feat(control-plane): tag controll plane created SSM Parameters (#4833)

README.md

@@ -167,6 +167,7 @@ Join our discord community via [this invite link](https://discord.gg/bxgXW8jJGh)
 | <a name="input_matcher_config_parameter_store_tier"></a> [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 |
 | <a name="input_metrics"></a> [metrics](#input\_metrics) | Configuration for metrics created by the module, by default disabled to avoid additional costs. When metrics are enable all metrics are created unless explicit configured otherwise. | <pre>object({<br/>    enable    = optional(bool, false)<br/>    namespace = optional(string, "GitHub Runners")<br/>    metric = optional(object({<br/>      enable_github_app_rate_limit    = optional(bool, true)<br/>      enable_job_retry                = optional(bool, true)<br/>      enable_spot_termination_warning = optional(bool, true)<br/>    }), {})<br/>  })</pre> | `{}` | no |
 | <a name="input_minimum_running_time_in_minutes"></a> [minimum\_running\_time\_in\_minutes](#input\_minimum\_running\_time\_in\_minutes) | The time an ec2 action runner should be running at minimum before terminated, if not busy. | `number` | `null` | no |
+| <a name="input_parameter_store_tags"></a> [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 |
 | <a name="input_pool_config"></a> [pool\_config](#input\_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 weekdays 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). | <pre>list(object({<br/>    schedule_expression          = string<br/>    schedule_expression_timezone = optional(string)<br/>    size                         = number<br/>  }))</pre> | `[]` | no |
 | <a name="input_pool_lambda_memory_size"></a> [pool\_lambda\_memory\_size](#input\_pool\_lambda\_memory\_size) | Memory size limit for scale-up lambda. | `number` | `512` | no |
 | <a name="input_pool_lambda_reserved_concurrent_executions"></a> [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 |

lambdas/functions/control-plane/src/pool/pool.ts

@@ -41,6 +41,9 @@ export async function adjust(event: PoolEvent): Promise<void> {
   const onDemandFailoverOnError = process.env.ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS
     ? (JSON.parse(process.env.ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS) as [string])
     : [];
+  const ssmParameterStoreTags = process.env.SSM_PARAMETER_STORE_TAGS
+    ? JSON.parse(process.env.SSM_PARAMETER_STORE_TAGS)
+    : [];
 
   const { ghesApiUrl, ghesBaseUrl } = getGitHubEnterpriseApiUrl();
 
@@ -81,6 +84,7 @@ export async function adjust(event: PoolEvent): Promise<void> {
         disableAutoUpdate: disableAutoUpdate,
         ssmTokenPath,
         ssmConfigPath,
+        ssmParameterStoreTags,
       },
       {
         ec2instanceCriteria: {

lambdas/functions/control-plane/src/scale-runners/scale-up.ts

@@ -49,6 +49,7 @@ interface CreateGitHubRunnerConfig {
   disableAutoUpdate: boolean;
   ssmTokenPath: string;
   ssmConfigPath: string;
+  ssmParameterStoreTags: { Key: string; Value: string }[];
 }
 
 interface CreateEC2RunnerConfig {
@@ -182,6 +183,9 @@ async function getRunnerGroupId(githubRunnerConfig: CreateGitHubRunnerConfig, gh
           `${githubRunnerConfig.ssmConfigPath}/runner-group/${githubRunnerConfig.runnerGroup}`,
           runnerGroupId.toString(),
           false,
+          {
+            tags: githubRunnerConfig.ssmParameterStoreTags,
+          },
         );
       } catch (err) {
         logger.debug('Error storing runner group id in SSM Parameter Store', err as Error);
@@ -251,6 +255,10 @@ export async function scaleUp(eventSource: string, payload: ActionRequestMessage
   const onDemandFailoverOnError = process.env.ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS
     ? (JSON.parse(process.env.ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS) as [string])
     : [];
+  const ssmParameterStoreTags: { Key: string; Value: string }[] =
+    process.env.SSM_PARAMETER_STORE_TAGS && process.env.SSM_PARAMETER_STORE_TAGS.trim() !== ''
+      ? JSON.parse(process.env.SSM_PARAMETER_STORE_TAGS)
+      : [];
 
