} + +output "resources" { + description = "Provider-specific MicroVM resources exposed by runner-config." + value = local.provider_resources +} + +output "provider" { + description = "Nested Lambda MicroVM compute-provider contract consumed by runner-config." + value = { + environment_variables = local.provider_environment_variables + policies = local.provider_policies + resources = local.provider_resources + } +} diff --git a/modules/compute-providers/aws/microvm/policies-runner.tf b/modules/compute-providers/aws/microvm/policies-runner.tf new file mode 100644 index 0000000000..9b514e396a --- /dev/null +++ b/modules/compute-providers/aws/microvm/policies-runner.tf @@ -0,0 +1,81 @@ +data "aws_caller_identity" "current" {} + +locals { + ssm_parameter_arn_prefix = "arn:${var.aws_partition}:ssm:${var.aws_region}:${data.aws_caller_identity.current.account_id}:parameter" + runner_token_path_arn = "${local.ssm_parameter_arn_prefix}/${trim(var.ssm.paths.root, "/")}/${trim(var.ssm.paths.tokens, "/")}/*" + runner_metadata_tags_arn = "${local.microvm_metadata_path_arn}/*.tags" + runner_enable_cloudwatch_arn = "${local.ssm_parameter_arn_prefix}${local.ssm_config_ssm_path}/enable_cloudwatch" + runner_cloudwatch_config_arn = "${local.ssm_parameter_arn_prefix}${local.ssm_config_ssm_path}/cloudwatch_agent_config_runner" + runner_cloudwatch_log_group_arns = [for name in local.runner_log_group_names : + "arn:${var.aws_partition}:logs:${var.aws_region}:${data.aws_caller_identity.current.account_id}:log-group:${name}" + ] + runner_inline_policies = merge({ + ssm_jit = { + name = "runner-microvm-ssm-jit" + policy_json = data.aws_iam_policy_document.runner_ssm_jit.json + } + runtime_logs = { + name = "runner-microvm-runtime-logs" + policy_json = data.aws_iam_policy_document.runner_runtime_logs.json + } + runner_metadata = { + name = "runner-microvm-metadata" + policy_json = data.aws_iam_policy_document.runner_metadata.json + } + }, var.config.cloudwatch_agent.enabled ? { + cloudwatch = { + name = "runner-microvm-cloudwatch" + policy_json = data.aws_iam_policy_document.runner_cloudwatch[0].json + } + } : {}) +} + +data "aws_iam_policy_document" "runner_ssm_jit" { + statement { + effect = "Allow" + actions = [ + "ssm:DeleteParameter", + "ssm:GetParameter", + ] + resources = [local.runner_token_path_arn] + } +} + +data "aws_iam_policy_document" "runner_metadata" { + statement { + effect = "Allow" + actions = ["ssm:GetParameter"] + resources = [local.runner_metadata_tags_arn, local.runner_enable_cloudwatch_arn] + } +} + +data "aws_iam_policy_document" "runner_cloudwatch" { + count = var.config.cloudwatch_agent.enabled ? 1 : 0 + + statement { + effect = "Allow" + actions = ["ssm:GetParameter"] + resources = [local.runner_cloudwatch_config_arn] + } + + statement { + effect = "Allow" + actions = [ + "logs:CreateLogStream", + "logs:DescribeLogStreams", + "logs:PutLogEvents", + ] + resources = [for arn in local.runner_cloudwatch_log_group_arns : "${arn}:*"] + } +} + +data "aws_iam_policy_document" "runner_runtime_logs" { + statement { + effect = "Allow" + actions = [ + "logs:CreateLogStream", + "logs:PutLogEvents", + ] + resources = ["${aws_cloudwatch_log_group.runtime.arn}:*"] + } +} diff --git a/modules/compute-providers/aws/microvm/provider-contract.tf b/modules/compute-providers/aws/microvm/provider-contract.tf new file mode 100644 index 0000000000..2f487a01d7 --- /dev/null +++ b/modules/compute-providers/aws/microvm/provider-contract.tf @@ -0,0 +1,36 @@ +locals { + provider_environment_variables = { + scale_up = local.scale_up_environment_variables + scale_down = local.scale_down_environment_variables + pool = local.pool_environment_variables + } + + provider_policies = { + runner = { + inline_policies = local.runner_inline_policies + managed_policy_arns = var.runner.iam.managed_policy_arns + } + scale_up = { + iam_policy_json = data.aws_iam_policy_document.scale_up.json + additional_iam_policy_json = var.config.iam.additional_policy_json.scale_up + managed_policy_enabled = var.config.iam.managed_policies.scale_up != null + managed_policy_arn = try(var.config.iam.managed_policies.scale_up.arn, null) + } + scale_down = { + iam_policy_json = data.aws_iam_policy_document.scale_down.json + } + pool = { + iam_policy_json = data.aws_iam_policy_document.scale_up.json + managed_policy_enabled = var.config.iam.managed_policies.pool != null + managed_policy_arn = try(var.config.iam.managed_policies.pool.arn, null) + } + } + + provider_resources = { + image_arn = var.config.image_arn + image_version = var.config.image_version + execution_role_arn = var.runner.iam.role.arn + runners_log_groups = concat([aws_cloudwatch_log_group.runtime], aws_cloudwatch_log_group.gh_runners) + logfiles = local.logfiles + } +} diff --git a/modules/compute-providers/aws/microvm/runner-config.tf b/modules/compute-providers/aws/microvm/runner-config.tf new file mode 100644 index 0000000000..de3b775106 --- /dev/null +++ b/modules/compute-providers/aws/microvm/runner-config.tf @@ -0,0 +1,6 @@ +resource "aws_ssm_parameter" "runner_enable_cloudwatch" { + name = "${local.ssm_config_ssm_path}/enable_cloudwatch" + type = "String" + value = var.config.cloudwatch_agent.enabled + tags = local.ssm_parameter_tags +} diff --git a/modules/compute-providers/aws/microvm/templates/cloudwatch_config.json b/modules/compute-providers/aws/microvm/templates/cloudwatch_config.json new file mode 100644 index 0000000000..554de026e5 --- /dev/null +++ b/modules/compute-providers/aws/microvm/templates/cloudwatch_config.json @@ -0,0 +1,12 @@ +{ + "agent": { + "metrics_collection_interval": 5 + }, + "logs": { + "logs_collected": { + "files": { + "collect_list": ${logfiles} + } + } + } +} diff --git a/modules/compute-providers/aws/microvm/tests/provider.tftest.hcl b/modules/compute-providers/aws/microvm/tests/provider.tftest.hcl new file mode 100644 index 0000000000..81f417e21c --- /dev/null +++ b/modules/compute-providers/aws/microvm/tests/provider.tftest.hcl @@ -0,0 +1,649 @@ +mock_provider "aws" { + mock_data "aws_caller_identity" { + defaults = { + account_id = "123456789012" + } + } + + mock_data "aws_iam_policy_document" { + defaults = { + json = "{}" + } + } + + mock_resource "aws_cloudwatch_log_group" { + defaults = { + arn = "arn:aws:logs:eu-west-1:123456789012:log-group:/github-self-hosted-runners/microvm-test/microvm" + } + } +} + +variables { + aws_region = "eu-west-1" + prefix = "microvm-test" + + tags = { + Module = "runner" + Name = "module" + } + + config = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + image_version = "3" + ingress_network_connectors = [ + "arn:aws:lambda:eu-west-1:123456789012:network-connector:ingress", + ] + egress_network_connectors = [ + "arn:aws:lambda:eu-west-1:123456789012:network-connector:egress", + ] + environment_variables = { + MICROVM_CLUSTER = "runner-cluster" + MICROVM_IMAGE_ARN = "caller-cannot-override-provider-contract" + MICROVM_METADATA_SSM_PATH = "/caller/cannot/override/provider-contract" + MICROVM_METADATA_TAGS = "retired-provider-contract" + MICROVM_RUNNER_CONFIG_SSM_ARN = "retired-provider-contract" + SSM_TOKEN_PATH = "/caller/cannot/override/token-path" + } + } + + runner = { + name_prefix = "microvm-" + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/microvm-test-runner" + name = "microvm-test-runner" + } + managed_policy_arns = { + readonly = "arn:aws:iam::aws:policy/ReadOnlyAccess" + } + } + } + + ssm = { + paths = { + root = "/github-action-runners" + tokens = "tokens" + config = "config" + } + tags = { + Name = "ssm" + Precedence = "ssm" + Ssm = "shared" + } + parameters = { + tags = { + Name = "parameter" + Parameter = "metadata" + Precedence = "parameter" + "ghr:environment" = "caller-cannot-override" + "ghr:runner_name_prefix" = "caller-cannot-override" + "ghr:ssm_config_path" = "caller-cannot-override" + } + } + } + + observability = { + logs = { + retention_in_days = 30 + kms_key_id = "arn:aws:kms:eu-west-1:123456789012:key/runtime-logs" + class = "INFREQUENT_ACCESS" + tags = { + Name = "microvm-runtime-logs" + LogOnly = "runtime" + } + } + } +} + +run "exposes_microvm_control_plane_contract" { + command = apply + + assert { + condition = toset(keys(output.provider)) == toset(["environment_variables", "policies", "resources"]) + error_message = "The MicroVM provider contract must expose only integration and resource data." + } + + assert { + condition = ( + output.provider.environment_variables.scale_up["MICROVM_CLUSTER"] == "runner-cluster" + && output.provider.environment_variables.scale_up["MICROVM_IMAGE_ARN"] == "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + && output.provider.environment_variables.scale_up["MICROVM_IMAGE_VERSION"] == "3" + && output.provider.environment_variables.scale_up["MICROVM_EXECUTION_ROLE_ARN"] == "arn:aws:iam::123456789012:role/microvm-test-runner" + && jsondecode(output.provider.environment_variables.scale_up["MICROVM_INGRESS_NETWORK_CONNECTORS"])[0] == "arn:aws:lambda:eu-west-1:123456789012:network-connector:ingress" + && jsondecode(output.provider.environment_variables.scale_up["MICROVM_EGRESS_NETWORK_CONNECTORS"])[0] == "arn:aws:lambda:eu-west-1:123456789012:network-connector:egress" + && output.provider.environment_variables.scale_up["MICROVM_LOG_GROUP"] == "/github-self-hosted-runners/microvm-test/microvm" + && output.provider.environment_variables.scale_up["MICROVM_METADATA_SSM_PATH"] == "/github-action-runners/config/microvm-metadata" + && output.provider.environment_variables.scale_up["SSM_TOKEN_PATH"] == "/github-action-runners/tokens" + ) + error_message = "The MicroVM provider must map every configured runtime input to the canonical Lambda environment contract." + } + + assert { + condition = ( + toset(keys(output.provider.environment_variables.scale_up)) == toset([ + "MICROVM_CLUSTER", + "MICROVM_EGRESS_NETWORK_CONNECTORS", + "MICROVM_EXECUTION_ROLE_ARN", + "MICROVM_IMAGE_ARN", + "MICROVM_IMAGE_VERSION", + "MICROVM_INGRESS_NETWORK_CONNECTORS", + "MICROVM_LOG_GROUP", + "MICROVM_METADATA_SSM_PATH", + "SSM_TOKEN_PATH", + ]) + && output.provider.environment_variables.scale_up == output.provider.environment_variables.scale_down + && output.provider.environment_variables.scale_up == output.provider.environment_variables.pool + && !contains(keys(output.provider.environment_variables.scale_up), "RUNNER_BOOT_TIME_IN_MINUTES") + && !contains(keys(output.provider.environment_variables.scale_up), "MICROVM_IMAGE_IDENTIFIER") + && !contains(keys(output.provider.environment_variables.scale_up), "MICROVM_MAXIMUM_DURATION_IN_SECONDS") + && !contains(keys(output.provider.environment_variables.scale_up), "MICROVM_RUN_CONFIG") + && !contains(keys(output.provider.environment_variables.scale_up), "MICROVM_TAGS") + && !contains(keys(output.provider.environment_variables.scale_up), "MICROVM_METADATA_TAGS") + && !contains(keys(output.provider.environment_variables.scale_up), "MICROVM_RUNNER_CONFIG_SSM_ARN") + ) + error_message = "All three control-plane fragments must match the runtime key inventory and omit stale or webhook-owned keys." + } + + assert { + condition = ( + data.aws_iam_policy_document.scale_up.statement[0].actions == toset(["lambda:ListMicrovms", "lambda:PassNetworkConnector"]) + && data.aws_iam_policy_document.scale_up.statement[0].resources == toset(["*"]) + && data.aws_iam_policy_document.scale_up.statement[1].actions == toset(["lambda:RunMicrovm", "lambda:TerminateMicrovm"]) + && data.aws_iam_policy_document.scale_up.statement[1].resources == toset(["arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner"]) + ) + error_message = "Scale-up and pool must receive the MicroVM inventory, connector, launch, and cleanup permissions." + } + + assert { + condition = ( + data.aws_iam_policy_document.scale_up.statement[2].actions == toset(["ssm:AddTagsToResource", "ssm:DeleteParameter", "ssm:PutParameter"]) + && data.aws_iam_policy_document.scale_up.statement[2].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*"]) + && data.aws_iam_policy_document.scale_up.statement[3].actions == toset(["ssm:GetParametersByPath"]) + && data.aws_iam_policy_document.scale_up.statement[3].resources == toset([ + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata", + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*", + ]) + && data.aws_iam_policy_document.scale_up.statement[4].actions == toset(["ssm:GetParameters"]) + && data.aws_iam_policy_document.scale_up.statement[4].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*"]) + ) + error_message = "Scale-up and pool must read the metadata hierarchy and exact JIT fence records while keeping metadata writes child-scoped." + } + + assert { + condition = ( + data.aws_iam_policy_document.scale_up.statement[5].actions == toset(["iam:PassRole"]) + && data.aws_iam_policy_document.scale_up.statement[5].resources == toset(["arn:aws:iam::123456789012:role/microvm-test-runner"]) + && length(data.aws_iam_policy_document.scale_up.statement[5].condition) == 0 + && data.aws_iam_policy_document.scale_up.statement[6].actions == toset(["ssm:DeleteParameter"]) + && data.aws_iam_policy_document.scale_up.statement[6].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + ) + error_message = "Scale-up and pool must receive exact runner-role PassRole and lane-token cleanup grants." + } + + assert { + condition = ( + data.aws_iam_policy_document.scale_down.statement[0].actions == toset(["lambda:ListMicrovms"]) + && data.aws_iam_policy_document.scale_down.statement[0].resources == toset(["*"]) + && data.aws_iam_policy_document.scale_down.statement[1].actions == toset(["lambda:TerminateMicrovm"]) + && data.aws_iam_policy_document.scale_down.statement[1].resources == toset(["arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner"]) + && data.aws_iam_policy_document.scale_down.statement[2].actions == toset(["ssm:DeleteParameter", "ssm:PutParameter"]) + && data.aws_iam_policy_document.scale_down.statement[2].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*"]) + && data.aws_iam_policy_document.scale_down.statement[3].actions == toset(["ssm:GetParametersByPath"]) + && data.aws_iam_policy_document.scale_down.statement[3].resources == toset([ + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata", + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*", + ]) + && data.aws_iam_policy_document.scale_down.statement[4].actions == toset(["ssm:DeleteParameter"]) + && data.aws_iam_policy_document.scale_down.statement[4].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + ) + error_message = "Scale-down must receive lifecycle, metadata, and exact lane-token cleanup permissions." + } + + assert { + condition = ( + length(setintersection(toset(flatten(data.aws_iam_policy_document.scale_up.statement[*].actions)), toset(["lambda:ListTags", "lambda:TagResource", "lambda:UntagResource"]))) == 0 + && length(setintersection(toset(flatten(data.aws_iam_policy_document.scale_down.statement[*].actions)), toset(["lambda:ListTags", "lambda:TagResource", "lambda:UntagResource"]))) == 0 + ) + error_message = "The MicroVM provider must not grant unsupported runtime tagging actions." + } + + assert { + condition = ( + toset(keys(output.provider.policies)) == toset(["runner", "scale_up", "scale_down", "pool"]) + && toset(keys(output.provider.policies.runner.inline_policies)) == toset(["cloudwatch", "runner_metadata", "runtime_logs", "ssm_jit"]) + && output.provider.policies.runner.inline_policies.cloudwatch.name == "runner-microvm-cloudwatch" + && output.provider.policies.runner.inline_policies.runner_metadata.name == "runner-microvm-metadata" + && output.provider.policies.runner.inline_policies.ssm_jit.name == "runner-microvm-ssm-jit" + && output.provider.policies.runner.inline_policies.runtime_logs.name == "runner-microvm-runtime-logs" + && output.provider.policies.runner.managed_policy_arns["readonly"] == "arn:aws:iam::aws:policy/ReadOnlyAccess" + && !output.provider.policies.scale_up.managed_policy_enabled + && !output.provider.policies.pool.managed_policy_enabled + ) + error_message = "The MicroVM provider must return policy fragments grouped by common component." + } + + assert { + condition = ( + data.aws_iam_policy_document.runner_ssm_jit.statement[0].actions == toset(["ssm:DeleteParameter", "ssm:GetParameter"]) + && data.aws_iam_policy_document.runner_ssm_jit.statement[0].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + && data.aws_iam_policy_document.runner_metadata.statement[0].actions == toset(["ssm:GetParameter"]) + && data.aws_iam_policy_document.runner_metadata.statement[0].resources == toset([ + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/enable_cloudwatch", + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*.tags", + ]) + && data.aws_iam_policy_document.runner_cloudwatch[0].statement[0].actions == toset(["ssm:GetParameter"]) + && data.aws_iam_policy_document.runner_cloudwatch[0].statement[0].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/cloudwatch_agent_config_runner"]) + && data.aws_iam_policy_document.runner_cloudwatch[0].statement[1].actions == toset(["logs:CreateLogStream", "logs:DescribeLogStreams", "logs:PutLogEvents"]) + && data.aws_iam_policy_document.runner_cloudwatch[0].statement[1].resources == toset([ + "arn:aws:logs:eu-west-1:123456789012:log-group:/github-self-hosted-runners/microvm-test/internal_service:*", + "arn:aws:logs:eu-west-1:123456789012:log-group:/github-self-hosted-runners/microvm-test/run:*", + "arn:aws:logs:eu-west-1:123456789012:log-group:/github-self-hosted-runners/microvm-test/runner:*", + ]) + && length(data.aws_iam_policy_document.runner_runtime_logs.statement) == 1 + && data.aws_iam_policy_document.runner_runtime_logs.statement[0].actions == toset(["logs:CreateLogStream", "logs:PutLogEvents"]) + && data.aws_iam_policy_document.runner_runtime_logs.statement[0].resources == toset(["arn:aws:logs:eu-west-1:123456789012:log-group:/github-self-hosted-runners/microvm-test/microvm:*"]) + ) + error_message = "Managed MicroVM runners must receive exact lane configuration, metadata, JIT, native-runtime, and CloudWatch-agent permissions." + } + + assert { + condition = ( + toset(keys(output.provider.resources)) == toset(["execution_role_arn", "image_arn", "image_version", "logfiles", "runners_log_groups"]) + && output.provider.resources.image_arn == "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + && output.provider.resources.image_version == "3" + && output.provider.resources.execution_role_arn == "arn:aws:iam::123456789012:role/microvm-test-runner" + && length(output.provider.resources.runners_log_groups) == 4 + && output.provider.resources.runners_log_groups[0].name == "/github-self-hosted-runners/microvm-test/microvm" + && toset(slice(output.provider.resources.runners_log_groups[*].name, 1, 4)) == toset([ + "/github-self-hosted-runners/microvm-test/internal_service", + "/github-self-hosted-runners/microvm-test/run", + "/github-self-hosted-runners/microvm-test/runner", + ]) + && output.provider.resources.logfiles == local.logfiles + ) + error_message = "The MicroVM provider must expose its selected image, execution role, native runtime group, and CloudWatch-agent resources." + } + + assert { + condition = ( + aws_cloudwatch_log_group.runtime.name == "/github-self-hosted-runners/microvm-test/microvm" + && aws_cloudwatch_log_group.runtime.retention_in_days == 30 + && aws_cloudwatch_log_group.runtime.kms_key_id == "arn:aws:kms:eu-west-1:123456789012:key/runtime-logs" + && aws_cloudwatch_log_group.runtime.log_group_class == "INFREQUENT_ACCESS" + && aws_cloudwatch_log_group.runtime.tags == tomap({ + Name = "microvm-runtime-logs" + Module = "runner" + LogOnly = "runtime" + }) + ) + error_message = "The MicroVM provider must own its lane-scoped log group and apply the common observability lifecycle and tag scopes." + } + + assert { + condition = ( + aws_ssm_parameter.runner_enable_cloudwatch.name == "/github-action-runners/config/enable_cloudwatch" + && aws_ssm_parameter.runner_enable_cloudwatch.value == "true" + && length(aws_ssm_parameter.cloudwatch_agent_config_runner) == 1 + && aws_ssm_parameter.cloudwatch_agent_config_runner[0].name == "/github-action-runners/config/cloudwatch_agent_config_runner" + && aws_ssm_parameter.runner_enable_cloudwatch.tags["Name"] == "parameter" + && aws_ssm_parameter.runner_enable_cloudwatch.tags["Module"] == "runner" + && aws_ssm_parameter.runner_enable_cloudwatch.tags["Ssm"] == "shared" + && aws_ssm_parameter.runner_enable_cloudwatch.tags["Parameter"] == "metadata" + && aws_ssm_parameter.runner_enable_cloudwatch.tags["Precedence"] == "parameter" + && aws_ssm_parameter.cloudwatch_agent_config_runner[0].tags == aws_ssm_parameter.runner_enable_cloudwatch.tags + ) + error_message = "The MicroVM provider must publish the EC2-compatible CloudWatch enablement and agent-config parameters with standard SSM tag precedence." + } + + assert { + condition = ( + length(local.logfiles) == 3 + && local.logfiles[0].file_path == "/var/log/microvm/internal-services.log" + && local.logfiles[0].log_group_name == "/github-self-hosted-runners/microvm-test/internal_service" + && local.logfiles[1].file_path == "/var/log/microvm/run.log" + && local.logfiles[1].log_group_name == "/github-self-hosted-runners/microvm-test/run" + && local.logfiles[2].file_path == "/opt/actions-runner/_diag/Runner_**.log" + && local.logfiles[2].log_group_name == "/github-self-hosted-runners/microvm-test/runner" + && alltrue([for log_file in local.logfiles : ( + log_file.log_group_class == "STANDARD" + && log_file.log_stream_name == "{microvm_id}" + )]) + && length(jsondecode(aws_ssm_parameter.cloudwatch_agent_config_runner[0].value).logs.logs_collected.files.collect_list) == 3 + && toset(aws_cloudwatch_log_group.gh_runners[*].name) == toset(local.runner_log_group_names) + && alltrue([for log_group in aws_cloudwatch_log_group.gh_runners : ( + log_group.retention_in_days == 30 + && log_group.kms_key_id == "arn:aws:kms:eu-west-1:123456789012:key/runtime-logs" + && log_group.tags == aws_cloudwatch_log_group.runtime.tags + )]) + ) + error_message = "The default MicroVM agent configuration must route internal-service, run, and runner files to separately managed log groups." + } +} + +run "normalizes_ssm_paths_and_arns" { + command = plan + + variables { + ssm = { + paths = { + root = "/github-action-runners/" + tokens = "/tokens/" + config = "/config/" + } + } + } + + assert { + condition = ( + output.provider.environment_variables.scale_up["MICROVM_METADATA_SSM_PATH"] == "/github-action-runners/config/microvm-metadata" + && output.provider.environment_variables.scale_up["SSM_TOKEN_PATH"] == "/github-action-runners/tokens" + && data.aws_iam_policy_document.scale_up.statement[6].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + && data.aws_iam_policy_document.scale_down.statement[4].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + && data.aws_iam_policy_document.runner_ssm_jit.statement[0].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + && data.aws_iam_policy_document.runner_metadata.statement[0].resources == toset([ + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/enable_cloudwatch", + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*.tags", + ]) + ) + error_message = "The MicroVM provider must normalize SSM path segments before exposing hook values or IAM resources." + } +} + +run "accepts_external_runner_role_and_policy_overrides" { + command = plan + + variables { + runner = { + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/external-microvm-runner" + name = "external-microvm-runner" + managed = false + } + } + } + config = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner-override" + iam = { + resource_arns = { + images = ["arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner-*"] + } + additional_policy_json = { + scale_up = "{\"Version\":\"2012-10-17\",\"Statement\":[]}" + } + managed_policies = { + scale_up = { + arn = "arn:aws:iam::123456789012:policy/microvm-scale-up" + } + pool = { + arn = "arn:aws:iam::123456789012:policy/microvm-pool" + } + } + } + } + } + + assert { + condition = ( + output.provider.environment_variables.scale_up["MICROVM_EXECUTION_ROLE_ARN"] == "arn:aws:iam::123456789012:role/external-microvm-runner" + && output.provider.environment_variables.scale_up["MICROVM_INGRESS_NETWORK_CONNECTORS"] == "" + && output.provider.environment_variables.scale_up["MICROVM_EGRESS_NETWORK_CONNECTORS"] == "" + && output.provider.environment_variables.scale_up["MICROVM_LOG_GROUP"] == "/github-self-hosted-runners/microvm-test/microvm" + && data.aws_iam_policy_document.scale_up.statement[0].resources == toset(["*"]) + && data.aws_iam_policy_document.scale_up.statement[1].resources == toset(["arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner-*"]) + && data.aws_iam_policy_document.scale_up.statement[2].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*"]) + && data.aws_iam_policy_document.scale_up.statement[3].resources == toset([ + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata", + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*", + ]) + && data.aws_iam_policy_document.scale_up.statement[4].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*"]) + && data.aws_iam_policy_document.scale_up.statement[5].resources == toset(["arn:aws:iam::123456789012:role/external-microvm-runner"]) + && data.aws_iam_policy_document.scale_up.statement[6].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + && data.aws_iam_policy_document.scale_down.statement[0].resources == toset(["*"]) + && data.aws_iam_policy_document.scale_down.statement[1].resources == toset(["arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner-*"]) + && data.aws_iam_policy_document.scale_down.statement[2].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*"]) + && data.aws_iam_policy_document.scale_down.statement[3].resources == toset([ + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata", + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*", + ]) + && data.aws_iam_policy_document.scale_down.statement[4].resources == toset(["arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/tokens/*"]) + ) + error_message = "The provider-neutral external runner role and image allowlist must reach their scoped statements without narrowing required list, connector, or metadata permissions." + } + + assert { + condition = ( + output.provider.policies.scale_up.additional_iam_policy_json == "{\"Version\":\"2012-10-17\",\"Statement\":[]}" + && output.provider.policies.scale_up.managed_policy_enabled + && output.provider.policies.scale_up.managed_policy_arn == "arn:aws:iam::123456789012:policy/microvm-scale-up" + && output.provider.policies.pool.managed_policy_enabled + && output.provider.policies.pool.managed_policy_arn == "arn:aws:iam::123456789012:policy/microvm-pool" + ) + error_message = "Optional MicroVM policy attachments must stay controlled by wrapper presence." + } + + + assert { + condition = ( + toset(keys(output.provider.policies.runner.inline_policies)) == toset(["cloudwatch", "runner_metadata", "runtime_logs", "ssm_jit"]) + && data.aws_iam_policy_document.runner_metadata.statement[0].resources == toset([ + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/enable_cloudwatch", + "arn:aws:ssm:eu-west-1:123456789012:parameter/github-action-runners/config/microvm-metadata/*.tags", + ]) + && length(data.aws_iam_policy_document.runner_runtime_logs.statement) == 1 + && data.aws_iam_policy_document.runner_runtime_logs.statement[0].resources == toset(["arn:aws:logs:eu-west-1:123456789012:log-group:/github-self-hosted-runners/microvm-test/microvm:*"]) + ) + error_message = "The provider contract must keep plan-known runner-policy keys and scope runtime logging to its provider-managed group." + } +} + +run "disables_cloudwatch_agent_without_disabling_native_runtime_logging" { + command = apply + + variables { + config = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + cloudwatch_agent = { + enabled = false + } + } + } + + assert { + condition = ( + tostring(aws_ssm_parameter.runner_enable_cloudwatch.value) == "false" + && length(aws_ssm_parameter.cloudwatch_agent_config_runner) == 0 + && length(aws_cloudwatch_log_group.gh_runners) == 0 + && length(local.logfiles) == 0 + && !contains(keys(output.provider.policies.runner.inline_policies), "cloudwatch") + && length(output.provider.resources.runners_log_groups) == 1 + && output.provider.resources.runners_log_groups[0].name == aws_cloudwatch_log_group.runtime.name + && output.provider.environment_variables.scale_up["MICROVM_LOG_GROUP"] == aws_cloudwatch_log_group.runtime.name + ) + error_message = "Disabling the image CloudWatch agent must retain the explicit false flag and native RunMicrovm logging while removing only agent-owned resources and permissions." + } +} + +run "accepts_custom_cloudwatch_agent_config_and_log_group" { + command = apply + + variables { + config = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + cloudwatch_agent = { + enabled = true + config = "{\"agent\":{\"region\":\"eu-west-1\"}}" + } + log_files = [{ + log_group_name = "custom-microvm" + prefix_log_group = false + file_path = "/var/log/custom.log" + log_stream_name = "{microvm_id}/custom" + log_class = "INFREQUENT_ACCESS" + }] + } + } + + assert { + condition = ( + aws_ssm_parameter.cloudwatch_agent_config_runner[0].value == "{\"agent\":{\"region\":\"eu-west-1\"}}" + && length(local.logfiles) == 1 + && local.logfiles[0].file_path == "/var/log/custom.log" + && local.logfiles[0].log_group_class == "INFREQUENT_ACCESS" + && local.logfiles[0].log_group_name == "/custom-microvm" + && local.logfiles[0].log_stream_name == "{microvm_id}/custom" + && aws_cloudwatch_log_group.gh_runners[0].name == "/custom-microvm" + && aws_cloudwatch_log_group.gh_runners[0].log_group_class == "INFREQUENT_ACCESS" + && data.aws_iam_policy_document.runner_cloudwatch[0].statement[1].resources == toset([ + "arn:aws:logs:eu-west-1:123456789012:log-group:/custom-microvm:*", + ]) + ) + error_message = "Custom MicroVM agent configuration and log-file routing must replace the generated defaults without widening IAM." + } +} + +run "rejects_invalid_image_arn" { + command = plan + + variables { + config = { + image_arn = "not-a-microvm-image-arn" + } + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_metadata_path_overlapping_jit_path" { + command = plan + + variables { + ssm = { + paths = { + root = "/github-action-runners" + tokens = "config/microvm-metadata" + config = "config" + } + } + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_invalid_metadata_path" { + command = plan + + variables { + ssm = { + paths = { + root = "/github-action-runners" + tokens = "tokens" + config = "invalid config" + } + } + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_metadata_path_with_duplicate_separators" { + command = plan + + variables { + ssm = { + paths = { + root = "/github-action-runners" + tokens = "tokens" + config = "config//invalid" + } + } + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_invalid_image_resource_allowlist" { + command = plan + + variables { + config = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + iam = { + resource_arns = { + images = [] + } + } + } + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_invalid_network_connector" { + command = plan + + variables { + config = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + ingress_network_connectors = [ + " ", + ] + } + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_more_than_ten_network_connectors" { + command = plan + + variables { + config = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + egress_network_connectors = [ + for index in range(11) : + "arn:aws:lambda:eu-west-1:123456789012:network-connector:egress-${index}" + ] + } + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_unsupported_runner_architecture" { + command = plan + + variables { + runner = { + os = "linux" + architecture = "x64" + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/microvm-test-runner" + name = "microvm-test-runner" + } + } + } + } + + expect_failures = [terraform_data.validate_runner] +} + +run "rejects_unsupported_runner_os" { + command = plan + + variables { + runner = { + os = "windows" + architecture = "arm64" + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/microvm-test-runner" + name = "microvm-test-runner" + } + } + } + } + + expect_failures = [terraform_data.validate_runner] +} diff --git a/modules/compute-providers/aws/microvm/trust-policy/README.md b/modules/compute-providers/aws/microvm/trust-policy/README.md new file mode 100644 index 0000000000..43302d1055 --- /dev/null +++ b/modules/compute-providers/aws/microvm/trust-policy/README.md @@ -0,0 +1,41 @@ +# AWS Lambda MicroVM runner trust policy + +This internal submodule builds the MicroVM runner-role trust policy independently from the runtime module that consumes the role. It preserves the default Lambda service trust and optionally merges an additional IAM trust policy document supplied by the common runner configuration. + + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.4.0 | +| [aws](#requirement\_aws) | >= 6.33 | + +## Providers + +| Name | Version | +|------|---------| +| [aws](#provider\_aws) | >= 6.33 | + +## Modules + +No modules. + +## Resources + +| Name | Type | +|------|------| +| [aws_iam_policy_document.assume_role](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.default](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | + +## Inputs + +| Name | Description | Type | Default | Required | +|------|-------------|------|---------|:--------:| +| [additional\_trust\_policy\_json](#input\_additional\_trust\_policy\_json) | Optional IAM policy document merged with the MicroVM provider's default runner-role trust policy. | `string` | `null` | no | + +## Outputs + +| Name | Description | +|------|-------------| +| [assume\_role\_policy](#output\_assume\_role\_policy) | MicroVM runner-role trust policy including any additional trust statements. | + diff --git a/modules/compute-providers/aws/microvm/trust-policy/assume-role.tf b/modules/compute-providers/aws/microvm/trust-policy/assume-role.tf new file mode 100644 index 0000000000..3654bce8bf --- /dev/null +++ b/modules/compute-providers/aws/microvm/trust-policy/assume-role.tf @@ -0,0 +1,21 @@ +data "aws_iam_policy_document" "default" { + statement { + effect = "Allow" + actions = [ + "sts:AssumeRole", + "sts:TagSession", + ] + + principals { + type = "Service" + identifiers = ["lambda.amazonaws.com"] + } + } +} + +data "aws_iam_policy_document" "assume_role" { + source_policy_documents = compact([ + data.aws_iam_policy_document.default.json, + var.additional_trust_policy_json, + ]) +} diff --git a/modules/compute-providers/aws/microvm/trust-policy/outputs.tf b/modules/compute-providers/aws/microvm/trust-policy/outputs.tf new file mode 100644 index 0000000000..8564675873 --- /dev/null +++ b/modules/compute-providers/aws/microvm/trust-policy/outputs.tf @@ -0,0 +1,4 @@ +output "assume_role_policy" { + description = "MicroVM runner-role trust policy including any additional trust statements." + value = data.aws_iam_policy_document.assume_role.json +} diff --git a/modules/compute-providers/aws/microvm/trust-policy/tests/trust-policy.tftest.hcl b/modules/compute-providers/aws/microvm/trust-policy/tests/trust-policy.tftest.hcl new file mode 100644 index 0000000000..5f0173ebc1 --- /dev/null +++ b/modules/compute-providers/aws/microvm/trust-policy/tests/trust-policy.tftest.hcl @@ -0,0 +1,59 @@ +mock_provider "aws" { + mock_data "aws_iam_policy_document" { + defaults = { + json = "{}" + } + } +} + +run "returns_default_microvm_trust_policy" { + command = plan + + assert { + condition = toset(data.aws_iam_policy_document.default.statement[0].actions) == toset(["sts:AssumeRole", "sts:TagSession"]) + error_message = "The MicroVM runner role must allow assume-role and tagged sessions." + } + + assert { + condition = anytrue([ + for principal in data.aws_iam_policy_document.default.statement[0].principals : + principal.type == "Service" && toset(principal.identifiers) == toset(["lambda.amazonaws.com"]) + ]) + error_message = "The MicroVM runner role must trust the Lambda service principal required by the provider." + } + + assert { + condition = ( + length(data.aws_iam_policy_document.assume_role.source_policy_documents) == 1 + && output.assume_role_policy == data.aws_iam_policy_document.assume_role.json + ) + error_message = "The MicroVM trust-policy module must return the default trust document as assume_role_policy." + } +} + +run "merges_additional_trust_policy" { + command = plan + + variables { + additional_trust_policy_json = "{\"Version\":\"2012-10-17\",\"Statement\":[{\"Sid\":\"TrustDeploymentRole\",\"Effect\":\"Allow\",\"Action\":\"sts:AssumeRole\",\"Principal\":{\"AWS\":\"arn:aws:iam::123456789012:role/deployer\"}}]}" + } + + assert { + condition = ( + length(data.aws_iam_policy_document.assume_role.source_policy_documents) == 2 + && contains(data.aws_iam_policy_document.assume_role.source_policy_documents, var.additional_trust_policy_json) + && output.assume_role_policy == data.aws_iam_policy_document.assume_role.json + ) + error_message = "The MicroVM trust-policy module must merge and return the additional trust policy document." + } +} + +run "rejects_invalid_additional_trust_policy" { + command = plan + + variables { + additional_trust_policy_json = "{" + } + + expect_failures = [var.additional_trust_policy_json] +} diff --git a/modules/compute-providers/aws/microvm/trust-policy/variables.tf b/modules/compute-providers/aws/microvm/trust-policy/variables.tf new file mode 100644 index 0000000000..1af67309d2 --- /dev/null +++ b/modules/compute-providers/aws/microvm/trust-policy/variables.tf @@ -0,0 +1,10 @@ +variable "additional_trust_policy_json" { + description = "Optional IAM policy document merged with the MicroVM provider's default runner-role trust policy." + type = string + default = null + + validation { + condition = var.additional_trust_policy_json == null ? true : can(jsondecode(var.additional_trust_policy_json)) + error_message = "additional_trust_policy_json must be valid JSON when set." + } +} diff --git a/modules/compute-providers/aws/microvm/trust-policy/versions.tf b/modules/compute-providers/aws/microvm/trust-policy/versions.tf new file mode 100644 index 0000000000..3ef011ea0a --- /dev/null +++ b/modules/compute-providers/aws/microvm/trust-policy/versions.tf @@ -0,0 +1,10 @@ +terraform { + required_version = ">= 1.4.0" + + required_providers { + aws = { + source = "hashicorp/aws" + version = ">= 6.33" + } + } +} diff --git a/modules/compute-providers/aws/microvm/validations.tf b/modules/compute-providers/aws/microvm/validations.tf new file mode 100644 index 0000000000..17c78b1d81 --- /dev/null +++ b/modules/compute-providers/aws/microvm/validations.tf @@ -0,0 +1,80 @@ +resource "terraform_data" "validate_config" { + lifecycle { + precondition { + condition = can(regex("^arn:[^:]+:lambda:[^:]+:[0-9]{12}:microvm-image:.+$", var.config.image_arn)) + error_message = "compute_provider.aws.microvm.image_arn must be a Lambda MicroVM image ARN." + } + + precondition { + condition = var.config.iam.resource_arns.images == null ? true : ( + length(var.config.iam.resource_arns.images) > 0 && + alltrue([ + for image_arn in var.config.iam.resource_arns.images : + image_arn == "*" || can(regex("^arn:[^:]+:lambda:[^:]+:[0-9]{12}:microvm-image:.+$", image_arn)) + ]) + ) + error_message = "compute_provider.aws.microvm.iam.resource_arns.images must be null or a non-empty list containing only * or Lambda MicroVM image ARN patterns." + } + + precondition { + condition = ( + length(var.config.ingress_network_connectors) <= 10 && + alltrue([ + for connector in var.config.ingress_network_connectors : + can(regex("^arn:[^:]+:lambda:[^:]+:([0-9]{12}|aws):network-connector:[^[:space:]]+$", connector)) + ]) + ) + error_message = "compute_provider.aws.microvm.ingress_network_connectors must contain at most 10 Lambda network-connector ARNs." + } + + precondition { + condition = ( + length(var.config.egress_network_connectors) <= 10 && + alltrue([ + for connector in var.config.egress_network_connectors : + can(regex("^arn:[^:]+:lambda:[^:]+:([0-9]{12}|aws):network-connector:[^[:space:]]+$", connector)) + ]) + ) + error_message = "compute_provider.aws.microvm.egress_network_connectors must contain at most 10 Lambda network-connector ARNs." + } + + precondition { + condition = try(var.config.iam.additional_policy_json.scale_up, null) == null ? true : can(jsondecode(var.config.iam.additional_policy_json.scale_up)) + error_message = "compute_provider.aws.microvm.iam.additional_policy_json.scale_up must be valid JSON when set." + } + + precondition { + condition = !( + local.microvm_metadata_ssm_path == local.runner_jit_ssm_path || + startswith(local.microvm_metadata_ssm_path, "${local.runner_jit_ssm_path}/") || + startswith(local.runner_jit_ssm_path, "${local.microvm_metadata_ssm_path}/") + ) + error_message = "The MicroVM metadata Parameter Store path must be separate from the runner JIT configuration path." + } + + precondition { + condition = ( + startswith(var.ssm.paths.root, "/") && + trim(var.ssm.paths.root, "/") != "" && + trim(var.ssm.paths.config, "/") != "" && + can(regex("^/[A-Za-z0-9_./-]+$", local.microvm_metadata_ssm_path)) && + length(regexall("//", local.microvm_metadata_ssm_path)) == 0 + ) + error_message = "The derived MicroVM metadata Parameter Store path must be an absolute path containing only letters, numbers, dot, underscore, hyphen, and slash." + } + } +} + +resource "terraform_data" "validate_runner" { + lifecycle { + precondition { + condition = var.runner.os == "linux" && var.runner.architecture == "arm64" + error_message = "Lambda MicroVM runners require runner.os = linux and runner.architecture = arm64." + } + + precondition { + condition = length(var.runner.name_prefix) <= 45 + error_message = "runner.name_prefix must be at most 45 characters." + } + } +} diff --git a/modules/compute-providers/aws/microvm/variables.tf b/modules/compute-providers/aws/microvm/variables.tf new file mode 100644 index 0000000000..388b06135a --- /dev/null +++ b/modules/compute-providers/aws/microvm/variables.tf @@ -0,0 +1,195 @@ +# tflint-ignore: terraform_unused_declarations +variable "aws_partition" { + description = "AWS partition used to construct IAM ARNs." + type = string + default = "aws" +} + +# tflint-ignore: terraform_unused_declarations +variable "aws_region" { + description = "AWS region used by compute-provider resources and policy documents." + type = string +} + +# tflint-ignore: terraform_unused_declarations +variable "prefix" { + description = "Prefix used to identify resources created for the runner configuration." + type = string + default = "github-actions" +} + +# tflint-ignore: terraform_unused_declarations +variable "tags" { + description = "Base tags available to taggable compute-provider resources. Provider-specific tags override this map within their documented scopes." + type = map(string) + default = {} +} + +variable "config" { + description = <<-EOT + Lambda MicroVM compute-provider configuration. Paths match `compute_provider.aws.microvm` in runner-config. + + - `image_arn`: ARN of the MicroVM image used to run GitHub runners. + - `image_version`: Optional MicroVM image version. + - `ingress_network_connectors`: Up to 10 Lambda network-connector ARNs passed to RunMicrovm. + - `egress_network_connectors`: Up to 10 Lambda network-connector ARNs passed to RunMicrovm. + - `cloudwatch_agent.enabled`: Enables the image CloudWatch agent through the shared runner configuration path. + - `cloudwatch_agent.config`: Optional complete CloudWatch agent configuration. Null renders the provider default from `log_files`. Custom log destinations must also be declared in `log_files` so Terraform creates their groups and IAM permissions. + - `log_files`: Optional files collected by the CloudWatch agent. Null uses the MicroVM defaults. + - `log_files[].log_group_name`: CloudWatch log-group name before optional prefixing. + - `log_files[].prefix_log_group`: Prefixes the log-group name with the runner configuration path. + - `log_files[].file_path`: File or glob read by the CloudWatch agent. + - `log_files[].log_stream_name`: Log-stream template. The image replaces `{microvm_id}` with the current MicroVM identifier. + - `log_files[].log_class`: CloudWatch log-group class for the collected file. + - `environment_variables`: Additional provider-specific Lambda environment variables merged into scale-up, scale-down, and pool. + - `iam.resource_arns.images`: Optional MicroVM image ARN allowlist for RunMicrovm and TerminateMicrovm. Null restricts both actions to `image_arn`; set an explicit list when dynamic image overrides are enabled. Provider-required list and connector permissions remain separately scoped to `*`. + - `iam.additional_policy_json.scale_up`: Optional additional provider policy attached separately to the scale-up Lambda role. + - `iam.managed_policies.scale_up`: Optional managed-policy wrapper attached to the scale-up Lambda role. Wrapper presence controls resource creation during planning. + - `iam.managed_policies.scale_up.arn`: ARN of the scale-up managed policy. The ARN may remain unknown until apply. + - `iam.managed_policies.pool`: Optional managed-policy wrapper attached to the pool Lambda role. Wrapper presence controls resource creation during planning. + - `iam.managed_policies.pool.arn`: ARN of the pool managed policy. The ARN may remain unknown until apply. + EOT + + type = object({ + image_arn = string + image_version = optional(string, null) + ingress_network_connectors = optional(list(string), []) + egress_network_connectors = optional(list(string), []) + cloudwatch_agent = optional(object({ + enabled = optional(bool, true) + config = optional(string, null) + }), {}) + log_files = optional(list(object({ + log_group_name = string + prefix_log_group = bool + file_path = string + log_stream_name = string + log_class = optional(string, "STANDARD") + })), null) + environment_variables = optional(map(string), {}) + iam = optional(object({ + resource_arns = optional(object({ + images = optional(list(string), null) + }), {}) + additional_policy_json = optional(object({ + scale_up = optional(string, null) + }), {}) + managed_policies = optional(object({ + scale_up = optional(object({ + arn = string + }), null) + pool = optional(object({ + arn = string + }), null) + }), {}) + }), {}) + }) + + nullable = false +} + +variable "runner" { + description = <<-EOT + Resolved runner settings consumed by the Lambda MicroVM compute provider. + + - `os`: Runner operating system. Lambda MicroVM requires `linux`. + - `architecture`: Runner distribution architecture. Lambda MicroVM requires `arm64`. + - `name_prefix`: Prefix added to registered runner names. + - `run_as_root`: Runs the runner service as root. + - `run_as`: Operating-system user used when `run_as_root` is false. + - `hooks.job_started`: Script installed as the runner job-started hook. + - `hooks.job_completed`: Script installed as the runner job-completed hook. + - `iam.role.arn`: Resolved runner-role ARN used as the MicroVM execution role and referenced by provider policies. + - `iam.role.name`: Resolved runner-role name used by provider resources. + - `iam.role.managed`: Whether runner-config manages the resolved runner role. Callers own an external role and must grant it `ssm:GetParameter` on the lane's `microvm-metadata/*.tags` and `enable_cloudwatch` parameters, `ssm:GetParameter` and `ssm:DeleteParameter` on the lane token path, plus `logs:CreateLogStream` and `logs:PutLogEvents` on the provider-managed runtime log group. When the CloudWatch agent is enabled, it also needs `ssm:GetParameter` on `cloudwatch_agent_config_runner` and stream access to the configured runner log groups. + - `iam.managed_policy_arns`: Common managed-policy ARNs returned with the provider-specific runner policies for attachment by runner-config. + - `iam.path`: IAM path available to provider-managed IAM resources. Null derives the path from `prefix`. + EOT + type = object({ + os = optional(string, "linux") + architecture = optional(string, "arm64") + name_prefix = optional(string, "") + run_as_root = optional(bool, false) + run_as = optional(string, "ec2-user") + hooks = optional(object({ + job_started = optional(string, "") + job_completed = optional(string, "") + }), {}) + iam = object({ + role = object({ + arn = string + name = string + managed = optional(bool, true) + }) + managed_policy_arns = optional(map(string), {}) + path = optional(string, null) + }) + }) + + nullable = false +} + +# tflint-ignore: terraform_unused_declarations +variable "github" { + description = <<-EOT + GitHub Enterprise Server settings available to compute-provider bootstrap data. + + - `enterprise_server.url`: Optional GitHub Enterprise Server base URL. Null selects GitHub.com. + - `enterprise_server.ssl_verify`: Enables TLS certificate verification for GitHub Enterprise Server. + EOT + type = object({ + enterprise_server = optional(object({ + url = optional(string, null) + ssl_verify = optional(bool, true) + }), {}) + }) + default = {} + nullable = false +} + +# tflint-ignore: terraform_unused_declarations +variable "ssm" { + description = <<-EOT + Parameter Store paths and tag scopes available to compute-provider bootstrap resources. + + - `paths.root`: Root Parameter Store path for the runner configuration. + - `paths.tokens`: Path segment used for registration tokens and just-in-time configuration. + - `paths.config`: Path segment used for persistent runner and provider configuration. MicroVM control-plane metadata is stored under its `microvm-metadata` child prefix. + - `tags`: Shared SSM tags that override module-level `tags`. + - `parameters.tags`: Parameter-specific tags that override module-level and shared SSM tags. + EOT + type = object({ + paths = object({ + root = string + tokens = string + config = string + }) + tags = optional(map(string), {}) + parameters = optional(object({ + tags = optional(map(string), {}) + }), {}) + }) + + nullable = false +} + +variable "observability" { + description = <<-EOT + Provider-neutral observability settings applied to the provider-managed MicroVM runtime log group. + + - `logs.retention_in_days`: CloudWatch Logs retention period. + - `logs.kms_key_id`: Optional KMS key ID or ARN used to encrypt the log group. + - `logs.class`: CloudWatch log-group class. + - `logs.tags`: Tags merged after module-level tags on the log group. + EOT + type = object({ + logs = optional(object({ + retention_in_days = optional(number, 180) + kms_key_id = optional(string, null) + class = optional(string, "STANDARD") + tags = optional(map(string), {}) + }), {}) + }) + default = {} + nullable = false +} diff --git a/modules/compute-providers/aws/microvm/versions.tf b/modules/compute-providers/aws/microvm/versions.tf new file mode 100644 index 0000000000..3ef011ea0a --- /dev/null +++ b/modules/compute-providers/aws/microvm/versions.tf @@ -0,0 +1,10 @@ +terraform { + required_version = ">= 1.4.0" + + required_providers { + aws = { + source = "hashicorp/aws" + version = ">= 6.33" + } + } +} diff --git a/modules/microvm-foundation/README.md b/modules/microvm-foundation/README.md new file mode 100644 index 0000000000..77b620c107 --- /dev/null +++ b/modules/microvm-foundation/README.md @@ -0,0 +1,134 @@ +# Lambda MicroVM Regional Foundation + +This module creates the regional AWS prerequisites for building and running +Lambda MicroVM GitHub Actions runners and is intended to be deployed once per +AWS Region. + +It manages: + +- A private, encrypted, versioned S3 bucket for content-addressed image build artifacts. +- A Lambda-trusted build role with scoped S3, CloudWatch Logs, and optional ECR pull access. +- Dedicated no-ingress security groups and native Lambda Network Connector resources for each configured VPC/subnet set. +- A Lambda-trusted Network Connector operator role and propagation barrier. +- An unattached runtime usage policy for the reserved image namespace and connector inventory. + +The module does not create MicroVM images, runner execution roles, or the +runner control plane. Attach `usage_policy_arn` to the control-plane role that +owns the runtime launch operations. The caller must also grant the Terraform +identity `iam:PassRole` for the operator role with +`iam:PassedToService=lambda.amazonaws.com`. + +The module deliberately does not configure an AWS provider. Configure the +provider in the root module or example so credentials and account selection +remain caller-owned. + +```hcl +provider "aws" { + region = "eu-west-1" +} + +module "microvm_foundation" { + source = "../../modules/microvm-foundation" + + aws_region = "eu-west-1" + tags = { Environment = "example" } + build_policy_name_prefix = "github-actions-runner-microvm-build-policy-" + build_role_name_prefix = "github-actions-runner-microvm-build-" + network_connector_operator_role_name_prefix = "github-actions-microvm-net-operator-" + usage_policy_name_prefix = "github-actions-runner-microvm-runtime-usage-policy-" + + image_name_prefix = "github-actions-runner-ubuntu-arm64" + + network_connectors = { + cicd = { + name = "github-actions-runner-egress" + vpc_id = "vpc-0123456789abcdef0" + subnet_ids = ["subnet-0123456789abcdef0"] + } + } +} +``` + +The companion `examples/microvm-foundation` directory is a complete setup +example. Apply it before following the direct Packer build instructions in +`images/microvm/README.md` or using the `examples/microvm` runner example. + + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.4.0 | +| [aws](#requirement\_aws) | >= 6.61 | +| [time](#requirement\_time) | >= 0.13 | + +## Providers + +| Name | Version | +|------|---------| +| [aws](#provider\_aws) | >= 6.61 | +| [time](#provider\_time) | >= 0.13 | + +## Modules + +No modules. + +## Resources + +| Name | Type | +|------|------| +| [aws_iam_policy.build](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_policy) | resource | +| [aws_iam_policy.usage](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_policy) | resource | +| [aws_iam_role.build](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role) | resource | +| [aws_iam_role.operator](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role) | resource | +| [aws_iam_role_policy_attachment.build](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy_attachment) | resource | +| [aws_iam_role_policy_attachment.operator](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy_attachment) | resource | +| [aws_lambdacore_network_connector.connector](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/lambdacore_network_connector) | resource | +| [aws_s3_bucket.artifacts](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/s3_bucket) | resource | +| [aws_s3_bucket_lifecycle_configuration.artifacts](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/s3_bucket_lifecycle_configuration) | resource | +| [aws_s3_bucket_ownership_controls.artifacts](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/s3_bucket_ownership_controls) | resource | +| [aws_s3_bucket_policy.artifacts](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/s3_bucket_policy) | resource | +| [aws_s3_bucket_public_access_block.artifacts](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/s3_bucket_public_access_block) | resource | +| [aws_s3_bucket_server_side_encryption_configuration.artifacts](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/s3_bucket_server_side_encryption_configuration) | resource | +| [aws_s3_bucket_versioning.artifacts](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/s3_bucket_versioning) | resource | +| [aws_security_group.connector](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/security_group) | resource | +| [aws_vpc_security_group_egress_rule.ipv4](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/vpc_security_group_egress_rule) | resource | +| [aws_vpc_security_group_egress_rule.ipv6](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/vpc_security_group_egress_rule) | resource | +| [time_sleep.operator_role_propagation](https://registry.terraform.io/providers/hashicorp/time/latest/docs/resources/sleep) | resource | +| [aws_caller_identity.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/caller_identity) | data source | +| [aws_iam_policy_document.artifact_bucket](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.build](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.lambda_service_assume_role](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.network_connector_assume_operator_role](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.usage](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_partition.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/partition) | data source | +| [aws_subnet.selected](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/subnet) | data source | + +## Inputs + +| Name | Description | Type | Default | Required | +|------|-------------|------|---------|:--------:| +| [artifact\_bucket\_name](#input\_artifact\_bucket\_name) | Optional name for the regional MicroVM build-artifact bucket. When null, AWS generates the bucket name. | `string` | `null` | no | +| [artifact\_retention\_days](#input\_artifact\_retention\_days) | Number of days to retain current and noncurrent MicroVM build artifacts. | `number` | `30` | no | +| [aws\_region](#input\_aws\_region) | AWS region in which to create the Lambda MicroVM prerequisites. | `string` | n/a | yes | +| [build\_policy\_name\_prefix](#input\_build\_policy\_name\_prefix) | Name prefix for the Lambda MicroVM build policy. | `string` | n/a | yes | +| [build\_role\_name\_prefix](#input\_build\_role\_name\_prefix) | Name prefix for the Lambda MicroVM build role. | `string` | n/a | yes | +| [ecr\_repository\_arns](#input\_ecr\_repository\_arns) | Optional regional ECR repository ARNs from which MicroVM image builds can pull runner base images. | `set(string)` | `[]` | no | +| [image\_name\_prefix](#input\_image\_name\_prefix) | IAM namespace prefix reserved for externally published Lambda MicroVM image names. This module does not create or enumerate images. | `string` | n/a | yes | +| [network\_connector\_operator\_role\_name\_prefix](#input\_network\_connector\_operator\_role\_name\_prefix) | Name prefix for the Lambda Network Connector operator role. | `string` | n/a | yes | +| [network\_connectors](#input\_network\_connectors) | Optional regional Lambda MicroVM Network Connectors keyed by a stable consumer-defined identity. |
map(object({
name = string
vpc_id = string
subnet_ids = set(string)
network_protocol = optional(string, "IPv4")
}))
| n/a | yes | +| [tags](#input\_tags) | A map of module-specific tags to apply to resources. | `map(string)` | n/a | yes | +| [usage\_policy\_name\_prefix](#input\_usage\_policy\_name\_prefix) | Name prefix for the Lambda MicroVM runtime usage policy. | `string` | n/a | yes | + +## Outputs + +| Name | Description | +|------|-------------| +| [artifact\_bucket\_arn](#output\_artifact\_bucket\_arn) | ARN of the regional S3 bucket used for Lambda MicroVM build artifacts. | +| [artifact\_bucket\_name](#output\_artifact\_bucket\_name) | Name of the regional S3 bucket used for Lambda MicroVM build artifacts. | +| [artifact\_prefix](#output\_artifact\_prefix) | Bucket prefix to which the MicroVM image publisher uploads content-addressed build artifacts. | +| [build\_role\_arn](#output\_build\_role\_arn) | ARN of the Lambda-trusted role used during MicroVM image builds. | +| [connector\_arns](#output\_connector\_arns) | Map of connector key to the ARN of each Lambda Network Connector. | +| [security\_group\_ids](#output\_security\_group\_ids) | Map of connector key to its dedicated no-ingress security group ID. | +| [usage\_policy\_arn](#output\_usage\_policy\_arn) | ARN of the reusable regional policy for operating MicroVM images in the reserved namespace and passing their Network Connectors. | + diff --git a/modules/microvm-foundation/build.tf b/modules/microvm-foundation/build.tf new file mode 100644 index 0000000000..160f3d9399 --- /dev/null +++ b/modules/microvm-foundation/build.tf @@ -0,0 +1,84 @@ +# Lambda assumes this role while building an image snapshot. +data "aws_iam_policy_document" "build" { + statement { + sid = "ReadRegionalBuildArtifact" + effect = "Allow" + actions = ["s3:GetObject"] + resources = ["${aws_s3_bucket.artifacts.arn}/${local.artifact_prefix}/*"] + } + + statement { + sid = "CreateMicrovmBuildLogGroups" + effect = "Allow" + actions = ["logs:CreateLogGroup"] + resources = [local.log_group_arn_pattern] + } + + statement { + sid = "WriteMicrovmBuildLogs" + effect = "Allow" + actions = [ + "logs:CreateLogStream", + "logs:PutLogEvents", + ] + resources = [local.log_stream_arn_pattern] + } + + dynamic "statement" { + for_each = length(var.ecr_repository_arns) > 0 ? [true] : [] + content { + sid = "AuthorizePrivateEcrPull" + effect = "Allow" + actions = ["ecr:GetAuthorizationToken"] + resources = ["*"] + } + } + + dynamic "statement" { + for_each = length(var.ecr_repository_arns) > 0 ? [true] : [] + content { + sid = "PullPrivateEcrImage" + effect = "Allow" + actions = [ + "ecr:BatchCheckLayerAvailability", + "ecr:BatchGetImage", + "ecr:GetDownloadUrlForLayer", + ] + resources = var.ecr_repository_arns + } + } +} + +resource "aws_iam_policy" "build" { + name_prefix = var.build_policy_name_prefix + description = "Regional permissions used by Lambda while building MicroVM images." + policy = data.aws_iam_policy_document.build.json + tags = var.tags +} + +resource "aws_iam_role_policy_attachment" "build" { + role = aws_iam_role.build.name + policy_arn = aws_iam_policy.build.arn +} + +data "aws_iam_policy_document" "lambda_service_assume_role" { + statement { + sid = "LambdaMicrovmService" + effect = "Allow" + actions = [ + "sts:AssumeRole", + "sts:TagSession", + ] + + principals { + type = "Service" + identifiers = ["lambda.amazonaws.com"] + } + } +} + +resource "aws_iam_role" "build" { + name_prefix = var.build_role_name_prefix + assume_role_policy = data.aws_iam_policy_document.lambda_service_assume_role.json + tags = var.tags +} diff --git a/modules/microvm-foundation/data.tf b/modules/microvm-foundation/data.tf new file mode 100644 index 0000000000..dc90004cc6 --- /dev/null +++ b/modules/microvm-foundation/data.tf @@ -0,0 +1,31 @@ +data "aws_caller_identity" "current" {} + +data "aws_partition" "current" {} + +data "aws_subnet" "selected" { + for_each = local.network_connector_subnets + id = each.value.subnet_id +} + +locals { + artifact_prefix = "lambda-microvms" + + image_arn_pattern = "arn:${data.aws_partition.current.partition}:lambda:${var.aws_region}:${data.aws_caller_identity.current.account_id}:microvm-image:${var.image_name_prefix}-*" + log_group_arn_pattern = "arn:${data.aws_partition.current.partition}:logs:${var.aws_region}:${data.aws_caller_identity.current.account_id}:log-group:/aws/lambda/microvms/${var.image_name_prefix}-*" + log_stream_arn_pattern = "${local.log_group_arn_pattern}:log-stream:*" + + network_connector_subnets = merge({}, [ + for connector_key, connector in var.network_connectors : { + for subnet_id in connector.subnet_ids : + "${connector_key}/${subnet_id}" => { + connector_key = connector_key + subnet_id = subnet_id + } + } + ]...) + + connector_arns = { + for connector_key, connector in aws_lambdacore_network_connector.connector : + connector_key => connector.arn + } +} diff --git a/modules/microvm-foundation/network_connector.tf b/modules/microvm-foundation/network_connector.tf new file mode 100644 index 0000000000..3e41d161b3 --- /dev/null +++ b/modules/microvm-foundation/network_connector.tf @@ -0,0 +1,31 @@ +resource "aws_lambdacore_network_connector" "connector" { + for_each = var.network_connectors + + name = each.value.name + operator_role = aws_iam_role.operator.arn + + configuration { + vpc_egress_configuration { + associated_compute_resource_types = ["MicroVm"] + network_protocol = each.value.network_protocol + security_group_ids = [aws_security_group.connector[each.key].id] + subnet_ids = sort(tolist(each.value.subnet_ids)) + } + } + + lifecycle { + precondition { + condition = alltrue([ + for subnet_id in each.value.subnet_ids : + data.aws_subnet.selected["${each.key}/${subnet_id}"].vpc_id == each.value.vpc_id + ]) + error_message = "Every subnet in network_connectors[${each.key}] must belong to its configured vpc_id." + } + } + + depends_on = [ + time_sleep.operator_role_propagation, + aws_vpc_security_group_egress_rule.ipv4, + aws_vpc_security_group_egress_rule.ipv6, + ] +} diff --git a/modules/microvm-foundation/network_connector_operator.tf b/modules/microvm-foundation/network_connector_operator.tf new file mode 100644 index 0000000000..fc7d03fd74 --- /dev/null +++ b/modules/microvm-foundation/network_connector_operator.tf @@ -0,0 +1,41 @@ +data "aws_iam_policy_document" "network_connector_assume_operator_role" { + statement { + sid = "LambdaNetworkConnectorService" + effect = "Allow" + actions = ["sts:AssumeRole"] + + principals { + type = "Service" + identifiers = ["network-connectors.lambda.amazonaws.com"] + } + } +} + +resource "aws_iam_role" "operator" { + name_prefix = var.network_connector_operator_role_name_prefix + assume_role_policy = data.aws_iam_policy_document.network_connector_assume_operator_role.json + tags = var.tags +} + +resource "aws_iam_role_policy_attachment" "operator" { + role = aws_iam_role.operator.name + policy_arn = "arn:${data.aws_partition.current.partition}:iam::aws:policy/AWSLambdaNetworkConnectorOperatorPolicy" +} + +# IAM reports role and policy writes before they are consistently available to +# Lambda. Wait before allowing the native Network Connector resource to create +# any connector. +resource "time_sleep" "operator_role_propagation" { + depends_on = [aws_iam_role_policy_attachment.operator] + + create_duration = "30s" + + triggers = { + operator_role_unique_id = aws_iam_role.operator.unique_id + operator_trust_policy_sha256 = sha256(aws_iam_role.operator.assume_role_policy) + } + + lifecycle { + replace_triggered_by = [aws_iam_role_policy_attachment.operator] + } +} diff --git a/modules/microvm-foundation/network_connector_security_group.tf b/modules/microvm-foundation/network_connector_security_group.tf new file mode 100644 index 0000000000..7d88e37d2d --- /dev/null +++ b/modules/microvm-foundation/network_connector_security_group.tf @@ -0,0 +1,40 @@ +# A connector gets its own no-ingress security group. Route tables and NACLs on +# the caller-selected subnets determine actual destinations reachable through +# the IPv4 or dual-stack egress rules. +resource "aws_security_group" "connector" { + #checkov:skip=CKV2_AWS_5:The security group is consumed by the Lambda Network Connector rather than by a Terraform-native ENI resource. + for_each = var.network_connectors + + name = "microvm-${each.value.name}-${var.aws_region}" + description = "Outbound egress for the ${each.value.name} Lambda MicroVM Network Connector" + vpc_id = each.value.vpc_id + + tags = merge(var.tags, { + Name = "microvm-${each.value.name}-${var.aws_region}" + }) +} + +resource "aws_vpc_security_group_egress_rule" "ipv4" { + #checkov:skip=CKV_AWS_382:The connector requires outbound access; subnet routes and NACLs provide the network destination boundary. + for_each = var.network_connectors + + security_group_id = aws_security_group.connector[each.key].id + description = "Lambda MicroVM connector IPv4 egress" + ip_protocol = "-1" + cidr_ipv4 = "0.0.0.0/0" + tags = var.tags +} + +resource "aws_vpc_security_group_egress_rule" "ipv6" { + #checkov:skip=CKV_AWS_382:Dual-stack connector egress is intentional; subnet routes and NACLs provide the network destination boundary. + for_each = { + for connector_key, connector in var.network_connectors : + connector_key => connector if connector.network_protocol == "DualStack" + } + + security_group_id = aws_security_group.connector[each.key].id + description = "Lambda MicroVM connector IPv6 egress" + ip_protocol = "-1" + cidr_ipv6 = "::/0" + tags = var.tags +} diff --git a/modules/microvm-foundation/outputs.tf b/modules/microvm-foundation/outputs.tf new file mode 100644 index 0000000000..9fd52ab4bf --- /dev/null +++ b/modules/microvm-foundation/outputs.tf @@ -0,0 +1,34 @@ +output "artifact_bucket_name" { + description = "Name of the regional S3 bucket used for Lambda MicroVM build artifacts." + value = aws_s3_bucket.artifacts.id +} + +output "artifact_bucket_arn" { + description = "ARN of the regional S3 bucket used for Lambda MicroVM build artifacts." + value = aws_s3_bucket.artifacts.arn +} + +output "artifact_prefix" { + description = "Bucket prefix to which the MicroVM image publisher uploads content-addressed build artifacts." + value = local.artifact_prefix +} + +output "build_role_arn" { + description = "ARN of the Lambda-trusted role used during MicroVM image builds." + value = aws_iam_role.build.arn +} + +output "usage_policy_arn" { + description = "ARN of the reusable regional policy for operating MicroVM images in the reserved namespace and passing their Network Connectors." + value = aws_iam_policy.usage.arn +} + +output "connector_arns" { + description = "Map of connector key to the ARN of each Lambda Network Connector." + value = local.connector_arns +} + +output "security_group_ids" { + description = "Map of connector key to its dedicated no-ingress security group ID." + value = { for connector_key, security_group in aws_security_group.connector : connector_key => security_group.id } +} diff --git a/modules/microvm-foundation/storage.tf b/modules/microvm-foundation/storage.tf new file mode 100644 index 0000000000..73ff52e172 --- /dev/null +++ b/modules/microvm-foundation/storage.tf @@ -0,0 +1,103 @@ +# Lambda MicroVM image source artifacts must be stored in an S3 bucket in the +# same region as the image. A separate helper deployment owns the bucket in each +# supported region. +resource "aws_s3_bucket" "artifacts" { + #checkov:skip=CKV_AWS_145:SSE-S3 protects ephemeral content-addressed build inputs; this helper has no CMK artifact contract. + #checkov:skip=CKV_AWS_144:Lambda MicroVM builds require same-region artifacts, so this regional bucket intentionally has no cross-region replication. + #checkov:skip=CKV_AWS_18:CloudTrail records control-plane access and the bucket contains short-lived build inputs; separate S3 access logging is not required. + #checkov:skip=CKV2_AWS_62:The publisher uploads artifacts synchronously and no event-driven consumer requires S3 notifications. + bucket = var.artifact_bucket_name + tags = var.tags +} + +resource "aws_s3_bucket_ownership_controls" "artifacts" { + bucket = aws_s3_bucket.artifacts.id + + rule { + object_ownership = "BucketOwnerEnforced" + } +} + +resource "aws_s3_bucket_versioning" "artifacts" { + bucket = aws_s3_bucket.artifacts.id + + versioning_configuration { + status = "Enabled" + } +} + +resource "aws_s3_bucket_server_side_encryption_configuration" "artifacts" { + bucket = aws_s3_bucket.artifacts.id + + rule { + apply_server_side_encryption_by_default { + sse_algorithm = "AES256" + } + } +} + +resource "aws_s3_bucket_public_access_block" "artifacts" { + bucket = aws_s3_bucket.artifacts.id + block_public_acls = true + block_public_policy = true + ignore_public_acls = true + restrict_public_buckets = true + skip_destroy = true +} + +resource "aws_s3_bucket_lifecycle_configuration" "artifacts" { + bucket = aws_s3_bucket.artifacts.id + + rule { + id = "expire-microvm-build-artifacts" + + # The bucket is dedicated to MicroVM build artifacts, so lifecycle cleanup + # applies to every object, including abandoned uploads outside the expected + # publisher prefix. + filter {} + + expiration { + days = var.artifact_retention_days + } + + noncurrent_version_expiration { + noncurrent_days = var.artifact_retention_days + } + + abort_incomplete_multipart_upload { + days_after_initiation = 7 + } + + status = "Enabled" + } + + depends_on = [aws_s3_bucket_versioning.artifacts] +} + +data "aws_iam_policy_document" "artifact_bucket" { + statement { + sid = "DenyInsecureTransport" + effect = "Deny" + actions = ["s3:*"] + resources = [ + aws_s3_bucket.artifacts.arn, + "${aws_s3_bucket.artifacts.arn}/*", + ] + + principals { + type = "*" + identifiers = ["*"] + } + + condition { + test = "Bool" + variable = "aws:SecureTransport" + values = ["false"] + } + } +} + +resource "aws_s3_bucket_policy" "artifacts" { + bucket = aws_s3_bucket.artifacts.id + policy = data.aws_iam_policy_document.artifact_bucket.json +} diff --git a/modules/microvm-foundation/usage_policy.tf b/modules/microvm-foundation/usage_policy.tf new file mode 100644 index 0000000000..8abe004bee --- /dev/null +++ b/modules/microvm-foundation/usage_policy.tf @@ -0,0 +1,58 @@ +# Consumer modules can attach this policy to a control-plane role they own. +# This helper deliberately leaves the managed policy unattached. +data "aws_iam_policy_document" "usage" { + statement { + sid = "UseConfiguredMicrovmImages" + effect = "Allow" + actions = [ + "lambda:CreateMicrovmAuthToken", + "lambda:GetMicrovm", + "lambda:GetMicrovmImage", + "lambda:GetMicrovmImageVersion", + "lambda:ListMicrovmImageVersions", + "lambda:ResumeMicrovm", + "lambda:RunMicrovm", + "lambda:SuspendMicrovm", + "lambda:TerminateMicrovm", + ] + resources = [local.image_arn_pattern] + } + + #checkov:skip=CKV_AWS_111:ListMicrovms and ListMicrovmImages do not support resource-level permissions. + #checkov:skip=CKV_AWS_356:Lambda MicroVM account-level list actions require Resource '*'. + statement { + sid = "DiscoverMicrovmRuntimeState" + effect = "Allow" + actions = [ + "lambda:ListMicrovmImages", + "lambda:ListMicrovms", + ] + resources = ["*"] + } + + statement { + sid = "ReadConfiguredNetworkConnectors" + effect = "Allow" + actions = ["lambda:GetNetworkConnector"] + resources = values(local.connector_arns) + } + + #checkov:skip=CKV_AWS_111:PassNetworkConnector and ListNetworkConnectors do not support resource-level permissions. + #checkov:skip=CKV_AWS_356:Lambda requires Resource '*' for PassNetworkConnector and the account-level list operation. + statement { + sid = "PassAndDiscoverNetworkConnectors" + effect = "Allow" + actions = [ + "lambda:ListNetworkConnectors", + "lambda:PassNetworkConnector", + ] + resources = ["*"] + } +} + +resource "aws_iam_policy" "usage" { + name_prefix = var.usage_policy_name_prefix + description = "Permissions to discover and operate configured Lambda MicroVM images and to read and pass their regional Network Connectors." + policy = data.aws_iam_policy_document.usage.json + tags = var.tags +} diff --git a/modules/microvm-foundation/variables.tf b/modules/microvm-foundation/variables.tf new file mode 100644 index 0000000000..72c1db000b --- /dev/null +++ b/modules/microvm-foundation/variables.tf @@ -0,0 +1,147 @@ +variable "aws_region" { + type = string + description = "AWS region in which to create the Lambda MicroVM prerequisites." +} + +variable "tags" { + type = map(string) + description = "A map of module-specific tags to apply to resources." +} + +variable "build_policy_name_prefix" { + type = string + description = "Name prefix for the Lambda MicroVM build policy." + + validation { + condition = length(var.build_policy_name_prefix) >= 1 && length(var.build_policy_name_prefix) <= 64 && can(regex("^[a-zA-Z0-9-_]+-$", var.build_policy_name_prefix)) + error_message = "build_policy_name_prefix must be 1 to 64 characters, contain only letters, numbers, hyphens, or underscores, and end with a hyphen." + } +} + +variable "usage_policy_name_prefix" { + type = string + description = "Name prefix for the Lambda MicroVM runtime usage policy." + + validation { + condition = length(var.usage_policy_name_prefix) >= 1 && length(var.usage_policy_name_prefix) <= 64 && can(regex("^[a-zA-Z0-9-_]+-$", var.usage_policy_name_prefix)) + error_message = "usage_policy_name_prefix must be 1 to 64 characters, contain only letters, numbers, hyphens, or underscores, and end with a hyphen." + } +} + +variable "build_role_name_prefix" { + type = string + description = "Name prefix for the Lambda MicroVM build role." + + validation { + condition = length(var.build_role_name_prefix) >= 1 && length(var.build_role_name_prefix) <= 64 && can(regex("^[a-zA-Z0-9-_]+-$", var.build_role_name_prefix)) + error_message = "build_role_name_prefix must be 1 to 64 characters, contain only letters, numbers, hyphens, or underscores, and end with a hyphen." + } +} + +variable "network_connector_operator_role_name_prefix" { + type = string + description = "Name prefix for the Lambda Network Connector operator role." + + validation { + condition = length(var.network_connector_operator_role_name_prefix) >= 1 && length(var.network_connector_operator_role_name_prefix) <= 38 && can(regex("^[a-zA-Z0-9-_]+-$", var.network_connector_operator_role_name_prefix)) + error_message = "network_connector_operator_role_name_prefix must be 1 to 38 characters, contain only letters, numbers, hyphens, or underscores, and end with a hyphen." + } +} + +variable "artifact_bucket_name" { + type = string + description = "Optional name for the regional MicroVM build-artifact bucket. When null, AWS generates the bucket name." + default = null + nullable = true + + validation { + condition = var.artifact_bucket_name == null ? true : length(var.artifact_bucket_name) > 0 + error_message = "artifact_bucket_name must be null or a non-empty string." + } +} + +variable "artifact_retention_days" { + type = number + description = "Number of days to retain current and noncurrent MicroVM build artifacts." + default = 30 + + validation { + condition = var.artifact_retention_days >= 1 && var.artifact_retention_days <= 3650 + error_message = "artifact_retention_days must be between 1 and 3650." + } +} + +variable "image_name_prefix" { + type = string + description = "IAM namespace prefix reserved for externally published Lambda MicroVM image names. This module does not create or enumerate images." + + validation { + condition = ( + length(var.image_name_prefix) >= 1 + && length(var.image_name_prefix) <= 62 + && can(regex("^[a-zA-Z0-9-_]+$", var.image_name_prefix)) + ) + error_message = "image_name_prefix must be a 1 to 62 character IAM namespace containing only letters, numbers, hyphens, or underscores; the publisher validates each complete image name." + } +} + +variable "ecr_repository_arns" { + type = set(string) + description = "Optional regional ECR repository ARNs from which MicroVM image builds can pull runner base images." + default = [] +} + +variable "network_connectors" { + type = map(object({ + name = string + vpc_id = string + subnet_ids = set(string) + network_protocol = optional(string, "IPv4") + })) + description = "Optional regional Lambda MicroVM Network Connectors keyed by a stable consumer-defined identity." + + validation { + condition = alltrue([ + for connector in values(var.network_connectors) : ( + length(connector.name) >= 1 + && length(connector.name) <= 64 + && can(regex("^[a-zA-Z0-9_-]+$", connector.name)) + ) + ]) + error_message = "Each network connector name must contain only letters, numbers, hyphens, or underscores and be at most 64 characters." + } + + validation { + condition = ( + length(distinct([for connector in values(var.network_connectors) : connector.name])) == length(var.network_connectors) + ) + error_message = "Each network connector name must be unique within the region." + } + + validation { + condition = alltrue([ + for connector in values(var.network_connectors) : can(regex("^vpc-[0-9a-f]+$", connector.vpc_id)) + ]) + error_message = "Each network connector vpc_id must be a valid VPC ID." + } + + validation { + condition = alltrue([ + for connector in values(var.network_connectors) : ( + length(connector.subnet_ids) >= 1 + && length(connector.subnet_ids) <= 16 + && alltrue([ + for subnet_id in connector.subnet_ids : can(regex("^subnet-[0-9a-f]+$", subnet_id)) + ]) + ) + ]) + error_message = "Each network connector must contain 1 to 16 valid subnet IDs." + } + + validation { + condition = alltrue([ + for connector in values(var.network_connectors) : contains(["IPv4", "DualStack"], connector.network_protocol) + ]) + error_message = "Each network connector network_protocol must be IPv4 or DualStack." + } +} diff --git a/modules/microvm-foundation/versions.tf b/modules/microvm-foundation/versions.tf new file mode 100644 index 0000000000..ccc4e5a4ef --- /dev/null +++ b/modules/microvm-foundation/versions.tf @@ -0,0 +1,14 @@ +terraform { + required_version = ">= 1.4.0" + + required_providers { + aws = { + source = "hashicorp/aws" + version = ">= 6.61" + } + time = { + source = "hashicorp/time" + version = ">= 0.13" + } + } +} diff --git a/modules/multi-runner/.terraform.lock.hcl b/modules/multi-runner/.terraform.lock.hcl new file mode 100644 index 0000000000..9559f5fbd8 --- /dev/null +++ b/modules/multi-runner/.terraform.lock.hcl @@ -0,0 +1,71 @@ +# This file is maintained automatically by "terraform init". +# Manual edits may be lost in future updates. + +provider "registry.terraform.io/hashicorp/aws" { + version = "6.63.0" + constraints = ">= 6.21.0, >= 6.33.0" + hashes = [ + "h1:9cre7jh1lSs/9igpgAcENMUAUlYW3HCtkav3up4oit0=", + "h1:dRlYHkc+r6fgzF57WC7Zjcmb6sF/6TTGDEgwGK+LAZY=", + "zh:005d56736afd17d963998c405cee6f434dbc23a415109f9435ff1542879ae611", + "zh:026ef126321a86ad7080b5d858e2527f96f5289678cbcd8856296e229c43339d", + "zh:06e0b58b2d1eddb5137fc86bee7ad2d07953c0bc3f57cccfc5ae0d2456068a3a", + "zh:07221735d61ababed84734e5ffcfc5bd59d01f29f029166ba5f2175895dceed1", + "zh:1a72db00583112bdb8c19b213a78a3f5de754fffc08f07e061f4e326289fab7d", + "zh:32968e74a53b03e97a084dc7050c22ef661fb5b3ea8a44f5a63e47bc45ad0e7c", + "zh:4b357dfe4b820e3e4acd2881cff8288b2186491e63416751f0d12692ba478ceb", + "zh:81e30884d7de686265e7d87bb92527e802878c65a378470ede2a1e9f4e40ccc9", + "zh:82e137297f6a5a08b9ce2138f7aabea245ad99495d9d9eff502f752d6ca90dbd", + "zh:8eb83b67099f0ea9df238a979dff933ff50ce06a2e3ff05a48556a10f10dd204", + "zh:9b12af85486a96aedd8d7984b0ff811a4b42e3d88dad1a3fb4c0b580d04fa425", + "zh:d0ba30886cbe41850fee689f51ef9088578f323cfd21817bb409951d43c465eb", + "zh:dd48e7089784454bc03d713e9057f5ca0ea1613bd402125054a51894957b7925", + "zh:f250fa81e54cf60fcb0e9c0fc4ac043f1ecc2ac24967f628b3609364fcab3d04", + "zh:f38fc09fc25a8d2cf89a4d4cd6a5ef7cb1aad72798dbdcad58b8876b6a551a54", + "zh:f7c7380fdf126e1901f2084588dbfd724c76cb131ccfa795a541219111103c06", + ] +} + +provider "registry.terraform.io/hashicorp/null" { + version = "3.3.1" + constraints = "~> 3.0, ~> 3.2" + hashes = [ + "h1:TuxJq10DVnRP7c5HBZPyyvQGcckNVfijyU1eXEu5e4M=", + "h1:m5FqidbIgh+E9OigiZh8/xbkvpUQFSj3hZo/jqNLCLQ=", + "zh:08c59776542ea16e5a8545752787b17ff412922182b4cfabe16139197be8ac44", + "zh:123109cc7e5ed6d515787fbc212f2a3fd5e75647bb24ab7c801ccd4d4ed42451", + "zh:14b3fa4372754b54844b41d5dbd4671a292d8d6828b90169061feb4d7b15dd05", + "zh:56a4daaa3212f57b764bf3d1f333141c6610c5f21abb240e0111221f7c7fa4d4", + "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3", + "zh:7e888a026dbacd2474a42264227ae35f639780f0f0c613529d10a95cd61988b3", + "zh:85a53646267e87d600df7124e4767ffde9bba3b6356d45d961618bdd68131cc7", + "zh:8ffa0e9c7c39b2ab0905b472465d6e35ef0b776b3f6273bb34c150340b61bff1", + "zh:9846510a1841530d4403f4818e233f91e3b3bade7441047599fbf800742f65be", + "zh:afa98d44860875f037c6def0a7e6ff208e042712ba771f620482b143cd336891", + "zh:bdca130d9ef27488ae0b13bc8fd8019e8bbdd4f2ceff29da066bd333165d68c5", + "zh:cb3b94cbca88210dd0d1f11e2b8a89333f48c3857faf8f70f589072ce7c28610", + "zh:f0c0ba87925fe32f84b80f7513b1efb1b0866f51f899ba825e95ad59ff09b018", + ] +} + +provider "registry.terraform.io/hashicorp/random" { + version = "3.9.0" + constraints = "~> 3.0" + hashes = [ + "h1:OO+IuvQJSPmWdN8AyyIEvPJbLvDQpgX/zbktoa9KsJE=", + "h1:UlBuNVuCGJ39tTv2c5gz2NRZnQbXfbIWbTzWcth5o74=", + "zh:161ad0bd9a75768c82f53fb6e7172a9d8be2d4889b012645a34795031aaf1bf1", + "zh:19dc9a5b17729725ccfc4f45b0500af0ee5bc6b6b160c7adb8f2bf617d2c80ea", + "zh:269eda8fe42daa7974d5a34d166c3ba9defe80cde86c01e4dadcfdf2e1f05e5f", + "zh:373f7c65566f8f2cc7f45d698654feb9d988996957e1266a69ca00c52d6d16d0", + "zh:5599d16804c41c83009ec621b6d6b6f74e102f5827678a4750f8809055546b61", + "zh:583be0440469a22bff70dcfa56593b01566860b29607437264adb51060cf46fc", + "zh:5f211d8ec3f2e1f414870d9584bfe26e6995560ef81c748f8447a48164767398", + "zh:78d5eefdd9e494defcb3c68d282b8f96630502cac21d1ea161f53cfe9bb483b3", + "zh:7b547fd16216761ef86efc3ed516ac5ac0c5c42b7c7eb24a08cef2d93f69ed5e", + "zh:7e7c0679daf2a382151d05068c8c3f0dae6b7b7dccf818827b73dd08638df2ef", + "zh:8089dec888a8038b9b4fb23b3df7e1057293dbc5b60b42cc47ff690d69d4b61b", + "zh:c51f15a031edfd6f23ce8ced3446ca7f8d8d647e2499890d7d5d10d5016d7257", + "zh:c94784f005708890dc6895afd53636ec00ec1e430b15d41e5aebfb1d4b39bd04", + ] +} diff --git a/modules/multi-runner/README.md b/modules/multi-runner/README.md index 61a558389f..635e078570 100644 --- a/modules/multi-runner/README.md +++ b/modules/multi-runner/README.md @@ -4,6 +4,8 @@ This module creates many runners with one or more GitHub Apps. The module utilizes the internal modules and deploys parts of the stack for each runner defined. +Terraform 1.4 or later is required. Terraform 1.3 and earlier are no longer supported by this module. + ### GitHub App round-robin To distribute GitHub API rate limit usage, this module supports configuring multiple GitHub Apps via the `additional_github_apps` variable. The control-plane lambdas (scale-up, scale-down, pool, job-retry) randomly select an app for each API call, spreading the load across all configured apps. @@ -18,13 +20,13 @@ The **webhook lambda** does not participate in round-robin: it only validates in The module takes a configuration as input containing a matcher for the labels. The [webhook](https://github-aws-runners.github.io/terraform-aws-github-runner/modules/internal/webhook/) lambda is using the configuration to delegate events based on the labels in the workflow job and sent them to a dedicated queue based on the configuration. Events on each queue are processed by a dedicated lambda per configuration to scale runners. -> **Experimental v2 configuration:** Set `experimental_features = ["multi-runner-v2"]` before using the provider-boundary inputs. Their schema may change during the experimental window; the acknowledgement flag will become a deprecated no-op for one release when the feature graduates. - For each configuration: - When enabled, the [distribution syncer](https://github-aws-runners.github.io/terraform-aws-github-runner/modules/internal/runner-binaries-syncer/) is deployed for each unique combination of OS and architecture. - For each configuration a queue is created and [runner module](https://github-aws-runners.github.io/terraform-aws-github-runner/modules/internal/runners/) is deployed +Experimental runner configurations may select the Lambda MicroVM provider with `compute_provider.aws.microvm`. MicroVM lanes use Linux ARM64 ephemeral runners with JIT configuration and do not participate in EC2 runner-binary synchronization. + ## Matching Matching of the configuration is done based on the labels specified in labelMatchers configuration. The webhook is processing the `workflow_job` event and match the labels against the labels specified in labelMatchers configuration in the order of configuration with exact-match true first, followed by all exact matches false. @@ -96,48 +98,12 @@ module "multi-runner" { } ``` -### Provider-boundary v2 configuration - -The v2 form of `multi_runner_config` keeps runner, Lambda, orchestration, SSM, observability, and compute-provider settings under one configuration entry. The webhook matcher is configured under `orchestration_provider.webhook.matcherConfig`. - -```hcl -multi_runner_config = { - "linux-x64" = { - tags = { - Environment = "production" - } - - runner = { - os = "linux" - architecture = "x64" - extra_labels = ["large"] - } - - orchestration_provider = { - webhook = { - matcherConfig = { - labelMatchers = [["self-hosted", "linux", "x64", "large"]] - } - } - } - - compute_provider = { - aws = { - ec2 = { - instance_types = ["m5.large"] - } - } - } - } -} -``` - ## Requirements | Name | Version | |------|---------| -| [terraform](#requirement\_terraform) | >= 1.3 | +| [terraform](#requirement\_terraform) | >= 1.4 | | [aws](#requirement\_aws) | >= 6.33 | | [random](#requirement\_random) | ~> 3.0 | @@ -145,8 +111,9 @@ multi_runner_config = { | Name | Version | |------|---------| -| [aws](#provider\_aws) | >= 6.33 | -| [random](#provider\_random) | ~> 3.0 | +| [aws](#provider\_aws) | 6.63.0 | +| [random](#provider\_random) | 3.9.0 | +| [terraform](#provider\_terraform) | n/a | ## Modules @@ -155,6 +122,7 @@ multi_runner_config = { | [ami\_housekeeper](#module\_ami\_housekeeper) | ../ami-housekeeper | n/a | | [instance\_termination\_watcher](#module\_instance\_termination\_watcher) | ../termination-watcher | n/a | | [runner\_binaries](#module\_runner\_binaries) | ../runner-binaries-syncer | n/a | +| [runner\_configs](#module\_runner\_configs) | ../runner-config | n/a | | [runners](#module\_runners) | ../runners | n/a | | [ssm](#module\_ssm) | ../ssm | n/a | | [webhook](#module\_webhook) | ../webhook | n/a | @@ -168,6 +136,8 @@ multi_runner_config = { | [aws_sqs_queue_policy.build_queue_dlq_policy](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/sqs_queue_policy) | resource | | [aws_sqs_queue_policy.build_queue_policy](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/sqs_queue_policy) | resource | | [random_string.random](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/string) | resource | +| [terraform_data.validate_v1](https://registry.terraform.io/providers/hashicorp/terraform/latest/docs/resources/data) | resource | +| [terraform_data.validate_v2](https://registry.terraform.io/providers/hashicorp/terraform/latest/docs/resources/data) | resource | | [aws_iam_policy_document.deny_insecure_transport](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | ## Inputs @@ -192,9 +162,9 @@ multi_runner_config = { | [experimental\_features](#input\_experimental\_features) | Explicit acknowledgement for opt-in features whose schemas may change
while experimental. Set to ["multi-runner-v2"] when using the v2
provider-boundary configuration. This flag will become a deprecated no-op
for one release when the feature graduates. | `set(string)` | `[]` | no | | [ghes\_ssl\_verify](#input\_ghes\_ssl\_verify) | GitHub Enterprise SSL verification. Set to 'false' when custom certificate (chains) is used for GitHub Enterprise Server (insecure). | `bool` | `true` | no | | [ghes\_url](#input\_ghes\_url) | GitHub Enterprise Server URL. Example: https://github.internal.co - DO NOT SET IF USING PUBLIC GITHUB. .However if you are using GitHub Enterprise Cloud with data-residency (ghe.com), set the endpoint here. Example - https://companyname.ghe.com\| | `string` | `null` | no | -| [github\_app](#input\_github\_app) | GitHub app parameters, see your github app.
You can optionally create the SSM parameters yourself and provide the ARN and name here, through the `*_ssm` attributes.
If you chose to provide the configuration values directly here,
please ensure the key is the base64-encoded `.pem` file (the output of `base64 app.private-key.pem`, not the content of `private-key.pem`).
Note: the provided SSM parameters arn and name have a precedence over the actual value (i.e `key_base64_ssm` has a precedence over `key_base64` etc). |
object({
key_base64 = optional(string)
key_base64_ssm = optional(object({
arn = string
name = string
}))
id = optional(string)
id_ssm = optional(object({
arn = string
name = string
}))
webhook_secret = optional(string)
webhook_secret_ssm = optional(object({
arn = string
name = string
}))
})
| n/a | yes | +| [github\_app](#input\_github\_app) | GitHub app parameters for the stable v1 interface, see your github app.
Omit this value when using the experimental v2 interface and provide the
app through `global_config_github` instead.
You can optionally create the SSM parameters yourself and provide the ARN and name here, through the `*_ssm` attributes.
If you chose to provide the configuration values directly here,
please ensure the key is the base64-encoded `.pem` file (the output of `base64 app.private-key.pem`, not the content of `private-key.pem`).
Note: the provided SSM parameters arn and name have a precedence over the actual value (i.e `key_base64_ssm` has a precedence over `key_base64` etc). |
object({
key_base64 = optional(string)
key_base64_ssm = optional(object({
arn = string
name = string
}))
id = optional(string)
id_ssm = optional(object({
arn = string
name = string
}))
webhook_secret = optional(string)
webhook_secret_ssm = optional(object({
arn = string
name = string
}))
})
| `{}` | no | | [global\_config](#input\_global\_config) | Global defaults shared by all runner lanes.

