{
- logger.info(`Received ${payload.eventType} from ${payload.repositoryOwner}/${payload.repositoryName}`);
-
+ logger.debug(`Received event`, { payload });
if (eventSource !== 'aws:sqs') throw Error('Cannot handle non-SQS events!');
+
+ const dynamicEc2TypesEnabled = yn(process.env.ENABLE_DYNAMIC_EC2_TYPES, { default: false });
+ const requestedInstanceType = payload.labels?.find(label => label.startsWith('ghr-ec2-'))?.replace('ghr-ec2-', '');
+
+ if (dynamicEc2TypesEnabled && requestedInstanceType) {
+ logger.info(`Dynamic EC2 instance type requested: ${requestedInstanceType}`);
+ }
+
+ // Store the requested instance type for use in createRunners
+ const ec2Config = {
+ ...payload,
+ requestedInstanceType: dynamicEc2TypesEnabled ? requestedInstanceType : undefined,
+ };
const enableOrgLevel = yn(process.env.ENABLE_ORGANIZATION_RUNNERS, { default: true });
const maximumRunners = parseInt(process.env.RUNNERS_MAXIMUM_COUNT || '3');
- const runnerLabels = process.env.RUNNER_LABELS || '';
+
+ // Combine configured runner labels with dynamic EC2 instance type label if present
+ let runnerLabels = process.env.RUNNER_LABELS || '';
+ if (dynamicEc2TypesEnabled && requestedInstanceType) {
+ const ec2Label = `ghr-ec2-${requestedInstanceType}`;
+ runnerLabels = runnerLabels ? `${runnerLabels},${ec2Label}` : ec2Label;
+ logger.debug(`Added dynamic EC2 instance type label: ${ec2Label} to runner config.`);
+ }
+
const runnerGroup = process.env.RUNNER_GROUP_NAME || 'Default';
const environment = process.env.ENVIRONMENT;
const ssmTokenPath = process.env.SSM_TOKEN_PATH;
@@ -337,6 +372,7 @@ export async function scaleUp(eventSource: string, payload: ActionRequestMessage
onDemandFailoverOnError,
},
githubInstallationClient,
+ ec2Config.requestedInstanceType,
);
await publishRetryMessage(payload);
diff --git a/lambdas/functions/webhook/src/runners/dispatch.ts b/lambdas/functions/webhook/src/runners/dispatch.ts
index a7a3a0307c..9855b1b55a 100644
--- a/lambdas/functions/webhook/src/runners/dispatch.ts
+++ b/lambdas/functions/webhook/src/runners/dispatch.ts
@@ -45,6 +45,7 @@ async function handleWorkflowJob(
installationId: body.installation?.id ?? 0,
queueId: queue.id,
repoOwnerType: body.repository.owner.type,
+ labels: body.workflow_job.labels,
});
logger.info(`Successfully dispatched job for ${body.repository.full_name} to the queue ${queue.id}`);
return {
@@ -70,13 +71,16 @@ export function canRunJob(
runnerLabelsMatchers: string[][],
workflowLabelCheckAll: boolean,
): boolean {
+ // Filter out ghr-ec2- labels as they are handled by the dynamic EC2 instance type feature
+ const filteredLabels = workflowJobLabels.filter(label => !label.startsWith('ghr-ec2-'));
+
runnerLabelsMatchers = runnerLabelsMatchers.map((runnerLabel) => {
return runnerLabel.map((label) => label.toLowerCase());
});
const matchLabels = workflowLabelCheckAll
- ? runnerLabelsMatchers.some((rl) => workflowJobLabels.every((wl) => rl.includes(wl.toLowerCase())))
- : runnerLabelsMatchers.some((rl) => workflowJobLabels.some((wl) => rl.includes(wl.toLowerCase())));
- const match = workflowJobLabels.length === 0 ? !matchLabels : matchLabels;
+ ? runnerLabelsMatchers.some((rl) => filteredLabels.every((wl) => rl.includes(wl.toLowerCase())))
+ : runnerLabelsMatchers.some((rl) => filteredLabels.some((wl) => rl.includes(wl.toLowerCase())));
+ const match = filteredLabels.length === 0 ? !matchLabels : matchLabels;
logger.debug(
`Received workflow job event with labels: '${JSON.stringify(workflowJobLabels)}'. The event does ${
diff --git a/lambdas/functions/webhook/src/sqs/index.ts b/lambdas/functions/webhook/src/sqs/index.ts
index a028d7dcc4..062a4e0ba9 100644
--- a/lambdas/functions/webhook/src/sqs/index.ts
+++ b/lambdas/functions/webhook/src/sqs/index.ts
@@ -6,12 +6,13 @@ const logger = createChildLogger('sqs');
export interface ActionRequestMessage {
id: number;
- eventType: string;
repositoryName: string;
repositoryOwner: string;
+ eventType: string;
installationId: number;
queueId: string;
repoOwnerType: string;
+ labels?: string[];
}
export interface MatcherConfig {
diff --git a/main.tf b/main.tf
index b9456c0a52..d85153097d 100644
--- a/main.tf
+++ b/main.tf
@@ -187,8 +187,9 @@ module "runners" {
github_app_parameters = local.github_app_parameters
enable_organization_runners = var.enable_organization_runners
enable_ephemeral_runners = var.enable_ephemeral_runners
- enable_jit_config = var.enable_jit_config
+ enable_dynamic_ec2_types = var.enable_dynamic_ec2_types
enable_job_queued_check = var.enable_job_queued_check
+ enable_jit_config = var.enable_jit_config
enable_on_demand_failover_for_errors = var.enable_runner_on_demand_failover_for_errors
disable_runner_autoupdate = var.disable_runner_autoupdate
enable_managed_runner_security_group = var.enable_managed_runner_security_group
diff --git a/modules/multi-runner/README.md b/modules/multi-runner/README.md
index dca32e2662..004a6297b1 100644
--- a/modules/multi-runner/README.md
+++ b/modules/multi-runner/README.md