   if (ephemeralEnabled && payload.eventType !== 'workflow_job') {
     logger.warn(`${payload.eventType} event is not supported in combination with ephemeral runners.`);
@@ -321,6 +329,7 @@ export async function scaleUp(eventSource: string, payload: ActionRequestMessage
           disableAutoUpdate,
           ssmTokenPath,
           ssmConfigPath,
+          ssmParameterStoreTags,
         },
         {
           ec2instanceCriteria: {
@@ -407,7 +416,7 @@ async function createRegistrationTokenConfig(
 
   for (const instance of instances) {
     await putParameter(`${githubRunnerConfig.ssmTokenPath}/${instance}`, runnerServiceConfig.join(' '), true, {
-      tags: [{ Key: 'InstanceId', Value: instance }],
+      tags: [{ Key: 'InstanceId', Value: instance }, ...githubRunnerConfig.ssmParameterStoreTags],
     });
     if (isDelay) {
       // Delay to prevent AWS ssm rate limits by being within the max throughput limit
@@ -465,7 +474,7 @@ async function createJitConfig(githubRunnerConfig: CreateGitHubRunnerConfig, ins
       instance: instance,
     });
     await putParameter(`${githubRunnerConfig.ssmTokenPath}/${instance}`, runnerConfig.data.encoded_jit_config, true, {
-      tags: [{ Key: 'InstanceId', Value: instance }],
+      tags: [{ Key: 'InstanceId', Value: instance }, ...githubRunnerConfig.ssmParameterStoreTags],
     });
     if (isDelay) {
       // Delay to prevent AWS ssm rate limits by being within the max throughput limit

main.tf

@@ -232,6 +232,7 @@ module "runners" {
   runner_log_files                 = var.runner_log_files
   runner_group_name                = var.runner_group_name
   runner_name_prefix               = var.runner_name_prefix
+  parameter_store_tags             = var.parameter_store_tags
 
   scale_up_reserved_concurrent_executions = var.scale_up_reserved_concurrent_executions
 

modules/multi-runner/runners.tf

@@ -80,6 +80,7 @@ module "runners" {
   runner_log_files                 = each.value.runner_config.runner_log_files
   runner_group_name                = each.value.runner_config.runner_group_name
   runner_name_prefix               = each.value.runner_config.runner_name_prefix
+  parameter_store_tags             = var.parameter_store_tags
 
   scale_up_reserved_concurrent_executions = each.value.runner_config.scale_up_reserved_concurrent_executions
 

modules/multi-runner/variables.tf

@@ -718,3 +718,9 @@ variable "user_agent" {
   type        = string
   default     = "github-aws-runners"
 }
+
+variable "parameter_store_tags" {
+  description = "Map of tags that will be added to all the SSM Parameter Store parameters created by the Lambda function."
+  type        = map(string)
+  default     = {}
+}

modules/runners/README.md

@@ -194,6 +194,7 @@ yarn run dist
 | <a name="input_metrics"></a> [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. | <pre>object({<br/>    enable    = optional(bool, false)<br/>    namespace = optional(string, "GitHub Runners")<br/>    metric = optional(object({<br/>      enable_github_app_rate_limit    = optional(bool, true)<br/>      enable_job_retry                = optional(bool, true)<br/>      enable_spot_termination_warning = optional(bool, true)<br/>    }), {})<br/>  })</pre> | `{}` | no |
 | <a name="input_minimum_running_time_in_minutes"></a> [minimum\_running\_time\_in\_minutes](#input\_minimum\_running\_time\_in\_minutes) | The time an ec2 action runner should be running at minimum before terminated if non busy. If not set the default is calculated based on the OS. | `number` | `null` | no |
 | <a name="input_overrides"></a> [overrides](#input\_overrides) | This map provides the possibility to override some defaults. The following attributes are supported: `name_sg` overrides the `Name` tag for all security groups created by this module. `name_runner_agent_instance` overrides the `Name` tag for the ec2 instance defined in the auto launch configuration. `name_docker_machine_runners` overrides the `Name` tag spot instances created by the runner agent. | `map(string)` | <pre>{<br/>  "name_runner": "",<br/>  "name_sg": ""<br/>}</pre> | no |
+| <a name="input_parameter_store_tags"></a> [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 |
 | <a name="input_pool_config"></a> [pool\_config](#input\_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). | <pre>list(object({<br/>    schedule_expression          = string<br/>    schedule_expression_timezone = optional(string)<br/>    size                         = number<br/>  }))</pre> | `[]` | no |
 | <a name="input_pool_lambda_memory_size"></a> [pool\_lambda\_memory\_size](#input\_pool\_lambda\_memory\_size) | Lambda Memory size limit in MB for pool lambda | `number` | `512` | no |
 | <a name="input_pool_lambda_reserved_concurrent_executions"></a> [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 |