global\_config = {
tags: "Tags applied to resources created for all runner lanes."
roles: {
path: "IAM path used for roles created for runner resources."
permissions\_boundary: "Optional IAM permissions boundary ARN applied to created roles."
}
runner: {
os: "Default operating system for runners."
architecture: "Default runner architecture."
disable\_default\_labels: "Whether to omit the default operating-system, architecture, and self-hosted labels."
extra\_labels: "Additional labels applied to all runners."
group\_name: "Default GitHub runner group."
name\_prefix: "Prefix for runner names."
run\_as\_root: "Whether the GitHub Actions runner executes as root."
run\_as: "User that runs the GitHub Actions agent when it is not running as root."
auto\_update\_disabled: "Whether automatic GitHub Actions runner updates are disabled."
tags: "Tags applied to runner resources."
hooks: {
job\_started: "Script executed when a job starts on a runner."
job\_completed: "Script executed when a job completes on a runner."
}
iam: {
role.arn: "Existing IAM role ARN to use for runners."
managed\_policy\_arns: "Managed policy ARNs attached to the runner IAM role."
additional\_trust\_policy\_json: "Additional trust policy JSON merged into the runner role trust policy."
path: "IAM path used for the runner role."
permissions\_boundary: "Optional IAM permissions boundary ARN for the runner role."
}
}
} |
object({
tags = optional(map(string), {})

roles = optional(object({
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})

runner = optional(object({
os = optional(string, null)
architecture = optional(string, null)
disable_default_labels = optional(bool, false)
extra_labels = optional(list(string), [])
group_name = optional(string, "Default")
name_prefix = optional(string, "")
run_as_root = optional(bool, false)
run_as = optional(string, "ec2-user")
auto_update_disabled = optional(bool, false)
tags = optional(map(string), {})
hooks = optional(object({
job_started = optional(string, "")
job_completed = optional(string, "")
}), {})
iam = optional(object({
role = optional(object({
arn = string
}), null)
managed_policy_arns = optional(map(string), {})
additional_trust_policy_json = optional(string, null)
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
}), {})
})
| `{}` | no | -| [global\_config\_compute\_provider](#input\_global\_config\_compute\_provider) | Global compute-provider configuration shared by all runner lanes.