@@ -148,7 +148,7 @@ module "multi-runner" {
| [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) | multi\_runner\_config = {
runner\_config: {
runner\_os: "The EC2 Operating System type to use for action runner instances (linux,windows)."
runner\_architecture: "The platform architecture of the runner instance\_type."
runner\_metadata\_options: "(Optional) Metadata options for the ec2 runner instances."
ami\_filter: "(Optional) List of maps used to create the AMI filter for the action runner AMI. By default amazon linux 2 is used."
ami\_owners: "(Optional) The list of owners used to select the AMI of action runner instances."
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 confiugration 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."
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 spot instances. AWS recommends to use `capacity-optimized` however the AWS default is `lowest-price`."
instance\_max\_spot\_price: "Max price price for spot intances 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 and 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` desiables 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."
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 avaialbe. In case you upgradeing 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."
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`."
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 insances 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 reate 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)."
}
matcherConfig: {
labelMatchers: "The list of list of labels supported by the runner configuration. `[[self-hosted, linux, x64, example]]`"
exactMatch: "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."
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."
}
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({
runner_config = 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_filter = optional(map(list(string)), { state = ["available"] })
ami_owners = optional(list(string), ["amazon"])
ami_id_ssm_parameter_name = optional(string, null)
ami_kms_key_arn = optional(string, "")
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), [])
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_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)
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")
})), [])
runner_log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = 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_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)
}), {})
})
matcherConfig = object({
labelMatchers = list(list(string))
exactMatch = optional(bool, false)
priority = optional(number, 999)
})
redrive_build_queue = optional(object({
enabled = bool
maxReceiveCount = number
}), {
enabled = false
maxReceiveCount = null
})
})) | n/a | yes |
+| [multi\_runner\_config](#input\_multi\_runner\_config) | multi\_runner\_config = {
runner\_config: {
runner\_os: "The EC2 Operating System type to use for action runner instances (linux,windows)."
runner\_architecture: "The platform architecture of the runner instance\_type."
runner\_metadata\_options: "(Optional) Metadata options for the ec2 runner instances."
ami\_filter: "(Optional) List of maps used to create the AMI filter for the action runner AMI. By default amazon linux 2 is used."
ami\_owners: "(Optional) The list of owners used to select the AMI of action runner instances."
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\_dynamic\_ec2\_types: "Enable dynamic EC2 instance types based on workflow job labels. When enabled, jobs can request specific instance types via the 'gh-ec2-instance-type' label (e.g., 'gh-ec2-t3.large')."
enable\_job\_queued\_check: "(Optional) Only scale if the job event received by the scale up lambda is is in the state queued. By default enabled for non ephemeral runners and disabled for ephemeral. Set this variable to overwrite the default behavior."
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."
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 spot instances. AWS recommends to use `capacity-optimized` however the AWS default is `lowest-price`."
instance\_max\_spot\_price: "Max price price for spot intances 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 and 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` desiables 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."
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 avaialbe. In case you upgradeing 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."
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`."
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 insances 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 reate 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)."
}
matcherConfig: {
labelMatchers: "The list of list of labels supported by the runner configuration. `[[self-hosted, linux, x64, example]]`"
exactMatch: "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."
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."