modules/runners/local.tf

@@ -0,0 +1,5 @@
+locals {
+  parameter_store_tags = "[${join(", ", [
+    for key, value in var.parameter_store_tags : "{ key = \"${key}\", value = \"${value}\" }"
+  ])}]"
+}

modules/runners/pool.tf

@@ -33,6 +33,7 @@ module "pool" {
       runtime                        = var.lambda_runtime
       timeout                        = var.pool_lambda_timeout
       zip                            = local.lambda_zip
+      parameter_store_tags           = local.parameter_store_tags
     }
     pool                      = var.pool_config
     role_path                 = local.role_path

modules/runners/pool/README.md

@@ -49,7 +49,7 @@ No modules.
 | Name | Description | Type | Default | Required |
 |------|-------------|------|---------|:--------:|
 | <a name="input_aws_partition"></a> [aws\_partition](#input\_aws\_partition) | (optional) partition for the arn if not 'aws' | `string` | `"aws"` | no |
-| <a name="input_config"></a> [config](#input\_config) | Lookup details in parent module. | <pre>object({<br/>    lambda = object({<br/>      log_level                      = string<br/>      logging_retention_in_days      = number<br/>      logging_kms_key_id             = string<br/>      reserved_concurrent_executions = number<br/>      s3_bucket                      = string<br/>      s3_key                         = string<br/>      s3_object_version              = string<br/>      security_group_ids             = list(string)<br/>      runtime                        = string<br/>      architecture                   = string<br/>      memory_size                    = number<br/>      timeout                        = number<br/>      zip                            = string<br/>      subnet_ids                     = list(string)<br/>    })<br/>    tags = map(string)<br/>    ghes = object({<br/>      url        = string<br/>      ssl_verify = string<br/>    })<br/>    github_app_parameters = object({<br/>      key_base64 = map(string)<br/>      id         = map(string)<br/>    })<br/>    subnet_ids = list(string)<br/>    runner = object({<br/>      disable_runner_autoupdate            = bool<br/>      ephemeral                            = bool<br/>      enable_jit_config                    = bool<br/>      enable_on_demand_failover_for_errors = list(string)<br/>      boot_time_in_minutes                 = number<br/>      labels                               = list(string)<br/>      launch_template = object({<br/>        name = string<br/>      })<br/>      group_name  = string<br/>      name_prefix = string<br/>      pool_owner  = string<br/>      role = object({<br/>        arn = string<br/>      })<br/>    })<br/>    instance_types                = list(string)<br/>    instance_target_capacity_type = string<br/>    instance_allocation_strategy  = string<br/>    instance_max_spot_price       = string<br/>    prefix                        = string<br/>    pool = list(object({<br/>      schedule_expression          = string<br/>      schedule_expression_timezone = string<br/>      size                         = number<br/>    }))<br/>    role_permissions_boundary            = string<br/>    kms_key_arn                          = string<br/>    ami_kms_key_arn                      = string<br/>    ami_id_ssm_parameter_arn             = string<br/>    role_path                            = string<br/>    ssm_token_path                       = string<br/>    ssm_config_path                      = string<br/>    ami_id_ssm_parameter_name            = string<br/>    ami_id_ssm_parameter_read_policy_arn = string<br/>    arn_ssm_parameters_path_config       = string<br/>    lambda_tags                          = map(string)<br/>    user_agent                           = string<br/>  })</pre> | n/a | yes |
+| <a name="input_config"></a> [config](#input\_config) | Lookup details in parent module. | <pre>object({<br/>    lambda = object({<br/>      log_level                      = string<br/>      logging_retention_in_days      = number<br/>      logging_kms_key_id             = string<br/>      reserved_concurrent_executions = number<br/>      s3_bucket                      = string<br/>      s3_key                         = string<br/>      s3_object_version              = string<br/>      security_group_ids             = list(string)<br/>      runtime                        = string<br/>      architecture                   = string<br/>      memory_size                    = number<br/>      timeout                        = number<br/>      zip                            = string<br/>      subnet_ids                     = list(string)<br/>      parameter_store_tags           = string<br/>    })<br/>    tags = map(string)<br/>    ghes = object({<br/>      url        = string<br/>      ssl_verify = string<br/>    })<br/>    github_app_parameters = object({<br/>      key_base64 = map(string)<br/>      id         = map(string)<br/>    })<br/>    subnet_ids = list(string)<br/>    runner = object({<br/>      disable_runner_autoupdate            = bool<br/>      ephemeral                            = bool<br/>      enable_jit_config                    = bool<br/>      enable_on_demand_failover_for_errors = list(string)<br/>      boot_time_in_minutes                 = number<br/>      labels                               = list(string)<br/>      launch_template = object({<br/>        name = string<br/>      })<br/>      group_name  = string<br/>      name_prefix = string<br/>      pool_owner  = string<br/>      role = object({<br/>        arn = string<br/>      })<br/>    })<br/>    instance_types                = list(string)<br/>    instance_target_capacity_type = string<br/>    instance_allocation_strategy  = string<br/>    instance_max_spot_price       = string<br/>    prefix                        = string<br/>    pool = list(object({<br/>      schedule_expression          = string<br/>      schedule_expression_timezone = string<br/>      size                         = number<br/>    }))<br/>    role_permissions_boundary            = string<br/>    kms_key_arn                          = string<br/>    ami_kms_key_arn                      = string<br/>    ami_id_ssm_parameter_arn             = string<br/>    role_path                            = string<br/>    ssm_token_path                       = string<br/>    ssm_config_path                      = string<br/>    ami_id_ssm_parameter_name            = string<br/>    ami_id_ssm_parameter_read_policy_arn = string<br/>    arn_ssm_parameters_path_config       = string<br/>    lambda_tags                          = map(string)<br/>    user_agent                           = string<br/>  })</pre> | n/a | yes |
 | <a name="input_tracing_config"></a> [tracing\_config](#input\_tracing\_config) | Configuration for lambda tracing. | <pre>object({<br/>    mode                  = optional(string, null)<br/>    capture_http_requests = optional(bool, false)<br/>    capture_error         = optional(bool, false)<br/>  })</pre> | `{}` | no |
 