global\_config\_compute\_provider = {
selections: "Compute-provider selections keyed by namespace."
selections.namespace: "Provider namespace used to resolve a compute implementation."
selections.type: "Compute-provider type selected for the namespace."
aws.ec2.vpc\_id: "Default VPC for EC2 runners."
aws.ec2.subnet\_ids: "Default subnets for EC2 runners."
aws.ec2.managed\_security\_group\_enabled: "Whether the module manages the default runner security group."
aws.ec2.egress\_rules: "Egress rules for the managed runner security group."
aws.ec2.egress\_rules.cidr\_blocks: "IPv4 CIDR blocks allowed by an egress rule."
aws.ec2.egress\_rules.ipv6\_cidr\_blocks: "IPv6 CIDR blocks allowed by an egress rule."
aws.ec2.egress\_rules.prefix\_list\_ids: "AWS prefix lists allowed by an egress rule."
aws.ec2.egress\_rules.from\_port: "Start of the egress port range."
aws.ec2.egress\_rules.protocol: "Protocol for the egress rule."
aws.ec2.egress\_rules.security\_groups: "Referenced security groups allowed by an egress rule."
aws.ec2.egress\_rules.self: "Whether the security group itself is allowed by an egress rule."
aws.ec2.egress\_rules.to\_port: "End of the egress port range."
aws.ec2.egress\_rules.description: "Description of the egress rule."
aws.ec2.additional\_security\_group\_ids: "Additional security groups attached to EC2 runners."
aws.ec2.cloudwatch\_agent.config: "CloudWatch Agent configuration for EC2 runners."
aws.ec2.instance\_profile\_path: "IAM path used for the EC2 instance profile."
aws.ec2.key\_name: "EC2 key pair name assigned to runner instances."
aws.ec2.associate\_public\_ipv4\_address: "Whether runner instances receive a public IPv4 address."
aws.ec2.tags: "Tags applied to EC2 runner resources."
aws.ec2.ami.housekeeper.enabled: "Whether AMI cleanup is enabled."
aws.ec2.ami.housekeeper.cleanup\_config.maxItems: "Maximum number of AMIs retained by cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.minimumDaysOld: "Minimum AMI age in days before cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.amiFilters: "AMI filters used to select AMIs for cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.amiFilters.Name: "AMI filter name."
aws.ec2.ami.housekeeper.cleanup\_config.amiFilters.Values: "Values matched by the AMI filter."
aws.ec2.ami.housekeeper.cleanup\_config.launchTemplateNames: "Launch template names associated with AMIs eligible for cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.ssmParameterNames: "SSM parameter names associated with AMIs eligible for cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.dryRun: "Whether AMI cleanup reports changes without deleting AMIs."
aws.ec2.ami.housekeeper.artifact.zip: "Local ZIP artifact used for the AMI housekeeper Lambda."
aws.ec2.ami.housekeeper.artifact.s3.key: "S3 object key for the AMI housekeeper Lambda artifact."
aws.ec2.ami.housekeeper.artifact.s3.object\_version: "Optional S3 object version for the AMI housekeeper artifact."
aws.ec2.ami.housekeeper.lambda.memory\_size: "Memory allocated to the AMI housekeeper Lambda."
aws.ec2.ami.housekeeper.lambda.timeout: "Timeout in seconds for the AMI housekeeper Lambda."
aws.ec2.ami.housekeeper.schedule.expression: "Schedule expression for AMI cleanup."
aws.ec2.instance\_termination\_watcher.enabled: "Whether the instance termination watcher is enabled."
aws.ec2.instance\_termination\_watcher.features.runner\_deregistration.enabled: "Whether terminated runners are deregistered."
aws.ec2.instance\_termination\_watcher.features.spot\_termination\_handler.enabled: "Whether spot termination events trigger runner handling."
aws.ec2.instance\_termination\_watcher.features.spot\_termination\_notification\_watcher.enabled: "Whether spot termination notification monitoring is enabled."
aws.ec2.instance\_termination\_watcher.environment\_variables: "Environment variables passed to the termination watcher."
aws.ec2.instance\_termination\_watcher.artifact.zip: "Local ZIP artifact used for the termination watcher Lambda."
aws.ec2.instance\_termination\_watcher.artifact.s3.key: "S3 object key for the termination watcher Lambda artifact."
aws.ec2.instance\_termination\_watcher.artifact.s3.object\_version: "Optional S3 object version for the termination watcher artifact."
aws.ec2.instance\_termination\_watcher.lambda.memory\_size: "Memory allocated to the termination watcher Lambda."
aws.ec2.instance\_termination\_watcher.lambda.timeout: "Timeout in seconds for the termination watcher Lambda."
aws.ec2.runner\_binaries.enabled: "Whether runner binary synchronization is enabled."
aws.ec2.runner\_binaries.s3.encryption.enabled: "Whether runner-binary S3 encryption is enabled."
aws.ec2.runner\_binaries.s3.encryption.bucket\_key\_enabled: "Whether an S3 bucket key is used for KMS encryption."
aws.ec2.runner\_binaries.s3.encryption.sse\_algorithm: "S3 server-side encryption algorithm."
aws.ec2.runner\_binaries.s3.encryption.kms\_master\_key\_id: "KMS key ID used for runner-binary S3 encryption."
aws.ec2.runner\_binaries.s3.tags: "Tags applied to the runner-binary S3 bucket."
aws.ec2.runner\_binaries.s3.versioning: "S3 versioning state for the runner-binary bucket."
aws.ec2.runner\_binaries.s3.logging.bucket: "S3 bucket receiving runner-binary access logs."
aws.ec2.runner\_binaries.s3.logging.prefix: "Prefix for runner-binary S3 access logs."
aws.ec2.runner\_binaries.syncer.artifact.zip: "Local ZIP artifact used for the runner-binary syncer Lambda."
aws.ec2.runner\_binaries.syncer.artifact.s3.key: "S3 object key for the runner-binary syncer artifact."
aws.ec2.runner\_binaries.syncer.artifact.s3.object\_version: "Optional S3 object version for the runner-binary syncer artifact."
aws.ec2.runner\_binaries.syncer.lambda.memory\_size: "Memory allocated to the runner-binary syncer Lambda."
aws.ec2.runner\_binaries.syncer.lambda.timeout: "Timeout in seconds for the runner-binary syncer Lambda."
aws.ec2.runner\_binaries.syncer.schedule.expression: "Schedule expression for runner-binary synchronization."
aws.ec2.runner\_binaries.syncer.schedule.state: "EventBridge rule state for runner-binary synchronization."
} |
object({
selections = optional(map(object({
namespace = string
type = string
})), null)
aws = optional(object({
ec2 = optional(object({
vpc_id = optional(string, null)
subnet_ids = optional(list(string), null)
managed_security_group_enabled = optional(bool, true)
egress_rules = optional(list(object({
cidr_blocks = list(string)
ipv6_cidr_blocks = list(string)
prefix_list_ids = list(string)
from_port = number
protocol = string
security_groups = list(string)
self = bool
to_port = number
description = string
})), [{
cidr_blocks = ["0.0.0.0/0"]
ipv6_cidr_blocks = ["::/0"]
prefix_list_ids = null
from_port = 0
protocol = "-1"
security_groups = null
self = null
to_port = 0
description = null
}])
additional_security_group_ids = optional(list(string), [])
cloudwatch_agent = optional(object({
config = optional(string, null)
}), {})
instance_profile_path = optional(string, null)
key_name = optional(string, null)
associate_public_ipv4_address = optional(bool, false)
tags = optional(map(string), {})
ami = optional(object({
housekeeper = optional(object({
enabled = optional(bool, false)
cleanup_config = optional(object({
maxItems = optional(number)
minimumDaysOld = optional(number)
amiFilters = optional(list(object({
Name = string
Values = list(string)
})))
launchTemplateNames = optional(list(string))
ssmParameterNames = optional(list(string))
dryRun = optional(bool)
}), {})
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
lambda = optional(object({
memory_size = optional(number, 256)
timeout = optional(number, 300)
}), {})
schedule = optional(object({
expression = optional(string, "cron(11 7 * * ? *)")
}), {})
}), {})
}), {})
instance_termination_watcher = optional(object({
enabled = optional(bool, false)
features = optional(object({
runner_deregistration = optional(object({
enabled = optional(bool, true)
}), {})
spot_termination_handler = optional(object({
enabled = optional(bool, true)
}), {})
spot_termination_notification_watcher = optional(object({
enabled = optional(bool, true)
}), {})
}), {})
environment_variables = optional(map(string), {})
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
lambda = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
}), {})
}), {})
runner_binaries = optional(object({
enabled = optional(bool, true)
s3 = optional(object({
encryption = optional(object({
enabled = optional(bool, true)
bucket_key_enabled = optional(bool, null)
sse_algorithm = optional(string, "AES256")
kms_master_key_id = optional(string, null)
}), {})
tags = optional(map(string), {})
versioning = optional(string, "Disabled")
logging = optional(object({
bucket = optional(string, null)
prefix = optional(string, null)
}), {})
}), {})
syncer = optional(object({
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
lambda = optional(object({
memory_size = optional(number, 256)
timeout = optional(number, 300)
}), {})
schedule = optional(object({
expression = optional(string, "cron(27 * * * ? *)")
state = optional(string, "ENABLED")
}), {})
}), {})
}), {})
}), {})
}), {})
})
| `{}` | no | +| [global\_config\_compute\_provider](#input\_global\_config\_compute\_provider) | Global compute-provider configuration shared by all runner lanes.

global\_config\_compute\_provider = {
selections: "Compute-provider selections keyed by namespace."
selections.namespace: "Provider namespace used to resolve a compute implementation."
selections.type: "Compute-provider type selected for the namespace."
aws.ec2.vpc\_id: "Default VPC for EC2 runners."
aws.ec2.subnet\_ids: "Default subnets for EC2 runners."
aws.ec2.managed\_security\_group\_enabled: "Whether the module manages the default runner security group."
aws.ec2.egress\_rules: "Egress rules for the managed runner security group."
aws.ec2.egress\_rules.cidr\_blocks: "IPv4 CIDR blocks allowed by an egress rule."
aws.ec2.egress\_rules.ipv6\_cidr\_blocks: "IPv6 CIDR blocks allowed by an egress rule."
aws.ec2.egress\_rules.prefix\_list\_ids: "AWS prefix lists allowed by an egress rule."
aws.ec2.egress\_rules.from\_port: "Start of the egress port range."
aws.ec2.egress\_rules.protocol: "Protocol for the egress rule."
aws.ec2.egress\_rules.security\_groups: "Referenced security groups allowed by an egress rule."
aws.ec2.egress\_rules.self: "Whether the security group itself is allowed by an egress rule."
aws.ec2.egress\_rules.to\_port: "End of the egress port range."
aws.ec2.egress\_rules.description: "Description of the egress rule."
aws.ec2.additional\_security\_group\_ids: "Additional security groups attached to EC2 runners."
aws.ec2.cloudwatch\_agent.config: "CloudWatch Agent configuration for EC2 runners."
aws.ec2.instance\_profile\_path: "IAM path used for the EC2 instance profile."
aws.ec2.key\_name: "EC2 key pair name assigned to runner instances."
aws.ec2.associate\_public\_ipv4\_address: "Whether runner instances receive a public IPv4 address."
aws.ec2.tags: "Tags applied to EC2 runner resources."
aws.ec2.ami.housekeeper.enabled: "Whether AMI cleanup is enabled."
aws.ec2.ami.housekeeper.cleanup\_config.maxItems: "Maximum number of AMIs retained by cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.minimumDaysOld: "Minimum AMI age in days before cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.amiFilters: "AMI filters used to select AMIs for cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.amiFilters.Name: "AMI filter name."
aws.ec2.ami.housekeeper.cleanup\_config.amiFilters.Values: "Values matched by the AMI filter."
aws.ec2.ami.housekeeper.cleanup\_config.launchTemplateNames: "Launch template names associated with AMIs eligible for cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.ssmParameterNames: "SSM parameter names associated with AMIs eligible for cleanup."
aws.ec2.ami.housekeeper.cleanup\_config.dryRun: "Whether AMI cleanup reports changes without deleting AMIs."
aws.ec2.ami.housekeeper.artifact.zip: "Local ZIP artifact used for the AMI housekeeper Lambda."
aws.ec2.ami.housekeeper.artifact.s3.key: "S3 object key for the AMI housekeeper Lambda artifact."
aws.ec2.ami.housekeeper.artifact.s3.object\_version: "Optional S3 object version for the AMI housekeeper artifact."
aws.ec2.ami.housekeeper.lambda.memory\_size: "Memory allocated to the AMI housekeeper Lambda."
aws.ec2.ami.housekeeper.lambda.timeout: "Timeout in seconds for the AMI housekeeper Lambda."
aws.ec2.ami.housekeeper.schedule.expression: "Schedule expression for AMI cleanup."
aws.ec2.instance\_termination\_watcher.enabled: "Whether the instance termination watcher is enabled."
aws.ec2.instance\_termination\_watcher.features.runner\_deregistration.enabled: "Whether terminated runners are deregistered."
aws.ec2.instance\_termination\_watcher.features.spot\_termination\_handler.enabled: "Whether spot termination events trigger runner handling."
aws.ec2.instance\_termination\_watcher.features.spot\_termination\_notification\_watcher.enabled: "Whether spot termination notification monitoring is enabled."
aws.ec2.instance\_termination\_watcher.environment\_variables: "Environment variables passed to the termination watcher."
aws.ec2.instance\_termination\_watcher.artifact.zip: "Local ZIP artifact used for the termination watcher Lambda."
aws.ec2.instance\_termination\_watcher.artifact.s3.key: "S3 object key for the termination watcher Lambda artifact."
aws.ec2.instance\_termination\_watcher.artifact.s3.object\_version: "Optional S3 object version for the termination watcher artifact."
aws.ec2.instance\_termination\_watcher.lambda.memory\_size: "Memory allocated to the termination watcher Lambda."
aws.ec2.instance\_termination\_watcher.lambda.timeout: "Timeout in seconds for the termination watcher Lambda."
aws.ec2.runner\_binaries.enabled: "Whether runner binary synchronization is enabled."
aws.ec2.runner\_binaries.s3.encryption.enabled: "Whether runner-binary S3 encryption is enabled."
aws.ec2.runner\_binaries.s3.encryption.bucket\_key\_enabled: "Whether an S3 bucket key is used for KMS encryption."
aws.ec2.runner\_binaries.s3.encryption.sse\_algorithm: "S3 server-side encryption algorithm."
aws.ec2.runner\_binaries.s3.encryption.kms\_master\_key\_id: "KMS key ID used for runner-binary S3 encryption."
aws.ec2.runner\_binaries.s3.tags: "Tags applied to the runner-binary S3 bucket."
aws.ec2.runner\_binaries.s3.versioning: "S3 versioning state for the runner-binary bucket."
aws.ec2.runner\_binaries.s3.logging.bucket: "S3 bucket receiving runner-binary access logs."
aws.ec2.runner\_binaries.s3.logging.prefix: "Prefix for runner-binary S3 access logs."
aws.ec2.runner\_binaries.syncer.artifact.zip: "Local ZIP artifact used for the runner-binary syncer Lambda."
aws.ec2.runner\_binaries.syncer.artifact.s3.key: "S3 object key for the runner-binary syncer artifact."
aws.ec2.runner\_binaries.syncer.artifact.s3.object\_version: "Optional S3 object version for the runner-binary syncer artifact."
aws.ec2.runner\_binaries.syncer.lambda.memory\_size: "Memory allocated to the runner-binary syncer Lambda."
aws.ec2.runner\_binaries.syncer.lambda.timeout: "Timeout in seconds for the runner-binary syncer Lambda."
aws.ec2.runner\_binaries.syncer.schedule.expression: "Schedule expression for runner-binary synchronization."
aws.ec2.runner\_binaries.syncer.schedule.state: "EventBridge rule state for runner-binary synchronization."
} |
object({
selections = optional(map(object({
namespace = string
type = string
})), null)
aws = optional(object({
ec2 = optional(object({
vpc_id = optional(string, null)
subnet_ids = optional(list(string), null)
managed_security_group_enabled = optional(bool, true)
egress_rules = optional(list(object({
cidr_blocks = list(string)
ipv6_cidr_blocks = list(string)
prefix_list_ids = list(string)
from_port = number
protocol = string
security_groups = list(string)
self = bool
to_port = number
description = string
})), [{
cidr_blocks = ["0.0.0.0/0"]
ipv6_cidr_blocks = ["::/0"]
prefix_list_ids = null
from_port = 0
protocol = "-1"
security_groups = null
self = null
to_port = 0
description = null
}])
additional_security_group_ids = optional(list(string), [])
cloudwatch_agent = optional(object({
config = optional(string, null)
}), {})
instance_profile_path = optional(string, null)
key_name = optional(string, null)
associate_public_ipv4_address = optional(bool, false)
tags = optional(map(string), {})
ami = optional(object({
housekeeper = optional(object({
enabled = optional(bool, false)
cleanup_config = optional(object({
maxItems = optional(number)
minimumDaysOld = optional(number)
amiFilters = optional(list(object({
Name = string
Values = list(string)
})))
launchTemplateNames = optional(list(string))
ssmParameterNames = optional(list(string))
dryRun = optional(bool)
}), {})
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
lambda = optional(object({
memory_size = optional(number, 256)
timeout = optional(number, 300)
}), {})
schedule = optional(object({
expression = optional(string, "cron(11 7 * * ? *)")
}), {})
}), {})
}), {})
instance_termination_watcher = optional(object({
enabled = optional(bool, false)
features = optional(object({
runner_deregistration = optional(object({
enabled = optional(bool, true)
}), {})
spot_termination_handler = optional(object({
enabled = optional(bool, true)
}), {})
spot_termination_notification_watcher = optional(object({
enabled = optional(bool, true)
}), {})
}), {})
environment_variables = optional(map(string), {})
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
lambda = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
}), {})
}), {})
runner_binaries = optional(object({
enabled = optional(bool, true)
s3 = optional(object({
encryption = optional(object({
enabled = optional(bool, true)
bucket_key_enabled = optional(bool, null)
sse_algorithm = optional(string, "AES256")
kms_master_key_id = optional(string, null)
}), {})
tags = optional(map(string), {})
versioning = optional(string, "Disabled")
logging = optional(object({
bucket = optional(string, null)
prefix = optional(string, null)
}), {})
}), {})
syncer = optional(object({
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
lambda = optional(object({
memory_size = optional(number, 256)
timeout = optional(number, 300)
}), {})
schedule = optional(object({
expression = optional(string, "cron(27 * * * ? *)")
state = optional(string, "ENABLED")
}), {})
}), {})
}), {})
}), {})
microvm = optional(object({
image_arn = optional(string, null)
image_version = optional(string, null)
ingress_network_connectors = optional(list(string), [])
egress_network_connectors = optional(list(string), [])
cloudwatch_agent = optional(object({
enabled = optional(bool, true)
config = optional(string, null)
}), {})
log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
environment_variables = optional(map(string), {})
iam = optional(object({
resource_arns = optional(object({
images = optional(list(string), null)
}), {})
additional_policy_json = optional(object({
scale_up = optional(string, null)
}), {})
managed_policies = optional(object({
scale_up = optional(object({
arn = string
}), null)
pool = optional(object({
arn = string
}), null)
}), {})
}), {})
}), {})
}), {})
})
| `{}` | no | | [global\_config\_github](#input\_global\_config\_github) | Global GitHub configuration shared by all runner lanes.

global\_config\_github = {
app: {
key\_base64: "Base64-encoded GitHub App private key."
key\_base64\_ssm: "SSM parameter containing the Base64-encoded GitHub App private key."
key\_base64\_ssm.arn: "ARN of the SSM parameter containing the GitHub App private key."
key\_base64\_ssm.name: "Name of the SSM parameter containing the GitHub App private key."
id: "GitHub App ID."
id\_ssm: "SSM parameter containing the GitHub App ID."
id\_ssm.arn: "ARN of the SSM parameter containing the GitHub App ID."
id\_ssm.name: "Name of the SSM parameter containing the GitHub App ID."
webhook\_secret: "GitHub App webhook secret."
webhook\_secret\_ssm: "SSM parameter containing the GitHub App webhook secret."
webhook\_secret\_ssm.arn: "ARN of the SSM parameter containing the GitHub App webhook secret."
webhook\_secret\_ssm.name: "Name of the SSM parameter containing the GitHub App webhook secret."
}
additional\_apps: "Additional GitHub Apps used to distribute GitHub API requests."
additional\_apps.key\_base64: "Base64-encoded private key for an additional GitHub App."
additional\_apps.key\_base64\_ssm: "SSM parameter containing an additional App private key."
additional\_apps.key\_base64\_ssm.arn: "ARN of the SSM parameter containing an additional App private key."
additional\_apps.key\_base64\_ssm.name: "Name of the SSM parameter containing an additional App private key."
additional\_apps.id: "ID of an additional GitHub App."
additional\_apps.id\_ssm: "SSM parameter containing an additional GitHub App ID."
additional\_apps.id\_ssm.arn: "ARN of the SSM parameter containing an additional GitHub App ID."
additional\_apps.id\_ssm.name: "Name of the SSM parameter containing an additional GitHub App ID."
additional\_apps.installation\_id: "Optional installation ID for an additional GitHub App."
additional\_apps.installation\_id\_ssm: "SSM parameter containing an additional App installation ID."
additional\_apps.installation\_id\_ssm.arn: "ARN of the SSM parameter containing an additional App installation ID."
additional\_apps.installation\_id\_ssm.name: "Name of the SSM parameter containing an additional App installation ID."
enterprise\_server.url: "GitHub Enterprise Server URL."
enterprise\_server.ssl\_verify: "Whether to verify the GitHub Enterprise Server TLS certificate."
user\_agent: "User-Agent value sent with GitHub API requests."
} |
object({
app = optional(object({
key_base64 = optional(string)
key_base64_ssm = optional(object({
arn = string
name = string
}))
id = optional(string)
id_ssm = optional(object({
arn = string
name = string
}))
webhook_secret = optional(string)
webhook_secret_ssm = optional(object({
arn = string
name = string
}))
}), null)
additional_apps = optional(list(object({
key_base64 = optional(string)
key_base64_ssm = optional(object({ arn = string, name = string }))
id = optional(string)
id_ssm = optional(object({ arn = string, name = string }))
installation_id = optional(string)
installation_id_ssm = optional(object({ arn = string, name = string }))
})), [])
enterprise_server = optional(object({
url = optional(string, null)
ssl_verify = optional(bool, true)
}), {})
user_agent = optional(string, "github-aws-runners")
})
| `{}` | no | | [global\_config\_lambda](#input\_global\_config\_lambda) | Global Lambda configuration shared by all runner lanes.

global\_config\_lambda = {
artifact.s3.bucket: "S3 bucket containing Lambda deployment artifacts."
runtime: "Default Lambda runtime."
architecture: "Default Lambda instruction-set architecture."
principals: "Additional AWS principals allowed to invoke the Lambda functions."
principals.type: "Principal type, such as AWS account, service, or organization."
principals.identifiers: "Identifiers allowed for the principal type."
subnet\_ids: "Subnets used by Lambda functions."
security\_group\_ids: "Security groups attached to Lambda functions."
tags: "Tags applied to Lambda functions and related resources."
role.path: "IAM path used for Lambda execution roles."
role.permissions\_boundary: "Optional IAM permissions boundary ARN for Lambda execution roles."
} |
object({
artifact = optional(object({
s3 = optional(object({
bucket = optional(string, null)
}), {})
}), {})
runtime = optional(string, "nodejs24.x")
architecture = optional(string, "arm64")
principals = optional(list(object({
type = string
identifiers = list(string)
})), [])
subnet_ids = optional(list(string), [])
security_group_ids = optional(list(string), [])
tags = optional(map(string), {})
role = optional(object({
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
})
| `{}` | no | | [global\_config\_observability](#input\_global\_config\_observability) | Global observability configuration shared by all runner lanes.

global\_config\_observability = {
logs.level: "Log level for module resources."
logs.retention\_in\_days: "CloudWatch log retention period in days."
logs.kms\_key\_id: "KMS key ID used to encrypt CloudWatch log groups."
logs.class: "CloudWatch log group class."
logs.tags: "Tags applied to CloudWatch log groups."
tracing.mode: "Tracing mode used by instrumented resources."
tracing.capture\_http\_requests: "Whether HTTP requests are captured by tracing."
tracing.capture\_error: "Whether errors are captured by tracing."
metrics.enabled: "Whether module metrics are enabled."
metrics.namespace: "CloudWatch namespace used for module metrics."
metrics.metric.github\_app\_rate\_limit.enabled: "Whether GitHub App rate-limit metrics are emitted."
metrics.metric.job\_retry.enabled: "Whether job-retry metrics are emitted."
metrics.metric.spot\_termination\_warning.enabled: "Whether spot-termination warning metrics are emitted."
} |
object({
logs = optional(object({
level = optional(string, "info")
retention_in_days = optional(number, 180)
kms_key_id = optional(string, null)
class = optional(string, "STANDARD")
tags = optional(map(string), {})
}), {})
tracing = optional(object({
mode = optional(string, null)
capture_http_requests = optional(bool, false)
capture_error = optional(bool, false)
}), {})
metrics = optional(object({
enabled = optional(bool, false)
namespace = optional(string, "GitHub Runners")
metric = optional(object({
github_app_rate_limit = optional(object({
enabled = optional(bool, true)
}), {})
job_retry = optional(object({
enabled = optional(bool, true)
}), {})
spot_termination_warning = optional(object({
enabled = optional(bool, true)
}), {})
}), {})
}), {})
})
| `{}` | no | @@ -220,7 +190,7 @@ multi_runner_config = { | [logging\_retention\_in\_days](#input\_logging\_retention\_in\_days) | Specifies the number of days you want to retain log events for the lambda log group. Possible values are: 0, 1, 3, 5, 7, 14, 30, 60, 90, 120, 150, 180, 365, 400, 545, 731, 1827, and 3653. | `number` | `180` | no | | [matcher\_config\_parameter\_store\_tier](#input\_matcher\_config\_parameter\_store\_tier) | The tier of the parameter store for the matcher configuration. Valid values are `Standard`, and `Advanced`. | `string` | `"Standard"` | no | | [metrics](#input\_metrics) | Configuration for metrics created by the module, by default metrics are disabled to avoid additional costs. When metrics are enable all metrics are created unless explicit configured otherwise. |
object({
enable = optional(bool, false)
namespace = optional(string, "GitHub Runners")
metric = optional(object({
enable_github_app_rate_limit = optional(bool, true)
enable_job_retry = optional(bool, true)
enable_spot_termination_warning = optional(bool, true)
}), {})
})
| `{}` | no | -| [multi\_runner\_config](#input\_multi\_runner\_config) | Accepts either the stable v1 runner configuration shape or the provider-boundary v2 shape. Entries with `runner_config` use the v1 shape; entries without `runner_config` use the v2 shape. A v2 entry does not need matcher configuration. A v2 entry must be acknowledged with `experimental_features = ["multi-runner-v2"]`; the v2 shape is experimental and may change before graduation.

multi\_runner\_config = {
runner\_config: {
runner\_os: "The EC2 Operating System type to use for action runner instances (linux, osx, windows)."
runner\_architecture: "The platform architecture of the runner instance\_type."
runner\_metadata\_options: "(Optional) Metadata options for the ec2 runner instances."
ami: "(Optional) AMI configuration for the action runner instances. This object allows you to specify all AMI-related settings in one place."
create\_service\_linked\_role\_spot: (Optional) create the serviced linked role for spot instances that is required by the scale-up lambda.
credit\_specification: "(Optional) The credit specification of the runner instance\_type. Can be unset, `standard` or `unlimited`.
delay\_webhook\_event: "The number of seconds the event accepted by the webhook is invisible on the queue before the scale up lambda will receive the event."
disable\_runner\_autoupdate: "Disable the auto update of the github runner agent. Be aware there is a grace period of 30 days, see also the [GitHub article](https://github.blog/changelog/2022-02-01-github-actions-self-hosted-runners-can-now-disable-automatic-updates/)"
ebs\_optimized: "The EC2 EBS optimized configuration."
enable\_ephemeral\_runners: "Enable ephemeral runners, runners will only be used once."
enable\_job\_queued\_check: Enables JIT configuration for creating runners instead of registration token based registraton. JIT configuration will only be applied for ephemeral runners. By default JIT configuration is enabled for ephemeral runners an can be disabled via this override. When running on GHES without support for JIT configuration this variable should be set to true for ephemeral runners."
enable\_on\_demand\_failover\_for\_errors: "Enable on-demand failover. For example to fall back to on demand when no spot capacity is available the variable can be set to `InsufficientInstanceCapacity`. When not defined the default behavior is to retry later."
scale\_errors: "List of AWS error codes that should trigger retry during scale up. This list replaces the module default scale-up retry errors"
enable\_organization\_runners: "Register runners to organization, instead of repo level"
enable\_runner\_binaries\_syncer: "Option to disable the lambda to sync GitHub runner distribution, useful when using a pre-build AMI."
enable\_ssm\_on\_runners: "Enable to allow access the runner instances for debugging purposes via SSM. Note that this adds additional permissions to the runner instances."
enable\_userdata: "Should the userdata script be enabled for the runner. Set this to false if you are using your own prebuilt AMI."
instance\_allocation\_strategy: "The allocation strategy for creating instances. For spot, AWS recommends `price-capacity-optimized`; for on-demand, use `lowest-price` or `prioritized`. The AWS default is `lowest-price`."
instance\_type\_priorities: "A map of instance type to priority for the `prioritized` and `capacity-optimized-prioritized` allocation strategies. Lower numbers mean higher priority. If not provided, priorities are assigned based on the order of `instance_types`."
instance\_max\_spot\_price: "Max price price for spot instances per hour. This variable will be passed to the create fleet as max spot price for the fleet."
instance\_target\_capacity\_type: "Default lifecycle used for runner instances, can be either `spot` or `on-demand`."
instance\_types: "List of instance types for the action runner. Defaults are based on runner\_os (al2023 for linux, macOS Sequoia for osx, Windows Server Core for win)."
job\_queue\_retention\_in\_seconds: "The number of seconds the job is held in the queue before it is purged"
minimum\_running\_time\_in\_minutes: "The time an ec2 action runner should be running at minimum before terminated if not busy."
pool\_runner\_owner: "The pool will deploy runners to the GitHub org ID, set this value to the org to which you want the runners deployed. Repo level is not supported."
runner\_additional\_security\_group\_ids: "List of additional security groups IDs to apply to the runner. If added outside the multi\_runner\_config block, the additional security group(s) will be applied to all runner configs. If added inside the multi\_runner\_config, the additional security group(s) will be applied to the individual runner."
runner\_as\_root: "Run the action runner under the root user. Variable `runner_run_as` will be ignored."
runner\_boot\_time\_in\_minutes: "The minimum time for an EC2 runner to boot and register as a runner."
runner\_disable\_default\_labels: "Disable default labels for the runners (os, architecture and `self-hosted`). If enabled, the runner will only have the extra labels provided in `runner_extra_labels`. In case you on own start script is used, this configuration parameter needs to be parsed via SSM."
runner\_extra\_labels: "Extra (custom) labels for the runners (GitHub). Separate each label by a comma. Labels checks on the webhook can be enforced by setting `multi_runner_config.matcherConfig.exactMatch`. GitHub read-only labels should not be provided."
runner\_group\_name: "Name of the runner group."
runner\_name\_prefix: "Prefix for the GitHub runner name."
runner\_run\_as: "Run the GitHub actions agent as user."
runners\_maximum\_count: "The maximum number of runners that will be created. Setting the variable to `-1` disables the maximum check."
scale\_down\_schedule\_expression: "Scheduler expression to check every x for scale down."
scale\_up\_reserved\_concurrent\_executions: "Amount of reserved concurrent executions for the scale-up lambda function. A value of 0 disables lambda from being triggered and -1 removes any concurrency limitations."
lambda\_event\_source\_mapping\_batch\_size: "(Optional) Maximum number of records per Lambda invocation for this runner flavor. Overrides the module-level `lambda_event_source_mapping_batch_size` when set."
lambda\_event\_source\_mapping\_maximum\_batching\_window\_in\_seconds: "(Optional) Maximum seconds to gather records before invoking Lambda for this runner flavor. Overrides the module-level `lambda_event_source_mapping_maximum_batching_window_in_seconds` when set."
userdata\_template: "Alternative user-data template, replacing the default template. By providing your own user\_data you have to take care of installing all required software, including the action runner. Variables userdata\_pre/post\_install are ignored."
enable\_jit\_config: "Overwrite the default behavior for JIT configuration. By default JIT configuration is enabled for ephemeral runners and disabled for non-ephemeral runners. In case of GHES check first if the JIT config API is available. In case you are upgrading from 3.x to 4.x you can set `enable_jit_config` to `false` to avoid a breaking change when having your own AMI."
enable\_runner\_detailed\_monitoring: "Should detailed monitoring be enabled for the runner. Set this to true if you want to use detailed monitoring. See https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/using-cloudwatch-new.html for details."
enable\_cloudwatch\_agent: "Enabling the cloudwatch agent on the ec2 runner instances, the runner contains default config. Configuration can be overridden via `cloudwatch_config`."
cloudwatch\_config: "(optional) Replaces the module default cloudwatch log config. See https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch-Agent-Configuration-File-Details.html for details."
userdata\_pre\_install: "Script to be ran before the GitHub Actions runner is installed on the EC2 instances"
userdata\_post\_install: "Script to be ran after the GitHub Actions runner is installed on the EC2 instances"
runner\_hook\_job\_started: "Script to be ran in the runner environment at the beginning of every job"
runner\_hook\_job\_completed: "Script to be ran in the runner environment at the end of every job"
runner\_ec2\_tags: "Map of tags that will be added to the launch template instance tag specifications."
runner\_iam\_role\_managed\_policy\_arns: "Attach AWS or customer-managed IAM policies (by ARN) to the runner IAM role"
vpc\_id: "The VPC for security groups of the action runners. If not set uses the value of `var.vpc_id`."
subnet\_ids: "List of subnets in which the action runners will be launched, the subnets needs to be subnets in the `vpc_id`. If not set, uses the value of `var.subnet_ids`."
idle\_config: "List of time period that can be defined as cron expression to keep a minimum amount of runners active instead of scaling down to 0. By defining this list you can ensure that in time periods that match the cron expression within 5 seconds a runner is kept idle."
license\_specifications: "Optional EC2 License Manager license configuration ARNs for the runner launch template. Required for macOS dedicated-host runners when the host resource group uses a Mac dedicated host license configuration."
use\_dedicated\_host: "Experimental! Can be removed / changed without trigger a major release. Whether to use EC2 dedicated hosts for the runners. Needed for macos runners Note that using dedicated hosts can increase cost significantly."
runner\_log\_files: "(optional) Replaces the module default cloudwatch log config. See https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch-Agent-Configuration-File-Details.html for details."
block\_device\_mappings: "The EC2 instance block device configuration. Takes the following keys: `device_name`, `delete_on_termination`, `volume_type`, `volume_size`, `encrypted`, `iops`, `throughput`, `kms_key_id`, `snapshot_id`, `volume_initialization_rate`."
job\_retry: "Experimental! Can be removed / changed without trigger a major release. Configure job retries. The configuration enables job retries (for ephemeral runners). After creating the instances a message will be published to a job retry queue. The job retry check lambda is checking after a delay if the job is queued. If not the message will be published again on the scale-up (build queue). Using this feature can impact the rate limit of the GitHub app."
pool\_config: "The configuration for updating the pool. The `pool_size` to adjust to by the events triggered by the `schedule_expression`. For example you can configure a cron expression for week days to adjust the pool to 10 and another expression for the weekend to adjust the pool to 1. Use `schedule_expression_timezone` to override the schedule time zone (defaults to UTC)."
iam\_overrides: "Allows to (optionally) override the instance profile and runner role created by the module. Set `override_instance_profile` to true and provide the `instance_profile_name` to use an existing instance profile. Set `override_runner_role` to true and provide the `runner_role_arn` to use an existing role for the runner instances."
}
# V2 contract
tags: "Tags applied to resources created for this runner configuration."
runner: "Runner settings such as the operating system, architecture, labels, hooks, runner group, name prefix, and IAM role configuration."
lambda: "Lambda settings such as runtime, architecture, networking, tags, and execution-role options for this runner configuration."
# Webhook, queue, and scale-up/scale-down orchestration settings.
orchestration\_provider: {
webhook: {
matcherConfig: "Label matching and dynamic-label policy used to route workflow jobs to this runner configuration."
runner: "Runner lifecycle settings including boot time, ephemeral mode, JIT configuration, and maximum runner count."
queue: "Build queue delay, retention, visibility timeout, redrive, and tags."
}
}
ssm: "SSM parameter paths, tags, and housekeeper settings for runner configuration storage."
observability: "Logging, tracing, and metric settings for the resources in this runner configuration."
# Compute settings for the runner provider.
compute\_provider: {
aws: {
ec2: "AWS EC2 runner settings, including AMI selection, instance types, capacity strategy, VPC and subnet placement, storage, user data, and runner access."
}
}
matcherConfig: {
labelMatchers: "The list of list of labels supported by the runner configuration. `[[self-hosted, linux, x64, example]]`"
exactMatch: "DEPRECATED: Use `bidirectionalLabelMatch` instead. If set to true all labels in the workflow job must match the GitHub labels (os, architecture and `self-hosted`). When false if __any__ workflow label matches it will trigger the webhook. Note: this only checks that workflow labels are a subset of runner labels, not the reverse."
bidirectionalLabelMatch: "If set to true, the runner labels and workflow job labels must be an exact two-way match (same set, any order, no extras or missing labels). This is stricter than `exactMatch` which only checks that workflow labels are a subset of runner labels. When false, if __any__ workflow label matches it will trigger the webhook."
priority: "If set it defines the priority of the matcher, the matcher with the lowest priority will be evaluated first. Default is 999, allowed values 0-999."
enableDynamicLabels: "Experimental! When true the dispatcher allows `ghr-*` dynamic labels for jobs routed to this runner. Default false."
awsDynamicLabelsPolicy: "Optional AWS dynamic label policy evaluated by the dispatcher. Only effective when `enableDynamicLabels = true`. Jobs whose provider dynamic labels violate every matching runner's policy are rejected with a 202 (a warning is logged). Evaluation: keys in `blocked_keys` are always rejected; keys in `restricted_keys` are allowed only when their value passes the rule; unlisted keys are allowed. Schema: `{ blocked_keys = [], restricted_keys = { = { allowed = [globs], denied = [globs], max = number|string } } }`. Keys use the dynamic label suffix, e.g. `instance-type` for `ghr-ec2-instance-type`."
}
redrive\_build\_queue: "Set options to attach (optional) a dead letter queue to the build queue, the queue between the webhook and the scale up lambda. You have the following options. 1. Disable by setting `enabled` to false. 2. Enable by setting `enabled` to `true`, `maxReceiveCount` to a number of max retries."
} |
map(object({
# V1 contract
runner_config = optional(object({
runner_os = string
runner_architecture = string
runner_metadata_options = optional(map(any), {
instance_metadata_tags = "enabled"
http_endpoint = "enabled"
http_tokens = "required"
http_put_response_hop_limit = 1
})
ami = optional(object({
filter = optional(map(list(string)), { state = ["available"] })
owners = optional(list(string), ["amazon"])
id_ssm_parameter_arn = optional(string, null)
kms_key_arn = optional(string, null)
}), null)
create_service_linked_role_spot = optional(bool, false)
credit_specification = optional(string, null)
delay_webhook_event = optional(number, 30)
disable_runner_autoupdate = optional(bool, false)
ebs_optimized = optional(bool, false)
enable_ephemeral_runners = optional(bool, false)
enable_job_queued_check = optional(bool, null)
enable_on_demand_failover_for_errors = optional(list(string), [])
scale_errors = optional(list(string), [
"UnfulfillableCapacity",
"MaxSpotInstanceCountExceeded",
"TargetCapacityLimitExceededException",
"RequestLimitExceeded",
"ResourceLimitExceeded",
"MaxSpotInstanceCountExceeded",
"MaxSpotFleetRequestCountExceeded",
"InsufficientInstanceCapacity",
"InsufficientCapacityOnHost",
])
enable_organization_runners = optional(bool, false)
enable_runner_binaries_syncer = optional(bool, true)
enable_ssm_on_runners = optional(bool, false)
enable_userdata = optional(bool, true)
instance_allocation_strategy = optional(string, "lowest-price")
instance_type_priorities = optional(map(number), null)
instance_max_spot_price = optional(string, null)
instance_target_capacity_type = optional(string, "spot")
instance_types = list(string)
job_queue_retention_in_seconds = optional(number, 86400)
minimum_running_time_in_minutes = optional(number, null)
pool_runner_owner = optional(string, null)
runner_as_root = optional(bool, false)
runner_boot_time_in_minutes = optional(number, 5)
runner_disable_default_labels = optional(bool, false)
runner_extra_labels = optional(list(string), [])
runner_group_name = optional(string, "Default")
runner_name_prefix = optional(string, "")
runner_run_as = optional(string, "ec2-user")
runners_maximum_count = number
runner_additional_security_group_ids = optional(list(string), [])
scale_down_schedule_expression = optional(string, "cron(*/5 * * * ? *)")
scale_up_reserved_concurrent_executions = optional(number, 1)
lambda_event_source_mapping_batch_size = optional(number, null)
lambda_event_source_mapping_maximum_batching_window_in_seconds = optional(number, null)
userdata_template = optional(string, null)
userdata_content = optional(string, null)
enable_jit_config = optional(bool, null)
enable_runner_detailed_monitoring = optional(bool, false)
enable_cloudwatch_agent = optional(bool, true)
cloudwatch_config = optional(string, null)
userdata_pre_install = optional(string, "")
userdata_post_install = optional(string, "")
runner_hook_job_started = optional(string, "")
runner_hook_job_completed = optional(string, "")
runner_ec2_tags = optional(map(string), {})
runner_iam_role_managed_policy_arns = optional(list(string), [])
vpc_id = optional(string, null)
subnet_ids = optional(list(string), null)
idle_config = optional(list(object({
cron = string
timeZone = string
idleCount = number
evictionStrategy = optional(string, "oldest_first")
})), [])
cpu_options = optional(object({
core_count = optional(number)
threads_per_core = optional(number)
amd_sev_snp = optional(string)
nested_virtualization = optional(string)
}), null)
placement = optional(object({
affinity = optional(string)
availability_zone = optional(string)
group_id = optional(string)
group_name = optional(string)
host_id = optional(string)
host_resource_group_arn = optional(string)
spread_domain = optional(string)
tenancy = optional(string)
partition_number = optional(number)
}), null)
license_specifications = optional(list(object({
license_configuration_arn = string
})), [])
use_dedicated_host = optional(bool, false)
runner_log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
block_device_mappings = optional(list(object({
delete_on_termination = optional(bool, true)
device_name = optional(string, "/dev/xvda")
encrypted = optional(bool, true)
iops = optional(number)
kms_key_id = optional(string)
snapshot_id = optional(string)
throughput = optional(number)
volume_initialization_rate = optional(number)
volume_size = number
volume_type = optional(string, "gp3")
})), [{
volume_size = 30
}])
pool_config = optional(list(object({
schedule_expression = string
schedule_expression_timezone = optional(string)
size = number
})), [])
job_retry = optional(object({
enable = optional(bool, false)
delay_in_seconds = optional(number, 300)
delay_backoff = optional(number, 2)
lambda_memory_size = optional(number, 256)
lambda_timeout = optional(number, 30)
max_attempts = optional(number, 1)
}), {})
iam_overrides = optional(object({
override_instance_profile = optional(bool, null)
instance_profile_name = optional(string, null)
override_runner_role = optional(bool, null)
runner_role_arn = optional(string, null)
}), {
override_instance_profile = false
instance_profile_name = null
override_runner_role = false
runner_role_arn = null
})
}), null)
matcherConfig = optional(object({
labelMatchers = list(list(string))
exactMatch = optional(bool, false)
bidirectionalLabelMatch = optional(bool, false)
priority = optional(number, 999)
enableDynamicLabels = optional(bool, false)
awsDynamicLabelsPolicy = optional(any, null)
}), null)
redrive_build_queue = optional(object({
enabled = bool
maxReceiveCount = number
}), {
enabled = false
maxReceiveCount = null
})

# V2 Contract
tags = optional(map(string), {})

runner = optional(object({
os = optional(string, null)
architecture = optional(string, null)
disable_default_labels = optional(bool, null)
extra_labels = optional(list(string), null)
group_name = optional(string, null)
name_prefix = optional(string, null)
run_as_root = optional(bool, null)
run_as = optional(string, null)
auto_update_disabled = optional(bool, null)
tags = optional(map(string), {})
hooks = optional(object({
job_started = optional(string, null)
job_completed = optional(string, null)
}), {})
iam = optional(object({
role = optional(object({
arn = string
}), null)
managed_policy_arns = optional(map(string), null)
additional_trust_policy_json = optional(string, null)
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
}), {})

lambda = optional(object({
runtime = optional(string, null)
architecture = optional(string, null)
subnet_ids = optional(list(string), null)
security_group_ids = optional(list(string), null)
tags = optional(map(string), {})
role = optional(object({
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
}), {})

orchestration_provider = optional(object({
webhook = optional(object({
runner = optional(object({
boot_time_in_minutes = optional(number, null)
ephemeral = optional(bool, null)
jit_config_enabled = optional(bool, null)
maximum_count = optional(number, null)
}), {})
github = optional(object({
organization_runners = optional(bool, false)
}), {})
matcherConfig = optional(object({
labelMatchers = list(list(string))
exactMatch = optional(bool, false)
bidirectionalLabelMatch = optional(bool, false)
priority = optional(number, 999)
dynamic_labels_enabled = optional(bool, false)
awsDynamicLabelsPolicy = optional(object({
blocked_keys = optional(list(string), [])
restricted_keys = optional(map(object({
allowed = optional(list(string), [])
denied = optional(list(string), [])
max = optional(string, null)
})), {})
}), null)
}), null)
queue = optional(object({
delay_webhook_event = optional(number, null)
job_queue_retention_in_seconds = optional(number, null)
visibility_timeout_seconds = optional(number, null)
redrive_build_queue = optional(object({
enabled = optional(bool, null)
maxReceiveCount = optional(number, null)
}), null)
tags = optional(map(string), {})
}), {})
lambda = optional(object({
scale = optional(object({
up = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
reserved_concurrent_executions = optional(number, null)
job_queued_check_enabled = optional(bool, null)
event_source_mapping = optional(object({
batch_size = optional(number, null)
maximum_batching_window_in_seconds = optional(number, null)
}), {})
tags = optional(map(string), {})
}), {})
down = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
schedule_expression = optional(string, null)
minimum_running_time_in_minutes = optional(number, null)
idle_config = optional(list(object({
cron = string
timeZone = string
idleCount = number
evictionStrategy = optional(string, "oldest_first")
})), null)
tags = optional(map(string), {})
}), {})
}), {})
pool = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
reserved_concurrent_executions = optional(number, null)
config = optional(list(object({
schedule_expression = string
schedule_expression_timezone = optional(string)
size = number
})), null)
include_busy_runners = optional(bool, null)
runner_owner = optional(string, null)
tags = optional(map(string), {})
}), {})
}), {})
job_retry = optional(object({
enabled = optional(bool, false)
delay_in_seconds = optional(number, 300)
delay_backoff = optional(number, 2)
max_attempts = optional(number, 1)
tags = optional(map(string), {})
lambda = optional(object({
memory_size = optional(number, 256)
reserved_concurrent_executions = optional(number, 1)
timeout = optional(number, 30)
}), {})
}), {})
}), null)
}), {})

ssm = optional(object({
paths = optional(object({
root = optional(string, null)
tokens = optional(string, null)
config = optional(string, null)
}), {})
tags = optional(map(string), {})
parameters = optional(object({
tags = optional(map(string), {})
}), {})
housekeeper = optional(object({
schedule_expression = optional(string, null)
state = optional(string, null)
tags = optional(map(string), {})
lambda = optional(object({
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
memory_size = optional(number, null)
timeout = optional(number, null)
}), {})
config = optional(object({
tokenPath = optional(string, null)
minimumDaysOld = optional(number, null)
dryRun = optional(bool, null)
}), {})
}), {})
}), {})

observability = optional(object({
logs = optional(object({
level = optional(string, null)
retention_in_days = optional(number, null)
kms_key_id = optional(string, null)
class = optional(string, null)
tags = optional(map(string), {})
}), {})
tracing = optional(object({
mode = optional(string, null)
capture_http_requests = optional(bool, null)
capture_error = optional(bool, null)
}), {})
metrics = optional(object({
enabled = optional(bool, null)
namespace = optional(string, null)
metric = optional(object({
github_app_rate_limit = optional(object({
enabled = optional(bool, null)
}), {})
job_retry = optional(object({
enabled = optional(bool, null)
}), {})
spot_termination_warning = optional(object({
enabled = optional(bool, null)
}), {})
}), {})
}), {})
}), {})

compute_provider = optional(object({
aws = optional(object({
ec2 = optional(object({
metadata_options = optional(object({
instance_metadata_tags = optional(string, "enabled")
http_endpoint = optional(string, "enabled")
http_tokens = optional(string, "required")
http_put_response_hop_limit = optional(number, 1)
}), {})
ami = optional(object({
filter = optional(map(list(string)), { state = ["available"] })
owners = optional(list(string), ["amazon"])
id_ssm_parameter = optional(object({
arn = string
}), null)
kms_key = optional(object({
arn = string
}), null)
}), null)
block_device_mappings = optional(list(object({
delete_on_termination = optional(bool, true)
device_name = optional(string, "/dev/xvda")
encrypted = optional(bool, true)
iops = optional(number)
kms_key_id = optional(string)
snapshot_id = optional(string)
throughput = optional(number)
volume_initialization_rate = optional(number)
volume_size = number
volume_type = optional(string, "gp3")
})), [{ volume_size = 30 }])
create_service_linked_role_spot = optional(bool, false)
credit_specification = optional(string, null)
ebs_optimized = optional(bool, false)
cloudwatch_agent = optional(object({
enabled = optional(bool, true)
config = optional(string, null)
}), {})
binaries_syncer = optional(object({
enabled = optional(bool, null)
}), {})
detailed_monitoring_enabled = optional(bool, false)
ssm_enabled = optional(bool, false)
user_data = optional(object({
enabled = optional(bool, true)
template = optional(string, null)
content = optional(string, null)
pre_install = optional(string, "")
post_install = optional(string, "")
debug_logging_enabled = optional(bool, false)
}), {})
instance_allocation_strategy = optional(string, "lowest-price")
instance_max_spot_price = optional(string, null)
instance_target_capacity_type = optional(string, "spot")
instance_type_priorities = optional(map(number), null)
instance_types = optional(list(string), [])
additional_security_group_ids = optional(list(string), null)
managed_security_group_enabled = optional(bool, null)
egress_rules = optional(list(object({
cidr_blocks = list(string)
ipv6_cidr_blocks = list(string)
prefix_list_ids = list(string)
from_port = number
protocol = string
security_groups = list(string)
self = bool
to_port = number
description = string
})), null)
instance_profile_path = optional(string, null)
key_name = optional(string, null)
associate_public_ipv4_address = optional(bool, null)
instance_profile = optional(object({
name = string
}), null)
on_demand_failover_for_errors = optional(list(string), [])
scale_errors = optional(list(string), [
"UnfulfillableCapacity",
"MaxSpotInstanceCountExceeded",
"TargetCapacityLimitExceededException",
"RequestLimitExceeded",
"ResourceLimitExceeded",
"MaxSpotInstanceCountExceeded",
"MaxSpotFleetRequestCountExceeded",
"InsufficientInstanceCapacity",
"InsufficientCapacityOnHost",
])
subnet_ids = optional(list(string), null)
vpc_id = optional(string, null)
cpu_options = optional(object({
core_count = optional(number)
threads_per_core = optional(number)
amd_sev_snp = optional(string)
nested_virtualization = optional(string)
}), null)
placement = optional(object({
affinity = optional(string)
availability_zone = optional(string)
group_id = optional(string)
group_name = optional(string)
host_id = optional(string)
host_resource_group_arn = optional(string)
spread_domain = optional(string)
tenancy = optional(string)
partition_number = optional(number)
}), null)
license_specifications = optional(list(object({
license_configuration_arn = string
})), [])
use_dedicated_host = optional(bool, false)
log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
tags = optional(map(string), {})
}), null)
}), {})
}), {})
}))
| n/a | yes | +| [multi\_runner\_config](#input\_multi\_runner\_config) | Accepts either the stable v1 runner configuration shape or the provider-boundary v2 shape. Entries with `runner_config` use the v1 shape; entries without `runner_config` use the v2 shape. A v2 entry does not need matcher configuration. A v2 entry must be acknowledged with `experimental_features = ["multi-runner-v2"]`; the v2 shape is experimental and may change before graduation.

multi\_runner\_config = {
runner\_config: {
runner\_os: "The EC2 Operating System type to use for action runner instances (linux, osx, windows)."
runner\_architecture: "The platform architecture of the runner instance\_type."
runner\_metadata\_options: "(Optional) Metadata options for the ec2 runner instances."
ami: "(Optional) AMI configuration for the action runner instances. This object allows you to specify all AMI-related settings in one place."
create\_service\_linked\_role\_spot: (Optional) create the serviced linked role for spot instances that is required by the scale-up lambda.
credit\_specification: "(Optional) The credit specification of the runner instance\_type. Can be unset, `standard` or `unlimited`.
delay\_webhook\_event: "The number of seconds the event accepted by the webhook is invisible on the queue before the scale up lambda will receive the event."
disable\_runner\_autoupdate: "Disable the auto update of the github runner agent. Be aware there is a grace period of 30 days, see also the [GitHub article](https://github.blog/changelog/2022-02-01-github-actions-self-hosted-runners-can-now-disable-automatic-updates/)"
ebs\_optimized: "The EC2 EBS optimized configuration."
enable\_ephemeral\_runners: "Enable ephemeral runners, runners will only be used once."
enable\_job\_queued\_check: Enables JIT configuration for creating runners instead of registration token based registraton. JIT configuration will only be applied for ephemeral runners. By default JIT configuration is enabled for ephemeral runners an can be disabled via this override. When running on GHES without support for JIT configuration this variable should be set to true for ephemeral runners."
enable\_on\_demand\_failover\_for\_errors: "Enable on-demand failover. For example to fall back to on demand when no spot capacity is available the variable can be set to `InsufficientInstanceCapacity`. When not defined the default behavior is to retry later."
scale\_errors: "List of AWS error codes that should trigger retry during scale up. This list replaces the module default scale-up retry errors"
enable\_organization\_runners: "Register runners to organization, instead of repo level"
enable\_runner\_binaries\_syncer: "Option to disable the lambda to sync GitHub runner distribution, useful when using a pre-build AMI."
enable\_ssm\_on\_runners: "Enable to allow access the runner instances for debugging purposes via SSM. Note that this adds additional permissions to the runner instances."
enable\_userdata: "Should the userdata script be enabled for the runner. Set this to false if you are using your own prebuilt AMI."
instance\_allocation\_strategy: "The allocation strategy for creating instances. For spot, AWS recommends `price-capacity-optimized`; for on-demand, use `lowest-price` or `prioritized`. The AWS default is `lowest-price`."
instance\_type\_priorities: "A map of instance type to priority for the `prioritized` and `capacity-optimized-prioritized` allocation strategies. Lower numbers mean higher priority. If not provided, priorities are assigned based on the order of `instance_types`."
instance\_max\_spot\_price: "Max price price for spot instances per hour. This variable will be passed to the create fleet as max spot price for the fleet."
instance\_target\_capacity\_type: "Default lifecycle used for runner instances, can be either `spot` or `on-demand`."
instance\_types: "List of instance types for the action runner. Defaults are based on runner\_os (al2023 for linux, macOS Sequoia for osx, Windows Server Core for win)."
job\_queue\_retention\_in\_seconds: "The number of seconds the job is held in the queue before it is purged"
minimum\_running\_time\_in\_minutes: "The time an ec2 action runner should be running at minimum before terminated if not busy."
pool\_runner\_owner: "The pool will deploy runners to the GitHub org ID, set this value to the org to which you want the runners deployed. Repo level is not supported."
runner\_additional\_security\_group\_ids: "List of additional security groups IDs to apply to the runner. If added outside the multi\_runner\_config block, the additional security group(s) will be applied to all runner configs. If added inside the multi\_runner\_config, the additional security group(s) will be applied to the individual runner."
runner\_as\_root: "Run the action runner under the root user. Variable `runner_run_as` will be ignored."
runner\_boot\_time\_in\_minutes: "The minimum time for an EC2 runner to boot and register as a runner."
runner\_disable\_default\_labels: "Disable default labels for the runners (os, architecture and `self-hosted`). If enabled, the runner will only have the extra labels provided in `runner_extra_labels`. In case you on own start script is used, this configuration parameter needs to be parsed via SSM."
runner\_extra\_labels: "Extra (custom) labels for the runners (GitHub). Separate each label by a comma. Labels checks on the webhook can be enforced by setting `multi_runner_config.matcherConfig.exactMatch`. GitHub read-only labels should not be provided."
runner\_group\_name: "Name of the runner group."
runner\_name\_prefix: "Prefix for the GitHub runner name."
runner\_run\_as: "Run the GitHub actions agent as user."
runners\_maximum\_count: "The maximum number of runners that will be created. Setting the variable to `-1` disables the maximum check."
scale\_down\_schedule\_expression: "Scheduler expression to check every x for scale down."
scale\_up\_reserved\_concurrent\_executions: "Amount of reserved concurrent executions for the scale-up lambda function. A value of 0 disables lambda from being triggered and -1 removes any concurrency limitations."
lambda\_event\_source\_mapping\_batch\_size: "(Optional) Maximum number of records per Lambda invocation for this runner flavor. Overrides the module-level `lambda_event_source_mapping_batch_size` when set."
lambda\_event\_source\_mapping\_maximum\_batching\_window\_in\_seconds: "(Optional) Maximum seconds to gather records before invoking Lambda for this runner flavor. Overrides the module-level `lambda_event_source_mapping_maximum_batching_window_in_seconds` when set."
userdata\_template: "Alternative user-data template, replacing the default template. By providing your own user\_data you have to take care of installing all required software, including the action runner. Variables userdata\_pre/post\_install are ignored."
enable\_jit\_config: "Overwrite the default behavior for JIT configuration. By default JIT configuration is enabled for ephemeral runners and disabled for non-ephemeral runners. In case of GHES check first if the JIT config API is available. In case you are upgrading from 3.x to 4.x you can set `enable_jit_config` to `false` to avoid a breaking change when having your own AMI."
enable\_runner\_detailed\_monitoring: "Should detailed monitoring be enabled for the runner. Set this to true if you want to use detailed monitoring. See https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/using-cloudwatch-new.html for details."
enable\_cloudwatch\_agent: "Enabling the cloudwatch agent on the ec2 runner instances, the runner contains default config. Configuration can be overridden via `cloudwatch_config`."
cloudwatch\_config: "(optional) Replaces the module default cloudwatch log config. See https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch-Agent-Configuration-File-Details.html for details."
userdata\_pre\_install: "Script to be ran before the GitHub Actions runner is installed on the EC2 instances"
userdata\_post\_install: "Script to be ran after the GitHub Actions runner is installed on the EC2 instances"
runner\_hook\_job\_started: "Script to be ran in the runner environment at the beginning of every job"
runner\_hook\_job\_completed: "Script to be ran in the runner environment at the end of every job"
runner\_ec2\_tags: "Map of tags that will be added to the launch template instance tag specifications."
runner\_iam\_role\_managed\_policy\_arns: "Attach AWS or customer-managed IAM policies (by ARN) to the runner IAM role"
vpc\_id: "The VPC for security groups of the action runners. If not set uses the value of `var.vpc_id`."
subnet\_ids: "List of subnets in which the action runners will be launched, the subnets needs to be subnets in the `vpc_id`. If not set, uses the value of `var.subnet_ids`."
idle\_config: "List of time period that can be defined as cron expression to keep a minimum amount of runners active instead of scaling down to 0. By defining this list you can ensure that in time periods that match the cron expression within 5 seconds a runner is kept idle."
license\_specifications: "Optional EC2 License Manager license configuration ARNs for the runner launch template. Required for macOS dedicated-host runners when the host resource group uses a Mac dedicated host license configuration."
use\_dedicated\_host: "Experimental! Can be removed / changed without trigger a major release. Whether to use EC2 dedicated hosts for the runners. Needed for macos runners Note that using dedicated hosts can increase cost significantly."
runner\_log\_files: "(optional) Replaces the module default cloudwatch log config. See https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch-Agent-Configuration-File-Details.html for details."
block\_device\_mappings: "The EC2 instance block device configuration. Takes the following keys: `device_name`, `delete_on_termination`, `volume_type`, `volume_size`, `encrypted`, `iops`, `throughput`, `kms_key_id`, `snapshot_id`, `volume_initialization_rate`."
job\_retry: "Experimental! Can be removed / changed without trigger a major release. Configure job retries. The configuration enables job retries (for ephemeral runners). After creating the instances a message will be published to a job retry queue. The job retry check lambda is checking after a delay if the job is queued. If not the message will be published again on the scale-up (build queue). Using this feature can impact the rate limit of the GitHub app."
pool\_config: "The configuration for updating the pool. The `pool_size` to adjust to by the events triggered by the `schedule_expression`. For example you can configure a cron expression for week days to adjust the pool to 10 and another expression for the weekend to adjust the pool to 1. Use `schedule_expression_timezone` to override the schedule time zone (defaults to UTC)."
iam\_overrides: "Allows to (optionally) override the instance profile and runner role created by the module. Set `override_instance_profile` to true and provide the `instance_profile_name` to use an existing instance profile. Set `override_runner_role` to true and provide the `runner_role_arn` to use an existing role for the runner instances."
}
# V2 contract
tags: "Tags applied to resources created for this runner configuration."
runner: "Runner settings such as the operating system, architecture, labels, hooks, runner group, name prefix, and IAM role configuration."
lambda: "Lambda settings such as runtime, architecture, networking, tags, and execution-role options for this runner configuration."
# Webhook, queue, and scale-up/scale-down orchestration settings.
orchestration\_provider: {
webhook: {
matcherConfig: "Label matching and dynamic-label policy used to route workflow jobs to this runner configuration."
runner: "Runner lifecycle settings including boot time, ephemeral mode, JIT configuration, and maximum runner count."
queue: "Build queue delay, retention, visibility timeout, redrive, and tags."
}
}
ssm: "SSM parameter paths, tags, and housekeeper settings for runner configuration storage."
observability: "Logging, tracing, and metric settings for the resources in this runner configuration."
# Compute settings for the runner provider.
compute\_provider: {
aws: {
ec2: "AWS EC2 runner settings, including AMI selection, instance types, capacity strategy, VPC and subnet placement, storage, user data, and runner access."
}
}
matcherConfig: {
labelMatchers: "The list of list of labels supported by the runner configuration. `[[self-hosted, linux, x64, example]]`"
exactMatch: "DEPRECATED: Use `bidirectionalLabelMatch` instead. If set to true all labels in the workflow job must match the GitHub labels (os, architecture and `self-hosted`). When false if __any__ workflow label matches it will trigger the webhook. Note: this only checks that workflow labels are a subset of runner labels, not the reverse."
bidirectionalLabelMatch: "If set to true, the runner labels and workflow job labels must be an exact two-way match (same set, any order, no extras or missing labels). This is stricter than `exactMatch` which only checks that workflow labels are a subset of runner labels. When false, if __any__ workflow label matches it will trigger the webhook."
priority: "If set it defines the priority of the matcher, the matcher with the lowest priority will be evaluated first. Default is 999, allowed values 0-999."
enableDynamicLabels: "Experimental! When true the dispatcher allows `ghr-*` dynamic labels for jobs routed to this runner. Default false."
awsDynamicLabelsPolicy: "Optional AWS dynamic label policy evaluated by the dispatcher. Only effective when `enableDynamicLabels = true`. Jobs whose provider dynamic labels violate every matching runner's policy are rejected with a 202 (a warning is logged). Evaluation: keys in `blocked_keys` are always rejected; keys in `restricted_keys` are allowed only when their value passes the rule; unlisted keys are allowed. Schema: `{ blocked_keys = [], restricted_keys = { = { allowed = [globs], denied = [globs], max = number|string } } }`. Keys use the dynamic label suffix, e.g. `instance-type` for `ghr-ec2-instance-type`."
}
redrive\_build\_queue: "Set options to attach (optional) a dead letter queue to the build queue, the queue between the webhook and the scale up lambda. You have the following options. 1. Disable by setting `enabled` to false. 2. Enable by setting `enabled` to `true`, `maxReceiveCount` to a number of max retries."
} |
map(object({
# V1 contract
runner_config = optional(object({
runner_os = string
runner_architecture = string
runner_metadata_options = optional(map(any), {
instance_metadata_tags = "enabled"
http_endpoint = "enabled"
http_tokens = "required"
http_put_response_hop_limit = 1
})
ami = optional(object({
filter = optional(map(list(string)), { state = ["available"] })
owners = optional(list(string), ["amazon"])
id_ssm_parameter_arn = optional(string, null)
kms_key_arn = optional(string, null)
}), null)
create_service_linked_role_spot = optional(bool, false)
credit_specification = optional(string, null)
delay_webhook_event = optional(number, 30)
disable_runner_autoupdate = optional(bool, false)
ebs_optimized = optional(bool, false)
enable_ephemeral_runners = optional(bool, false)
enable_job_queued_check = optional(bool, null)
enable_on_demand_failover_for_errors = optional(list(string), [])
scale_errors = optional(list(string), [
"UnfulfillableCapacity",
"MaxSpotInstanceCountExceeded",
"TargetCapacityLimitExceededException",
"RequestLimitExceeded",
"ResourceLimitExceeded",
"MaxSpotInstanceCountExceeded",
"MaxSpotFleetRequestCountExceeded",
"InsufficientInstanceCapacity",
"InsufficientCapacityOnHost",
])
enable_organization_runners = optional(bool, false)
enable_runner_binaries_syncer = optional(bool, true)
enable_ssm_on_runners = optional(bool, false)
enable_userdata = optional(bool, true)
instance_allocation_strategy = optional(string, "lowest-price")
instance_type_priorities = optional(map(number), null)
instance_max_spot_price = optional(string, null)
instance_target_capacity_type = optional(string, "spot")
instance_types = list(string)
job_queue_retention_in_seconds = optional(number, 86400)
minimum_running_time_in_minutes = optional(number, null)
pool_runner_owner = optional(string, null)
runner_as_root = optional(bool, false)
runner_boot_time_in_minutes = optional(number, 5)
runner_disable_default_labels = optional(bool, false)
runner_extra_labels = optional(list(string), [])
runner_group_name = optional(string, "Default")
runner_name_prefix = optional(string, "")
runner_run_as = optional(string, "ec2-user")
runners_maximum_count = number
runner_additional_security_group_ids = optional(list(string), [])
scale_down_schedule_expression = optional(string, "cron(*/5 * * * ? *)")
scale_up_reserved_concurrent_executions = optional(number, 1)
lambda_event_source_mapping_batch_size = optional(number, null)
lambda_event_source_mapping_maximum_batching_window_in_seconds = optional(number, null)
userdata_template = optional(string, null)
userdata_content = optional(string, null)
enable_jit_config = optional(bool, null)
enable_runner_detailed_monitoring = optional(bool, false)
enable_cloudwatch_agent = optional(bool, true)
cloudwatch_config = optional(string, null)
userdata_pre_install = optional(string, "")
userdata_post_install = optional(string, "")
runner_hook_job_started = optional(string, "")
runner_hook_job_completed = optional(string, "")
runner_ec2_tags = optional(map(string), {})
runner_iam_role_managed_policy_arns = optional(list(string), [])
vpc_id = optional(string, null)
subnet_ids = optional(list(string), null)
idle_config = optional(list(object({
cron = string
timeZone = string
idleCount = number
evictionStrategy = optional(string, "oldest_first")
})), [])
cpu_options = optional(object({
core_count = optional(number)
threads_per_core = optional(number)
amd_sev_snp = optional(string)
nested_virtualization = optional(string)
}), null)
placement = optional(object({
affinity = optional(string)
availability_zone = optional(string)
group_id = optional(string)
group_name = optional(string)
host_id = optional(string)
host_resource_group_arn = optional(string)
spread_domain = optional(string)
tenancy = optional(string)
partition_number = optional(number)
}), null)
license_specifications = optional(list(object({
license_configuration_arn = string
})), [])
use_dedicated_host = optional(bool, false)
runner_log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
block_device_mappings = optional(list(object({
delete_on_termination = optional(bool, true)
device_name = optional(string, "/dev/xvda")
encrypted = optional(bool, true)
iops = optional(number)
kms_key_id = optional(string)
snapshot_id = optional(string)
throughput = optional(number)
volume_initialization_rate = optional(number)
volume_size = number
volume_type = optional(string, "gp3")
})), [{
volume_size = 30
}])
pool_config = optional(list(object({
schedule_expression = string
schedule_expression_timezone = optional(string)
size = number
})), [])
job_retry = optional(object({
enable = optional(bool, false)
delay_in_seconds = optional(number, 300)
delay_backoff = optional(number, 2)
lambda_memory_size = optional(number, 256)
lambda_timeout = optional(number, 30)
max_attempts = optional(number, 1)
}), {})
iam_overrides = optional(object({
override_instance_profile = optional(bool, null)
instance_profile_name = optional(string, null)
override_runner_role = optional(bool, null)
runner_role_arn = optional(string, null)
}), {
override_instance_profile = false
instance_profile_name = null
override_runner_role = false
runner_role_arn = null
})
}), null)
matcherConfig = optional(object({
labelMatchers = list(list(string))
exactMatch = optional(bool, false)
bidirectionalLabelMatch = optional(bool, false)
priority = optional(number, 999)
enableDynamicLabels = optional(bool, false)
awsDynamicLabelsPolicy = optional(any, null)
}), null)
redrive_build_queue = optional(object({
enabled = bool
maxReceiveCount = number
}), {
enabled = false
maxReceiveCount = null
})

# V2 Contract
tags = optional(map(string), {})

runner = optional(object({
os = optional(string, null)
architecture = optional(string, null)
disable_default_labels = optional(bool, null)
extra_labels = optional(list(string), null)
group_name = optional(string, null)
name_prefix = optional(string, null)
run_as_root = optional(bool, null)
run_as = optional(string, null)
auto_update_disabled = optional(bool, null)
tags = optional(map(string), {})
hooks = optional(object({
job_started = optional(string, null)
job_completed = optional(string, null)
}), {})
iam = optional(object({
role = optional(object({
arn = string
}), null)
managed_policy_arns = optional(map(string), null)
additional_trust_policy_json = optional(string, null)
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
}), {})

lambda = optional(object({
runtime = optional(string, null)
architecture = optional(string, null)
subnet_ids = optional(list(string), null)
security_group_ids = optional(list(string), null)
tags = optional(map(string), {})
role = optional(object({
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
}), {})

orchestration_provider = optional(object({
webhook = optional(object({
runner = optional(object({
boot_time_in_minutes = optional(number, null)
ephemeral = optional(bool, null)
jit_config_enabled = optional(bool, null)
maximum_count = optional(number, null)
}), {})
github = optional(object({
organization_runners = optional(bool, false)
}), {})
matcherConfig = optional(object({
labelMatchers = list(list(string))
exactMatch = optional(bool, false)
bidirectionalLabelMatch = optional(bool, false)
priority = optional(number, 999)
dynamic_labels_enabled = optional(bool, false)
awsDynamicLabelsPolicy = optional(object({
blocked_keys = optional(list(string), [])
restricted_keys = optional(map(object({
allowed = optional(list(string), [])
denied = optional(list(string), [])
max = optional(string, null)
})), {})
}), null)
}), null)
queue = optional(object({
delay_webhook_event = optional(number, null)
job_queue_retention_in_seconds = optional(number, null)
visibility_timeout_seconds = optional(number, null)
redrive_build_queue = optional(object({
enabled = optional(bool, null)
maxReceiveCount = optional(number, null)
}), null)
tags = optional(map(string), {})
}), {})
lambda = optional(object({
scale = optional(object({
up = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
reserved_concurrent_executions = optional(number, null)
job_queued_check_enabled = optional(bool, null)
event_source_mapping = optional(object({
batch_size = optional(number, null)
maximum_batching_window_in_seconds = optional(number, null)
}), {})
tags = optional(map(string), {})
}), {})
down = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
schedule_expression = optional(string, null)
minimum_running_time_in_minutes = optional(number, null)
idle_config = optional(list(object({
cron = string
timeZone = string
idleCount = number
evictionStrategy = optional(string, "oldest_first")
})), null)
tags = optional(map(string), {})
}), {})
}), {})
pool = optional(object({
memory_size = optional(number, null)
timeout = optional(number, null)
reserved_concurrent_executions = optional(number, null)
config = optional(list(object({
schedule_expression = string
schedule_expression_timezone = optional(string)
size = number
})), null)
include_busy_runners = optional(bool, null)
runner_owner = optional(string, null)
tags = optional(map(string), {})
}), {})
}), {})
job_retry = optional(object({
enabled = optional(bool, false)
delay_in_seconds = optional(number, 300)
delay_backoff = optional(number, 2)
max_attempts = optional(number, 1)
tags = optional(map(string), {})
lambda = optional(object({
memory_size = optional(number, 256)
reserved_concurrent_executions = optional(number, 1)
timeout = optional(number, 30)
}), {})
}), {})
}), null)
}), {})

ssm = optional(object({
paths = optional(object({
root = optional(string, null)
tokens = optional(string, null)
config = optional(string, null)
}), {})
tags = optional(map(string), {})
parameters = optional(object({
tags = optional(map(string), {})
}), {})
housekeeper = optional(object({
schedule_expression = optional(string, null)
state = optional(string, null)
tags = optional(map(string), {})
lambda = optional(object({
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
memory_size = optional(number, null)
timeout = optional(number, null)
}), {})
config = optional(object({
tokenPath = optional(string, null)
minimumDaysOld = optional(number, null)
dryRun = optional(bool, null)
}), {})
}), {})
}), {})

observability = optional(object({
logs = optional(object({
level = optional(string, null)
retention_in_days = optional(number, null)
kms_key_id = optional(string, null)
class = optional(string, null)
tags = optional(map(string), {})
}), {})
tracing = optional(object({
mode = optional(string, null)
capture_http_requests = optional(bool, null)
capture_error = optional(bool, null)
}), {})
metrics = optional(object({
enabled = optional(bool, null)
namespace = optional(string, null)
metric = optional(object({
github_app_rate_limit = optional(object({
enabled = optional(bool, null)
}), {})
job_retry = optional(object({
enabled = optional(bool, null)
}), {})
spot_termination_warning = optional(object({
enabled = optional(bool, null)
}), {})
}), {})
}), {})
}), {})