 ## Outputs

modules/runners/pool/main.tf

@@ -47,6 +47,7 @@ resource "aws_lambda_function" "pool" {
       POWERTOOLS_TRACER_CAPTURE_HTTPS_REQUESTS = var.tracing_config.capture_http_requests
       POWERTOOLS_TRACER_CAPTURE_ERROR          = var.tracing_config.capture_error
       ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS     = jsonencode(var.config.runner.enable_on_demand_failover_for_errors)
+      SSM_PARAMETER_STORE_TAGS                 = var.config.lambda.parameter_store_tags
     }
   }
 

modules/runners/pool/variables.tf

@@ -16,6 +16,7 @@ variable "config" {
       timeout                        = number
       zip                            = string
       subnet_ids                     = list(string)
+      parameter_store_tags           = string
     })
     tags = map(string)
     ghes = object({

modules/runners/scale-up.tf

@@ -57,6 +57,7 @@ resource "aws_lambda_function" "scale_up" {
       POWERTOOLS_SERVICE_NAME                  = "runners-scale-up"
       SSM_TOKEN_PATH                           = local.token_path
       SSM_CONFIG_PATH                          = "${var.ssm_paths.root}/${var.ssm_paths.config}"
+      SSM_PARAMETER_STORE_TAGS                 = local.parameter_store_tags
       SUBNET_IDS                               = join(",", var.subnet_ids)
       ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS     = jsonencode(var.enable_on_demand_failover_for_errors)
       JOB_RETRY_CONFIG                         = jsonencode(local.job_retry_config)

modules/runners/variables.tf

@@ -770,3 +770,9 @@ variable "user_agent" {
   type        = string
   default     = null
 }
+
+variable "parameter_store_tags" {
+  description = "Map of tags that will be added to all the SSM Parameter Store parameters created by the Lambda function."
+  type        = map(string)
+  default     = {}
+}

variables.tf

@@ -1016,3 +1016,9 @@ variable "user_agent" {
   type        = string
   default     = "github-aws-runners"
 }
+
+variable "parameter_store_tags" {
+  description = "Map of tags that will be added to all the SSM Parameter Store parameters created by the Lambda function."
+  type        = map(string)
+  default     = {}
+}