compute_provider = optional(object({
aws = optional(object({
ec2 = optional(object({
metadata_options = optional(object({
instance_metadata_tags = optional(string, "enabled")
http_endpoint = optional(string, "enabled")
http_tokens = optional(string, "required")
http_put_response_hop_limit = optional(number, 1)
}), {})
ami = optional(object({
filter = optional(map(list(string)), { state = ["available"] })
owners = optional(list(string), ["amazon"])
id_ssm_parameter = optional(object({
arn = string
}), null)
kms_key = optional(object({
arn = string
}), null)
}), null)
block_device_mappings = optional(list(object({
delete_on_termination = optional(bool, true)
device_name = optional(string, "/dev/xvda")
encrypted = optional(bool, true)
iops = optional(number)
kms_key_id = optional(string)
snapshot_id = optional(string)
throughput = optional(number)
volume_initialization_rate = optional(number)
volume_size = number
volume_type = optional(string, "gp3")
})), [{ volume_size = 30 }])
create_service_linked_role_spot = optional(bool, false)
credit_specification = optional(string, null)
ebs_optimized = optional(bool, false)
cloudwatch_agent = optional(object({
enabled = optional(bool, true)
config = optional(string, null)
}), {})
binaries_syncer = optional(object({
enabled = optional(bool, null)
}), {})
detailed_monitoring_enabled = optional(bool, false)
ssm_enabled = optional(bool, false)
user_data = optional(object({
enabled = optional(bool, true)
template = optional(string, null)
content = optional(string, null)
pre_install = optional(string, "")
post_install = optional(string, "")
debug_logging_enabled = optional(bool, false)
}), {})
instance_allocation_strategy = optional(string, "lowest-price")
instance_max_spot_price = optional(string, null)
instance_target_capacity_type = optional(string, "spot")
instance_type_priorities = optional(map(number), null)
instance_types = optional(list(string), [])
additional_security_group_ids = optional(list(string), null)
managed_security_group_enabled = optional(bool, null)
egress_rules = optional(list(object({
cidr_blocks = list(string)
ipv6_cidr_blocks = list(string)
prefix_list_ids = list(string)
from_port = number
protocol = string
security_groups = list(string)
self = bool
to_port = number
description = string
})), null)
instance_profile_path = optional(string, null)
key_name = optional(string, null)
associate_public_ipv4_address = optional(bool, null)
instance_profile = optional(object({
name = string
}), null)
on_demand_failover_for_errors = optional(list(string), [])
scale_errors = optional(list(string), [
"UnfulfillableCapacity",
"MaxSpotInstanceCountExceeded",
"TargetCapacityLimitExceededException",
"RequestLimitExceeded",
"ResourceLimitExceeded",
"MaxSpotInstanceCountExceeded",
"MaxSpotFleetRequestCountExceeded",
"InsufficientInstanceCapacity",
"InsufficientCapacityOnHost",
])
subnet_ids = optional(list(string), null)
vpc_id = optional(string, null)
cpu_options = optional(object({
core_count = optional(number)
threads_per_core = optional(number)
amd_sev_snp = optional(string)
nested_virtualization = optional(string)
}), null)
placement = optional(object({
affinity = optional(string)
availability_zone = optional(string)
group_id = optional(string)
group_name = optional(string)
host_id = optional(string)
host_resource_group_arn = optional(string)
spread_domain = optional(string)
tenancy = optional(string)
partition_number = optional(number)
}), null)
license_specifications = optional(list(object({
license_configuration_arn = string
})), [])
use_dedicated_host = optional(bool, false)
log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
tags = optional(map(string), {})
}), null)
microvm = optional(object({
image_arn = optional(string, null)
image_version = optional(string, null)
ingress_network_connectors = optional(list(string), null)
egress_network_connectors = optional(list(string), null)
cloudwatch_agent = optional(object({
enabled = optional(bool, null)
config = optional(string, null)
}), {})
log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
environment_variables = optional(map(string), {})
iam = optional(object({
resource_arns = optional(object({
images = optional(list(string), null)
}), {})
additional_policy_json = optional(object({
scale_up = optional(string, null)
}), {})
managed_policies = optional(object({
scale_up = optional(object({
arn = string
}), null)
pool = optional(object({
arn = string
}), null)
}), {})
}), {})
}), null)
}), {})
}), {})
}))
| `{}` | no | | [parameter\_store\_tags](#input\_parameter\_store\_tags) | Map of tags that will be added to all the SSM Parameter Store parameters created by the Lambda function. | `map(string)` | `{}` | no | | [pool\_lambda\_reserved\_concurrent\_executions](#input\_pool\_lambda\_reserved\_concurrent\_executions) | Amount of reserved concurrent executions for the scale-up lambda function. A value of 0 disables lambda from being triggered and -1 removes any concurrency limitations. | `number` | `1` | no | | [pool\_lambda\_timeout](#input\_pool\_lambda\_timeout) | Time out for the pool lambda in seconds. | `number` | `60` | no | @@ -248,13 +218,13 @@ multi_runner_config = { | [scale\_up\_lambda\_memory\_size](#input\_scale\_up\_lambda\_memory\_size) | Memory size limit in MB for scale\_up lambda. | `number` | `512` | no | | [ssm\_paths](#input\_ssm\_paths) | The root path used in SSM to store configuration and secrets. |
object({
root = optional(string, "github-action-runners")
app = optional(string, "app")
runners = optional(string, "runners")
webhook = optional(string, "webhook")
})
| `{}` | no | | [state\_event\_rule\_binaries\_syncer](#input\_state\_event\_rule\_binaries\_syncer) | Option to disable EventBridge Lambda trigger for the binary syncer, useful to stop automatic updates of binary distribution | `string` | `"ENABLED"` | no | -| [subnet\_ids](#input\_subnet\_ids) | List of subnets in which the action runners will be launched, the subnets needs to be subnets in the `vpc_id`. | `list(string)` | n/a | yes | +| [subnet\_ids](#input\_subnet\_ids) | List of subnets in which stable v1 action runners will be launched. Omit when using the experimental v2 interface. | `list(string)` | `null` | no | | [syncer\_lambda\_s3\_key](#input\_syncer\_lambda\_s3\_key) | S3 key for syncer lambda function. Required if using S3 bucket to specify lambdas. | `string` | `null` | no | | [syncer\_lambda\_s3\_object\_version](#input\_syncer\_lambda\_s3\_object\_version) | S3 object version for syncer lambda function. Useful if S3 versioning is enabled on source bucket. | `string` | `null` | no | | [tags](#input\_tags) | Map of tags that will be added to created resources. By default resources will be tagged with name and environment. | `map(string)` | `{}` | no | | [tracing\_config](#input\_tracing\_config) | Configuration for lambda tracing. |
object({
mode = optional(string, null)
capture_http_requests = optional(bool, false)
capture_error = optional(bool, false)
})
| `{}` | no | | [user\_agent](#input\_user\_agent) | User agent used for API calls by lambda functions. | `string` | `"github-aws-runners"` | no | -| [vpc\_id](#input\_vpc\_id) | The VPC for security groups of the action runners. | `string` | n/a | yes | +| [vpc\_id](#input\_vpc\_id) | The VPC for security groups of stable v1 action runners. Omit when using the experimental v2 interface. | `string` | `null` | no | | [webhook\_lambda\_apigateway\_access\_log\_settings](#input\_webhook\_lambda\_apigateway\_access\_log\_settings) | Access log settings for webhook API gateway. |
object({
destination_arn = string
format = string
})
| `null` | no | | [webhook\_lambda\_memory\_size](#input\_webhook\_lambda\_memory\_size) | Memory size limit in MB for webhook lambda. | `number` | `256` | no | | [webhook\_lambda\_s3\_key](#input\_webhook\_lambda\_s3\_key) | S3 key for webhook lambda function. Required if using S3 bucket to specify lambdas. | `string` | `null` | no | @@ -270,6 +240,7 @@ multi_runner_config = { | [instance\_termination\_handler](#output\_instance\_termination\_handler) | n/a | | [instance\_termination\_watcher](#output\_instance\_termination\_watcher) | n/a | | [runners\_map](#output\_runners\_map) | n/a | +| [runners\_map\_v2](#output\_runners\_map\_v2) | n/a | | [ssm\_parameters](#output\_ssm\_parameters) | n/a | | [webhook](#output\_webhook) | n/a | diff --git a/modules/multi-runner/config.experimental.resolved.tf b/modules/multi-runner/config.experimental.resolved.tf index b7e2e26ab0..ac6f482970 100644 --- a/modules/multi-runner/config.experimental.resolved.tf +++ b/modules/multi-runner/config.experimental.resolved.tf @@ -480,6 +480,54 @@ locals { } tags = merge(local.normalized_config.compute_provider.aws.ec2.tags, v.compute_provider.aws.ec2.tags) }) + microvm = v.compute_provider.aws.microvm == null ? null : merge(v.compute_provider.aws.microvm, { + image_arn = try(coalesce(v.compute_provider.aws.microvm.image_arn, local.normalized_config.compute_provider.aws.microvm.image_arn), null) + image_version = try(coalesce(v.compute_provider.aws.microvm.image_version, local.normalized_config.compute_provider.aws.microvm.image_version), null) + ingress_network_connectors = v.compute_provider.aws.microvm.ingress_network_connectors != null ? ( + v.compute_provider.aws.microvm.ingress_network_connectors + ) : local.normalized_config.compute_provider.aws.microvm.ingress_network_connectors + egress_network_connectors = v.compute_provider.aws.microvm.egress_network_connectors != null ? ( + v.compute_provider.aws.microvm.egress_network_connectors + ) : local.normalized_config.compute_provider.aws.microvm.egress_network_connectors + cloudwatch_agent = { + enabled = coalesce( + v.compute_provider.aws.microvm.cloudwatch_agent.enabled, + local.normalized_config.compute_provider.aws.microvm.cloudwatch_agent.enabled, + ) + config = try(coalesce( + v.compute_provider.aws.microvm.cloudwatch_agent.config, + local.normalized_config.compute_provider.aws.microvm.cloudwatch_agent.config, + ), null) + } + log_files = v.compute_provider.aws.microvm.log_files != null ? ( + v.compute_provider.aws.microvm.log_files + ) : local.normalized_config.compute_provider.aws.microvm.log_files + environment_variables = merge( + local.normalized_config.compute_provider.aws.microvm.environment_variables, + v.compute_provider.aws.microvm.environment_variables, + ) + iam = { + resource_arns = { + images = v.compute_provider.aws.microvm.iam.resource_arns.images != null ? ( + v.compute_provider.aws.microvm.iam.resource_arns.images + ) : local.normalized_config.compute_provider.aws.microvm.iam.resource_arns.images + } + additional_policy_json = { + scale_up = try(coalesce( + v.compute_provider.aws.microvm.iam.additional_policy_json.scale_up, + local.normalized_config.compute_provider.aws.microvm.iam.additional_policy_json.scale_up, + ), null) + } + managed_policies = { + scale_up = v.compute_provider.aws.microvm.iam.managed_policies.scale_up != null ? ( + v.compute_provider.aws.microvm.iam.managed_policies.scale_up + ) : local.normalized_config.compute_provider.aws.microvm.iam.managed_policies.scale_up + pool = v.compute_provider.aws.microvm.iam.managed_policies.pool != null ? ( + v.compute_provider.aws.microvm.iam.managed_policies.pool + ) : local.normalized_config.compute_provider.aws.microvm.iam.managed_policies.pool + } + } + }) } } }) diff --git a/modules/multi-runner/config.experimental.translation.tf b/modules/multi-runner/config.experimental.translation.tf index 07df28e2e7..16b6f45d4e 100644 --- a/modules/multi-runner/config.experimental.translation.tf +++ b/modules/multi-runner/config.experimental.translation.tf @@ -301,6 +301,30 @@ locals { } } } + microvm = { + image_arn = null + image_version = null + ingress_network_connectors = [] + egress_network_connectors = [] + cloudwatch_agent = { + enabled = true + config = null + } + log_files = null + environment_variables = {} + iam = { + resource_arns = { + images = null + } + additional_policy_json = { + scale_up = null + } + managed_policies = { + scale_up = null + pool = null + } + } + } } } @@ -552,6 +576,30 @@ locals { log_files = v.runner_config.runner_log_files tags = v.runner_config.runner_ec2_tags } + microvm = { + image_arn = null + image_version = null + ingress_network_connectors = [] + egress_network_connectors = [] + cloudwatch_agent = { + enabled = true + config = null + } + log_files = null + environment_variables = {} + iam = { + resource_arns = { + images = null + } + additional_policy_json = { + scale_up = null + } + managed_policies = { + scale_up = null + pool = null + } + } + } } } } diff --git a/modules/multi-runner/outputs.tf b/modules/multi-runner/outputs.tf index 7c4a9807d1..4c7d4a6cd3 100644 --- a/modules/multi-runner/outputs.tf +++ b/modules/multi-runner/outputs.tf @@ -21,6 +21,18 @@ output "runners_map" { } } +output "runners_map_v2" { + value = { for runner_key, runner in module.runner_configs : runner_key => { + runner = runner.runner + orchestration_provider = runner.orchestration_provider + scale_up = runner.scale_up + scale_down = runner.scale_down + pool = runner.pool + provider = runner.provider + } + } +} + output "binaries_syncer_map" { value = { for runner_binary_key, runner_binary in module.runner_binaries : runner_binary_key => { lambda = runner_binary.lambda diff --git a/modules/multi-runner/runners.experimental.tf b/modules/multi-runner/runners.experimental.tf new file mode 100644 index 0000000000..4e8652aa00 --- /dev/null +++ b/modules/multi-runner/runners.experimental.tf @@ -0,0 +1,38 @@ +module "runner_configs" { + source = "../runner-config" + for_each = { + for runner_key, runner_config in local.effective_config.multi_runner_config : + runner_key => runner_config if local.use_v2_config + } + + aws_region = var.aws_region + aws_partition = var.aws_partition + prefix = "${var.prefix}-${each.key}" + + tags = merge( + each.value.tags, + { "ghr:environment" = var.prefix }, + ) + runner = each.value.runner + github = merge(each.value.github, { + app_parameters = local.github_app_parameters + }) + lambda = each.value.lambda + orchestration_provider = { + webhook = each.value.orchestration_provider.webhook == null ? null : { + runner = each.value.orchestration_provider.webhook.runner + github = each.value.orchestration_provider.webhook.github + queue = merge(each.value.orchestration_provider.webhook.queue, { + build = { + arn = aws_sqs_queue.queued_builds[each.key].arn + url = aws_sqs_queue.queued_builds[each.key].url + } + }) + lambda = each.value.orchestration_provider.webhook.lambda + job_retry = each.value.orchestration_provider.webhook.job_retry + } + } + ssm = each.value.ssm + observability = each.value.observability + compute_provider = each.value.compute_provider +} diff --git a/modules/multi-runner/runners.tf b/modules/multi-runner/runners.tf index 61c5f57583..5e0bc44022 100644 --- a/modules/multi-runner/runners.tf +++ b/modules/multi-runner/runners.tf @@ -1,6 +1,9 @@ module "runners" { - source = "../runners" - for_each = local.effective_config.multi_runner_config + source = "../runners" + for_each = { + for runner_key, runner_config in local.effective_config.multi_runner_config : + runner_key => runner_config if !local.use_v2_config + } aws_region = var.aws_region aws_partition = var.aws_partition vpc_id = each.value.compute_provider.aws.ec2.vpc_id diff --git a/modules/multi-runner/tests/config-resolution.tftest.hcl b/modules/multi-runner/tests/config-resolution.tftest.hcl index efb117ed7f..a4a6f2af00 100644 --- a/modules/multi-runner/tests/config-resolution.tftest.hcl +++ b/modules/multi-runner/tests/config-resolution.tftest.hcl @@ -59,30 +59,9 @@ mock_provider "random" {} mock_provider "null" {} variables { - aws_region = "eu-west-1" - vpc_id = "vpc-stable" - subnet_ids = ["subnet-stable"] - - github_app = { - key_base64_ssm = { - arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/tests/github-app/key" - name = "/tests/github-app/key" - } - id_ssm = { - arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/tests/github-app/id" - name = "/tests/github-app/id" - } - webhook_secret_ssm = { - arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/tests/github-app/webhook-secret" - name = "/tests/github-app/webhook-secret" - } - } - - lambda_s3_bucket = "test-lambda-artifacts" - runners_lambda_zip = "README.md" - runners_lambda_s3_key = "runners.zip" - webhook_lambda_s3_key = "webhook.zip" - syncer_lambda_s3_key = "runner-binaries-syncer.zip" + aws_region = "eu-west-1" + prefix = "test" + aws_partition = "aws" global_config_github = { app = { @@ -152,6 +131,30 @@ run "v1_stable_inputs_translate_into_effective_base" { command = plan variables { + vpc_id = "vpc-stable" + subnet_ids = ["subnet-stable"] + + github_app = { + key_base64_ssm = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/tests/github-app/key" + name = "/tests/github-app/key" + } + id_ssm = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/tests/github-app/id" + name = "/tests/github-app/id" + } + webhook_secret_ssm = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/tests/github-app/webhook-secret" + name = "/tests/github-app/webhook-secret" + } + } + + lambda_s3_bucket = "test-lambda-artifacts" + runners_lambda_zip = "README.md" + runners_lambda_s3_key = "runners.zip" + webhook_lambda_s3_key = "webhook.zip" + syncer_lambda_s3_key = "runner-binaries-syncer.zip" + tags = { source = "v1" } @@ -189,18 +192,29 @@ run "v1_stable_inputs_translate_into_effective_base" { && local.resolved_config.multi_runner_config["stable"].runner.group_name == "v1-lane" && local.resolved_config.multi_runner_config["stable"].orchestration_provider.webhook.runner.maximum_count == 2 && toset(local.resolved_config.multi_runner_config["stable"].compute_provider.aws.ec2.instance_types) == toset(["m5.large"]) + && local.resolved_config.multi_runner_config["stable"].compute_provider.aws.microvm.image_arn == null + && local.resolved_config.multi_runner_config["stable"].compute_provider.aws.microvm.cloudwatch_agent.enabled + && length(local.resolved_config.multi_runner_config["stable"].compute_provider.aws.microvm.environment_variables) == 0 && toset(local.effective_config.multi_runner_config["stable"].runner.labels) == toset(["linux", "self-hosted", "x64"]) ) error_message = "Stable v1 inputs must translate into the effective experimental base without leaking v2 globals." } + + assert { + condition = ( + keys(module.runners) == ["stable"] + && length(module.runner_configs) == 0 + && keys(output.runners_map) == ["stable"] + && length(output.runners_map_v2) == 0 + ) + error_message = "Stable v1 configurations must route through module.runners and not the experimental runner-config module." + } } run "v2_inputs_resolve_lane_over_global" { command = plan variables { - experimental_features = ["multi-runner-v2"] - tags = { source = "v1-must-not-leak" } @@ -372,4 +386,186 @@ run "v2_inputs_resolve_lane_over_global" { ) error_message = "v2 inputs must resolve lane overrides before v2 global defaults." } + + assert { + condition = ( + length(module.runners) == 0 + && keys(module.runner_configs) == ["lane"] + && length(output.runners_map) == 0 + && keys(output.runners_map_v2) == ["lane"] + ) + error_message = "Experimental v2 configurations must route through module.runner_configs and skip the legacy runners module." + } +} + +run "v2_inputs_do_not_require_legacy_arguments" { + command = plan + + variables { + global_config_compute_provider = { + aws = { + ec2 = { + vpc_id = "vpc-v2" + subnet_ids = ["subnet-v2"] + runner_binaries = { + enabled = false + } + } + } + } + multi_runner_config = { + lane = { + orchestration_provider = { + webhook = { + matcherConfig = { + labelMatchers = [["self-hosted", "linux", "x64"]] + } + } + } + compute_provider = { + aws = { + ec2 = { + instance_types = ["m5.large"] + binaries_syncer = { + enabled = false + } + } + } + } + } + } + } + + assert { + condition = ( + local.use_v2_config + && keys(module.runner_configs) == ["lane"] + && length(module.runners) == 0 + && local.resolved_config.multi_runner_config["lane"].compute_provider.aws.ec2.vpc_id == "vpc-v2" + ) + error_message = "The v2 interface must work without the stable v1 GitHub App, VPC, subnet, or runner configuration inputs." + } +} + +run "v2_microvm_inputs_route_to_microvm_provider" { + command = plan + + variables { + global_config = { + runner = { + os = "linux" + architecture = "arm64" + } + } + + global_config_github = { + app = { + key_base64 = "experimental-app-key" + id = "experimental-app-id" + webhook_secret = "experimental-webhook-secret" + } + } + + global_config_lambda = { + artifact = { + s3 = { + bucket = "global-lambda-artifacts" + } + } + } + + global_config_orchestration_provider = { + webhook = { + eventbridge = { + enabled = false + } + runner = { + ephemeral = true + jit_config_enabled = true + } + lambda = { + artifact = { + s3 = { + key = "global-runners.zip" + } + } + webhook = { + artifact = { + s3 = { + key = "global-webhook.zip" + } + } + } + } + } + } + + global_config_ssm = { + housekeeper = { + lambda = { + artifact = { + s3 = { + key = "global-housekeeper.zip" + } + } + } + } + } + + global_config_compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:global" + image_version = "7" + } + } + } + + multi_runner_config = { + microvm = { + runner = { + name_prefix = "microvm-" + } + orchestration_provider = { + webhook = { + matcherConfig = { + labelMatchers = [["microvm"]] + } + } + } + compute_provider = { + aws = { + microvm = { + image_version = "8" + } + } + } + } + } + } + + assert { + condition = ( + local.use_v2_config + && keys(local.resolved_config.multi_runner_config) == ["microvm"] + && local.resolved_config.multi_runner_config["microvm"].runner.os == "linux" + && local.resolved_config.multi_runner_config["microvm"].runner.architecture == "arm64" + && local.resolved_config.multi_runner_config["microvm"].compute_provider.aws.ec2 == null + && local.resolved_config.multi_runner_config["microvm"].compute_provider.aws.microvm.image_arn == "arn:aws:lambda:eu-west-1:123456789012:microvm-image:global" + && local.resolved_config.multi_runner_config["microvm"].compute_provider.aws.microvm.image_version == "8" + && local.effective_config.orchestration_provider.webhook.lambda.webhook.artifact.s3.key == "global-webhook.zip" + ) + error_message = "Experimental MicroVM lanes must resolve Linux ARM64 settings, inherit global provider values, and place the webhook artifact key under lambda.webhook.artifact." + } + + assert { + condition = ( + length(module.runners) == 0 + && keys(module.runner_configs) == ["microvm"] + && output.runners_map_v2["microvm"].provider.aws.ec2 == null + && output.runners_map_v2["microvm"].provider.aws.microvm.image_arn == "arn:aws:lambda:eu-west-1:123456789012:microvm-image:global" + && output.runners_map_v2["microvm"].provider.aws.microvm.image_version == "8" + ) + error_message = "Experimental MicroVM lanes must route through module.runner_configs and expose the MicroVM provider contract without an EC2 provider." + } } diff --git a/modules/multi-runner/validations.tf b/modules/multi-runner/validations.tf new file mode 100644 index 0000000000..4be542eb59 --- /dev/null +++ b/modules/multi-runner/validations.tf @@ -0,0 +1,112 @@ +locals { + common_validation_errors = concat( + alltrue([ + for app in var.additional_github_apps : + (app.key_base64 != null || app.key_base64_ssm != null) && + (app.id != null || app.id_ssm != null) + ]) ? [] : ["Each additional GitHub app must provide either key_base64 or key_base64_ssm, and either id or id_ssm."], + contains(["STANDARD", "INFREQUENT_ACCESS"], var.log_class) ? [] : ["`log_class` must be either `STANDARD` or `INFREQUENT_ACCESS`."], + contains(["first", "random", "all"], var.queue_selection_strategy) ? [] : ["`queue_selection_strategy` value not valid. Valid values are 'first', 'random', 'all'."], + contains(["silly", "trace", "debug", "info", "warn", "error", "fatal"], var.log_level) ? [] : ["`log_level` value not valid. Valid values are 'silly', 'trace', 'debug', 'info', 'warn', 'error', 'fatal'."], + contains(["arm64", "x86_64"], var.lambda_architecture) ? [] : ["`lambda_architecture` value is not valid, valid values are: `arm64` and `x86_64`."], + contains(["ENABLED", "DISABLED", "ENABLED_WITH_ALL_CLOUDTRAIL_MANAGEMENT_EVENTS"], var.state_event_rule_binaries_syncer) ? [] : ["`state_event_rule_binaries_syncer` value is not valid, valid values are: `ENABLED`, `DISABLED`, `ENABLED_WITH_ALL_CLOUDTRAIL_MANAGEMENT_EVENTS`."], + var.queue_encryption == null || var.queue_encryption.sqs_managed_sse_enabled != null && var.queue_encryption.kms_master_key_id == null && var.queue_encryption.kms_data_key_reuse_period_seconds == null || var.queue_encryption.sqs_managed_sse_enabled == null && var.queue_encryption.kms_master_key_id != null ? [] : ["Invalid configuration for `queue_encryption`. Valid configurations are encryption disabled, enabled via SSE. Or encryption via KMS."], + contains(["Standard", "Advanced"], var.matcher_config_parameter_store_tier) ? [] : ["`matcher_config_parameter_store_tier` value is not valid, valid values are: `Standard`, and `Advanced`."], + !var.iam_overrides.override_instance_profile || var.iam_overrides.instance_profile_name != null ? [] : ["instance_profile_name must be provided when override_instance_profile is true."], + !var.iam_overrides.override_runner_role || var.iam_overrides.runner_role_arn != null ? [] : ["runner_role_arn must be provided when override_runner_role is true."] + ) +} + +resource "terraform_data" "validate_v1" { + count = local.use_v2_config ? 0 : 1 + + lifecycle { + precondition { + condition = length(local.common_validation_errors) == 0 + error_message = join("\n", local.common_validation_errors) + } + + precondition { + condition = ( + (var.github_app.key_base64 != null || var.github_app.key_base64_ssm != null) && + (var.github_app.id != null || var.github_app.id_ssm != null) && + (var.github_app.webhook_secret != null || var.github_app.webhook_secret_ssm != null) && + var.vpc_id != null && + var.subnet_ids != null && + length(var.multi_runner_config) > 0 + ) + error_message = "Stable v1 configuration requires github_app, vpc_id, subnet_ids, and multi_runner_config." + } + } +} + +resource "terraform_data" "validate_v2" { + count = local.use_v2_config ? 1 : 0 + + lifecycle { + precondition { + condition = length(local.common_validation_errors) == 0 + error_message = join("\n", local.common_validation_errors) + } + + precondition { + condition = ( + ( + try(var.global_config_github.app.key_base64, null) != null || + try(var.global_config_github.app.key_base64_ssm, null) != null + ) && ( + try(var.global_config_github.app.id, null) != null || + try(var.global_config_github.app.id_ssm, null) != null + ) && ( + try(var.global_config_github.app.webhook_secret, null) != null || + try(var.global_config_github.app.webhook_secret_ssm, null) != null + ) + ) + error_message = "Experimental v2 configuration requires a complete GitHub App under global_config_github.app." + } + + precondition { + condition = alltrue([ + for config in local.resolved_config.multi_runner_config : ( + try(config.orchestration_provider.webhook != null, false) + ) + ]) + error_message = "Each experimental v2 runner lane requires a webhook provider." + } + + precondition { + condition = alltrue([ + for config in local.resolved_config.multi_runner_config : length([ + for provider_config in [ + try(config.compute_provider.aws.ec2, null), + try(config.compute_provider.aws.microvm, null), + ] : provider_config if provider_config != null + ]) == 1 + ]) + error_message = "Each experimental v2 runner lane requires exactly one compute provider. Supported providers: aws.ec2, aws.microvm." + } + + precondition { + condition = alltrue([ + for config in local.resolved_config.multi_runner_config : ( + !try(config.compute_provider.aws.ec2 != null, false) || ( + try(length(config.compute_provider.aws.ec2.instance_types) > 0, false) && + try(config.compute_provider.aws.ec2.vpc_id != null, false) && + try(length(config.compute_provider.aws.ec2.subnet_ids) > 0, false) + ) + ) + ]) + error_message = "Each experimental v2 EC2 runner lane requires instance_types, vpc_id, and at least one subnet." + } + + precondition { + condition = alltrue([ + for config in local.resolved_config.multi_runner_config : ( + !try(config.compute_provider.aws.microvm != null, false) || + try(config.compute_provider.aws.microvm.image_arn != null, false) + ) + ]) + error_message = "Each experimental v2 MicroVM runner lane requires image_arn." + } + } +} diff --git a/modules/multi-runner/variables.experimental.compute-provider.tf b/modules/multi-runner/variables.experimental.compute-provider.tf index 4780a156c3..1684ef8e74 100644 --- a/modules/multi-runner/variables.experimental.compute-provider.tf +++ b/modules/multi-runner/variables.experimental.compute-provider.tf @@ -199,6 +199,40 @@ variable "global_config_compute_provider" { }), {}) }), {}) }), {}) + microvm = optional(object({ + image_arn = optional(string, null) + image_version = optional(string, null) + ingress_network_connectors = optional(list(string), []) + egress_network_connectors = optional(list(string), []) + cloudwatch_agent = optional(object({ + enabled = optional(bool, true) + config = optional(string, null) + }), {}) + log_files = optional(list(object({ + log_group_name = string + prefix_log_group = bool + file_path = string + log_stream_name = string + log_class = optional(string, "STANDARD") + })), null) + environment_variables = optional(map(string), {}) + iam = optional(object({ + resource_arns = optional(object({ + images = optional(list(string), null) + }), {}) + additional_policy_json = optional(object({ + scale_up = optional(string, null) + }), {}) + managed_policies = optional(object({ + scale_up = optional(object({ + arn = string + }), null) + pool = optional(object({ + arn = string + }), null) + }), {}) + }), {}) + }), {}) }), {}) }) default = {} diff --git a/modules/multi-runner/variables.tf b/modules/multi-runner/variables.tf index bddc0873b4..4f08bc8a8a 100644 --- a/modules/multi-runner/variables.tf +++ b/modules/multi-runner/variables.tf @@ -1,6 +1,8 @@ variable "github_app" { description = < This module is treated as an internal module; breaking changes do not trigger a major release bump. + +This internal module implements the experimental provider-neutral runner configuration selected by `experimental.multi_runner_config`. It is composed by `multi-runner` and is not intended as a standalone public entry point. Its direct contract may change while v2 remains experimental. + +The module selects the [`webhook` orchestration provider](../orchestration-providers/webhook), which owns its [`scale-runners`](../orchestration-providers/webhook/scale-runners), [`pool`](../orchestration-providers/webhook/pool), and [`job-retry`](../orchestration-providers/webhook/job-retry) leaves. The configuration module retains the common [`ssm-housekeeper`](./ssm-housekeeper), creates or selects the runner IAM role, manages shared runner configuration in SSM, and dispatches the selected compute provider. + +Runner demand orchestration is selected independently through `orchestration_provider`. `orchestration_provider.webhook` is the currently supported provider and owns the build queue reference; runner lifecycle, boot time, and capacity under `orchestration_provider.webhook.runner`; runner registration scope; scaling controls; scheduled pool; and job retry. Common `runner` contains no webhook lifecycle or capacity settings. The provider resolves its lifecycle contract before runner-config serializes the existing bootstrap parameters. The provider wrapper is nullable so a future sibling provider can be added without moving this webhook contract again, while validation requires exactly one provider to be selected. + +Common `lambda` contains only shared execution substrate and the optional shared artifact bucket. The webhook provider owns the runner-control archive shared by scale, pool, and job-retry at `orchestration_provider.webhook.lambda.artifact` and combines its zip or S3 key/version with that common substrate. The common SSM housekeeper independently owns `ssm.housekeeper.lambda.artifact`: an S3 selection combines its component key/version with the common bucket, a local zip is used otherwise when configured, and the packaged runner control-plane archive is the final fallback. It never inherits the webhook runner-control archive. + +Provider-owned settings remain nested under a typed namespace and provider leaf. EC2 settings live under `compute_provider.aws.ec2`, while Lambda MicroVM settings live under `compute_provider.aws.microvm`. `multi-runner` resolves experimental globals and runner-configuration overrides first, then preserves the wrapped `{ aws = { ec2 = ..., microvm = ... } }` object expected by this module. Exactly one provider leaf must be non-null. Runner-config flattens the selected namespace and type only for Terraform dispatch: `aws_ec2` maps to runtime type `ec2`, and `aws_microvm` maps to runtime type `microvm`. + +The EC2 leaf reaches runner-config with `compute_provider.aws.ec2.binaries_syncer = { enabled, s3 }`; the S3 object is null when synchronization is disabled. Binary discovery and this shape adaptation happen in `multi-runner`, not inside runner-config. Runner-config calls [`compute-providers/aws/ec2/trust-policy`](../compute-providers/aws/ec2/trust-policy) as `module.compute_aws_ec2_trust_policy[0]`, then dispatches the full [`compute-providers/aws/ec2`](../compute-providers/aws/ec2) module at `module.compute_aws_ec2[0]`. Declarative moved blocks preserve state from the earlier experimental `module.compute_ec2_trust_policy[0]` and `module.compute_ec2[0]` labels. + +The MicroVM leaf similarly uses [`compute-providers/aws/microvm/trust-policy`](../compute-providers/aws/microvm/trust-policy) at `module.compute_aws_microvm_trust_policy[0]` and the full [`compute-providers/aws/microvm`](../compute-providers/aws/microvm) module at `module.compute_aws_microvm[0]`. It uses the resolved common `runner.iam.role` as the MicroVM execution role and exports the IAM and runtime-environment fragments required by the webhook control plane. MicroVM lanes require Linux on ARM64 and ephemeral webhook orchestration with JIT configuration enabled. MicroVM is introduced directly at its namespaced labels, so the EC2 moved blocks do not apply to it. + +The common configuration module attaches each selected provider's returned policy groups to its managed runner or webhook-provider roles. Provider-specific outputs remain grouped under the matching path: `provider.aws.ec2` or `provider.aws.microvm`. Moved blocks do not rewrite output references, so consumers of the former experimental `provider.ec2` path must update their expressions. + +## Tagging + +`tags` supplies module-wide defaults. Shared resource tags are set with `lambda.tags`, `orchestration_provider.webhook.queue.tags`, and `observability.logs.tags`. Component tags under `runner`, `orchestration_provider.webhook.lambda.scale.up`, `orchestration_provider.webhook.lambda.scale.down`, `orchestration_provider.webhook.lambda.pool`, `orchestration_provider.webhook.job_retry`, and `ssm` apply to the taggable resources owned by that component. `ssm.parameters.tags` and `ssm.housekeeper.tags` provide narrower SSM scopes. + +Tags are merged from broadest to narrowest: module tags, shared resource tags, component tags, and then subcomponent tags. The narrowest value wins when a key is repeated. For example, a scale-up Lambda receives `tags`, `lambda.tags`, and `orchestration_provider.webhook.lambda.scale.up.tags`, while its log group receives `tags`, `observability.logs.tags`, and `orchestration_provider.webhook.lambda.scale.up.tags`. + +Provider-specific runner tags remain inside the provider boundary. `compute_provider.aws.ec2.tags` applies to runtime EC2 instance, volume, network-interface, and spot-request tag specifications. `multi-runner` derives that map from global and runner-configuration `compute_provider.aws.ec2.tags` values. The EC2 provider applies the bootstrap tags `ghr:environment`, `ghr:ssm_config_path`, and `ghr:runner_name_prefix` last so they cannot be overridden; those tags are not added to common Lambda, IAM, queue, log-group, or SSM resources. + +## Provider behavior + +### EC2 runners + +The EC2 provider creates runners from a launch template. Bootstrap is handled by user data, and the runner retrieves its configuration from Parameter Store. + +### Lambda MicroVM runners + +The MicroVM provider starts Linux ARM64 capacity with `RunMicrovm`. The control plane generates the ephemeral runner's JIT payload, and the MicroVM image retrieves that payload from Parameter Store through its `/run` hook. The resolved common runner role is the MicroVM execution role. + +### Lambda scale up + +The scale-up Lambda is triggered by events on the runner configuration's SQS queue. It verifies that the workflow remains queued and that capacity limits permit another runner, then delegates creation to the selected compute provider: EC2 launches from the provider launch template, while MicroVM calls `RunMicrovm` with the resolved image, execution role, connector, duration, and logging settings. + +### Lambda scale down + +The scale-down Lambda runs on the schedule configured by `orchestration_provider.webhook.lambda.scale.down.schedule_expression`. It lists capacity through the selected compute provider, correlates it with GitHub runner state, and terminates removable EC2 instances or MicroVMs through that provider's API. + +--8<-- "modules/orchestration-providers/webhook/scale-down-state-diagram.md:mkdocs_scale_down_state_diagram" + +## Lambda Function + +The Lambda function is written in [TypeScript](https://www.typescriptlang.org/) and requires Node 12.x and yarn. Sources are located in [./lambdas/runners]. Two lambda functions share the same sources, there is one entry point for `scaleDown` and another one for `scaleUp`. + +### Install + +```bash +cd lambdas/runners +yarn install +``` + +### Test + +Test are implemented with [vitest][https://vitest.dev/]), calls to AWS and GitHub are mocked. + +```bash +yarn run test +``` + +### Package + +To compile all TypeScript/JavaScript sources in a single file [ncc](https://github.com/zeit/ncc) is used. + +```bash +yarn run dist +``` + + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.4.0 | +| [aws](#requirement\_aws) | >= 6.33 | + +## Providers + +| Name | Version | +|------|---------| +| [aws](#provider\_aws) | >= 6.33 | +| [terraform](#provider\_terraform) | n/a | + +## Modules + +| Name | Source | Version | +|------|--------|---------| +| [compute\_aws\_ec2](#module\_compute\_aws\_ec2) | ../compute-providers/aws/ec2 | n/a | +| [compute\_aws\_ec2\_trust\_policy](#module\_compute\_aws\_ec2\_trust\_policy) | ../compute-providers/aws/ec2/trust-policy | n/a | +| [compute\_aws\_microvm](#module\_compute\_aws\_microvm) | ../compute-providers/aws/microvm | n/a | +| [compute\_aws\_microvm\_trust\_policy](#module\_compute\_aws\_microvm\_trust\_policy) | ../compute-providers/aws/microvm/trust-policy | n/a | +| [orchestration\_webhook](#module\_orchestration\_webhook) | ../orchestration-providers/webhook | n/a | +| [ssm\_housekeeper](#module\_ssm\_housekeeper) | ./ssm-housekeeper | n/a | + +## Resources + +| Name | Type | +|------|------| +| [aws_iam_role.runner](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role) | resource | +| [aws_iam_role_policy.runner_provider](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy) | resource | +| [aws_iam_role_policy_attachment.runner](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy_attachment) | resource | +| [aws_ssm_parameter.disable_default_labels](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ssm_parameter) | resource | +| [aws_ssm_parameter.jit_config_enabled](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ssm_parameter) | resource | +| [aws_ssm_parameter.runner_agent_mode](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ssm_parameter) | resource | +| [aws_ssm_parameter.token_path](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/ssm_parameter) | resource | +| [terraform_data.validate_config](https://registry.terraform.io/providers/hashicorp/terraform/latest/docs/resources/data) | resource | +| [aws_caller_identity.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/caller_identity) | data source | + +## Inputs + +| Name | Description | Type | Default | Required | +|------|-------------|------|---------|:--------:| +| [aws\_partition](#input\_aws\_partition) | AWS partition used to construct ARNs. | `string` | `"aws"` | no | +| [aws\_region](#input\_aws\_region) | AWS region. | `string` | n/a | yes | +| [compute\_provider](#input\_compute\_provider) | Typed compute-provider configuration. Provider-owned settings remain inside the selected compute-provider block.

Exactly one compute-provider block must be non-null. The populated block selects the provider, and its presence must be known during planning. Values inside the selected block may remain unknown until apply.

- `aws`: AWS compute-provider configurations.
- `aws.ec2`: EC2 compute-provider configuration.
- `aws.ec2.ami`: Optional AMI discovery or external AMI-parameter configuration. Null uses the operating-system and architecture defaults.
- `aws.ec2.ami.filter`: EC2 AMI filters combined with the provider's default AMI-name filter.
- `aws.ec2.ami.owners`: AWS account IDs or aliases allowed to own the selected AMI.
- `aws.ec2.ami.id_ssm_parameter`: Optional externally managed SSM parameter containing the AMI ID. Null creates a provider-managed AMI-ID parameter. The wrapper's presence is the plan-time ownership discriminator, so keep the object literal even when its ARN comes from another resource.
- `aws.ec2.ami.id_ssm_parameter.arn`: ARN of the externally managed SSM parameter. The ARN may be unknown until apply.
- `aws.ec2.ami.kms_key`: Optional KMS key required to launch encrypted AMIs or snapshots. The wrapper's presence is the plan-time policy discriminator.
- `aws.ec2.ami.kms_key.arn`: ARN of the KMS key. The ARN may be unknown until apply.
- `aws.ec2.vpc_id`: VPC in which runner networking resources are created.
- `aws.ec2.subnet_ids`: Subnets from which scale-up may launch runner instances.
- `aws.ec2.overrides`: Optional resource-name overrides.
- `aws.ec2.overrides.name_runner`: Name tag used for runner compute resources. An empty value uses the generated provider name.
- `aws.ec2.overrides.name_sg`: Name tag used for the managed runner security group. An empty value uses the generated provider name.
- `aws.ec2.instance_profile`: Optional externally managed instance profile used by the launch template.
- `aws.ec2.instance_profile.name`: Name of the externally managed instance profile.
- `aws.ec2.instance_profile_path`: IAM path for the provider-managed instance profile. Null uses a path derived from the runner-configuration prefix.
- `aws.ec2.binaries_syncer`: Runner-distribution synchronization configuration.
- `aws.ec2.binaries_syncer.enabled`: Enables use of a synchronized runner distribution from S3.
- `aws.ec2.binaries_syncer.s3`: S3 object containing the synchronized runner distribution. Required when synchronization is enabled.
- `aws.ec2.binaries_syncer.s3.arn`: ARN of the runner-distribution bucket, used by IAM policies.
- `aws.ec2.binaries_syncer.s3.id`: Bucket name used to construct the runner-distribution S3 URI.
- `aws.ec2.binaries_syncer.s3.key`: Object key of the runner distribution.
- `aws.ec2.block_device_mappings`: EBS mappings added to the runner launch template.
- `aws.ec2.block_device_mappings[].delete_on_termination`: Deletes the volume when its runner instance terminates.
- `aws.ec2.block_device_mappings[].device_name`: Device name exposed to the runner instance.
- `aws.ec2.block_device_mappings[].encrypted`: Enables EBS encryption.
- `aws.ec2.block_device_mappings[].iops`: Provisioned IOPS for volume types that support it.
- `aws.ec2.block_device_mappings[].kms_key_id`: KMS key ID or ARN used to encrypt the volume.
- `aws.ec2.block_device_mappings[].snapshot_id`: Snapshot used to initialize the volume.
- `aws.ec2.block_device_mappings[].throughput`: Provisioned throughput for volume types that support it.
- `aws.ec2.block_device_mappings[].volume_initialization_rate`: Fixed initialization rate in MiB/s for supported snapshot-backed volumes.
- `aws.ec2.block_device_mappings[].volume_size`: Volume size in GiB.
- `aws.ec2.block_device_mappings[].volume_type`: EBS volume type.
- `aws.ec2.ebs_optimized`: Requests EBS-optimized runner instances.
- `aws.ec2.instance_target_capacity_type`: Primary capacity type, either `spot` or `on-demand`.
- `aws.ec2.instance_allocation_strategy`: EC2 Fleet allocation strategy used to select instance capacity.
- `aws.ec2.instance_type_priorities`: Optional numeric priorities keyed by instance type.
- `aws.ec2.instance_max_spot_price`: Optional maximum hourly Spot price.
- `aws.ec2.instance_types`: EC2 instance types available to the scale-up and pool functions.
- `aws.ec2.user_data`: Runner bootstrap user-data configuration.
- `aws.ec2.user_data.enabled`: Enables launch-template user data.
- `aws.ec2.user_data.template`: Optional path to a custom user-data template.
- `aws.ec2.user_data.content`: Optional complete user-data content. When set, it is used instead of rendering a template.
- `aws.ec2.user_data.pre_install`: Script content inserted before runner installation in the default template.
- `aws.ec2.user_data.post_install`: Script content inserted after runner installation in the default template.
- `aws.ec2.user_data.debug_logging_enabled`: Enables verbose user-data tracing, which can expose secrets in logs.
- `aws.ec2.ssm_enabled`: Attaches runner permissions and policies required for AWS Systems Manager access.
- `aws.ec2.create_service_linked_role_spot`: Allows scale-up to create the EC2 Spot service-linked role.
- `aws.ec2.cloudwatch_agent`: CloudWatch agent configuration for runner instances.
- `aws.ec2.cloudwatch_agent.enabled`: Installs and configures the CloudWatch agent through the default bootstrap flow.
- `aws.ec2.cloudwatch_agent.config`: Optional complete CloudWatch agent configuration. Null renders the provider default from `log_files`.
- `aws.ec2.managed_security_group_enabled`: Creates and attaches the provider-managed runner security group.
- `aws.ec2.log_files`: Optional log files collected by the CloudWatch agent. Null uses the provider defaults.
- `aws.ec2.log_files[].log_group_name`: CloudWatch log-group name, before optional prefixing.
- `aws.ec2.log_files[].prefix_log_group`: Prefixes the log-group name with the runner configuration path when true.
- `aws.ec2.log_files[].file_path`: File or glob read by the CloudWatch agent.
- `aws.ec2.log_files[].log_stream_name`: CloudWatch log-stream name template.
- `aws.ec2.log_files[].log_class`: CloudWatch log-group class for the collected file.
- `aws.ec2.key_name`: Optional EC2 key-pair name added to the launch template.
- `aws.ec2.additional_security_group_ids`: Existing security groups attached in addition to the managed security group.
- `aws.ec2.detailed_monitoring_enabled`: Enables detailed EC2 monitoring for runner instances.
- `aws.ec2.egress_rules`: Egress rules created on the managed runner security group.
- `aws.ec2.egress_rules[].cidr_blocks`: IPv4 CIDR destinations.
- `aws.ec2.egress_rules[].ipv6_cidr_blocks`: IPv6 CIDR destinations.
- `aws.ec2.egress_rules[].prefix_list_ids`: AWS prefix-list destinations.
- `aws.ec2.egress_rules[].from_port`: First destination port in the permitted range.
- `aws.ec2.egress_rules[].protocol`: IP protocol name or number. Use `-1` for all protocols.
- `aws.ec2.egress_rules[].security_groups`: Destination security-group IDs.
- `aws.ec2.egress_rules[].self`: Allows traffic to the managed security group itself when true.
- `aws.ec2.egress_rules[].to_port`: Last destination port in the permitted range.
- `aws.ec2.egress_rules[].description`: Optional rule description.
- `aws.ec2.tags`: Additional tags for runner instances, EBS volumes, network interfaces, and eligible Spot instance requests created from the launch template. They override module-level tags and the generated runner `Name`; the provider-managed `ghr:environment`, `ghr:ssm_config_path`, and `ghr:runner_name_prefix` bootstrap tags take final precedence. These tags do not apply to static provider resources such as the launch template, security group, IAM resources, SSM parameters, or log groups.
- `aws.ec2.metadata_options`: Instance Metadata Service configuration in the launch template.
- `aws.ec2.metadata_options.instance_metadata_tags`: Exposes instance tags through Instance Metadata Service when `enabled`.
- `aws.ec2.metadata_options.http_endpoint`: Enables or disables the Instance Metadata Service endpoint.
- `aws.ec2.metadata_options.http_tokens`: Controls whether IMDSv2 session tokens are optional or required.
- `aws.ec2.metadata_options.http_put_response_hop_limit`: Network hop limit for Instance Metadata Service token responses.
- `aws.ec2.credit_specification`: CPU credit mode for burstable instance types, either `standard` or `unlimited`.
- `aws.ec2.cpu_options`: CPU topology and processor-feature configuration.
- `aws.ec2.cpu_options.core_count`: Number of CPU cores exposed to the runner instance.
- `aws.ec2.cpu_options.threads_per_core`: Number of hardware threads exposed per CPU core.
- `aws.ec2.cpu_options.amd_sev_snp`: Enables or disables AMD SEV-SNP on supported instance types.
- `aws.ec2.cpu_options.nested_virtualization`: Enables or disables nested virtualization on supported instance types.
- `aws.ec2.placement`: EC2 placement configuration for runner instances.
- `aws.ec2.placement.affinity`: Host affinity setting.
- `aws.ec2.placement.availability_zone`: Availability Zone in which the instance is placed.
- `aws.ec2.placement.group_id`: Placement-group ID.
- `aws.ec2.placement.group_name`: Placement-group name.
- `aws.ec2.placement.host_id`: Dedicated Host ID.
- `aws.ec2.placement.host_resource_group_arn`: ARN of the host resource group used for placement.
- `aws.ec2.placement.spread_domain`: Spread-domain placement value.
- `aws.ec2.placement.tenancy`: Instance tenancy, such as `default`, `dedicated`, or `host`.
- `aws.ec2.placement.partition_number`: Placement-group partition number.
- `aws.ec2.license_specifications`: License Manager configurations added to the launch template.
- `aws.ec2.license_specifications[].license_configuration_arn`: ARN of a License Manager license configuration.
- `aws.ec2.associate_public_ipv4_address`: Associates a public IPv4 address with runner network interfaces.
- `aws.ec2.on_demand_failover_for_errors`: EC2 error codes that trigger an on-demand fallback after a Spot launch failure.
- `aws.ec2.scale_errors`: EC2 error codes treated as retryable scale-up failures.
- `aws.ec2.use_dedicated_host`: Enables the dedicated-host launch path, required for macOS runners. |
object({
aws = optional(object({
ec2 = optional(object({
ami = optional(object({
filter = optional(map(list(string)), { state = ["available"] })
owners = optional(list(string), ["amazon"])
id_ssm_parameter = optional(object({
arn = string
}), null)
kms_key = optional(object({
arn = string
}), null)
}), null)
vpc_id = string
subnet_ids = list(string)
overrides = optional(object({
name_runner = optional(string, "")
name_sg = optional(string, "")
}), {})
instance_profile = optional(object({
name = string
}), null)
instance_profile_path = optional(string, null)
binaries_syncer = optional(object({
enabled = optional(bool, true)
s3 = optional(object({
arn = string
id = string
key = string
}), null)
}), {})
block_device_mappings = optional(list(object({
delete_on_termination = optional(bool, true)
device_name = optional(string, "/dev/xvda")
encrypted = optional(bool, true)
iops = optional(number)
kms_key_id = optional(string)
snapshot_id = optional(string)
throughput = optional(number)
volume_initialization_rate = optional(number)
volume_size = number
volume_type = optional(string, "gp3")
})), [{ volume_size = 30 }])
ebs_optimized = optional(bool, false)
instance_target_capacity_type = optional(string, "spot")
instance_allocation_strategy = optional(string, "lowest-price")
instance_type_priorities = optional(map(number), null)
instance_max_spot_price = optional(string, null)
instance_types = list(string)
user_data = optional(object({
enabled = optional(bool, true)
template = optional(string, null)
content = optional(string, null)
pre_install = optional(string, "")
post_install = optional(string, "")
debug_logging_enabled = optional(bool, false)
}), {})
ssm_enabled = optional(bool, false)
create_service_linked_role_spot = optional(bool, false)
cloudwatch_agent = optional(object({
enabled = optional(bool, true)
config = optional(string, null)
}), {})
managed_security_group_enabled = optional(bool, true)
log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
key_name = optional(string, null)
additional_security_group_ids = optional(list(string), [])
detailed_monitoring_enabled = optional(bool, false)
egress_rules = optional(list(object({
cidr_blocks = list(string)
ipv6_cidr_blocks = list(string)
prefix_list_ids = list(string)
from_port = number
protocol = string
security_groups = list(string)
self = bool
to_port = number
description = string
})), [{
cidr_blocks = ["0.0.0.0/0"]
ipv6_cidr_blocks = ["::/0"]
prefix_list_ids = null
from_port = 0
protocol = "-1"
security_groups = null
self = null
to_port = 0
description = null
}])
tags = optional(map(string), {})
metadata_options = optional(object({
instance_metadata_tags = optional(string, "enabled")
http_endpoint = optional(string, "enabled")
http_tokens = optional(string, "required")
http_put_response_hop_limit = optional(number, 1)
}), {})
credit_specification = optional(string, null)
cpu_options = optional(object({
core_count = optional(number)
threads_per_core = optional(number)
amd_sev_snp = optional(string)
nested_virtualization = optional(string)
}), null)
placement = optional(object({
affinity = optional(string)
availability_zone = optional(string)
group_id = optional(string)
group_name = optional(string)
host_id = optional(string)
host_resource_group_arn = optional(string)
spread_domain = optional(string)
tenancy = optional(string)
partition_number = optional(number)
}), null)
license_specifications = optional(list(object({
license_configuration_arn = string
})), [])
associate_public_ipv4_address = optional(bool, false)
on_demand_failover_for_errors = optional(list(string), [])
scale_errors = optional(list(string), [
"UnfulfillableCapacity",
"MaxSpotInstanceCountExceeded",
"TargetCapacityLimitExceededException",
"RequestLimitExceeded",
"ResourceLimitExceeded",
"MaxSpotInstanceCountExceeded",
"MaxSpotFleetRequestCountExceeded",
"InsufficientInstanceCapacity",
"InsufficientCapacityOnHost",
])
use_dedicated_host = optional(bool, false)
}), null)
microvm = optional(object({
image_arn = string
image_version = optional(string, null)
ingress_network_connectors = optional(list(string), [])
egress_network_connectors = optional(list(string), [])
cloudwatch_agent = optional(object({
enabled = optional(bool, true)
config = optional(string, null)
}), {})
log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = string
log_class = optional(string, "STANDARD")
})), null)
environment_variables = optional(map(string), {})
iam = optional(object({
resource_arns = optional(object({
images = optional(list(string), null)
}), {})
additional_policy_json = optional(object({
scale_up = optional(string, null)
}), {})
managed_policies = optional(object({
scale_up = optional(object({
arn = string
}), null)
pool = optional(object({
arn = string
}), null)
}), {})
}), {})
}), null)
}), {})
})
| n/a | yes | +| [compute\_provider\_key](#input\_compute\_provider\_key) | Optional plan-known compute-provider dispatch key. Null discovers the key from the exactly one populated compute\_provider block. | `string` | `null` | no | +| [github](#input\_github) | GitHub API and runner-registration configuration.

- `app_parameters.key_base64`: Ordered Parameter Store references for GitHub App private keys.
- `app_parameters.id`: Ordered Parameter Store references for GitHub App IDs.
- `app_parameters.installation_id`: Ordered optional Parameter Store references for GitHub App installation IDs.
- `enterprise_server.url`: Optional GitHub Enterprise Server base URL. Null selects GitHub.com.
- `enterprise_server.ssl_verify`: Enables TLS certificate verification for GitHub Enterprise Server requests.
- `user_agent`: Optional User-Agent value added to GitHub API requests. |
object({
app_parameters = object({
key_base64 = list(map(string))
id = list(map(string))
installation_id = list(object({ name = string, arn = string }))
})
enterprise_server = optional(object({
url = optional(string, null)
ssl_verify = optional(bool, true)
}), {})
user_agent = optional(string, null)
})
| n/a | yes | +| [lambda](#input\_lambda) | Common Lambda substrate independent of the selected runner orchestration provider.

- `artifact.s3.bucket`: Optional shared S3 bucket containing component-owned Lambda artifacts. An orchestration provider selects its own object key and version; the bucket alone selects no artifact.
- `runtime`: Runtime used by the control-plane Lambda functions.
- `architecture`: Instruction-set architecture used by the control-plane Lambda functions. Supported values are `arm64` and `x86_64`.
- `subnet_ids`: Subnets used for Lambda VPC configuration.
- `security_group_ids`: Security groups used for Lambda VPC configuration.
- `tags`: Shared tags applied to Lambda function resources only. These override module-level `tags`; component `tags` override this map when keys conflict.
- `principals`: Additional principals allowed to assume the control-plane Lambda roles.
- `role.path`: IAM path for module-managed Lambda execution roles. Defaults to a path derived from `prefix`.
- `role.permissions_boundary`: Permissions-boundary ARN applied to module-managed Lambda execution roles. |
object({
artifact = optional(object({
s3 = optional(object({
bucket = optional(string, null)
}), {})
}), {})
runtime = optional(string, "nodejs24.x")
architecture = optional(string, "arm64")
subnet_ids = optional(list(string), [])
security_group_ids = optional(list(string), [])
tags = optional(map(string), {})
principals = optional(list(object({
type = string
identifiers = list(string)
})), [])
role = optional(object({
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
})
| `{}` | no | +| [observability](#input\_observability) | Logging, tracing, and metrics configuration for control-plane and provider resources.

- `logs.level`: Application log level supplied to the control-plane functions.
- `logs.retention_in_days`: CloudWatch Logs retention period.
- `logs.kms_key_id`: Optional KMS key ID or ARN used to encrypt CloudWatch log groups.
- `logs.class`: CloudWatch log-group class. Supported values are `STANDARD` and `INFREQUENT_ACCESS`.
- `logs.tags`: Shared tags for CloudWatch log groups. These override module-level `tags`; component `tags` override this map when keys conflict.
- `tracing.mode`: Optional Lambda active-tracing mode. Null disables X-Ray tracing configuration.
- `tracing.capture_http_requests`: Enables HTTP request capture in the tracing helper.
- `tracing.capture_error`: Enables error capture in the tracing helper.
- `metrics.enabled`: Enables module-emitted metrics.
- `metrics.namespace`: CloudWatch namespace used for emitted metrics.
- `metrics.metric.github_app_rate_limit.enabled`: Emits GitHub App rate-limit metrics.
- `metrics.metric.job_retry.enabled`: Emits job-retry metrics.
- `metrics.metric.spot_termination_warning.enabled`: Emits spot-termination warning metrics where supported. |
object({
logs = optional(object({
level = optional(string, "info")
retention_in_days = optional(number, 180)
kms_key_id = optional(string, null)
class = optional(string, "STANDARD")
tags = optional(map(string), {})
}), {})
tracing = optional(object({
mode = optional(string, null)
capture_http_requests = optional(bool, false)
capture_error = optional(bool, false)
}), {})
metrics = optional(object({
enabled = optional(bool, false)
namespace = optional(string, "GitHub Runners")
metric = optional(object({
github_app_rate_limit = optional(object({
enabled = optional(bool, true)
}), {})
job_retry = optional(object({
enabled = optional(bool, true)
}), {})
spot_termination_warning = optional(object({
enabled = optional(bool, true)
}), {})
}), {})
}), {})
})
| `{}` | no | +| [orchestration\_provider](#input\_orchestration\_provider) | Runner demand-orchestration provider configuration. Exactly one provider block must be non-null. Wrapper presence selects the provider and must therefore be known during planning; values inside the selected provider may remain unknown until apply.

- `webhook`: Selects the workflow-job webhook control plane. It owns runner lifecycle and capacity, the build queue reference, the runner-control artifact, scale-up, scale-down, scheduled pool, and optional job-retry controls. Future providers can be added as sibling blocks without moving this contract.
- `webhook.runner`: Runner lifecycle, boot timeout, and capacity settings owned by webhook orchestration.
- `webhook.runner.boot_time_in_minutes`: Expected runner boot duration used by scale-down and pool controls. The default is `5`.
- `webhook.runner.ephemeral`: Registers runners in ephemeral mode. The default is `false`.
- `webhook.runner.jit_config_enabled`: Explicitly enables or disables just-in-time configuration. The default is null, which follows `runner.ephemeral`.
- `webhook.runner.maximum_count`: Maximum number of runners managed for this runner configuration. The default is `3`.
- `webhook.github.organization_runners`: Registers runners at organization scope when true; otherwise registration is repository-scoped.
- `webhook.queue.build.arn`: ARN of the runner configuration's build queue.
- `webhook.queue.build.url`: URL of the runner configuration's build queue.
- `webhook.queue.kms_key_id`: Optional KMS key ARN encrypting the build queue. The default is null and is independent from the Parameter Store KMS key.
- `webhook.queue.tags`: Tags inherited by queue-related provider resources before component-specific overrides. The default is `{}`.
- `webhook.lambda.artifact`: Runner-control artifact shared by scale, pool, and job-retry components. Set at most one of `zip` or `s3`; no selection uses the packaged runner archive.
- `webhook.lambda.artifact.zip`: Optional local path to the runner-control Lambda archive. The default is null.
- `webhook.lambda.artifact.s3`: Optional S3 object selector in the common `lambda.artifact.s3.bucket`. Wrapper presence must be known during planning, selecting it requires a non-null common bucket, and the default is null.
- `webhook.lambda.artifact.s3.key`: Object key of the runner-control Lambda archive.
- `webhook.lambda.artifact.s3.object_version`: Optional object version of the runner-control Lambda archive. The default is null.
- `webhook.lambda.scale.up.memory_size`: Memory allocated to the scale-up Lambda in MB. The default is `512`.
- `webhook.lambda.scale.up.timeout`: Scale-up Lambda timeout in seconds. The default is `60`.
- `webhook.lambda.scale.up.reserved_concurrent_executions`: Reserved concurrency for scale-up. The default is `1`; use `-1` for unreserved concurrency.
- `webhook.lambda.scale.up.job_queued_check_enabled`: Enables queued-job verification before scaling. The default is null, which follows the resolved runner mode.
- `webhook.lambda.scale.up.event_source_mapping.batch_size`: Maximum build-queue records delivered per scale-up invocation. The default is `10`.
- `webhook.lambda.scale.up.event_source_mapping.maximum_batching_window_in_seconds`: Maximum batching window for build-queue records. The default is `0`.
- `webhook.lambda.scale.up.tags`: Tags applied within scale-up resource scopes after common provider tags. The default is `{}`.
- `webhook.lambda.scale.down.memory_size`: Memory allocated to the scale-down Lambda in MB. The default is `512`.
- `webhook.lambda.scale.down.timeout`: Scale-down Lambda timeout in seconds. The default is `60`.
- `webhook.lambda.scale.down.schedule_expression`: EventBridge schedule expression that invokes scale-down. The default is `cron(*/5 * * * ? *)`.
- `webhook.lambda.scale.down.minimum_running_time_in_minutes`: Optional minimum runner age before scale-down may terminate it. The default is null, which selects the operating-system default.
- `webhook.lambda.scale.down.idle_config`: Time-based desired idle-runner configurations. The default is `[]`.
- `webhook.lambda.scale.down.idle_config[].cron`: Cron expression identifying when the idle configuration applies.
- `webhook.lambda.scale.down.idle_config[].timeZone`: IANA time zone used to evaluate the cron expression.
- `webhook.lambda.scale.down.idle_config[].idleCount`: Number of idle runners retained during the matching period.
- `webhook.lambda.scale.down.idle_config[].evictionStrategy`: Selection strategy used when excess idle runners are removed. The default is `oldest_first`.
- `webhook.lambda.scale.down.tags`: Tags applied within scale-down resource scopes after common provider tags. The default is `{}`.
- `webhook.lambda.pool.memory_size`: Memory allocated to the pool Lambda in MB. The default is `512`.
- `webhook.lambda.pool.timeout`: Pool Lambda timeout in seconds. The default is `60`.
- `webhook.lambda.pool.reserved_concurrent_executions`: Reserved concurrency for the pool Lambda. The default is `1`; use `-1` for unreserved concurrency.
- `webhook.lambda.pool.config`: Scheduled target pool sizes. The default is `[]`, which disables the pool component.
- `webhook.lambda.pool.config[].schedule_expression`: Scheduler expression that activates the target size.
- `webhook.lambda.pool.config[].schedule_expression_timezone`: Optional IANA time zone used to evaluate the schedule.
- `webhook.lambda.pool.config[].size`: Desired number of runners for the schedule.
- `webhook.lambda.pool.include_busy_runners`: Includes busy runners when reconciling scheduled pool capacity. The default is `false`.
- `webhook.lambda.pool.runner_owner`: Optional GitHub organization or repository owner used for pooled runners. The default is null.
- `webhook.lambda.pool.tags`: Tags applied within pool resource scopes after common provider tags. The default is `{}`.
- `webhook.job_retry.enabled`: Creates the retry queue, Lambda function, event-source mapping, and related IAM resources. The default is `false`.
- `webhook.job_retry.delay_in_seconds`: Initial delay before a queued-job retry check. The default is `300`.
- `webhook.job_retry.delay_backoff`: Multiplier applied to the delay after each unsuccessful check. The default is `2`.
- `webhook.job_retry.max_attempts`: Maximum retry-check attempts before the message is no longer republished. The default is `1`.
- `webhook.job_retry.tags`: Tags applied within job-retry resource scopes after common provider tags. The default is `{}`.
- `webhook.job_retry.lambda.memory_size`: Memory allocated to the job-retry Lambda in MB. The default is `256`.
- `webhook.job_retry.lambda.reserved_concurrent_executions`: Reserved concurrency for job retry. The default is `1`; use `-1` for unreserved concurrency.
- `webhook.job_retry.lambda.timeout`: Job-retry Lambda timeout in seconds and visibility timeout for its retry queue. The default is `30`. |
object({
webhook = optional(object({
runner = optional(object({
boot_time_in_minutes = optional(number, 5)
ephemeral = optional(bool, false)
jit_config_enabled = optional(bool, null)
maximum_count = optional(number, 3)
}), {})
github = object({
organization_runners = bool
})
queue = object({
build = object({
arn = string
url = string
})
kms_key_id = optional(string, null)
tags = optional(map(string), {})
})
lambda = optional(object({
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
scale = optional(object({
up = optional(object({
memory_size = optional(number, 512)
timeout = optional(number, 60)
reserved_concurrent_executions = optional(number, 1)
job_queued_check_enabled = optional(bool, null)
event_source_mapping = optional(object({
batch_size = optional(number, 10)
maximum_batching_window_in_seconds = optional(number, 0)
}), {})
tags = optional(map(string), {})
}), {})
down = optional(object({
memory_size = optional(number, 512)
timeout = optional(number, 60)
schedule_expression = optional(string, "cron(*/5 * * * ? *)")
minimum_running_time_in_minutes = optional(number, null)
idle_config = optional(list(object({
cron = string
timeZone = string
idleCount = number
evictionStrategy = optional(string, "oldest_first")
})), [])
tags = optional(map(string), {})
}), {})
}), {})
pool = optional(object({
memory_size = optional(number, 512)
timeout = optional(number, 60)
reserved_concurrent_executions = optional(number, 1)
config = optional(list(object({
schedule_expression = string
schedule_expression_timezone = optional(string)
size = number
})), [])
include_busy_runners = optional(bool, false)
runner_owner = optional(string, null)
tags = optional(map(string), {})
}), {})
}), {})
job_retry = optional(object({
enabled = optional(bool, false)
delay_in_seconds = optional(number, 300)
delay_backoff = optional(number, 2)
max_attempts = optional(number, 1)
tags = optional(map(string), {})
lambda = optional(object({
memory_size = optional(number, 256)
reserved_concurrent_executions = optional(number, 1)
timeout = optional(number, 30)
}), {})
}), {})
}), null)
})
| n/a | yes | +| [prefix](#input\_prefix) | The prefix used for naming resources. | `string` | `"github-actions"` | no | +| [runner](#input\_runner) | Provider-neutral GitHub runner configuration.

- `os`: Runner operating system. Supported values are `linux`, `osx`, and `windows`.
- `architecture`: Runner distribution architecture, such as `x64` or `arm64`.
- `disable_default_labels`: Prevents GitHub's default self-hosted, operating-system, and architecture labels from being registered.
- `labels`: Complete set of labels supplied to the control-plane functions.
- `group_name`: GitHub runner group used during registration.
- `name_prefix`: Prefix added to registered runner names.
- `run_as_root`: Runs the runner service as root when supported by the compute provider.
- `run_as`: Operating-system user used when `run_as_root` is false.
- `auto_update_disabled`: Disables the GitHub runner application's built-in updater.
- `tags`: Additional tags for common runner resources, currently the managed runner IAM role. These override module-level `tags` with the same key.
- `hooks.job_started`: Script content installed as the runner job-started hook.
- `hooks.job_completed`: Script content installed as the runner job-completed hook.
- `iam.role.arn`: ARN of an externally managed runner role. When set, this module does not create or modify that role.
- `iam.managed_policy_arns`: Named managed-policy ARNs attached to the module-managed runner role.
- `iam.additional_trust_policy_json`: Optional IAM policy document merged with the selected compute provider's default runner-role trust policy.
- `iam.path`: IAM path for the module-managed runner role. Defaults to a path derived from `prefix`.
- `iam.permissions_boundary`: Permissions-boundary ARN for the module-managed runner role. |
object({
os = optional(string, "linux")
architecture = optional(string, "x64")
disable_default_labels = optional(bool, false)
labels = list(string)
group_name = optional(string, "Default")
name_prefix = optional(string, "")
run_as_root = optional(bool, false)
run_as = optional(string, "ec2-user")
auto_update_disabled = optional(bool, false)
tags = optional(map(string), {})
hooks = optional(object({
job_started = optional(string, "")
job_completed = optional(string, "")
}), {})
iam = optional(object({
role = optional(object({
arn = string
}), null)
managed_policy_arns = optional(map(string), {})
additional_trust_policy_json = optional(string, null)
path = optional(string, null)
permissions_boundary = optional(string, null)
}), {})
})
| n/a | yes | +| [ssm](#input\_ssm) | Parameter Store paths, encryption, tag scopes, and housekeeper configuration.

- `paths.root`: Root Parameter Store path for this runner configuration.
- `paths.tokens`: Path segment under `paths.root` used for registration tokens and just-in-time configuration.
- `paths.config`: Path segment under `paths.root` used for persistent runner configuration.
- `kms_key_id`: Optional customer-managed KMS key ARN used by control-plane IAM policies to decrypt shared GitHub App parameters. The ARN may be unknown until apply; null omits the provider-owned KMS statements. It does not select encryption for runtime-created runner parameters.
- `tags`: Shared tags for SSM-related resources. These override module-level `tags` and are inherited by parameter and housekeeper resources.
- `parameters.tags`: Tags for Terraform-managed runner configuration parameters and temporary parameters created by the scale-up and pool Lambdas. These override module-level and `ssm.tags` values with the same key.
- `housekeeper.schedule_expression`: EventBridge schedule expression that invokes the SSM housekeeper.
- `housekeeper.state`: EventBridge rule state, such as `ENABLED` or `DISABLED`.
- `housekeeper.tags`: Tags for housekeeper resources, including the Lambda function, log group, EventBridge rule, and IAM role. These override module-level, `ssm.tags`, shared Lambda, and shared log tags when keys conflict.
- `housekeeper.lambda.artifact`: Component-owned SSM-housekeeper artifact selection. Set at most one of `zip` or `s3`; when neither is selected, the module uses its packaged runner control-plane archive. This selector does not inherit an orchestration-provider artifact.
- `housekeeper.lambda.artifact.zip`: Optional local path to the SSM-housekeeper Lambda archive.
- `housekeeper.lambda.artifact.s3`: Optional object key and version in the shared `lambda.artifact.s3.bucket`. Selecting S3 requires that common bucket.
- `housekeeper.lambda.artifact.s3.key`: Object key of the SSM-housekeeper Lambda archive.
- `housekeeper.lambda.artifact.s3.object_version`: Optional object version of the SSM-housekeeper Lambda archive.
- `housekeeper.lambda.memory_size`: Memory allocated to the SSM housekeeper Lambda in MB.
- `housekeeper.lambda.timeout`: SSM housekeeper Lambda timeout in seconds.
- `housekeeper.config.tokenPath`: Parameter Store token path cleaned by the housekeeper. When omitted, the configured runner token path is used.
- `housekeeper.config.minimumDaysOld`: Minimum parameter age in days before deletion is allowed.
- `housekeeper.config.dryRun`: Reports eligible parameters without deleting them when true. |
object({
paths = object({
root = string
tokens = string
config = string
})
kms_key_id = optional(string, null)
tags = optional(map(string), {})
parameters = optional(object({
tags = optional(map(string), {})
}), {})
housekeeper = optional(object({
schedule_expression = optional(string, "rate(1 day)")
state = optional(string, "ENABLED")
tags = optional(map(string), {})
lambda = optional(object({
artifact = optional(object({
zip = optional(string, null)
s3 = optional(object({
key = string
object_version = optional(string, null)
}), null)
}), {})
memory_size = optional(number, 512)
timeout = optional(number, 60)
}), {})
config = optional(object({
tokenPath = optional(string)
minimumDaysOld = optional(number, 1)
dryRun = optional(bool, false)
}), {})
}), {})
})
| n/a | yes | +| [tags](#input\_tags) | Base tags added to taggable resources created by this runner configuration. Shared, component, and compute-provider tag maps override matching keys within their documented resource scopes. | `map(string)` | `{}` | no | + +## Outputs + +| Name | Description | +|------|-------------| +| [orchestration\_provider](#output\_orchestration\_provider) | Resources grouped under the selected runner orchestration provider. | +| [pool](#output\_pool) | Scheduled pool resources. Null when no pool configuration is supplied. | +| [provider](#output\_provider) | Provider-specific resources grouped under the selected provider namespace and type. | +| [runner](#output\_runner) | Common runner resources. The role is null when an external runner role is used. | +| [scale\_down](#output\_scale\_down) | Scale-down control-plane resources. Null when webhook orchestration is not configured. | +| [scale\_up](#output\_scale\_up) | Scale-up control-plane resources. Null when webhook orchestration is not configured. | + diff --git a/modules/runner-config/common-config.tf b/modules/runner-config/common-config.tf new file mode 100644 index 0000000000..660fcc60ab --- /dev/null +++ b/modules/runner-config/common-config.tf @@ -0,0 +1,44 @@ +# Shared control-plane configuration: naming, paths, tags, and normalized values. +locals { + common_tags = var.tags + runner_tags = merge(local.common_tags, var.runner.tags) + lambda_tags = merge(local.common_tags, var.lambda.tags) + observability_log_tags = merge(local.common_tags, var.observability.logs.tags) + + ssm_tags = merge(local.common_tags, var.ssm.tags) + ssm_parameter_tags = merge(local.ssm_tags, var.ssm.parameters.tags) + ssm_housekeeper_tags = merge(local.ssm_tags, var.ssm.housekeeper.tags) + ssm_housekeeper_lambda_tags = merge(local.lambda_tags, var.ssm.tags, var.ssm.housekeeper.tags) + ssm_housekeeper_log_tags = merge(local.observability_log_tags, var.ssm.tags, var.ssm.housekeeper.tags) + + lambda_role_path = var.lambda.role.path == null ? "/${var.prefix}/" : var.lambda.role.path + runner_role_path = var.runner.iam.path == null ? "/${var.prefix}/" : var.runner.iam.path + packaged_runners_lambda_zip = "${path.module}/../../lambdas/functions/control-plane/runners.zip" + ssm_housekeeper_artifact_s3_selected = ( + var.ssm.housekeeper.lambda.artifact.s3 != null + ) + ssm_housekeeper_artifact = { + zip = local.ssm_housekeeper_artifact_s3_selected ? null : coalesce( + var.ssm.housekeeper.lambda.artifact.zip, + local.packaged_runners_lambda_zip, + ) + s3 = { + bucket = local.ssm_housekeeper_artifact_s3_selected ? var.lambda.artifact.s3.bucket : null + key = try(var.ssm.housekeeper.lambda.artifact.s3.key, null) + object_version = try(var.ssm.housekeeper.lambda.artifact.s3.object_version, null) + } + } + kms_key_id = var.ssm.kms_key_id + token_path = "${var.ssm.paths.root}/${var.ssm.paths.tokens}" + arn_ssm_parameters_path_tokens = "arn:${var.aws_partition}:ssm:${var.aws_region}:${data.aws_caller_identity.current.account_id}:parameter${var.ssm.paths.root}/${var.ssm.paths.tokens}" + arn_ssm_parameters_path_config = "arn:${var.aws_partition}:ssm:${var.aws_region}:${data.aws_caller_identity.current.account_id}:parameter${var.ssm.paths.root}/${var.ssm.paths.config}" + + parameter_store_tags = jsonencode([ + for key, value in local.ssm_parameter_tags : { + Key = key + Value = value + } + ]) +} + +data "aws_caller_identity" "current" {} diff --git a/modules/runner-config/compute-provider.aws.ec2.tf b/modules/runner-config/compute-provider.aws.ec2.tf new file mode 100644 index 0000000000..5d053a73dc --- /dev/null +++ b/modules/runner-config/compute-provider.aws.ec2.tf @@ -0,0 +1,37 @@ +module "compute_aws_ec2_trust_policy" { + count = local.provider_key == "aws_ec2" ? 1 : 0 + source = "../compute-providers/aws/ec2/trust-policy" + + additional_trust_policy_json = var.runner.iam.additional_trust_policy_json +} + +module "compute_aws_ec2" { + count = local.provider_key == "aws_ec2" ? 1 : 0 + source = "../compute-providers/aws/ec2" + + aws_partition = var.aws_partition + aws_region = var.aws_region + prefix = var.prefix + tags = var.tags + + config = var.compute_provider.aws.ec2 + runner = merge(var.runner, { + iam = merge(var.runner.iam, { + role = local.runner_role + managed_policy_arns = local.common_runner_managed_policy_arns + }) + }) + github = var.github + ssm = var.ssm + observability = var.observability +} + +moved { + from = module.compute_ec2_trust_policy + to = module.compute_aws_ec2_trust_policy +} + +moved { + from = module.compute_ec2 + to = module.compute_aws_ec2 +} diff --git a/modules/runner-config/compute-provider.aws.microvm.tf b/modules/runner-config/compute-provider.aws.microvm.tf new file mode 100644 index 0000000000..bdfb5a8f30 --- /dev/null +++ b/modules/runner-config/compute-provider.aws.microvm.tf @@ -0,0 +1,27 @@ +module "compute_aws_microvm_trust_policy" { + count = local.provider_key == "aws_microvm" ? 1 : 0 + source = "../compute-providers/aws/microvm/trust-policy" + + additional_trust_policy_json = var.runner.iam.additional_trust_policy_json +} + +module "compute_aws_microvm" { + count = local.provider_key == "aws_microvm" ? 1 : 0 + source = "../compute-providers/aws/microvm" + + aws_partition = var.aws_partition + aws_region = var.aws_region + prefix = var.prefix + tags = var.tags + + config = var.compute_provider.aws.microvm + runner = merge(var.runner, { + iam = merge(var.runner.iam, { + role = local.runner_role + managed_policy_arns = local.common_runner_managed_policy_arns + }) + }) + github = var.github + ssm = var.ssm + observability = var.observability +} diff --git a/modules/runner-config/compute-provider.tf b/modules/runner-config/compute-provider.tf new file mode 100644 index 0000000000..c768c47c22 --- /dev/null +++ b/modules/runner-config/compute-provider.tf @@ -0,0 +1,33 @@ +locals { + compute_providers = { + aws_ec2 = var.compute_provider.aws.ec2 + aws_microvm = var.compute_provider.aws.microvm + } + + discovered_provider_key = one([ + for provider_key, provider_config in local.compute_providers : provider_key + if provider_config != null + ]) + provider_key = var.compute_provider_key != null ? var.compute_provider_key : local.discovered_provider_key + + provider_types = { + aws_ec2 = "ec2" + aws_microvm = "microvm" + } + + provider_type = local.provider_types[local.provider_key] + + provider_assume_role_policies = { + aws_ec2 = try(module.compute_aws_ec2_trust_policy[0].assume_role_policy, null) + aws_microvm = try(module.compute_aws_microvm_trust_policy[0].assume_role_policy, null) + } + + provider_assume_role_policy = local.provider_assume_role_policies[local.provider_key] + + provider_contracts = { + aws_ec2 = one(module.compute_aws_ec2[*].provider) + aws_microvm = one(module.compute_aws_microvm[*].provider) + } + + provider_contract = local.provider_contracts[local.provider_key] +} diff --git a/modules/runner-config/orchestration-provider.tf b/modules/runner-config/orchestration-provider.tf new file mode 100644 index 0000000000..25994beaba --- /dev/null +++ b/modules/runner-config/orchestration-provider.tf @@ -0,0 +1,73 @@ +locals { + orchestration_providers = { + for provider_type, provider_config in var.orchestration_provider : provider_type => provider_config + if provider_config != null + } + + orchestration_provider_type = one(keys(local.orchestration_providers)) + + orchestration_provider_enabled = { + webhook = local.orchestration_provider_type == "webhook" + } + + orchestration_provider_runner_lifecycle = { + webhook = one(module.orchestration_webhook[*].runner_lifecycle) + }[local.orchestration_provider_type] +} + +module "orchestration_webhook" { + source = "../orchestration-providers/webhook" + count = local.orchestration_provider_enabled.webhook ? 1 : 0 + + aws_partition = var.aws_partition + prefix = var.prefix + tags = var.tags + + config = var.orchestration_provider.webhook + runner = var.runner + github = var.github + lambda = { + artifact = var.lambda.artifact + runtime = var.lambda.runtime + architecture = var.lambda.architecture + subnet_ids = var.lambda.subnet_ids + security_group_ids = var.lambda.security_group_ids + tags = var.lambda.tags + role = { + path = local.lambda_role_path + permissions_boundary = var.lambda.role.permissions_boundary + principals = var.lambda.principals + } + } + ssm = { + token_path = local.token_path + token_path_arn = local.arn_ssm_parameters_path_tokens + config_path = "${var.ssm.paths.root}/${var.ssm.paths.config}" + config_path_arn = local.arn_ssm_parameters_path_config + kms_key_id = local.kms_key_id + parameter_store_tags = local.parameter_store_tags + } + observability = var.observability + + runner_provider = { + type = local.provider_type + scale_up = { + environment_variables = local.provider_contract.environment_variables.scale_up + iam_policy_json = local.provider_contract.policies.scale_up.iam_policy_json + additional_iam_policy_json = local.provider_contract.policies.scale_up.additional_iam_policy_json + managed_policy = local.provider_contract.policies.scale_up.managed_policy_enabled ? { + arn = local.provider_contract.policies.scale_up.managed_policy_arn + } : null + } + scale_down = { + environment_variables = local.provider_contract.environment_variables.scale_down + iam_policy_json = local.provider_contract.policies.scale_down.iam_policy_json + } + pool = { + environment_variables = local.provider_contract.environment_variables.pool + iam_policy_json = local.provider_contract.policies.pool.iam_policy_json + managed_policy_enabled = local.provider_contract.policies.pool.managed_policy_enabled + managed_policy_arn = local.provider_contract.policies.pool.managed_policy_arn + } + } +} diff --git a/modules/runner-config/outputs.tf b/modules/runner-config/outputs.tf new file mode 100644 index 0000000000..93582279da --- /dev/null +++ b/modules/runner-config/outputs.tf @@ -0,0 +1,43 @@ +output "runner" { + description = "Common runner resources. The role is null when an external runner role is used." + value = { + role = one(aws_iam_role.runner[*]) + } +} + +output "scale_up" { + description = "Scale-up control-plane resources. Null when webhook orchestration is not configured." + value = one(module.orchestration_webhook[*].scale_up) +} + +output "scale_down" { + description = "Scale-down control-plane resources. Null when webhook orchestration is not configured." + value = one(module.orchestration_webhook[*].scale_down) +} + +output "pool" { + description = "Scheduled pool resources. Null when no pool configuration is supplied." + value = one(module.orchestration_webhook[*].pool) +} + +output "orchestration_provider" { + description = "Resources grouped under the selected runner orchestration provider." + value = { + webhook = local.orchestration_provider_enabled.webhook ? { + scale_up = one(module.orchestration_webhook[*].scale_up) + scale_down = one(module.orchestration_webhook[*].scale_down) + pool = one(module.orchestration_webhook[*].pool) + job_retry = one(module.orchestration_webhook[*].job_retry) + } : null + } +} + +output "provider" { + description = "Provider-specific resources grouped under the selected provider namespace and type." + value = { + aws = { + ec2 = local.provider_key == "aws_ec2" ? local.provider_contract.resources : null + microvm = local.provider_key == "aws_microvm" ? local.provider_contract.resources : null + } + } +} diff --git a/modules/runner-config/runner-role.tf b/modules/runner-config/runner-role.tf new file mode 100644 index 0000000000..6baa1e4206 --- /dev/null +++ b/modules/runner-config/runner-role.tf @@ -0,0 +1,48 @@ +locals { + # Role ownership belongs to the common runner configuration. The selected trust-policy + # submodule supplies the assume-role document, while the full compute provider + # supplies permissions after the role has been resolved. + create_runner_role = var.runner.iam.role == null + + runner_role = { + arn = local.create_runner_role ? one(aws_iam_role.runner[*].arn) : var.runner.iam.role.arn + name = local.create_runner_role ? one(aws_iam_role.runner[*].name) : basename(var.runner.iam.role.arn) + managed = local.create_runner_role + } + + common_runner_managed_policy_arns = merge( + { + for policy_name, policy_arn in var.runner.iam.managed_policy_arns : + "user-${policy_name}" => policy_arn + }, + var.observability.tracing.mode != null ? { + xray = "arn:${var.aws_partition}:iam::aws:policy/AWSXRayDaemonWriteAccess" + } : {}, + ) + + provider_runner_policies = local.provider_contract.policies.runner +} + +resource "aws_iam_role" "runner" { + count = local.create_runner_role ? 1 : 0 + name = "${substr("${var.prefix}-runner", 0, 54)}-${substr(md5("${var.prefix}-runner"), 0, 8)}" + assume_role_policy = local.provider_assume_role_policy + path = local.runner_role_path + permissions_boundary = var.runner.iam.permissions_boundary + tags = local.runner_tags +} + +resource "aws_iam_role_policy" "runner_provider" { + for_each = local.create_runner_role ? local.provider_runner_policies.inline_policies : {} + + name = each.value.name + role = aws_iam_role.runner[0].name + policy = each.value.policy_json +} + +resource "aws_iam_role_policy_attachment" "runner" { + for_each = local.create_runner_role ? local.provider_runner_policies.managed_policy_arns : {} + + role = aws_iam_role.runner[0].name + policy_arn = each.value +} diff --git a/modules/runner-config/runner-ssm-parameters.tf b/modules/runner-config/runner-ssm-parameters.tf new file mode 100644 index 0000000000..1d97c908a8 --- /dev/null +++ b/modules/runner-config/runner-ssm-parameters.tf @@ -0,0 +1,28 @@ +# Shared runner configuration stored in SSM Parameter Store. +resource "aws_ssm_parameter" "runner_agent_mode" { + name = "${var.ssm.paths.root}/${var.ssm.paths.config}/agent_mode" + type = "String" + value = local.orchestration_provider_runner_lifecycle.ephemeral ? "ephemeral" : "persistent" + tags = local.ssm_parameter_tags +} + +resource "aws_ssm_parameter" "disable_default_labels" { + name = "${var.ssm.paths.root}/${var.ssm.paths.config}/disable_default_labels" + type = "String" + value = var.runner.disable_default_labels + tags = local.ssm_parameter_tags +} + +resource "aws_ssm_parameter" "jit_config_enabled" { + name = "${var.ssm.paths.root}/${var.ssm.paths.config}/enable_jit_config" + type = "String" + value = local.orchestration_provider_runner_lifecycle.jit_config_enabled + tags = local.ssm_parameter_tags +} + +resource "aws_ssm_parameter" "token_path" { + name = "${var.ssm.paths.root}/${var.ssm.paths.config}/token_path" + type = "String" + value = "${var.ssm.paths.root}/${var.ssm.paths.tokens}" + tags = local.ssm_parameter_tags +} diff --git a/modules/runner-config/ssm-housekeeper.tf b/modules/runner-config/ssm-housekeeper.tf new file mode 100644 index 0000000000..5bb31bb7b5 --- /dev/null +++ b/modules/runner-config/ssm-housekeeper.tf @@ -0,0 +1,57 @@ +locals { + ssm_housekeeper_token_path = coalesce(var.ssm.housekeeper.config.tokenPath, local.token_path) + ssm_housekeeper_parameter_path_arn = ( + "arn:${var.aws_partition}:ssm:${var.aws_region}:${data.aws_caller_identity.current.account_id}:parameter${local.ssm_housekeeper_token_path}*" + ) +} + +module "ssm_housekeeper" { + source = "./ssm-housekeeper" + + config = { + prefix = var.prefix + aws_partition = var.aws_partition + schedule = { + expression = var.ssm.housekeeper.schedule_expression + state = var.ssm.housekeeper.state + } + cleanup = { + token_path = local.ssm_housekeeper_token_path + parameter_path_arn = local.ssm_housekeeper_parameter_path_arn + minimum_days_old = var.ssm.housekeeper.config.minimumDaysOld + dry_run = var.ssm.housekeeper.config.dryRun + } + lambda = { + # The housekeeper resolves only its component-owned selector and never + # inherits the selected orchestration provider's runner-control artifact. + artifact = local.ssm_housekeeper_artifact + runtime = var.lambda.runtime + architecture = var.lambda.architecture + memory_size = var.ssm.housekeeper.lambda.memory_size + timeout = var.ssm.housekeeper.lambda.timeout + vpc = { + subnet_ids = var.lambda.subnet_ids + security_group_ids = var.lambda.security_group_ids + } + role = { + path = local.lambda_role_path + permissions_boundary = var.lambda.role.permissions_boundary + principals = var.lambda.principals + } + } + observability = { + logs = { + level = var.observability.logs.level + retention_in_days = var.observability.logs.retention_in_days + kms_key_id = var.observability.logs.kms_key_id + class = var.observability.logs.class + } + tracing = var.observability.tracing + } + tags = { + resources = local.ssm_housekeeper_tags + lambda = local.ssm_housekeeper_lambda_tags + log_group = local.ssm_housekeeper_log_tags + } + } +} diff --git a/modules/runner-config/ssm-housekeeper/README.md b/modules/runner-config/ssm-housekeeper/README.md new file mode 100644 index 0000000000..5f5d1ad166 --- /dev/null +++ b/modules/runner-config/ssm-housekeeper/README.md @@ -0,0 +1,57 @@ +# SSM housekeeper module + +> This module is treated as an internal module; breaking changes do not trigger a major release bump. + +This provider-neutral child module owns the Lambda function, EventBridge schedule, IAM policies, and CloudWatch log group used to remove expired runner registration parameters from Parameter Store. + +The module is an implementation detail of the experimental runner configuration. It is composed by `runner-config` and is not intended to be called directly. + + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.3.0 | +| [aws](#requirement\_aws) | >= 6.33 | + +## Providers + +| Name | Version | +|------|---------| +| [aws](#provider\_aws) | >= 6.33 | + +## Modules + +No modules. + +## Resources + +| Name | Type | +|------|------| +| [aws_cloudwatch_event_rule.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/cloudwatch_event_rule) | resource | +| [aws_cloudwatch_event_target.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/cloudwatch_event_target) | resource | +| [aws_cloudwatch_log_group.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/cloudwatch_log_group) | resource | +| [aws_iam_role.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role) | resource | +| [aws_iam_role_policy.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy) | resource | +| [aws_iam_role_policy.ssm_housekeeper_logging](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy) | resource | +| [aws_iam_role_policy.ssm_housekeeper_xray](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy) | resource | +| [aws_iam_role_policy_attachment.ssm_housekeeper_vpc_execution_role](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/iam_role_policy_attachment) | resource | +| [aws_lambda_function.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/lambda_function) | resource | +| [aws_lambda_permission.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/lambda_permission) | resource | +| [aws_iam_policy_document.lambda_assume_role](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.lambda_xray](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.ssm_housekeeper](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | +| [aws_iam_policy_document.ssm_housekeeper_logging](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/iam_policy_document) | data source | + +## Inputs + +| Name | Description | Type | Default | Required | +|------|-------------|------|---------|:--------:| +| [config](#input\_config) | Provider-neutral SSM housekeeper configuration assembled by runner-config.

- `prefix`: Prefix used to name the housekeeper resources.
- `aws_partition`: AWS partition used to construct IAM policy ARNs.
- `schedule.expression`: EventBridge schedule expression that invokes the housekeeper.
- `schedule.state`: State of the EventBridge rule.
- `cleanup.token_path`: Parameter Store token path supplied to the Lambda.
- `cleanup.parameter_path_arn`: IAM resource ARN matching `cleanup.token_path`.
- `cleanup.minimum_days_old`: Minimum parameter age before deletion.
- `cleanup.dry_run`: Reports eligible parameters without deleting them when true.
- `lambda.artifact.zip`: Resolved local control-plane archive.
- `lambda.artifact.s3.bucket`: Optional S3 bucket containing the Lambda archive.
- `lambda.artifact.s3.key`: Object key of the Lambda archive.
- `lambda.artifact.s3.object_version`: Optional object version of the Lambda archive.
- `lambda.runtime`: Runtime used by the housekeeper Lambda.
- `lambda.architecture`: Instruction-set architecture used by the housekeeper Lambda.
- `lambda.memory_size`: Memory allocated to the housekeeper Lambda.
- `lambda.timeout`: Housekeeper Lambda timeout in seconds.
- `lambda.vpc.subnet_ids`: Subnets used for Lambda VPC configuration.
- `lambda.vpc.security_group_ids`: Security groups used for Lambda VPC configuration.
- `lambda.role.path`: IAM path used for the housekeeper Lambda role.
- `lambda.role.permissions_boundary`: Optional permissions boundary for the housekeeper role.
- `lambda.role.principals`: Additional principals allowed to assume the housekeeper Lambda role.
- `observability.logs`: Logging level, retention, encryption, and log-class configuration.
- `observability.tracing`: Lambda X-Ray and tracing-helper configuration.
- `tags.resources`: Tags for the housekeeper role and EventBridge rule.
- `tags.lambda`: Tags for the housekeeper Lambda function.
- `tags.log_group`: Tags for the housekeeper log group. |
object({
prefix = string
aws_partition = string
schedule = object({
expression = string
state = string
})
cleanup = object({
token_path = string
parameter_path_arn = string
minimum_days_old = number
dry_run = bool
})
lambda = object({
artifact = object({
zip = string
s3 = object({
bucket = optional(string, null)
key = optional(string, null)
object_version = optional(string, null)
})
})
runtime = string
architecture = string
memory_size = number
timeout = number
vpc = object({
subnet_ids = list(string)
security_group_ids = list(string)
})
role = object({
path = string
permissions_boundary = optional(string, null)
principals = optional(list(object({
type = string
identifiers = list(string)
})), [])
})
})
observability = object({
logs = object({
level = string
retention_in_days = number
kms_key_id = optional(string, null)
class = string
})
tracing = object({
mode = optional(string, null)
capture_http_requests = bool
capture_error = bool
})
})
tags = object({
resources = map(string)
lambda = map(string)
log_group = map(string)
})
})
| n/a | yes | + +## Outputs + +| Name | Description | +|------|-------------| +| [housekeeper](#output\_housekeeper) | SSM housekeeper Lambda resources. | + diff --git a/modules/runner-config/ssm-housekeeper/iam-policies.tf b/modules/runner-config/ssm-housekeeper/iam-policies.tf new file mode 100644 index 0000000000..8d3bab2865 --- /dev/null +++ b/modules/runner-config/ssm-housekeeper/iam-policies.tf @@ -0,0 +1,58 @@ +data "aws_iam_policy_document" "lambda_assume_role" { + statement { + actions = ["sts:AssumeRole"] + + principals { + type = "Service" + identifiers = ["lambda.amazonaws.com"] + } + + dynamic "principals" { + for_each = var.config.lambda.role.principals + + content { + type = principals.value.type + identifiers = principals.value.identifiers + } + } + } +} + +data "aws_iam_policy_document" "lambda_xray" { + count = var.config.observability.tracing.mode != null ? 1 : 0 + + # AWS X-Ray trace APIs do not support resource-level permissions. + statement { + sid = "AllowXRay" + effect = "Allow" + actions = [ + "xray:BatchGetTraces", + "xray:GetTraceSummaries", + "xray:PutTelemetryRecords", + "xray:PutTraceSegments", + ] + resources = ["*"] + } +} + +data "aws_iam_policy_document" "ssm_housekeeper" { + statement { + effect = "Allow" + actions = [ + "ssm:DeleteParameter", + "ssm:GetParametersByPath", + ] + resources = [var.config.cleanup.parameter_path_arn] + } +} + +data "aws_iam_policy_document" "ssm_housekeeper_logging" { + statement { + effect = "Allow" + actions = [ + "logs:CreateLogStream", + "logs:PutLogEvents", + ] + resources = ["${aws_cloudwatch_log_group.ssm_housekeeper.arn}*"] + } +} diff --git a/modules/runner-config/ssm-housekeeper/outputs.tf b/modules/runner-config/ssm-housekeeper/outputs.tf new file mode 100644 index 0000000000..064f5a1ab1 --- /dev/null +++ b/modules/runner-config/ssm-housekeeper/outputs.tf @@ -0,0 +1,8 @@ +output "housekeeper" { + description = "SSM housekeeper Lambda resources." + value = { + lambda = aws_lambda_function.ssm_housekeeper + log_group = aws_cloudwatch_log_group.ssm_housekeeper + role = aws_iam_role.ssm_housekeeper + } +} diff --git a/modules/runner-config/ssm-housekeeper/ssm-housekeeper.tf b/modules/runner-config/ssm-housekeeper/ssm-housekeeper.tf new file mode 100644 index 0000000000..bcafed201a --- /dev/null +++ b/modules/runner-config/ssm-housekeeper/ssm-housekeeper.tf @@ -0,0 +1,119 @@ +locals { + vpc_enabled = ( + length(var.config.lambda.vpc.subnet_ids) > 0 && + length(var.config.lambda.vpc.security_group_ids) > 0 + ) + + cleanup_config = { + tokenPath = var.config.cleanup.token_path + minimumDaysOld = var.config.cleanup.minimum_days_old + dryRun = var.config.cleanup.dry_run + } +} + +resource "aws_lambda_function" "ssm_housekeeper" { + s3_bucket = var.config.lambda.artifact.s3.bucket + s3_key = var.config.lambda.artifact.s3.key + s3_object_version = var.config.lambda.artifact.s3.object_version + filename = var.config.lambda.artifact.s3.bucket == null ? var.config.lambda.artifact.zip : null + source_code_hash = var.config.lambda.artifact.s3.bucket == null ? filebase64sha256(var.config.lambda.artifact.zip) : null + function_name = "${var.config.prefix}-ssm-housekeeper" + role = aws_iam_role.ssm_housekeeper.arn + handler = "index.ssmHousekeeper" + runtime = var.config.lambda.runtime + timeout = var.config.lambda.timeout + tags = var.config.tags.lambda + memory_size = var.config.lambda.memory_size + architectures = [var.config.lambda.architecture] + + environment { + variables = { + ENVIRONMENT = var.config.prefix + LOG_LEVEL = upper(var.config.observability.logs.level) + SSM_CLEANUP_CONFIG = jsonencode(local.cleanup_config) + POWERTOOLS_SERVICE_NAME = "${var.config.prefix}-ssm-housekeeper" + POWERTOOLS_TRACE_ENABLED = var.config.observability.tracing.mode != null + POWERTOOLS_TRACER_CAPTURE_HTTPS_REQUESTS = var.config.observability.tracing.capture_http_requests + POWERTOOLS_TRACER_CAPTURE_ERROR = var.config.observability.tracing.capture_error + } + } + + dynamic "vpc_config" { + for_each = local.vpc_enabled ? [true] : [] + + content { + security_group_ids = var.config.lambda.vpc.security_group_ids + subnet_ids = var.config.lambda.vpc.subnet_ids + } + } + + dynamic "tracing_config" { + for_each = var.config.observability.tracing.mode != null ? [true] : [] + + content { + mode = var.config.observability.tracing.mode + } + } +} + +resource "aws_cloudwatch_log_group" "ssm_housekeeper" { + name = "/aws/lambda/${aws_lambda_function.ssm_housekeeper.function_name}" + retention_in_days = var.config.observability.logs.retention_in_days + kms_key_id = var.config.observability.logs.kms_key_id + log_group_class = var.config.observability.logs.class + tags = var.config.tags.log_group +} + +resource "aws_cloudwatch_event_rule" "ssm_housekeeper" { + name = "${var.config.prefix}-ssm-housekeeper" + schedule_expression = var.config.schedule.expression + state = var.config.schedule.state + tags = var.config.tags.resources +} + +resource "aws_cloudwatch_event_target" "ssm_housekeeper" { + rule = aws_cloudwatch_event_rule.ssm_housekeeper.name + arn = aws_lambda_function.ssm_housekeeper.arn +} + +resource "aws_lambda_permission" "ssm_housekeeper" { + statement_id = "AllowExecutionFromCloudWatch" + action = "lambda:InvokeFunction" + function_name = aws_lambda_function.ssm_housekeeper.function_name + principal = "events.amazonaws.com" + source_arn = aws_cloudwatch_event_rule.ssm_housekeeper.arn +} + +resource "aws_iam_role" "ssm_housekeeper" { + name = "${substr("${var.config.prefix}-ssm-hk-lambda", 0, 54)}-${substr(md5("${var.config.prefix}-ssm-hk-lambda"), 0, 8)}" + description = "Lambda role for SSM Housekeeper (${var.config.prefix})" + assume_role_policy = data.aws_iam_policy_document.lambda_assume_role.json + path = var.config.lambda.role.path + permissions_boundary = var.config.lambda.role.permissions_boundary + tags = var.config.tags.resources +} + +resource "aws_iam_role_policy" "ssm_housekeeper" { + name = "ssm-policy" + role = aws_iam_role.ssm_housekeeper.name + policy = data.aws_iam_policy_document.ssm_housekeeper.json +} + +resource "aws_iam_role_policy" "ssm_housekeeper_logging" { + name = "logging-policy" + role = aws_iam_role.ssm_housekeeper.name + policy = data.aws_iam_policy_document.ssm_housekeeper_logging.json +} + +resource "aws_iam_role_policy_attachment" "ssm_housekeeper_vpc_execution_role" { + count = local.vpc_enabled ? 1 : 0 + role = aws_iam_role.ssm_housekeeper.name + policy_arn = "arn:${var.config.aws_partition}:iam::aws:policy/service-role/AWSLambdaVPCAccessExecutionRole" +} + +resource "aws_iam_role_policy" "ssm_housekeeper_xray" { + count = var.config.observability.tracing.mode != null ? 1 : 0 + name = "xray-policy" + policy = data.aws_iam_policy_document.lambda_xray[0].json + role = aws_iam_role.ssm_housekeeper.name +} diff --git a/modules/runner-config/ssm-housekeeper/tests/ssm-housekeeper.tftest.hcl b/modules/runner-config/ssm-housekeeper/tests/ssm-housekeeper.tftest.hcl new file mode 100644 index 0000000000..bac30c6752 --- /dev/null +++ b/modules/runner-config/ssm-housekeeper/tests/ssm-housekeeper.tftest.hcl @@ -0,0 +1,263 @@ +mock_provider "aws" { + mock_data "aws_iam_policy_document" { + defaults = { + json = "{\"Version\":\"2012-10-17\",\"Statement\":[]}" + } + } + + mock_resource "aws_iam_role" { + defaults = { + arn = "arn:aws:iam::123456789012:role/ssm-housekeeper-test" + } + } + + mock_resource "aws_lambda_function" { + defaults = { + arn = "arn:aws:lambda:eu-west-1:123456789012:function:ssm-housekeeper-test" + } + } + + mock_resource "aws_cloudwatch_event_rule" { + defaults = { + arn = "arn:aws:events:eu-west-1:123456789012:rule/ssm-housekeeper-test" + } + } + + mock_resource "aws_cloudwatch_log_group" { + defaults = { + arn = "arn:aws:logs:eu-west-1:123456789012:log-group:/aws/lambda/ssm-housekeeper-test" + } + } +} + +variables { + config = { + prefix = "ssm-housekeeper-test" + aws_partition = "aws-us-gov" + schedule = { + expression = "rate(6 hours)" + state = "DISABLED" + } + cleanup = { + token_path = "/custom/runner/tokens" + parameter_path_arn = "arn:aws-us-gov:ssm:us-gov-west-1:123456789012:parameter/custom/runner/tokens*" + minimum_days_old = 7 + dry_run = true + } + lambda = { + artifact = { + zip = "unused-with-s3.zip" + s3 = { + bucket = "lambda-artifacts" + key = "control-plane/runners.zip" + object_version = "version-1" + } + } + runtime = "nodejs24.x" + architecture = "arm64" + memory_size = 384 + timeout = 45 + vpc = { + subnet_ids = [] + security_group_ids = [] + } + role = { + path = "/runner-config/" + permissions_boundary = null + principals = [{ + type = "AWS" + identifiers = ["arn:aws-us-gov:iam::123456789012:role/local-testing"] + }] + } + } + observability = { + logs = { + level = "debug" + retention_in_days = 30 + kms_key_id = null + class = "STANDARD" + } + tracing = { + mode = null + capture_http_requests = false + capture_error = false + } + } + tags = { + resources = { + Scope = "housekeeper" + } + lambda = { + Scope = "housekeeper" + Resource = "lambda" + } + log_group = { + Scope = "housekeeper" + Resource = "logs" + } + } + } +} + +run "configures_schedule_cleanup_and_outputs" { + command = plan + + assert { + condition = ( + length(data.aws_iam_policy_document.lambda_assume_role.statement[0].principals) == 2 && + contains(data.aws_iam_policy_document.lambda_assume_role.statement[0].principals[*].type, "AWS") + ) + error_message = "The housekeeper Lambda trust policy must include configured additional principals." + } + + assert { + condition = ( + aws_cloudwatch_event_rule.ssm_housekeeper.schedule_expression == "rate(6 hours)" && + aws_cloudwatch_event_rule.ssm_housekeeper.state == "DISABLED" + ) + error_message = "The housekeeper EventBridge rule must use the configured schedule and state." + } + + assert { + condition = ( + jsondecode(aws_lambda_function.ssm_housekeeper.environment[0].variables["SSM_CLEANUP_CONFIG"]).tokenPath == "/custom/runner/tokens" && + jsondecode(aws_lambda_function.ssm_housekeeper.environment[0].variables["SSM_CLEANUP_CONFIG"]).minimumDaysOld == 7 && + jsondecode(aws_lambda_function.ssm_housekeeper.environment[0].variables["SSM_CLEANUP_CONFIG"]).dryRun + ) + error_message = "The Lambda cleanup configuration must preserve the configured path override, age, and dry-run setting." + } + + assert { + condition = contains( + data.aws_iam_policy_document.ssm_housekeeper.statement[0].resources, + "arn:aws-us-gov:ssm:us-gov-west-1:123456789012:parameter/custom/runner/tokens*", + ) + error_message = "The housekeeper IAM policy must authorize the same overridden Parameter Store path supplied to the Lambda." + } + + assert { + condition = toset(keys(output.housekeeper)) == toset(["lambda", "log_group", "role"]) + error_message = "The module must expose Lambda, log-group, and role resources through one nested housekeeper output." + } + + assert { + condition = ( + output.housekeeper.lambda.tags == tomap({ + Scope = "housekeeper" + Resource = "lambda" + }) && + output.housekeeper.log_group.tags == tomap({ + Scope = "housekeeper" + Resource = "logs" + }) && + output.housekeeper.role.tags == tomap({ + Scope = "housekeeper" + }) + ) + error_message = "Each nested output resource must retain its resolved component tags." + } + + assert { + condition = ( + length(aws_lambda_function.ssm_housekeeper.vpc_config) == 0 && + length(aws_iam_role_policy_attachment.ssm_housekeeper_vpc_execution_role) == 0 && + length(aws_lambda_function.ssm_housekeeper.tracing_config) == 0 && + length(aws_iam_role_policy.ssm_housekeeper_xray) == 0 + ) + error_message = "Empty VPC configuration and disabled tracing must not create their optional Lambda or IAM configuration." + } +} + +run "enables_vpc_and_xray_together" { + command = plan + + variables { + config = { + prefix = "ssm-housekeeper-vpc-test" + aws_partition = "aws-us-gov" + schedule = { + expression = "rate(1 day)" + state = "ENABLED" + } + cleanup = { + token_path = "/github-runner/tokens" + parameter_path_arn = "arn:aws-us-gov:ssm:us-gov-west-1:123456789012:parameter/github-runner/tokens*" + minimum_days_old = 1 + dry_run = false + } + lambda = { + artifact = { + zip = "unused-with-s3.zip" + s3 = { + bucket = "lambda-artifacts" + key = "control-plane/runners.zip" + } + } + runtime = "nodejs24.x" + architecture = "arm64" + memory_size = 512 + timeout = 60 + vpc = { + subnet_ids = ["subnet-12345678"] + security_group_ids = ["sg-12345678"] + } + role = { + path = "/runner-config/" + permissions_boundary = null + } + } + observability = { + logs = { + level = "info" + retention_in_days = 14 + kms_key_id = null + class = "STANDARD" + } + tracing = { + mode = "Active" + capture_http_requests = true + capture_error = true + } + } + tags = { + resources = {} + lambda = {} + log_group = {} + } + } + } + + assert { + condition = ( + length(aws_lambda_function.ssm_housekeeper.vpc_config) == 1 && + aws_lambda_function.ssm_housekeeper.vpc_config[0].subnet_ids == toset(["subnet-12345678"]) && + aws_lambda_function.ssm_housekeeper.vpc_config[0].security_group_ids == toset(["sg-12345678"]) && + length(aws_iam_role_policy_attachment.ssm_housekeeper_vpc_execution_role) == 1 && + aws_iam_role_policy_attachment.ssm_housekeeper_vpc_execution_role[0].policy_arn == "arn:aws-us-gov:iam::aws:policy/service-role/AWSLambdaVPCAccessExecutionRole" + ) + error_message = "A complete VPC configuration must configure the Lambda and attach the partition-aware VPC execution policy." + } + + assert { + condition = ( + length(aws_lambda_function.ssm_housekeeper.tracing_config) == 1 && + aws_lambda_function.ssm_housekeeper.tracing_config[0].mode == "Active" && + length(aws_iam_role_policy.ssm_housekeeper_xray) == 1 && + aws_lambda_function.ssm_housekeeper.environment[0].variables["POWERTOOLS_TRACE_ENABLED"] == "true" && + aws_lambda_function.ssm_housekeeper.environment[0].variables["POWERTOOLS_TRACER_CAPTURE_HTTPS_REQUESTS"] == "true" && + aws_lambda_function.ssm_housekeeper.environment[0].variables["POWERTOOLS_TRACER_CAPTURE_ERROR"] == "true" + ) + error_message = "Active tracing must configure Lambda tracing, X-Ray IAM permissions, and tracing-helper environment variables." + } + + assert { + condition = ( + data.aws_iam_policy_document.lambda_xray[0].statement[0].resources == toset(["*"]) + && alltrue([ + for action in data.aws_iam_policy_document.lambda_xray[0].statement[0].actions : + startswith(action, "xray:") + ]) + ) + error_message = "The housekeeper wildcard resource must be limited to X-Ray APIs, which do not support resource-level IAM permissions." + } +} diff --git a/modules/runner-config/ssm-housekeeper/variables.tf b/modules/runner-config/ssm-housekeeper/variables.tf new file mode 100644 index 0000000000..64848fc33c --- /dev/null +++ b/modules/runner-config/ssm-housekeeper/variables.tf @@ -0,0 +1,93 @@ +variable "config" { + description = <<-EOT + Provider-neutral SSM housekeeper configuration assembled by runner-config. + + - `prefix`: Prefix used to name the housekeeper resources. + - `aws_partition`: AWS partition used to construct IAM policy ARNs. + - `schedule.expression`: EventBridge schedule expression that invokes the housekeeper. + - `schedule.state`: State of the EventBridge rule. + - `cleanup.token_path`: Parameter Store token path supplied to the Lambda. + - `cleanup.parameter_path_arn`: IAM resource ARN matching `cleanup.token_path`. + - `cleanup.minimum_days_old`: Minimum parameter age before deletion. + - `cleanup.dry_run`: Reports eligible parameters without deleting them when true. + - `lambda.artifact.zip`: Resolved local control-plane archive. + - `lambda.artifact.s3.bucket`: Optional S3 bucket containing the Lambda archive. + - `lambda.artifact.s3.key`: Object key of the Lambda archive. + - `lambda.artifact.s3.object_version`: Optional object version of the Lambda archive. + - `lambda.runtime`: Runtime used by the housekeeper Lambda. + - `lambda.architecture`: Instruction-set architecture used by the housekeeper Lambda. + - `lambda.memory_size`: Memory allocated to the housekeeper Lambda. + - `lambda.timeout`: Housekeeper Lambda timeout in seconds. + - `lambda.vpc.subnet_ids`: Subnets used for Lambda VPC configuration. + - `lambda.vpc.security_group_ids`: Security groups used for Lambda VPC configuration. + - `lambda.role.path`: IAM path used for the housekeeper Lambda role. + - `lambda.role.permissions_boundary`: Optional permissions boundary for the housekeeper role. + - `lambda.role.principals`: Additional principals allowed to assume the housekeeper Lambda role. + - `observability.logs`: Logging level, retention, encryption, and log-class configuration. + - `observability.tracing`: Lambda X-Ray and tracing-helper configuration. + - `tags.resources`: Tags for the housekeeper role and EventBridge rule. + - `tags.lambda`: Tags for the housekeeper Lambda function. + - `tags.log_group`: Tags for the housekeeper log group. + EOT + + type = object({ + prefix = string + aws_partition = string + schedule = object({ + expression = string + state = string + }) + cleanup = object({ + token_path = string + parameter_path_arn = string + minimum_days_old = number + dry_run = bool + }) + lambda = object({ + artifact = object({ + zip = string + s3 = object({ + bucket = optional(string, null) + key = optional(string, null) + object_version = optional(string, null) + }) + }) + runtime = string + architecture = string + memory_size = number + timeout = number + vpc = object({ + subnet_ids = list(string) + security_group_ids = list(string) + }) + role = object({ + path = string + permissions_boundary = optional(string, null) + principals = optional(list(object({ + type = string + identifiers = list(string) + })), []) + }) + }) + observability = object({ + logs = object({ + level = string + retention_in_days = number + kms_key_id = optional(string, null) + class = string + }) + tracing = object({ + mode = optional(string, null) + capture_http_requests = bool + capture_error = bool + }) + }) + tags = object({ + resources = map(string) + lambda = map(string) + log_group = map(string) + }) + }) + + nullable = false +} diff --git a/modules/runner-config/ssm-housekeeper/versions.tf b/modules/runner-config/ssm-housekeeper/versions.tf new file mode 100644 index 0000000000..da9769f550 --- /dev/null +++ b/modules/runner-config/ssm-housekeeper/versions.tf @@ -0,0 +1,10 @@ +terraform { + required_version = ">= 1.3.0" + + required_providers { + aws = { + source = "hashicorp/aws" + version = ">= 6.33" + } + } +} diff --git a/modules/runner-config/tests/README.md b/modules/runner-config/tests/README.md new file mode 100644 index 0000000000..fa55dfecd9 --- /dev/null +++ b/modules/runner-config/tests/README.md @@ -0,0 +1,72 @@ +# Terraform Tests + +This directory contains [Terraform test files](https://developer.hashicorp.com/terraform/language/tests) (`.tftest.hcl`) for the runners module. + +## Why `terraform test` instead of `terraform validate`? + +`terraform validate` only checks syntax and basic type correctness of the configuration. It **cannot** detect: + +- Conditional expressions with inconsistent result types (e.g., one branch returns an object with 1 attribute, the other returns 16) +- Runtime type mismatches that only surface during `plan` +- Invalid cross-module references that depend on resource attribute shapes + +`terraform test` with `mock_provider` runs a full plan without needing real cloud credentials, catching these classes of bugs in CI. + +## Requirements + +- Terraform >= 1.7 (for `mock_provider` and `mock_data` support) +- No AWS credentials required — all providers are mocked + +## Running locally + +```bash +cd modules/runners +terraform test -test-directory=tests +``` + +Expected output: + +``` +tests/pool.tftest.hcl... in progress + run "plan_with_pool_enabled"... pass +tests/pool.tftest.hcl... pass + +Success! 1 passed, 0 failed. +``` + +## Writing new tests + +1. Create a `.tftest.hcl` file in this directory +2. Use `mock_provider "aws" {}` to avoid needing credentials +3. Use `mock_data` blocks to provide realistic values for data sources that perform validation (e.g., `aws_iam_policy_document` validates JSON) +4. Set all required variables in a `variables {}` block +5. Use `run` blocks with `command = plan` and `assert` conditions + +### Example template + +```hcl +mock_provider "aws" { + mock_data "aws_iam_policy_document" { + defaults = { + json = "{\"Version\":\"2012-10-17\",\"Statement\":[{\"Effect\":\"Allow\",\"Principal\":{\"Service\":\"lambda.amazonaws.com\"},\"Action\":\"sts:AssumeRole\"}]}" + } + } +} + +variables { + # ... required variables ... +} + +run "descriptive_test_name" { + command = plan + + assert { + condition = + error_message = "Explanation of what failed" + } +} +``` + +## CI integration + +These tests run automatically in the `terraform_test` job of `.github/workflows/terraform.yml` on every PR that touches `*.tf` or `*.hcl` files. diff --git a/modules/runner-config/tests/computed-iam-inputs.tftest.hcl b/modules/runner-config/tests/computed-iam-inputs.tftest.hcl new file mode 100644 index 0000000000..ff36530377 --- /dev/null +++ b/modules/runner-config/tests/computed-iam-inputs.tftest.hcl @@ -0,0 +1,44 @@ +mock_provider "aws" { + mock_data "aws_iam_policy_document" { + defaults = { + json = "{\"Version\":\"2012-10-17\",\"Statement\":[]}" + } + } +} + +run "computed_external_values_keep_plan_shape_known" { + command = plan + + module { + source = "./tests/fixtures/computed-iam-inputs" + } + + # The packaged runner archive is added by the release build, so the computed + # IAM fixture isolates the two common housekeeper children in a source checkout. + override_module { + target = module.external_iam.module.ssm_housekeeper + } + + override_module { + target = module.generated_policy.module.ssm_housekeeper + } + + override_module { + target = module.computed_microvm.module.ssm_housekeeper + } + + assert { + condition = output.external_role_runner_count == 0 + error_message = "Computed external AMI parameter, KMS key, role, and profile values must not make resource or policy-block counts unknown." + } + + assert { + condition = output.generated_policy_role_runner_count == 1 + error_message = "A computed managed-policy ARN under a caller-known map key must keep attachment planning stable." + } + + assert { + condition = output.computed_microvm_role_runner_count == 1 + error_message = "A computed MicroVM image ARN and computed managed-policy ARNs inside plan-known wrappers must keep provider dispatch and attachment counts stable." + } +} diff --git a/modules/runner-config/tests/fixtures/computed-iam-inputs/README.md b/modules/runner-config/tests/fixtures/computed-iam-inputs/README.md new file mode 100644 index 0000000000..46d64bdce2 --- /dev/null +++ b/modules/runner-config/tests/fixtures/computed-iam-inputs/README.md @@ -0,0 +1,42 @@ + +## Requirements + +| Name | Version | +|------|---------| +| [terraform](#requirement\_terraform) | >= 1.3 | +| [random](#requirement\_random) | ~> 3.0 | + +## Providers + +| Name | Version | +|------|---------| +| [random](#provider\_random) | ~> 3.0 | + +## Modules + +| Name | Source | Version | +|------|--------|---------| +| [computed\_microvm](#module\_computed\_microvm) | ../../.. | n/a | +| [external\_iam](#module\_external\_iam) | ../../.. | n/a | +| [generated\_policy](#module\_generated\_policy) | ../../.. | n/a | + +## Resources + +| Name | Type | +|------|------| +| [random_id.external](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/id) | resource | +| [random_id.generated_policy](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/id) | resource | +| [random_id.microvm](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/id) | resource | + +## Inputs + +No inputs. + +## Outputs + +| Name | Description | +|------|-------------| +| [computed\_microvm\_role\_runner\_count](#output\_computed\_microvm\_role\_runner\_count) | n/a | +| [external\_role\_runner\_count](#output\_external\_role\_runner\_count) | n/a | +| [generated\_policy\_role\_runner\_count](#output\_generated\_policy\_role\_runner\_count) | n/a | + diff --git a/modules/runner-config/tests/fixtures/computed-iam-inputs/computed-iam-inputs.tf b/modules/runner-config/tests/fixtures/computed-iam-inputs/computed-iam-inputs.tf new file mode 100644 index 0000000000..a4114c5832 --- /dev/null +++ b/modules/runner-config/tests/fixtures/computed-iam-inputs/computed-iam-inputs.tf @@ -0,0 +1,314 @@ +# A .tftest.hcl variable block supplies plan-known values. This wrapper uses +# random_id results to exercise caller inputs that remain unknown during plan, +# which catches invalid count, for_each, and dynamic-block expressions in the +# IAM boundary. +resource "random_id" "external" { + byte_length = 4 +} + +resource "random_id" "generated_policy" { + byte_length = 4 +} + +resource "random_id" "microvm" { + byte_length = 4 +} + +module "external_iam" { + source = "../../.." + + aws_region = "eu-west-1" + prefix = "computed-external" + + compute_provider = { + aws = { + ec2 = { + vpc_id = "vpc-12345678" + subnet_ids = ["subnet-12345678"] + instance_types = ["m5.large"] + ami = { + id_ssm_parameter = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/external-ami-${random_id.external.hex}" + } + kms_key = { + arn = "arn:aws:kms:eu-west-1:123456789012:key/${random_id.external.hex}" + } + } + instance_profile = { + name = "external-runner-${random_id.external.hex}" + } + cloudwatch_agent = { + enabled = false + } + binaries_syncer = { + enabled = false + } + } + } + } + + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/external-runner-${random_id.external.hex}" + } + } + } + + lambda = { + artifact = { + s3 = { + bucket = "lambda-artifacts" + } + } + } + + github = { + app_parameters = { + key_base64 = [{ + name = "/github-runner/key-base64" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/key-base64" + }] + id = [{ + name = "/github-runner/app-id" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/app-id" + }] + installation_id = [null] + } + } + + orchestration_provider = { + webhook = { + runner = { + maximum_count = 3 + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:computed-external" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/computed-external" + } + kms_key_id = "arn:aws:kms:eu-west-1:123456789012:key/build-queue-${random_id.external.hex}" + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + pool = { + runner_owner = "example" + config = [{ + schedule_expression = "cron(0 8 * * ? *)" + size = 1 + }] + } + } + job_retry = { + enabled = true + } + } + } + + ssm = { + kms_key_id = "arn:aws:kms:eu-west-1:123456789012:key/${random_id.external.hex}" + paths = { + root = "/github-runner/computed-external" + tokens = "tokens" + config = "config" + } + } +} + +module "generated_policy" { + source = "../../.." + + aws_region = "eu-west-1" + prefix = "computed-policy" + + compute_provider = { + aws = { + ec2 = { + vpc_id = "vpc-12345678" + subnet_ids = ["subnet-12345678"] + instance_types = ["m5.large"] + cloudwatch_agent = { + enabled = false + } + binaries_syncer = { + enabled = false + } + } + } + } + + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + managed_policy_arns = { + generated = "arn:aws:iam::123456789012:policy/generated-runner-${random_id.generated_policy.hex}" + } + } + } + + lambda = { + artifact = { + s3 = { + bucket = "lambda-artifacts" + } + } + } + + github = { + app_parameters = { + key_base64 = [{ + name = "/github-runner/key-base64" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/key-base64" + }] + id = [{ + name = "/github-runner/app-id" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/app-id" + }] + installation_id = [null] + } + } + + orchestration_provider = { + webhook = { + runner = { + maximum_count = 3 + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:computed-policy" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/computed-policy" + } + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + } + } + } + + ssm = { + paths = { + root = "/github-runner/computed-policy" + tokens = "tokens" + config = "config" + } + } +} + +module "computed_microvm" { + source = "../../.." + + aws_region = "eu-west-1" + prefix = "computed-microvm" + + compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner-${random_id.microvm.hex}" + iam = { + managed_policies = { + scale_up = { + arn = "arn:aws:iam::123456789012:policy/microvm-scale-up-${random_id.microvm.hex}" + } + pool = { + arn = "arn:aws:iam::123456789012:policy/microvm-pool-${random_id.microvm.hex}" + } + } + } + } + } + } + + runner = { + os = "linux" + architecture = "arm64" + labels = ["self-hosted", "linux", "arm64", "microvm"] + } + + lambda = { + artifact = { + s3 = { + bucket = "lambda-artifacts" + } + } + } + + github = { + app_parameters = { + key_base64 = [{ + name = "/github-runner/key-base64" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/key-base64" + }] + id = [{ + name = "/github-runner/app-id" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/app-id" + }] + installation_id = [null] + } + } + + orchestration_provider = { + webhook = { + runner = { + ephemeral = true + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:computed-microvm" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/computed-microvm" + } + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + pool = { + runner_owner = "example" + config = [{ + schedule_expression = "cron(0 8 * * ? *)" + size = 1 + }] + } + } + } + } + + ssm = { + paths = { + root = "/github-runner/computed-microvm" + tokens = "tokens" + config = "config" + } + } +} + +output "external_role_runner_count" { + value = module.external_iam.runner.role == null ? 0 : 1 +} + +output "generated_policy_role_runner_count" { + value = module.generated_policy.runner.role == null ? 0 : 1 +} + +output "computed_microvm_role_runner_count" { + value = module.computed_microvm.runner.role == null ? 0 : 1 +} diff --git a/modules/runner-config/tests/fixtures/computed-iam-inputs/versions.tf b/modules/runner-config/tests/fixtures/computed-iam-inputs/versions.tf new file mode 100644 index 0000000000..9fd85fad8f --- /dev/null +++ b/modules/runner-config/tests/fixtures/computed-iam-inputs/versions.tf @@ -0,0 +1,13 @@ +terraform { + required_version = ">= 1.3" + + required_providers { + aws = { + source = "hashicorp/aws" + } + random = { + source = "hashicorp/random" + version = "~> 3.0" + } + } +} diff --git a/modules/runner-config/tests/pool.tftest.hcl b/modules/runner-config/tests/pool.tftest.hcl new file mode 100644 index 0000000000..c8a0a383f5 --- /dev/null +++ b/modules/runner-config/tests/pool.tftest.hcl @@ -0,0 +1,983 @@ +mock_provider "aws" { + mock_data "aws_caller_identity" { + defaults = { + account_id = "123456789012" + } + } + + mock_data "aws_iam_policy_document" { + defaults = { + json = "{\"Version\":\"2012-10-17\",\"Statement\":[{\"Effect\":\"Allow\",\"Principal\":{\"Service\":\"lambda.amazonaws.com\"},\"Action\":\"sts:AssumeRole\"}]}" + } + } + + mock_resource "aws_iam_role" { + defaults = { + arn = "arn:aws:iam::123456789012:role/runner-test" + } + } + + mock_resource "aws_ssm_parameter" { + defaults = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/ami-id" + } + } +} + +# The runner archive is injected during packaging, so isolate the common +# housekeeper child in source-checkout tests where that build artifact is absent. +override_module { + target = module.ssm_housekeeper +} + +variables { + aws_region = "eu-west-1" + + compute_provider = { + aws = { + ec2 = { + vpc_id = "vpc-12345678" + subnet_ids = ["subnet-12345678"] + instance_types = ["m5.large"] + ami = { + filter = { state = ["available"] } + owners = ["amazon"] + id_ssm_parameter = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/external-ami-id" + } + kms_key = null + } + binaries_syncer = { + s3 = { + arn = "arn:aws:s3:::my-bucket" + id = "my-bucket" + key = "runners/linux/actions-runner.tar.gz" + } + } + ssm_enabled = true + } + } + } + + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + managed_policy_arns = { + readonly = "arn:aws:iam::aws:policy/ReadOnlyAccess" + } + additional_trust_policy_json = jsonencode({ + Version = "2012-10-17" + Statement = [{ + Sid = "AdditionalTrustedAccount" + Effect = "Allow" + Action = "sts:AssumeRole" + Principal = { AWS = "arn:aws:iam::210987654321:root" } + }] + }) + } + } + + lambda = { + artifact = { + s3 = { + bucket = "my-lambda-bucket" + } + } + } + + github = { + app_parameters = { + key_base64 = [{ name = "/github-runner/key-base64", arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/key-base64" }] + id = [{ name = "/github-runner/app-id", arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/app-id" }] + installation_id = [null] + } + } + + orchestration_provider = { + webhook = { + runner = { + boot_time_in_minutes = 8 + ephemeral = true + jit_config_enabled = null + maximum_count = 9 + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:build-queue" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/build-queue" + } + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + pool = { + config = [{ + schedule_expression = "cron(0 8 * * ? *)" + size = 1 + }] + } + } + } + } + + ssm = { + paths = { + root = "/github-runner" + tokens = "tokens" + config = "config" + } + } + +} + +run "plan_with_pool_enabled" { + command = plan + + assert { + condition = module.orchestration_webhook[0].pool != null + error_message = "Pool module should be enabled when pool.config is non-empty" + } + + assert { + condition = ( + !contains(keys(var.runner), "maximum_count") + && !contains(keys(var.runner), "boot_time_in_minutes") + && !contains(keys(var.runner), "ephemeral") + && !contains(keys(var.runner), "jit_config_enabled") + && var.orchestration_provider.webhook.runner.boot_time_in_minutes == 8 + && var.orchestration_provider.webhook.runner.ephemeral + && var.orchestration_provider.webhook.runner.jit_config_enabled == null + && var.orchestration_provider.webhook.runner.maximum_count == 9 + && module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["RUNNERS_MAXIMUM_COUNT"] == "9" + && module.orchestration_webhook[0].scale_down.lambda.environment[0].variables["RUNNER_BOOT_TIME_IN_MINUTES"] == "8" + && module.orchestration_webhook[0].pool.lambda.environment[0].variables["RUNNERS_MAXIMUM_COUNT"] == "9" + && module.orchestration_webhook[0].pool.lambda.environment[0].variables["RUNNER_BOOT_TIME_IN_MINUTES"] == "8" + ) + error_message = "Runner capacity and boot time must be owned by orchestration_provider.webhook.runner and routed to webhook controls, not retained in the common runner contract." + } + + assert { + condition = ( + aws_ssm_parameter.runner_agent_mode.value == "ephemeral" + && aws_ssm_parameter.jit_config_enabled.value == "true" + ) + error_message = "Runner-config must serialize the webhook provider's resolved lifecycle contract without duplicating its JIT fallback." + } + + assert { + condition = ( + module.orchestration_webhook[0].scale_up.lambda.s3_bucket == "my-lambda-bucket" + && module.orchestration_webhook[0].scale_up.lambda.s3_key == "runners.zip" + && local.ssm_housekeeper_artifact.s3.bucket == null + && endswith(local.ssm_housekeeper_artifact.zip, "/lambdas/functions/control-plane/runners.zip") + ) + error_message = "The webhook provider must combine its artifact key with the shared bucket while the common SSM housekeeper remains on the packaged archive." + } + + assert { + condition = ( + toset(keys(output.provider)) == toset(["aws"]) + && toset(keys(output.provider.aws)) == toset(["ec2", "microvm"]) + && output.provider.aws.microvm == null + ) + error_message = "The runner configuration must expose resources under the selected provider namespace and type." + } + + assert { + condition = contains(keys(output.provider.aws.ec2), "launch_template") + error_message = "The runner configuration must expose EC2 resources only under provider.aws.ec2." + } + + assert { + condition = length(aws_iam_role.runner) == 1 && output.runner.role != null + error_message = "The common runner configuration must create and expose the runner role." + } + + assert { + condition = ( + length(module.compute_aws_ec2_trust_policy) == 1 + && length(module.compute_aws_microvm_trust_policy) == 0 + && length(module.compute_aws_microvm) == 0 + && aws_iam_role.runner[0].assume_role_policy == module.compute_aws_ec2_trust_policy[0].assume_role_policy + ) + error_message = "The common runner role must use the selected EC2 trust-policy submodule output." + } + + assert { + condition = ( + output.pool != null + && toset(keys(output.pool)) == toset(["lambda", "log_group", "role"]) + ) + error_message = "An enabled pool must expose its Lambda, log group, and role through the nested pool output." + } + + assert { + condition = ( + toset(keys(output.orchestration_provider)) == toset(["webhook"]) + && output.orchestration_provider.webhook != null + && output.orchestration_provider.webhook.scale_up != null + && output.orchestration_provider.webhook.scale_down != null + && output.orchestration_provider.webhook.pool != null + ) + error_message = "The canonical orchestration output must group the existing webhook control-plane resources while flat aliases remain available." + } + + assert { + condition = length(jsondecode(module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["SSM_PARAMETER_STORE_TAGS"])) == 0 + error_message = "Runtime Parameter Store tags must remain empty when no module or SSM tags are configured; EC2 bootstrap tags must not leak into them." + } + + assert { + condition = !contains(keys(output.provider.aws.ec2), "role_runner") + error_message = "The common runner role must not be duplicated in the EC2 resource output." + } + + assert { + condition = toset(keys(aws_iam_role_policy.runner_provider)) == toset([ + "ssm_parameters", + "describe_tags", + "create_tags", + "terminate_self", + "session_manager", + "distribution_bucket", + "cloudwatch", + ]) + error_message = "The common runner configuration must attach every enabled EC2 runner policy by its stable provider key." + } + + assert { + condition = aws_iam_role_policy_attachment.runner["user-readonly"].policy_arn == "arn:aws:iam::aws:policy/ReadOnlyAccess" + error_message = "The selected EC2 provider contract must return common managed runner policies for one attachment path." + } + + assert { + condition = ( + module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["COMPUTE_PROVIDER_TYPE"] == "ec2" + && module.orchestration_webhook[0].scale_down.lambda.environment[0].variables["COMPUTE_PROVIDER_TYPE"] == "ec2" + ) + error_message = "Scaling Lambdas must receive the provider type from the selected provider." + } + + assert { + condition = module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["INSTANCE_TYPES"] == "m5.large" + error_message = "Scale-up must merge the EC2 environment fragment." + } + + assert { + condition = module.orchestration_webhook[0].scale_down.lambda.environment[0].variables["RUNNER_BOOT_TIME_IN_MINUTES"] == "8" + error_message = "Scale-down must receive boot time from the webhook orchestration configuration." + } + + assert { + condition = ( + toset(keys(module.orchestration_webhook[0].scale_up)) == toset(["lambda", "log_group", "role"]) + && toset(keys(module.orchestration_webhook[0].scale_down)) == toset(["lambda", "log_group", "role"]) + ) + error_message = "The scale-runners child module must forward the nested scale-up and scale-down resource contracts." + } + +} + +run "housekeeper_uses_component_s3_artifact" { + command = plan + + variables { + ssm = { + paths = { + root = "/github-runner" + tokens = "tokens" + config = "config" + } + housekeeper = { + lambda = { + artifact = { + s3 = { + key = "housekeeper/runner-config.zip" + object_version = "housekeeper-version" + } + } + } + } + } + } + + assert { + condition = ( + local.ssm_housekeeper_artifact.zip == null + && local.ssm_housekeeper_artifact.s3.bucket == "my-lambda-bucket" + && local.ssm_housekeeper_artifact.s3.key == "housekeeper/runner-config.zip" + && local.ssm_housekeeper_artifact.s3.object_version == "housekeeper-version" + ) + error_message = "The SSM housekeeper must combine its component-owned S3 key and version with the common Lambda artifact bucket." + } +} + +run "housekeeper_uses_component_local_zip" { + command = plan + + variables { + ssm = { + paths = { + root = "/github-runner" + tokens = "tokens" + config = "config" + } + housekeeper = { + lambda = { + artifact = { + zip = "README.md" + } + } + } + } + } + + assert { + condition = ( + local.ssm_housekeeper_artifact.zip == "README.md" + && local.ssm_housekeeper_artifact.s3.bucket == null + && local.ssm_housekeeper_artifact.s3.key == null + && local.ssm_housekeeper_artifact.s3.object_version == null + ) + error_message = "The SSM housekeeper must use its component-owned local zip without inheriting the common bucket or webhook artifact." + } +} + +run "rejects_conflicting_housekeeper_artifacts" { + command = plan + + variables { + ssm = { + paths = { + root = "/github-runner" + tokens = "tokens" + config = "config" + } + housekeeper = { + lambda = { + artifact = { + zip = "README.md" + s3 = { + key = "housekeeper/runner-config.zip" + } + } + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_housekeeper_s3_without_common_bucket" { + command = plan + + variables { + lambda = { + artifact = { + s3 = { + bucket = null + } + } + } + ssm = { + paths = { + root = "/github-runner" + tokens = "tokens" + config = "config" + } + housekeeper = { + lambda = { + artifact = { + s3 = { + key = "housekeeper/runner-config.zip" + } + } + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_missing_orchestration_provider" { + command = plan + + variables { + orchestration_provider = { + webhook = null + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "external_runner_role_is_not_managed_by_common" { + command = plan + + variables { + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/external/runner-role" + } + } + } + } + + assert { + condition = length(aws_iam_role.runner) == 0 && length(aws_iam_role_policy.runner_provider) == 0 && length(aws_iam_role_policy_attachment.runner) == 0 + error_message = "An external runner role must remain unmanaged by the common runner configuration." + } + + assert { + condition = output.runner.role == null + error_message = "The nested runner role output must be null when an external role is selected." + } + + + assert { + condition = output.provider.aws.ec2.launch_template.iam_instance_profile[0].name == "github-actions-runner-profile" + error_message = "EC2 must create an instance profile around an externally supplied runner role when no profile override is provided." + } +} + +run "external_runner_role_and_profile_remain_external" { + command = plan + + variables { + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/external/runner-role" + } + } + } + compute_provider = { + aws = { + ec2 = { + vpc_id = "vpc-12345678" + subnet_ids = ["subnet-12345678"] + instance_types = ["m5.large"] + instance_profile = { + name = "external-runner-profile" + } + binaries_syncer = { + enabled = false + } + } + } + } + } + + assert { + condition = length(aws_iam_role.runner) == 0 && length(aws_iam_role_policy.runner_provider) == 0 + error_message = "The common runner configuration must not manage an external role." + } + + assert { + condition = output.provider.aws.ec2.launch_template.iam_instance_profile[0].name == "external-runner-profile" + error_message = "The EC2 launch template must use the external instance profile." + } +} + +run "empty_runner_iam_uses_common_role" { + command = plan + + variables { + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = {} + } + } + + assert { + condition = length(aws_iam_role.runner) == 1 + error_message = "An empty runner.iam object must use common role ownership." + } +} + +run "external_role_rejects_managed_policy_attachments" { + command = plan + + variables { + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/external/runner-role" + } + managed_policy_arns = { + readonly = "arn:aws:iam::aws:policy/ReadOnlyAccess" + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "external_role_rejects_trust_policy_extension" { + command = plan + + variables { + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/external/runner-role" + } + additional_trust_policy_json = "{\"Version\":\"2012-10-17\",\"Statement\":[]}" + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_invalid_trust_policy_extension" { + command = plan + + variables { + runner = { + labels = ["self-hosted", "linux", "x64"] + iam = { + additional_trust_policy_json = "{" + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_empty_compute_provider" { + command = plan + + variables { + compute_provider = {} + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_empty_aws_compute_provider_namespace" { + command = plan + + variables { + compute_provider = { + aws = {} + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "job_retry_uses_common_runner_configuration_identity" { + command = plan + + variables { + runner = { + labels = ["self-hosted", "linux", "x64"] + name_prefix = "provider-neutral-" + } + orchestration_provider = { + webhook = { + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:build-queue" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/build-queue" + } + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + } + job_retry = { + enabled = true + lambda = { + reserved_concurrent_executions = 2 + } + } + } + } + } + + assert { + condition = module.orchestration_webhook[0].job_retry.lambda.function.environment[0].variables["RUNNER_NAME_PREFIX"] == "provider-neutral-" + error_message = "Job retry must receive the common runner-configuration name prefix." + } + + assert { + condition = module.orchestration_webhook[0].job_retry.lambda.function.reserved_concurrent_executions == 2 + error_message = "Job retry must apply its configured Lambda reserved concurrency." + } +} + +run "routes_lambda_microvm_provider" { + command = plan + + variables { + compute_provider_key = "aws_microvm" + runner = { + os = "linux" + architecture = "arm64" + labels = ["self-hosted", "linux", "arm64", "microvm"] + } + compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + image_version = "7" + ingress_network_connectors = [ + "arn:aws:lambda:eu-west-1:123456789012:network-connector:private-ingress", + ] + egress_network_connectors = [ + "arn:aws:lambda:eu-west-1:aws:network-connector:aws-network-connector:INTERNET_EGRESS", + ] + } + } + } + orchestration_provider = { + webhook = { + runner = { + ephemeral = true + jit_config_enabled = null + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:build-queue" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/build-queue" + } + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + } + } + } + } + + assert { + condition = ( + length(module.compute_aws_ec2) == 0 + && length(module.compute_aws_ec2_trust_policy) == 0 + && length(module.compute_aws_microvm) == 1 + && length(module.compute_aws_microvm_trust_policy) == 1 + && aws_iam_role.runner[0].assume_role_policy == module.compute_aws_microvm_trust_policy[0].assume_role_policy + && toset(keys(aws_iam_role_policy.runner_provider)) == toset(["cloudwatch", "runner_metadata", "runtime_logs", "ssm_jit"]) + && aws_iam_role_policy.runner_provider["cloudwatch"].name == "runner-microvm-cloudwatch" + && aws_iam_role_policy.runner_provider["runner_metadata"].name == "runner-microvm-metadata" + && aws_iam_role_policy.runner_provider["runtime_logs"].name == "runner-microvm-runtime-logs" + && aws_iam_role_policy.runner_provider["ssm_jit"].name == "runner-microvm-ssm-jit" + ) + error_message = "The aws.microvm leaf must dispatch only to the namespaced provider modules and attach all required policies to its managed runner role." + } + + assert { + condition = ( + toset(keys(output.provider.aws)) == toset(["ec2", "microvm"]) + && output.provider.aws.ec2 == null + && output.provider.aws.microvm.image_arn == "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + && output.provider.aws.microvm.image_version == "7" + && contains(keys(output.provider.aws.microvm), "execution_role_arn") + && output.provider.aws.microvm.runners_log_groups[0].name == "/github-self-hosted-runners/github-actions/microvm" + && toset(slice(output.provider.aws.microvm.runners_log_groups[*].name, 1, 4)) == toset([ + "/github-self-hosted-runners/github-actions/internal_service", + "/github-self-hosted-runners/github-actions/run", + "/github-self-hosted-runners/github-actions/runner", + ]) + && output.provider.aws.microvm.logfiles[2].file_path == "/opt/actions-runner/_diag/Runner_**.log" + ) + error_message = "The selected MicroVM resources must be exposed only under provider.aws.microvm." + } + + assert { + condition = ( + module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["COMPUTE_PROVIDER_TYPE"] == "microvm" + && module.orchestration_webhook[0].scale_down.lambda.environment[0].variables["COMPUTE_PROVIDER_TYPE"] == "microvm" + && module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["MICROVM_IMAGE_ARN"] == "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + && contains(keys(module.orchestration_webhook[0].scale_up.lambda.environment[0].variables), "MICROVM_EXECUTION_ROLE_ARN") + && module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["MICROVM_LOG_GROUP"] == "/github-self-hosted-runners/github-actions/microvm" + && module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["MICROVM_METADATA_SSM_PATH"] == "/github-runner/config/microvm-metadata" + && module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["SSM_CONFIG_PATH"] == "/github-runner/config" + && module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["ENVIRONMENT"] == "github-actions" + && module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["RUNNER_NAME_PREFIX"] == "" + && module.orchestration_webhook[0].scale_down.lambda.environment[0].variables["MICROVM_METADATA_SSM_PATH"] == "/github-runner/config/microvm-metadata" + && module.orchestration_webhook[0].scale_down.lambda.environment[0].variables["SSM_TOKEN_PATH"] == "/github-runner/tokens" + && module.orchestration_webhook[0].scale_down.lambda.environment[0].variables["RUNNER_BOOT_TIME_IN_MINUTES"] == "5" + && !contains(keys(module.orchestration_webhook[0].scale_up.lambda.environment[0].variables), "MICROVM_RUN_CONFIG") + && !contains(keys(module.orchestration_webhook[0].scale_up.lambda.environment[0].variables), "MICROVM_TAGS") + && !contains(keys(module.orchestration_webhook[0].scale_up.lambda.environment[0].variables), "MICROVM_METADATA_TAGS") + && !contains(keys(module.orchestration_webhook[0].scale_up.lambda.environment[0].variables), "MICROVM_RUNNER_CONFIG_SSM_ARN") + ) + error_message = "Runner-config must preserve the runtime provider type and merge the canonical MicroVM environment with webhook-owned lifecycle values." + } +} + +run "external_microvm_runner_role_remains_unmanaged" { + command = plan + + variables { + runner = { + os = "linux" + architecture = "arm64" + labels = ["self-hosted", "linux", "arm64", "microvm"] + iam = { + role = { + arn = "arn:aws:iam::123456789012:role/external/microvm-runner" + } + } + } + compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + } + } + } + orchestration_provider = { + webhook = { + runner = { + ephemeral = true + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:build-queue" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/build-queue" + } + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + } + } + } + } + + assert { + condition = ( + length(aws_iam_role.runner) == 0 + && length(aws_iam_role_policy.runner_provider) == 0 + && length(aws_iam_role_policy_attachment.runner) == 0 + && output.provider.aws.microvm.execution_role_arn == "arn:aws:iam::123456789012:role/external/microvm-runner" + ) + error_message = "An external provider-neutral runner role must remain caller-owned while serving as the MicroVM execution role." + } +} + +run "rejects_multiple_aws_compute_providers" { + command = plan + + variables { + compute_provider = { + aws = { + ec2 = { + vpc_id = "vpc-12345678" + subnet_ids = ["subnet-12345678"] + instance_types = ["m5.large"] + } + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_non_ephemeral_microvm_runner" { + command = plan + + variables { + runner = { + os = "linux" + architecture = "arm64" + labels = ["self-hosted", "linux", "arm64", "microvm"] + } + compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + } + } + } + orchestration_provider = { + webhook = { + runner = { + ephemeral = false + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:build-queue" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/build-queue" + } + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_microvm_runner_with_jit_disabled" { + command = plan + + variables { + runner = { + os = "linux" + architecture = "arm64" + labels = ["self-hosted", "linux", "arm64", "microvm"] + } + compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + } + } + } + orchestration_provider = { + webhook = { + runner = { + ephemeral = true + jit_config_enabled = false + } + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:build-queue" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/build-queue" + } + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_non_arm64_microvm_runner" { + command = plan + + variables { + runner = { + os = "linux" + architecture = "x64" + labels = ["self-hosted", "linux", "x64", "microvm"] + } + compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} + +run "rejects_non_linux_microvm_runner" { + command = plan + + variables { + runner = { + os = "windows" + architecture = "arm64" + labels = ["self-hosted", "windows", "arm64", "microvm"] + } + compute_provider = { + aws = { + microvm = { + image_arn = "arn:aws:lambda:eu-west-1:123456789012:microvm-image:runner" + } + } + } + } + + plan_options { + target = [terraform_data.validate_config] + } + + expect_failures = [terraform_data.validate_config] +} diff --git a/modules/runner-config/tests/tags.tftest.hcl b/modules/runner-config/tests/tags.tftest.hcl new file mode 100644 index 0000000000..6c004879ba --- /dev/null +++ b/modules/runner-config/tests/tags.tftest.hcl @@ -0,0 +1,322 @@ +mock_provider "aws" { + mock_data "aws_iam_policy_document" { + defaults = { + json = "{\"Version\":\"2012-10-17\",\"Statement\":[]}" + } + } + + mock_resource "aws_iam_role" { + defaults = { + arn = "arn:aws:iam::123456789012:role/runner-test" + } + } + + mock_resource "aws_ssm_parameter" { + defaults = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/config" + } + } +} + +# The runner archive is injected during packaging, so model the common +# housekeeper output while testing parent-level tag composition from source. +override_module { + target = module.ssm_housekeeper +} + +variables { + aws_region = "eu-west-1" + + tags = { + precedence = "module" + module = "yes" + } + + compute_provider = { + aws = { + ec2 = { + vpc_id = "vpc-12345678" + subnet_ids = ["subnet-12345678"] + instance_types = ["m5.large"] + ami = { + filter = { state = ["available"] } + owners = ["amazon"] + id_ssm_parameter = { + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/external-ami-id" + } + kms_key = null + } + binaries_syncer = { + s3 = { + arn = "arn:aws:s3:::my-bucket" + id = "my-bucket" + key = "runners/linux/actions-runner.tar.gz" + } + } + } + } + } + + runner = { + labels = ["self-hosted", "linux", "x64"] + tags = { + precedence = "runner" + runner = "yes" + } + } + + lambda = { + artifact = { + s3 = { + bucket = "my-lambda-bucket" + } + } + tags = { + precedence = "lambda" + lambda = "yes" + } + } + + github = { + app_parameters = { + key_base64 = [{ + name = "/github-runner/key-base64" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/key-base64" + }] + id = [{ + name = "/github-runner/app-id" + arn = "arn:aws:ssm:eu-west-1:123456789012:parameter/github-runner/app-id" + }] + installation_id = [null] + } + } + + orchestration_provider = { + webhook = { + github = { + organization_runners = true + } + queue = { + build = { + arn = "arn:aws:sqs:eu-west-1:123456789012:build-queue" + url = "https://sqs.eu-west-1.amazonaws.com/123456789012/build-queue" + } + tags = { + precedence = "queue" + queue = "yes" + } + } + lambda = { + artifact = { + s3 = { + key = "runners.zip" + } + } + scale = { + up = { + tags = { + precedence = "scale-up" + scale_up = "yes" + } + } + down = { + tags = { + precedence = "scale-down" + scale_down = "yes" + } + } + } + pool = { + config = [{ + schedule_expression = "cron(0 8 * * ? *)" + size = 1 + }] + tags = { + precedence = "pool" + pool = "yes" + } + } + } + job_retry = { + enabled = true + tags = { + precedence = "job-retry" + job_retry = "yes" + } + } + } + } + + ssm = { + paths = { + root = "/github-runner" + tokens = "tokens" + config = "config" + } + tags = { + precedence = "ssm" + ssm = "yes" + } + parameters = { + tags = { + precedence = "ssm-parameter" + parameter = "yes" + } + } + housekeeper = { + tags = { + precedence = "ssm-housekeeper" + housekeeper = "yes" + } + } + } + + observability = { + logs = { + level = "debug" + tags = { + precedence = "log" + log = "yes" + } + } + } +} + +run "layered_component_tags" { + command = plan + + assert { + condition = module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["LOG_LEVEL"] == "DEBUG" + error_message = "The nested observability.logs.level value must configure the control-plane functions." + } + + assert { + condition = module.orchestration_webhook[0].scale_up.lambda.tags == tomap({ + precedence = "scale-up" + module = "yes" + lambda = "yes" + scale_up = "yes" + }) && module.orchestration_webhook[0].scale_up.log_group.tags == tomap({ + precedence = "scale-up" + module = "yes" + log = "yes" + scale_up = "yes" + }) && module.orchestration_webhook[0].scale_up.role.tags == tomap({ + precedence = "scale-up" + module = "yes" + scale_up = "yes" + }) + error_message = "Scale-up tags must layer module, shared resource, and component tags with the component taking precedence." + } + + assert { + condition = module.orchestration_webhook[0].scale_down.lambda.tags == tomap({ + precedence = "scale-down" + module = "yes" + lambda = "yes" + scale_down = "yes" + }) && module.orchestration_webhook[0].scale_down.log_group.tags == tomap({ + precedence = "scale-down" + module = "yes" + log = "yes" + scale_down = "yes" + }) && module.orchestration_webhook[0].scale_down.role.tags == tomap({ + precedence = "scale-down" + module = "yes" + scale_down = "yes" + }) + error_message = "Scale-down tags must layer module, shared resource, and component tags with the component taking precedence." + } + + assert { + condition = aws_iam_role.runner[0].tags == tomap({ + precedence = "runner" + module = "yes" + runner = "yes" + }) + error_message = "Runner tags must override module tags on the common runner role." + } + + assert { + condition = aws_ssm_parameter.runner_agent_mode.tags == tomap({ + precedence = "ssm-parameter" + module = "yes" + ssm = "yes" + parameter = "yes" + }) && tomap({ + for tag in jsondecode(module.orchestration_webhook[0].scale_up.lambda.environment[0].variables["SSM_PARAMETER_STORE_TAGS"]) : + tag.Key => tag.Value + }) == tomap({ + precedence = "ssm-parameter" + module = "yes" + ssm = "yes" + parameter = "yes" + }) + error_message = "Terraform-managed and runtime-created SSM parameters must use the same layered parameter tags." + } + + assert { + condition = local.ssm_housekeeper_lambda_tags == tomap({ + precedence = "ssm-housekeeper" + module = "yes" + lambda = "yes" + ssm = "yes" + housekeeper = "yes" + }) && local.ssm_housekeeper_log_tags == tomap({ + precedence = "ssm-housekeeper" + module = "yes" + log = "yes" + ssm = "yes" + housekeeper = "yes" + }) && local.ssm_housekeeper_tags == tomap({ + precedence = "ssm-housekeeper" + module = "yes" + ssm = "yes" + housekeeper = "yes" + }) + error_message = "SSM housekeeper tags must layer module, SSM, shared resource, and housekeeper tags." + } + + assert { + condition = module.orchestration_webhook[0].pool.lambda.tags == tomap({ + precedence = "pool" + module = "yes" + lambda = "yes" + pool = "yes" + }) && module.orchestration_webhook[0].pool.log_group.tags == tomap({ + precedence = "pool" + module = "yes" + log = "yes" + pool = "yes" + }) && module.orchestration_webhook[0].pool.role.tags == tomap({ + precedence = "pool" + module = "yes" + pool = "yes" + }) + error_message = "Pool tags must layer module, shared resource, and component tags with the component taking precedence." + } + + assert { + condition = module.orchestration_webhook[0].job_retry.lambda.function.tags == tomap({ + precedence = "job-retry" + module = "yes" + lambda = "yes" + job_retry = "yes" + }) && module.orchestration_webhook[0].job_retry.lambda.log_group.tags == tomap({ + precedence = "job-retry" + module = "yes" + log = "yes" + job_retry = "yes" + }) && module.orchestration_webhook[0].job_retry.lambda.role.tags == tomap({ + precedence = "job-retry" + module = "yes" + job_retry = "yes" + }) && module.orchestration_webhook[0].job_retry.queue.tags == tomap({ + precedence = "job-retry" + module = "yes" + queue = "yes" + job_retry = "yes" + }) + error_message = "Job-retry tags must layer module, shared resource, and component tags with the component taking precedence." + } +} diff --git a/modules/runner-config/validations.tf b/modules/runner-config/validations.tf new file mode 100644 index 0000000000..2b3bfddccb --- /dev/null +++ b/modules/runner-config/validations.tf @@ -0,0 +1,137 @@ +resource "terraform_data" "validate_config" { + lifecycle { + precondition { + condition = contains(["linux", "osx", "windows"], var.runner.os) + error_message = "Valid values for runner.os are linux, osx, and windows." + } + + precondition { + condition = length(var.runner.name_prefix) <= 45 + error_message = "runner.name_prefix must be at most 45 characters." + } + + precondition { + condition = var.runner.iam.role == null ? true : trimspace(var.runner.iam.role.arn) != "" + error_message = "runner.iam.role.arn must be a non-empty ARN when set." + } + + precondition { + condition = var.runner.iam.role == null || length(var.runner.iam.managed_policy_arns) == 0 + error_message = "runner.iam.managed_policy_arns cannot be set with an external runner.iam.role because external roles are not managed by this module." + } + + precondition { + condition = var.runner.iam.additional_trust_policy_json == null ? true : can(jsondecode(var.runner.iam.additional_trust_policy_json)) + error_message = "runner.iam.additional_trust_policy_json must be valid JSON when set." + } + + precondition { + condition = var.runner.iam.role == null || var.runner.iam.additional_trust_policy_json == null + error_message = "runner.iam.additional_trust_policy_json cannot be set with an external runner.iam.role because external role trust is not managed by this module." + } + + precondition { + condition = contains(["arm64", "x86_64"], var.lambda.architecture) + error_message = "lambda.architecture must be arm64 or x86_64." + } + + precondition { + condition = !( + var.ssm.housekeeper.lambda.artifact.zip != null && + var.ssm.housekeeper.lambda.artifact.s3 != null + ) + error_message = "ssm.housekeeper.lambda.artifact must select at most one of zip or s3." + } + + precondition { + condition = ( + var.ssm.housekeeper.lambda.artifact.s3 == null || + var.lambda.artifact.s3.bucket != null + ) + error_message = "lambda.artifact.s3.bucket must be set when ssm.housekeeper.lambda.artifact.s3 is selected." + } + + precondition { + condition = contains(["STANDARD", "INFREQUENT_ACCESS"], var.observability.logs.class) + error_message = "observability.logs.class must be STANDARD or INFREQUENT_ACCESS." + } + + precondition { + condition = contains([ + "silly", + "trace", + "debug", + "info", + "warn", + "error", + "fatal", + ], var.observability.logs.level) + error_message = "observability.logs.level must be one of silly, trace, debug, info, warn, error, or fatal." + } + + precondition { + condition = length([ + for provider_key, provider_config in local.compute_providers : provider_key + if provider_config != null + ]) == 1 + error_message = "Exactly one compute-provider block must be set. Supported compute-provider blocks: aws.ec2, aws.microvm." + } + + precondition { + condition = var.compute_provider.aws.microvm == null ? true : ( + var.runner.os == "linux" && var.runner.architecture == "arm64" + ) + error_message = "compute_provider.aws.microvm requires runner.os = linux and runner.architecture = arm64." + } + + precondition { + condition = var.compute_provider_key == null || try( + local.compute_providers[var.compute_provider_key] != null, + false, + ) + error_message = "compute_provider_key must identify the non-null typed compute-provider block." + } + + precondition { + condition = length([ + for provider_name, provider_config in var.orchestration_provider : provider_name + if provider_config != null + ]) == 1 + error_message = "Exactly one orchestration provider must be configured. Supported providers: webhook." + } + + precondition { + condition = var.compute_provider.aws.microvm == null ? true : ( + try(var.orchestration_provider.webhook.runner.ephemeral, false) && + try(coalesce( + var.orchestration_provider.webhook.runner.jit_config_enabled, + var.orchestration_provider.webhook.runner.ephemeral, + ), false) + ) + error_message = "compute_provider.aws.microvm requires webhook orchestration with ephemeral and JIT runner configuration enabled." + } + + precondition { + condition = var.orchestration_provider.webhook == null ? true : ( + var.orchestration_provider.webhook.lambda.scale.up.event_source_mapping.batch_size >= 1 && + var.orchestration_provider.webhook.lambda.scale.up.event_source_mapping.batch_size <= 1000 && + var.orchestration_provider.webhook.lambda.scale.up.event_source_mapping.maximum_batching_window_in_seconds >= 0 && + var.orchestration_provider.webhook.lambda.scale.up.event_source_mapping.maximum_batching_window_in_seconds <= 300 + ) + error_message = "orchestration_provider.webhook.lambda.scale.up.event_source_mapping batch size must be between 1 and 1000 and its batching window between 0 and 300 seconds." + } + + precondition { + condition = var.orchestration_provider.webhook == null ? true : !( + var.orchestration_provider.webhook.lambda.artifact.zip != null && + var.orchestration_provider.webhook.lambda.artifact.s3 != null + ) + error_message = "orchestration_provider.webhook.lambda.artifact must select at most one of zip or s3." + } + + precondition { + condition = var.orchestration_provider.webhook == null ? true : (!var.orchestration_provider.webhook.job_retry.enabled || var.orchestration_provider.webhook.job_retry.delay_in_seconds <= 900) + error_message = "orchestration_provider.webhook.job_retry.delay_in_seconds cannot exceed the SQS maximum of 900 seconds." + } + } +} diff --git a/modules/runner-config/variables.compute-provider.tf b/modules/runner-config/variables.compute-provider.tf new file mode 100644 index 0000000000..7e07705894 --- /dev/null +++ b/modules/runner-config/variables.compute-provider.tf @@ -0,0 +1,297 @@ +# Optional plan-known dispatch key supplied by the multi-runner topology layer. +variable "compute_provider_key" { + description = "Optional plan-known compute-provider dispatch key. Null discovers the key from the exactly one populated compute_provider block." + type = string + default = null + + validation { + condition = var.compute_provider_key == null ? true : contains(["aws_ec2", "aws_microvm"], var.compute_provider_key) + error_message = "compute_provider_key must be null, aws_ec2, or aws_microvm." + } +} + +# Typed compute-provider input boundary between the common control plane and compute implementations. +variable "compute_provider" { + description = <<-EOT + Typed compute-provider configuration. Provider-owned settings remain inside the selected compute-provider block. + + Exactly one compute-provider block must be non-null. The populated block selects the provider, and its presence must be known during planning. Values inside the selected block may remain unknown until apply. + + - `aws`: AWS compute-provider configurations. + - `aws.ec2`: EC2 compute-provider configuration. + - `aws.ec2.ami`: Optional AMI discovery or external AMI-parameter configuration. Null uses the operating-system and architecture defaults. + - `aws.ec2.ami.filter`: EC2 AMI filters combined with the provider's default AMI-name filter. + - `aws.ec2.ami.owners`: AWS account IDs or aliases allowed to own the selected AMI. + - `aws.ec2.ami.id_ssm_parameter`: Optional externally managed SSM parameter containing the AMI ID. Null creates a provider-managed AMI-ID parameter. The wrapper's presence is the plan-time ownership discriminator, so keep the object literal even when its ARN comes from another resource. + - `aws.ec2.ami.id_ssm_parameter.arn`: ARN of the externally managed SSM parameter. The ARN may be unknown until apply. + - `aws.ec2.ami.kms_key`: Optional KMS key required to launch encrypted AMIs or snapshots. The wrapper's presence is the plan-time policy discriminator. + - `aws.ec2.ami.kms_key.arn`: ARN of the KMS key. The ARN may be unknown until apply. + - `aws.ec2.vpc_id`: VPC in which runner networking resources are created. + - `aws.ec2.subnet_ids`: Subnets from which scale-up may launch runner instances. + - `aws.ec2.overrides`: Optional resource-name overrides. + - `aws.ec2.overrides.name_runner`: Name tag used for runner compute resources. An empty value uses the generated provider name. + - `aws.ec2.overrides.name_sg`: Name tag used for the managed runner security group. An empty value uses the generated provider name. + - `aws.ec2.instance_profile`: Optional externally managed instance profile used by the launch template. + - `aws.ec2.instance_profile.name`: Name of the externally managed instance profile. + - `aws.ec2.instance_profile_path`: IAM path for the provider-managed instance profile. Null uses a path derived from the runner-configuration prefix. + - `aws.ec2.binaries_syncer`: Runner-distribution synchronization configuration. + - `aws.ec2.binaries_syncer.enabled`: Enables use of a synchronized runner distribution from S3. + - `aws.ec2.binaries_syncer.s3`: S3 object containing the synchronized runner distribution. Required when synchronization is enabled. + - `aws.ec2.binaries_syncer.s3.arn`: ARN of the runner-distribution bucket, used by IAM policies. + - `aws.ec2.binaries_syncer.s3.id`: Bucket name used to construct the runner-distribution S3 URI. + - `aws.ec2.binaries_syncer.s3.key`: Object key of the runner distribution. + - `aws.ec2.block_device_mappings`: EBS mappings added to the runner launch template. + - `aws.ec2.block_device_mappings[].delete_on_termination`: Deletes the volume when its runner instance terminates. + - `aws.ec2.block_device_mappings[].device_name`: Device name exposed to the runner instance. + - `aws.ec2.block_device_mappings[].encrypted`: Enables EBS encryption. + - `aws.ec2.block_device_mappings[].iops`: Provisioned IOPS for volume types that support it. + - `aws.ec2.block_device_mappings[].kms_key_id`: KMS key ID or ARN used to encrypt the volume. + - `aws.ec2.block_device_mappings[].snapshot_id`: Snapshot used to initialize the volume. + - `aws.ec2.block_device_mappings[].throughput`: Provisioned throughput for volume types that support it. + - `aws.ec2.block_device_mappings[].volume_initialization_rate`: Fixed initialization rate in MiB/s for supported snapshot-backed volumes. + - `aws.ec2.block_device_mappings[].volume_size`: Volume size in GiB. + - `aws.ec2.block_device_mappings[].volume_type`: EBS volume type. + - `aws.ec2.ebs_optimized`: Requests EBS-optimized runner instances. + - `aws.ec2.instance_target_capacity_type`: Primary capacity type, either `spot` or `on-demand`. + - `aws.ec2.instance_allocation_strategy`: EC2 Fleet allocation strategy used to select instance capacity. + - `aws.ec2.instance_type_priorities`: Optional numeric priorities keyed by instance type. + - `aws.ec2.instance_max_spot_price`: Optional maximum hourly Spot price. + - `aws.ec2.instance_types`: EC2 instance types available to the scale-up and pool functions. + - `aws.ec2.user_data`: Runner bootstrap user-data configuration. + - `aws.ec2.user_data.enabled`: Enables launch-template user data. + - `aws.ec2.user_data.template`: Optional path to a custom user-data template. + - `aws.ec2.user_data.content`: Optional complete user-data content. When set, it is used instead of rendering a template. + - `aws.ec2.user_data.pre_install`: Script content inserted before runner installation in the default template. + - `aws.ec2.user_data.post_install`: Script content inserted after runner installation in the default template. + - `aws.ec2.user_data.debug_logging_enabled`: Enables verbose user-data tracing, which can expose secrets in logs. + - `aws.ec2.ssm_enabled`: Attaches runner permissions and policies required for AWS Systems Manager access. + - `aws.ec2.create_service_linked_role_spot`: Allows scale-up to create the EC2 Spot service-linked role. + - `aws.ec2.cloudwatch_agent`: CloudWatch agent configuration for runner instances. + - `aws.ec2.cloudwatch_agent.enabled`: Installs and configures the CloudWatch agent through the default bootstrap flow. + - `aws.ec2.cloudwatch_agent.config`: Optional complete CloudWatch agent configuration. Null renders the provider default from `log_files`. + - `aws.ec2.managed_security_group_enabled`: Creates and attaches the provider-managed runner security group. + - `aws.ec2.log_files`: Optional log files collected by the CloudWatch agent. Null uses the provider defaults. + - `aws.ec2.log_files[].log_group_name`: CloudWatch log-group name, before optional prefixing. + - `aws.ec2.log_files[].prefix_log_group`: Prefixes the log-group name with the runner configuration path when true. + - `aws.ec2.log_files[].file_path`: File or glob read by the CloudWatch agent. + - `aws.ec2.log_files[].log_stream_name`: CloudWatch log-stream name template. + - `aws.ec2.log_files[].log_class`: CloudWatch log-group class for the collected file. + - `aws.ec2.key_name`: Optional EC2 key-pair name added to the launch template. + - `aws.ec2.additional_security_group_ids`: Existing security groups attached in addition to the managed security group. + - `aws.ec2.detailed_monitoring_enabled`: Enables detailed EC2 monitoring for runner instances. + - `aws.ec2.egress_rules`: Egress rules created on the managed runner security group. + - `aws.ec2.egress_rules[].cidr_blocks`: IPv4 CIDR destinations. + - `aws.ec2.egress_rules[].ipv6_cidr_blocks`: IPv6 CIDR destinations. + - `aws.ec2.egress_rules[].prefix_list_ids`: AWS prefix-list destinations. + - `aws.ec2.egress_rules[].from_port`: First destination port in the permitted range. + - `aws.ec2.egress_rules[].protocol`: IP protocol name or number. Use `-1` for all protocols. + - `aws.ec2.egress_rules[].security_groups`: Destination security-group IDs. + - `aws.ec2.egress_rules[].self`: Allows traffic to the managed security group itself when true. + - `aws.ec2.egress_rules[].to_port`: Last destination port in the permitted range. + - `aws.ec2.egress_rules[].description`: Optional rule description. + - `aws.ec2.tags`: Additional tags for runner instances, EBS volumes, network interfaces, and eligible Spot instance requests created from the launch template. They override module-level tags and the generated runner `Name`; the provider-managed `ghr:environment`, `ghr:ssm_config_path`, and `ghr:runner_name_prefix` bootstrap tags take final precedence. These tags do not apply to static provider resources such as the launch template, security group, IAM resources, SSM parameters, or log groups. + - `aws.ec2.metadata_options`: Instance Metadata Service configuration in the launch template. + - `aws.ec2.metadata_options.instance_metadata_tags`: Exposes instance tags through Instance Metadata Service when `enabled`. + - `aws.ec2.metadata_options.http_endpoint`: Enables or disables the Instance Metadata Service endpoint. + - `aws.ec2.metadata_options.http_tokens`: Controls whether IMDSv2 session tokens are optional or required. + - `aws.ec2.metadata_options.http_put_response_hop_limit`: Network hop limit for Instance Metadata Service token responses. + - `aws.ec2.credit_specification`: CPU credit mode for burstable instance types, either `standard` or `unlimited`. + - `aws.ec2.cpu_options`: CPU topology and processor-feature configuration. + - `aws.ec2.cpu_options.core_count`: Number of CPU cores exposed to the runner instance. + - `aws.ec2.cpu_options.threads_per_core`: Number of hardware threads exposed per CPU core. + - `aws.ec2.cpu_options.amd_sev_snp`: Enables or disables AMD SEV-SNP on supported instance types. + - `aws.ec2.cpu_options.nested_virtualization`: Enables or disables nested virtualization on supported instance types. + - `aws.ec2.placement`: EC2 placement configuration for runner instances. + - `aws.ec2.placement.affinity`: Host affinity setting. + - `aws.ec2.placement.availability_zone`: Availability Zone in which the instance is placed. + - `aws.ec2.placement.group_id`: Placement-group ID. + - `aws.ec2.placement.group_name`: Placement-group name. + - `aws.ec2.placement.host_id`: Dedicated Host ID. + - `aws.ec2.placement.host_resource_group_arn`: ARN of the host resource group used for placement. + - `aws.ec2.placement.spread_domain`: Spread-domain placement value. + - `aws.ec2.placement.tenancy`: Instance tenancy, such as `default`, `dedicated`, or `host`. + - `aws.ec2.placement.partition_number`: Placement-group partition number. + - `aws.ec2.license_specifications`: License Manager configurations added to the launch template. + - `aws.ec2.license_specifications[].license_configuration_arn`: ARN of a License Manager license configuration. + - `aws.ec2.associate_public_ipv4_address`: Associates a public IPv4 address with runner network interfaces. + - `aws.ec2.on_demand_failover_for_errors`: EC2 error codes that trigger an on-demand fallback after a Spot launch failure. + - `aws.ec2.scale_errors`: EC2 error codes treated as retryable scale-up failures. + - `aws.ec2.use_dedicated_host`: Enables the dedicated-host launch path, required for macOS runners. + EOT + + type = object({ + aws = optional(object({ + ec2 = optional(object({ + ami = optional(object({ + filter = optional(map(list(string)), { state = ["available"] }) + owners = optional(list(string), ["amazon"]) + id_ssm_parameter = optional(object({ + arn = string + }), null) + kms_key = optional(object({ + arn = string + }), null) + }), null) + vpc_id = string + subnet_ids = list(string) + overrides = optional(object({ + name_runner = optional(string, "") + name_sg = optional(string, "") + }), {}) + instance_profile = optional(object({ + name = string + }), null) + instance_profile_path = optional(string, null) + binaries_syncer = optional(object({ + enabled = optional(bool, true) + s3 = optional(object({ + arn = string + id = string + key = string + }), null) + }), {}) + block_device_mappings = optional(list(object({ + delete_on_termination = optional(bool, true) + device_name = optional(string, "/dev/xvda") + encrypted = optional(bool, true) + iops = optional(number) + kms_key_id = optional(string) + snapshot_id = optional(string) + throughput = optional(number) + volume_initialization_rate = optional(number) + volume_size = number + volume_type = optional(string, "gp3") + })), [{ volume_size = 30 }]) + ebs_optimized = optional(bool, false) + instance_target_capacity_type = optional(string, "spot") + instance_allocation_strategy = optional(string, "lowest-price") + instance_type_priorities = optional(map(number), null) + instance_max_spot_price = optional(string, null) + instance_types = list(string) + user_data = optional(object({ + enabled = optional(bool, true) + template = optional(string, null) + content = optional(string, null) + pre_install = optional(string, "") + post_install = optional(string, "") + debug_logging_enabled = optional(bool, false) + }), {}) + ssm_enabled = optional(bool, false) + create_service_linked_role_spot = optional(bool, false) + cloudwatch_agent = optional(object({ + enabled = optional(bool, true) + config = optional(string, null) + }), {}) + managed_security_group_enabled = optional(bool, true) + log_files = optional(list(object({ + log_group_name = string + prefix_log_group = bool + file_path = string + log_stream_name = string + log_class = optional(string, "STANDARD") + })), null) + key_name = optional(string, null) + additional_security_group_ids = optional(list(string), []) + detailed_monitoring_enabled = optional(bool, false) + egress_rules = optional(list(object({ + cidr_blocks = list(string) + ipv6_cidr_blocks = list(string) + prefix_list_ids = list(string) + from_port = number + protocol = string + security_groups = list(string) + self = bool + to_port = number + description = string + })), [{ + cidr_blocks = ["0.0.0.0/0"] + ipv6_cidr_blocks = ["::/0"] + prefix_list_ids = null + from_port = 0 + protocol = "-1" + security_groups = null + self = null + to_port = 0 + description = null + }]) + tags = optional(map(string), {}) + metadata_options = optional(object({ + instance_metadata_tags = optional(string, "enabled") + http_endpoint = optional(string, "enabled") + http_tokens = optional(string, "required") + http_put_response_hop_limit = optional(number, 1) + }), {}) + credit_specification = optional(string, null) + cpu_options = optional(object({ + core_count = optional(number) + threads_per_core = optional(number) + amd_sev_snp = optional(string) + nested_virtualization = optional(string) + }), null) + placement = optional(object({ + affinity = optional(string) + availability_zone = optional(string) + group_id = optional(string) + group_name = optional(string) + host_id = optional(string) + host_resource_group_arn = optional(string) + spread_domain = optional(string) + tenancy = optional(string) + partition_number = optional(number) + }), null) + license_specifications = optional(list(object({ + license_configuration_arn = string + })), []) + associate_public_ipv4_address = optional(bool, false) + on_demand_failover_for_errors = optional(list(string), []) + scale_errors = optional(list(string), [ + "UnfulfillableCapacity", + "MaxSpotInstanceCountExceeded", + "TargetCapacityLimitExceededException", + "RequestLimitExceeded", + "ResourceLimitExceeded", + "MaxSpotInstanceCountExceeded", + "MaxSpotFleetRequestCountExceeded", + "InsufficientInstanceCapacity", + "InsufficientCapacityOnHost", + ]) + use_dedicated_host = optional(bool, false) + }), null) + microvm = optional(object({ + image_arn = string + image_version = optional(string, null) + ingress_network_connectors = optional(list(string), []) + egress_network_connectors = optional(list(string), []) + cloudwatch_agent = optional(object({ + enabled = optional(bool, true) + config = optional(string, null) + }), {}) + log_files = optional(list(object({ + log_group_name = string + prefix_log_group = bool + file_path = string + log_stream_name = string + log_class = optional(string, "STANDARD") + })), null) + environment_variables = optional(map(string), {}) + iam = optional(object({ + resource_arns = optional(object({ + images = optional(list(string), null) + }), {}) + additional_policy_json = optional(object({ + scale_up = optional(string, null) + }), {}) + managed_policies = optional(object({ + scale_up = optional(object({ + arn = string + }), null) + pool = optional(object({ + arn = string + }), null) + }), {}) + }), {}) + }), null) + }), {}) + }) + +} diff --git a/modules/runner-config/variables.orchestration-provider.tf b/modules/runner-config/variables.orchestration-provider.tf new file mode 100644 index 0000000000..6d176ad6d7 --- /dev/null +++ b/modules/runner-config/variables.orchestration-provider.tf @@ -0,0 +1,141 @@ +# Typed orchestration-provider input boundary between the common runner configuration and demand controllers. +variable "orchestration_provider" { + description = <<-EOT + Runner demand-orchestration provider configuration. Exactly one provider block must be non-null. Wrapper presence selects the provider and must therefore be known during planning; values inside the selected provider may remain unknown until apply. + + - `webhook`: Selects the workflow-job webhook control plane. It owns runner lifecycle and capacity, the build queue reference, the runner-control artifact, scale-up, scale-down, scheduled pool, and optional job-retry controls. Future providers can be added as sibling blocks without moving this contract. + - `webhook.runner`: Runner lifecycle, boot timeout, and capacity settings owned by webhook orchestration. + - `webhook.runner.boot_time_in_minutes`: Expected runner boot duration used by scale-down and pool controls. The default is `5`. + - `webhook.runner.ephemeral`: Registers runners in ephemeral mode. The default is `false`. + - `webhook.runner.jit_config_enabled`: Explicitly enables or disables just-in-time configuration. The default is null, which follows `runner.ephemeral`. + - `webhook.runner.maximum_count`: Maximum number of runners managed for this runner configuration. The default is `3`. + - `webhook.github.organization_runners`: Registers runners at organization scope when true; otherwise registration is repository-scoped. + - `webhook.queue.build.arn`: ARN of the runner configuration's build queue. + - `webhook.queue.build.url`: URL of the runner configuration's build queue. + - `webhook.queue.kms_key_id`: Optional KMS key ARN encrypting the build queue. The default is null and is independent from the Parameter Store KMS key. + - `webhook.queue.tags`: Tags inherited by queue-related provider resources before component-specific overrides. The default is `{}`. + - `webhook.lambda.artifact`: Runner-control artifact shared by scale, pool, and job-retry components. Set at most one of `zip` or `s3`; no selection uses the packaged runner archive. + - `webhook.lambda.artifact.zip`: Optional local path to the runner-control Lambda archive. The default is null. + - `webhook.lambda.artifact.s3`: Optional S3 object selector in the common `lambda.artifact.s3.bucket`. Wrapper presence must be known during planning, selecting it requires a non-null common bucket, and the default is null. + - `webhook.lambda.artifact.s3.key`: Object key of the runner-control Lambda archive. + - `webhook.lambda.artifact.s3.object_version`: Optional object version of the runner-control Lambda archive. The default is null. + - `webhook.lambda.scale.up.memory_size`: Memory allocated to the scale-up Lambda in MB. The default is `512`. + - `webhook.lambda.scale.up.timeout`: Scale-up Lambda timeout in seconds. The default is `60`. + - `webhook.lambda.scale.up.reserved_concurrent_executions`: Reserved concurrency for scale-up. The default is `1`; use `-1` for unreserved concurrency. + - `webhook.lambda.scale.up.job_queued_check_enabled`: Enables queued-job verification before scaling. The default is null, which follows the resolved runner mode. + - `webhook.lambda.scale.up.event_source_mapping.batch_size`: Maximum build-queue records delivered per scale-up invocation. The default is `10`. + - `webhook.lambda.scale.up.event_source_mapping.maximum_batching_window_in_seconds`: Maximum batching window for build-queue records. The default is `0`. + - `webhook.lambda.scale.up.tags`: Tags applied within scale-up resource scopes after common provider tags. The default is `{}`. + - `webhook.lambda.scale.down.memory_size`: Memory allocated to the scale-down Lambda in MB. The default is `512`. + - `webhook.lambda.scale.down.timeout`: Scale-down Lambda timeout in seconds. The default is `60`. + - `webhook.lambda.scale.down.schedule_expression`: EventBridge schedule expression that invokes scale-down. The default is `cron(*/5 * * * ? *)`. + - `webhook.lambda.scale.down.minimum_running_time_in_minutes`: Optional minimum runner age before scale-down may terminate it. The default is null, which selects the operating-system default. + - `webhook.lambda.scale.down.idle_config`: Time-based desired idle-runner configurations. The default is `[]`. + - `webhook.lambda.scale.down.idle_config[].cron`: Cron expression identifying when the idle configuration applies. + - `webhook.lambda.scale.down.idle_config[].timeZone`: IANA time zone used to evaluate the cron expression. + - `webhook.lambda.scale.down.idle_config[].idleCount`: Number of idle runners retained during the matching period. + - `webhook.lambda.scale.down.idle_config[].evictionStrategy`: Selection strategy used when excess idle runners are removed. The default is `oldest_first`. + - `webhook.lambda.scale.down.tags`: Tags applied within scale-down resource scopes after common provider tags. The default is `{}`. + - `webhook.lambda.pool.memory_size`: Memory allocated to the pool Lambda in MB. The default is `512`. + - `webhook.lambda.pool.timeout`: Pool Lambda timeout in seconds. The default is `60`. + - `webhook.lambda.pool.reserved_concurrent_executions`: Reserved concurrency for the pool Lambda. The default is `1`; use `-1` for unreserved concurrency. + - `webhook.lambda.pool.config`: Scheduled target pool sizes. The default is `[]`, which disables the pool component. + - `webhook.lambda.pool.config[].schedule_expression`: Scheduler expression that activates the target size. + - `webhook.lambda.pool.config[].schedule_expression_timezone`: Optional IANA time zone used to evaluate the schedule. + - `webhook.lambda.pool.config[].size`: Desired number of runners for the schedule. + - `webhook.lambda.pool.include_busy_runners`: Includes busy runners when reconciling scheduled pool capacity. The default is `false`. + - `webhook.lambda.pool.runner_owner`: Optional GitHub organization or repository owner used for pooled runners. The default is null. + - `webhook.lambda.pool.tags`: Tags applied within pool resource scopes after common provider tags. The default is `{}`. + - `webhook.job_retry.enabled`: Creates the retry queue, Lambda function, event-source mapping, and related IAM resources. The default is `false`. + - `webhook.job_retry.delay_in_seconds`: Initial delay before a queued-job retry check. The default is `300`. + - `webhook.job_retry.delay_backoff`: Multiplier applied to the delay after each unsuccessful check. The default is `2`. + - `webhook.job_retry.max_attempts`: Maximum retry-check attempts before the message is no longer republished. The default is `1`. + - `webhook.job_retry.tags`: Tags applied within job-retry resource scopes after common provider tags. The default is `{}`. + - `webhook.job_retry.lambda.memory_size`: Memory allocated to the job-retry Lambda in MB. The default is `256`. + - `webhook.job_retry.lambda.reserved_concurrent_executions`: Reserved concurrency for job retry. The default is `1`; use `-1` for unreserved concurrency. + - `webhook.job_retry.lambda.timeout`: Job-retry Lambda timeout in seconds and visibility timeout for its retry queue. The default is `30`. + EOT + type = object({ + webhook = optional(object({ + runner = optional(object({ + boot_time_in_minutes = optional(number, 5) + ephemeral = optional(bool, false) + jit_config_enabled = optional(bool, null) + maximum_count = optional(number, 3) + }), {}) + github = object({ + organization_runners = bool + }) + queue = object({ + build = object({ + arn = string + url = string + }) + kms_key_id = optional(string, null) + tags = optional(map(string), {}) + }) + lambda = optional(object({ + artifact = optional(object({ + zip = optional(string, null) + s3 = optional(object({ + key = string + object_version = optional(string, null) + }), null) + }), {}) + scale = optional(object({ + up = optional(object({ + memory_size = optional(number, 512) + timeout = optional(number, 60) + reserved_concurrent_executions = optional(number, 1) + job_queued_check_enabled = optional(bool, null) + event_source_mapping = optional(object({ + batch_size = optional(number, 10) + maximum_batching_window_in_seconds = optional(number, 0) + }), {}) + tags = optional(map(string), {}) + }), {}) + down = optional(object({ + memory_size = optional(number, 512) + timeout = optional(number, 60) + schedule_expression = optional(string, "cron(*/5 * * * ? *)") + minimum_running_time_in_minutes = optional(number, null) + idle_config = optional(list(object({ + cron = string + timeZone = string + idleCount = number + evictionStrategy = optional(string, "oldest_first") + })), []) + tags = optional(map(string), {}) + }), {}) + }), {}) + pool = optional(object({ + memory_size = optional(number, 512) + timeout = optional(number, 60) + reserved_concurrent_executions = optional(number, 1) + config = optional(list(object({ + schedule_expression = string + schedule_expression_timezone = optional(string) + size = number + })), []) + include_busy_runners = optional(bool, false) + runner_owner = optional(string, null) + tags = optional(map(string), {}) + }), {}) + }), {}) + job_retry = optional(object({ + enabled = optional(bool, false) + delay_in_seconds = optional(number, 300) + delay_backoff = optional(number, 2) + max_attempts = optional(number, 1) + tags = optional(map(string), {}) + lambda = optional(object({ + memory_size = optional(number, 256) + reserved_concurrent_executions = optional(number, 1) + timeout = optional(number, 30) + }), {}) + }), {}) + }), null) + }) + nullable = false + +} diff --git a/modules/runner-config/variables.tf b/modules/runner-config/variables.tf new file mode 100644 index 0000000000..5928693ade --- /dev/null +++ b/modules/runner-config/variables.tf @@ -0,0 +1,246 @@ +variable "aws_region" { + description = "AWS region." + type = string +} + +variable "aws_partition" { + description = "AWS partition used to construct ARNs." + type = string + default = "aws" +} + +variable "prefix" { + description = "The prefix used for naming resources." + type = string + default = "github-actions" +} + +variable "tags" { + description = "Base tags added to taggable resources created by this runner configuration. Shared, component, and compute-provider tag maps override matching keys within their documented resource scopes." + type = map(string) + default = {} +} + +variable "runner" { + description = <<-EOT + Provider-neutral GitHub runner configuration. + + - `os`: Runner operating system. Supported values are `linux`, `osx`, and `windows`. + - `architecture`: Runner distribution architecture, such as `x64` or `arm64`. + - `disable_default_labels`: Prevents GitHub's default self-hosted, operating-system, and architecture labels from being registered. + - `labels`: Complete set of labels supplied to the control-plane functions. + - `group_name`: GitHub runner group used during registration. + - `name_prefix`: Prefix added to registered runner names. + - `run_as_root`: Runs the runner service as root when supported by the compute provider. + - `run_as`: Operating-system user used when `run_as_root` is false. + - `auto_update_disabled`: Disables the GitHub runner application's built-in updater. + - `tags`: Additional tags for common runner resources, currently the managed runner IAM role. These override module-level `tags` with the same key. + - `hooks.job_started`: Script content installed as the runner job-started hook. + - `hooks.job_completed`: Script content installed as the runner job-completed hook. + - `iam.role.arn`: ARN of an externally managed runner role. When set, this module does not create or modify that role. + - `iam.managed_policy_arns`: Named managed-policy ARNs attached to the module-managed runner role. + - `iam.additional_trust_policy_json`: Optional IAM policy document merged with the selected compute provider's default runner-role trust policy. + - `iam.path`: IAM path for the module-managed runner role. Defaults to a path derived from `prefix`. + - `iam.permissions_boundary`: Permissions-boundary ARN for the module-managed runner role. + EOT + type = object({ + os = optional(string, "linux") + architecture = optional(string, "x64") + disable_default_labels = optional(bool, false) + labels = list(string) + group_name = optional(string, "Default") + name_prefix = optional(string, "") + run_as_root = optional(bool, false) + run_as = optional(string, "ec2-user") + auto_update_disabled = optional(bool, false) + tags = optional(map(string), {}) + hooks = optional(object({ + job_started = optional(string, "") + job_completed = optional(string, "") + }), {}) + iam = optional(object({ + role = optional(object({ + arn = string + }), null) + managed_policy_arns = optional(map(string), {}) + additional_trust_policy_json = optional(string, null) + path = optional(string, null) + permissions_boundary = optional(string, null) + }), {}) + }) + +} + +variable "github" { + description = <<-EOT + GitHub API and runner-registration configuration. + + - `app_parameters.key_base64`: Ordered Parameter Store references for GitHub App private keys. + - `app_parameters.id`: Ordered Parameter Store references for GitHub App IDs. + - `app_parameters.installation_id`: Ordered optional Parameter Store references for GitHub App installation IDs. + - `enterprise_server.url`: Optional GitHub Enterprise Server base URL. Null selects GitHub.com. + - `enterprise_server.ssl_verify`: Enables TLS certificate verification for GitHub Enterprise Server requests. + - `user_agent`: Optional User-Agent value added to GitHub API requests. + EOT + type = object({ + app_parameters = object({ + key_base64 = list(map(string)) + id = list(map(string)) + installation_id = list(object({ name = string, arn = string })) + }) + enterprise_server = optional(object({ + url = optional(string, null) + ssl_verify = optional(bool, true) + }), {}) + user_agent = optional(string, null) + }) +} + +variable "lambda" { + description = <<-EOT + Common Lambda substrate independent of the selected runner orchestration provider. + + - `artifact.s3.bucket`: Optional shared S3 bucket containing component-owned Lambda artifacts. An orchestration provider selects its own object key and version; the bucket alone selects no artifact. + - `runtime`: Runtime used by the control-plane Lambda functions. + - `architecture`: Instruction-set architecture used by the control-plane Lambda functions. Supported values are `arm64` and `x86_64`. + - `subnet_ids`: Subnets used for Lambda VPC configuration. + - `security_group_ids`: Security groups used for Lambda VPC configuration. + - `tags`: Shared tags applied to Lambda function resources only. These override module-level `tags`; component `tags` override this map when keys conflict. + - `principals`: Additional principals allowed to assume the control-plane Lambda roles. + - `role.path`: IAM path for module-managed Lambda execution roles. Defaults to a path derived from `prefix`. + - `role.permissions_boundary`: Permissions-boundary ARN applied to module-managed Lambda execution roles. + EOT + type = object({ + artifact = optional(object({ + s3 = optional(object({ + bucket = optional(string, null) + }), {}) + }), {}) + runtime = optional(string, "nodejs24.x") + architecture = optional(string, "arm64") + subnet_ids = optional(list(string), []) + security_group_ids = optional(list(string), []) + tags = optional(map(string), {}) + principals = optional(list(object({ + type = string + identifiers = list(string) + })), []) + role = optional(object({ + path = optional(string, null) + permissions_boundary = optional(string, null) + }), {}) + }) + default = {} + +} + +variable "ssm" { + description = <<-EOT + Parameter Store paths, encryption, tag scopes, and housekeeper configuration. + + - `paths.root`: Root Parameter Store path for this runner configuration. + - `paths.tokens`: Path segment under `paths.root` used for registration tokens and just-in-time configuration. + - `paths.config`: Path segment under `paths.root` used for persistent runner configuration. + - `kms_key_id`: Optional customer-managed KMS key ARN used by control-plane IAM policies to decrypt shared GitHub App parameters. The ARN may be unknown until apply; null omits the provider-owned KMS statements. It does not select encryption for runtime-created runner parameters. + - `tags`: Shared tags for SSM-related resources. These override module-level `tags` and are inherited by parameter and housekeeper resources. + - `parameters.tags`: Tags for Terraform-managed runner configuration parameters and temporary parameters created by the scale-up and pool Lambdas. These override module-level and `ssm.tags` values with the same key. + - `housekeeper.schedule_expression`: EventBridge schedule expression that invokes the SSM housekeeper. + - `housekeeper.state`: EventBridge rule state, such as `ENABLED` or `DISABLED`. + - `housekeeper.tags`: Tags for housekeeper resources, including the Lambda function, log group, EventBridge rule, and IAM role. These override module-level, `ssm.tags`, shared Lambda, and shared log tags when keys conflict. + - `housekeeper.lambda.artifact`: Component-owned SSM-housekeeper artifact selection. Set at most one of `zip` or `s3`; when neither is selected, the module uses its packaged runner control-plane archive. This selector does not inherit an orchestration-provider artifact. + - `housekeeper.lambda.artifact.zip`: Optional local path to the SSM-housekeeper Lambda archive. + - `housekeeper.lambda.artifact.s3`: Optional object key and version in the shared `lambda.artifact.s3.bucket`. Selecting S3 requires that common bucket. + - `housekeeper.lambda.artifact.s3.key`: Object key of the SSM-housekeeper Lambda archive. + - `housekeeper.lambda.artifact.s3.object_version`: Optional object version of the SSM-housekeeper Lambda archive. + - `housekeeper.lambda.memory_size`: Memory allocated to the SSM housekeeper Lambda in MB. + - `housekeeper.lambda.timeout`: SSM housekeeper Lambda timeout in seconds. + - `housekeeper.config.tokenPath`: Parameter Store token path cleaned by the housekeeper. When omitted, the configured runner token path is used. + - `housekeeper.config.minimumDaysOld`: Minimum parameter age in days before deletion is allowed. + - `housekeeper.config.dryRun`: Reports eligible parameters without deleting them when true. + EOT + type = object({ + paths = object({ + root = string + tokens = string + config = string + }) + kms_key_id = optional(string, null) + tags = optional(map(string), {}) + parameters = optional(object({ + tags = optional(map(string), {}) + }), {}) + housekeeper = optional(object({ + schedule_expression = optional(string, "rate(1 day)") + state = optional(string, "ENABLED") + tags = optional(map(string), {}) + lambda = optional(object({ + artifact = optional(object({ + zip = optional(string, null) + s3 = optional(object({ + key = string + object_version = optional(string, null) + }), null) + }), {}) + memory_size = optional(number, 512) + timeout = optional(number, 60) + }), {}) + config = optional(object({ + tokenPath = optional(string) + minimumDaysOld = optional(number, 1) + dryRun = optional(bool, false) + }), {}) + }), {}) + }) + +} + +variable "observability" { + description = <<-EOT + Logging, tracing, and metrics configuration for control-plane and provider resources. + + - `logs.level`: Application log level supplied to the control-plane functions. + - `logs.retention_in_days`: CloudWatch Logs retention period. + - `logs.kms_key_id`: Optional KMS key ID or ARN used to encrypt CloudWatch log groups. + - `logs.class`: CloudWatch log-group class. Supported values are `STANDARD` and `INFREQUENT_ACCESS`. + - `logs.tags`: Shared tags for CloudWatch log groups. These override module-level `tags`; component `tags` override this map when keys conflict. + - `tracing.mode`: Optional Lambda active-tracing mode. Null disables X-Ray tracing configuration. + - `tracing.capture_http_requests`: Enables HTTP request capture in the tracing helper. + - `tracing.capture_error`: Enables error capture in the tracing helper. + - `metrics.enabled`: Enables module-emitted metrics. + - `metrics.namespace`: CloudWatch namespace used for emitted metrics. + - `metrics.metric.github_app_rate_limit.enabled`: Emits GitHub App rate-limit metrics. + - `metrics.metric.job_retry.enabled`: Emits job-retry metrics. + - `metrics.metric.spot_termination_warning.enabled`: Emits spot-termination warning metrics where supported. + EOT + type = object({ + logs = optional(object({ + level = optional(string, "info") + retention_in_days = optional(number, 180) + kms_key_id = optional(string, null) + class = optional(string, "STANDARD") + tags = optional(map(string), {}) + }), {}) + tracing = optional(object({ + mode = optional(string, null) + capture_http_requests = optional(bool, false) + capture_error = optional(bool, false) + }), {}) + metrics = optional(object({ + enabled = optional(bool, false) + namespace = optional(string, "GitHub Runners") + metric = optional(object({ + github_app_rate_limit = optional(object({ + enabled = optional(bool, true) + }), {}) + job_retry = optional(object({ + enabled = optional(bool, true) + }), {}) + spot_termination_warning = optional(object({ + enabled = optional(bool, true) + }), {}) + }), {}) + }), {}) + }) + default = {} + +} diff --git a/modules/runner-config/versions.tf b/modules/runner-config/versions.tf new file mode 100644 index 0000000000..3ef011ea0a --- /dev/null +++ b/modules/runner-config/versions.tf @@ -0,0 +1,10 @@ +terraform { + required_version = ">= 1.4.0" + + required_providers { + aws = { + source = "hashicorp/aws" + version = ">= 6.33" + } + } +} diff --git a/tests/ministack/README.md b/tests/ministack/README.md index b6442194ff..eb35b954a7 100644 --- a/tests/ministack/README.md +++ b/tests/ministack/README.md @@ -1,14 +1,17 @@ # MiniStack example tests The MiniStack workflow runs the `base`, `prebuilt`, `default`, `ephemeral`, -`multi-runner`, and `termination-watcher` examples directly with Terraform -1.4.0 and the latest Terraform release. +`multi-runner`, `multi-runner-v2`, `microvm-foundation`, and `termination-watcher` examples directly +with Terraform 1.4.0 and the latest Terraform release. The examples with input variables get their inputs from their own tfvars files in this directory. The `termination-watcher` example has no input variables -and uses the configuration checked into the example itself. No override files, -setup module, or checked-in Terraform fixture configuration is used. The -helper creates and removes a temporary AMI override for `default` and -`ephemeral`, and temporary SSM parameters for `multi-runner`. +and uses the configuration checked into the example itself. The +`microvm-foundation` lane uses an isolated tfvars file with no network +connectors because MiniStack does not provide the regional Lambda Network +Connector API. No override files or setup module are checked in. The helper +creates and removes a temporary AMI override for `default` and +`ephemeral`, temporary SSM parameters for `multi-runner`, and temporary AMI +fixtures plus an override for `multi-runner-v2`. Start MiniStack, set the AWS endpoint and test credentials, then run: @@ -23,6 +26,10 @@ tests/ministack/run-example.sh apply ephemeral # or tests/ministack/run-example.sh apply multi-runner # or +tests/ministack/run-example.sh apply multi-runner-v2 +# or +tests/ministack/run-example.sh apply microvm-foundation +# or tests/ministack/run-example.sh apply termination-watcher ``` diff --git a/tests/ministack/microvm-foundation.tfvars b/tests/ministack/microvm-foundation.tfvars new file mode 100644 index 0000000000..9d576d77c7 --- /dev/null +++ b/tests/ministack/microvm-foundation.tfvars @@ -0,0 +1,3 @@ +aws_region = "eu-west-1" + +network_connectors = {} diff --git a/tests/ministack/multi-runner-v2.tfvars b/tests/ministack/multi-runner-v2.tfvars new file mode 100644 index 0000000000..0d646a95f2 --- /dev/null +++ b/tests/ministack/multi-runner-v2.tfvars @@ -0,0 +1,7 @@ +environment = "ministack-multi-runner-v2" +aws_region = "eu-west-1" + +github_app = { + id = "0" + key_base64 = "ministack-invalid-key" +} diff --git a/tests/ministack/run-example.sh b/tests/ministack/run-example.sh index e1a1b6a813..8961f71db9 100755 --- a/tests/ministack/run-example.sh +++ b/tests/ministack/run-example.sh @@ -6,22 +6,23 @@ export AWS_ACCESS_KEY_ID="${AWS_ACCESS_KEY_ID:-000000000000}" export AWS_SECRET_ACCESS_KEY="${AWS_SECRET_ACCESS_KEY:-test-only}" export AWS_DEFAULT_REGION="${AWS_DEFAULT_REGION:-eu-west-1}" export AWS_REGION="${AWS_REGION:-eu-west-1}" -export AWS_ENDPOINT_URL="${AWS_ENDPOINT_URL:-http://127.0.0.1:4566}" +export AWS_ENDPOINT_URL="${AWS_ENDPOINT_URL:-http://localhost:4566}" export AWS_EC2_METADATA_DISABLED="${AWS_EC2_METADATA_DISABLED:-true}" action="${1:-}" example="${2:-}" tfvars_file="${3:-${MINISTACK_TFVARS_FILE:-}}" +microvm_foundation_default_tfvars=false case "$example" in - base | prebuilt | default | ephemeral | multi-runner) + base | prebuilt | default | ephemeral | multi-runner | multi-runner-v2 | microvm-foundation) use_tfvars=true ;; termination-watcher) use_tfvars=false ;; *) - echo "Supported examples for the runner are: base, prebuilt, default, ephemeral, multi-runner, termination-watcher" >&2 + echo "Supported examples for the runner are: base, prebuilt, default, ephemeral, multi-runner, multi-runner-v2, microvm-foundation, termination-watcher" >&2 exit 64 ;; esac @@ -29,7 +30,7 @@ esac case "$action" in init | plan | apply | destroy) ;; *) - echo "Usage: $0 {init|plan|apply|destroy} {base|prebuilt|default|ephemeral|multi-runner|termination-watcher} [TFVARS_FILE]" >&2 + echo "Usage: $0 {init|plan|apply|destroy} {base|prebuilt|default|ephemeral|multi-runner|multi-runner-v2|microvm-foundation|termination-watcher} [TFVARS_FILE]" >&2 exit 64 ;; esac @@ -41,6 +42,9 @@ example_root="$source_root/examples/$example" if [ "$use_tfvars" = true ]; then if [ -z "$tfvars_file" ]; then tfvars_file="$script_dir/$example.tfvars" + if [ "$example" = microvm-foundation ]; then + microvm_foundation_default_tfvars=true + fi fi case "$tfvars_file" in @@ -53,6 +57,7 @@ if [ "$use_tfvars" = true ]; then echo "Pass it as the third argument or set MINISTACK_TFVARS_FILE." >&2 exit 66 fi + fi lambda_fixture_dir="" @@ -60,6 +65,7 @@ lambda_created_paths="" ami_created_ids="" ssm_created_names="" override_created_paths="" +tfvars_created_paths="" lambda_zip_paths=" $source_root/lambdas/functions/ami-housekeeper/ami-housekeeper.zip $source_root/lambdas/functions/control-plane/runners.zip @@ -73,6 +79,10 @@ cleanup() { rm -f "$override_file" done + for fixture_file in $tfvars_created_paths; do + rm -f "$fixture_file" + done + for name in $ssm_created_names; do ministack_aws ssm delete-parameter --name "$name" >/dev/null 2>&1 || true done @@ -150,6 +160,48 @@ create_ssm_fixture() { $name" } +create_microvm_foundation_fixture() { + vpc_id=$(ministack_aws ec2 describe-vpcs \ + --filters Name=is-default,Values=true \ + --query 'Vpcs[0].VpcId' \ + --output text) + subnet_id=$(ministack_aws ec2 describe-subnets \ + --filters "Name=vpc-id,Values=$vpc_id" "Name=state,Values=available" \ + --query 'Subnets[0].SubnetId' \ + --output text) + + case "$vpc_id" in + vpc-[0-9a-f]*) ;; + *) + echo "MiniStack default VPC fixture was not found." >&2 + exit 70 + ;; + esac + + case "$subnet_id" in + subnet-[0-9a-f]*) ;; + *) + echo "MiniStack default subnet fixture was not found." >&2 + exit 70 + ;; + esac + + fixture_tfvars=$(mktemp "${TMPDIR:-/tmp}/terraform-aws-github-runner-microvm-foundation.XXXXXX") + printf '%s\n' \ + "aws_region = \"$AWS_DEFAULT_REGION\"" \ + '' \ + 'network_connectors = {' \ + ' ministack = {' \ + ' name = "ministack"' \ + " vpc_id = \"$vpc_id\"" \ + " subnet_ids = [\"$subnet_id\"]" \ + ' }' \ + '}' > "$fixture_tfvars" + tfvars_created_paths="$tfvars_created_paths +$fixture_tfvars" + tfvars_file="$fixture_tfvars" +} + create_ami_override() { override_file="$example_root/zz_ministack_ami_override.tf" printf '%s\n' \ @@ -195,6 +247,111 @@ create_multi_runner_override() { $override_file" } +create_multi_runner_v2_override() { + override_file="$example_root/zz_ministack_override.tf" + printf '%s\n' \ + 'module "runners" {' \ + ' global_config_compute_provider = {' \ + ' aws = {' \ + ' ec2 = {' \ + ' vpc_id = module.base.vpc.vpc_id' \ + ' subnet_ids = module.base.vpc.private_subnets' \ + ' ssm_enabled = true' \ + ' runner_binaries = {' \ + ' enabled = false' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + ' multi_runner_config = {' \ + ' linux-arm64 = {' \ + ' runner = {' \ + ' architecture = "arm64"' \ + ' name_prefix = "amazon-arm64-"' \ + ' extra_labels = ["amazon"]' \ + ' }' \ + ' orchestration_provider = {' \ + ' webhook = {' \ + ' runner = { maximum_count = 1 }' \ + ' matcherConfig = {' \ + ' exactMatch = true' \ + ' labelMatchers = [["self-hosted", "linux", "arm64", "amazon"]]' \ + ' }' \ + ' }' \ + ' }' \ + ' compute_provider = {' \ + ' aws = {' \ + ' ec2 = {' \ + ' instance_types = ["t4g.large", "c6g.large"]' \ + ' ami = {' \ + ' filter = { name = ["ministack-v2-linux-arm64"], state = ["available"] }' \ + ' owners = ["self"]' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + ' linux-x64 = {' \ + ' runner = {' \ + ' name_prefix = "amazon-x64-"' \ + ' extra_labels = ["amazon"]' \ + ' }' \ + ' orchestration_provider = {' \ + ' webhook = {' \ + ' runner = { ephemeral = true, maximum_count = 1 }' \ + ' matcherConfig = {' \ + ' labelMatchers = [["self-hosted", "linux", "x64", "amazon"]]' \ + ' exactMatch = false' \ + ' priority = 1' \ + ' }' \ + ' queue = { delay_webhook_event = 0 }' \ + ' job_retry = { enabled = true }' \ + ' }' \ + ' }' \ + ' compute_provider = {' \ + ' aws = {' \ + ' ec2 = {' \ + ' instance_types = ["m5a.large", "m5ad.large"]' \ + ' ami = {' \ + ' filter = { name = ["ministack-v2-linux-x64"], state = ["available"] }' \ + ' owners = ["self"]' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + ' windows-x64 = {' \ + ' runner = {' \ + ' os = "windows"' \ + ' name_prefix = "windows-x64-"' \ + ' }' \ + ' orchestration_provider = {' \ + ' webhook = {' \ + ' runner = { boot_time_in_minutes = 20, maximum_count = 1 }' \ + ' matcherConfig = {' \ + ' exactMatch = true' \ + ' labelMatchers = [["self-hosted", "windows", "x64", "servercore-2022"]]' \ + ' }' \ + ' }' \ + ' }' \ + ' compute_provider = {' \ + ' aws = {' \ + ' ec2 = {' \ + ' instance_types = ["m5.large", "c5.large"]' \ + ' ami = {' \ + ' filter = { name = ["ministack-v2-windows-x64"], state = ["available"] }' \ + ' owners = ["self"]' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + ' }' \ + '}' > "$override_file" + override_created_paths="$override_created_paths +$override_file" +} + create_ministack_fixtures() { if ! command -v aws >/dev/null 2>&1; then echo "AWS CLI is required to seed MiniStack API fixtures." >&2 @@ -213,6 +370,10 @@ create_ministack_fixtures() { wait_for_ministack + if [ "$microvm_foundation_default_tfvars" = true ]; then + create_microvm_foundation_fixture + fi + lambda_fixture_dir=$(mktemp -d "${TMPDIR:-/tmp}/terraform-aws-github-runner-ministack-lambda.XXXXXX") printf '%s\n' 'exports.handler = async () => ({ statusCode: 200, body: "ministack" });' > "$lambda_fixture_dir/index.js" (CDPATH='' cd -- "$lambda_fixture_dir" && zip -q ministack-lambda.zip index.js) @@ -245,6 +406,12 @@ $lambda_zip" "/aws/service/ami-amazon-linux-latest/al2023-ami-kernel-6.1-arm64" \ "ami-0abcdef1234567890" ;; + multi-runner-v2) + create_multi_runner_v2_override + create_ami_fixture "ministack-v2-linux-arm64" arm64 >/dev/null + create_ami_fixture "ministack-v2-linux-x64" x86_64 >/dev/null + create_ami_fixture "ministack-v2-windows-x64" x86_64 >/dev/null + ;; esac }