}
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({
runner_config = 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_filter = optional(map(list(string)), { state = ["available"] })
ami_owners = optional(list(string), ["amazon"])
ami_id_ssm_parameter_name = optional(string, null)
ami_kms_key_arn = optional(string, "")
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_dynamic_ec2_types = optional(bool, false)
enable_job_queued_check = optional(bool, null)
enable_on_demand_failover_for_errors = optional(list(string), [])
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_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)
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")
})), [])
runner_log_files = optional(list(object({
log_group_name = string
prefix_log_group = bool
file_path = string
log_stream_name = 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_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)
}), {})
})
matcherConfig = object({
labelMatchers = list(list(string))
exactMatch = optional(bool, false)
priority = optional(number, 999)
})
redrive_build_queue = optional(object({
enabled = bool
maxReceiveCount = number
}), {
enabled = false
maxReceiveCount = null
})
})) | n/a | yes |
| [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 |
| [prefix](#input\_prefix) | The prefix used for naming resources | `string` | `"github-actions"` | no |
diff --git a/modules/multi-runner/variables.tf b/modules/multi-runner/variables.tf
index ff4419d4d9..58ce5d6278 100644
--- a/modules/multi-runner/variables.tf
+++ b/modules/multi-runner/variables.tf
@@ -75,6 +75,7 @@ variable "multi_runner_config" {
disable_runner_autoupdate = optional(bool, false)
ebs_optimized = optional(bool, false)
enable_ephemeral_runners = optional(bool, false)
+ enable_dynamic_ec2_types = optional(bool, false)
enable_job_queued_check = optional(bool, null)
enable_on_demand_failover_for_errors = optional(list(string), [])
enable_organization_runners = optional(bool, false)
@@ -179,7 +180,8 @@ variable "multi_runner_config" {
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 confiugration 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_dynamic_ec2_types: "Enable dynamic EC2 instance types based on workflow job labels. When enabled, jobs can request specific instance types via the 'gh-ec2-instance-type' label (e.g., 'gh-ec2-t3.large')."
+ enable_job_queued_check: "(Optional) Only scale if the job event received by the scale up lambda is is in the state queued. By default enabled for non ephemeral runners and disabled for ephemeral. Set this variable to overwrite the default behavior."
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."
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."
diff --git a/modules/runners/README.md b/modules/runners/README.md
index 2d8e11a0c3..9cd4f974e8 100644
--- a/modules/runners/README.md
+++ b/modules/runners/README.md
@@ -147,6 +147,7 @@ yarn run dist
| [ebs\_optimized](#input\_ebs\_optimized) | The EC2 EBS optimized configuration. | `bool` | `false` | no |
| [egress\_rules](#input\_egress\_rules) | List of egress rules for the GitHub runner instances. | 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"
],
"description": null,
"from_port": 0,
"ipv6_cidr_blocks": [
"::/0"
],
"prefix_list_ids": null,
"protocol": "-1",
"security_groups": null,
"self": null,
"to_port": 0
}
]
| no |
| [enable\_cloudwatch\_agent](#input\_enable\_cloudwatch\_agent) | Enabling the cloudwatch agent on the ec2 runner instances, the runner contains default config. Configuration can be overridden via `cloudwatch_config`. | `bool` | `true` | no |
+| [enable\_dynamic\_ec2\_types](#input\_enable\_dynamic\_ec2\_types) | Enable dynamic EC2 instance types based on workflow job labels. When enabled, jobs can request specific instance types via the 'gh:ec2:instance-type' label. | `bool` | `false` | no |
| [enable\_ephemeral\_runners](#input\_enable\_ephemeral\_runners) | Enable ephemeral runners, runners will only be used once. | `bool` | `false` | no |
| [enable\_jit\_config](#input\_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 avaialbe. In case you upgradeing from 3.x to 4.x you can set `enable_jit_config` to `false` to avoid a breaking change when having your own AMI. | `bool` | `null` | no |
| [enable\_job\_queued\_check](#input\_enable\_job\_queued\_check) | Only scale if the job event received by the scale up lambda is is in the state queued. By default enabled for non ephemeral runners and disabled for ephemeral. Set this variable to overwrite the default behavior. | `bool` | `null` | no |
diff --git a/modules/runners/scale-up.tf b/modules/runners/scale-up.tf
index 538487ca8a..36c062c763 100644
--- a/modules/runners/scale-up.tf
+++ b/modules/runners/scale-up.tf
@@ -28,6 +28,7 @@ resource "aws_lambda_function" "scale_up" {
AMI_ID_SSM_PARAMETER_NAME = var.ami_id_ssm_parameter_name
DISABLE_RUNNER_AUTOUPDATE = var.disable_runner_autoupdate
ENABLE_EPHEMERAL_RUNNERS = var.enable_ephemeral_runners
+ ENABLE_DYNAMIC_EC2_TYPES = var.enable_dynamic_ec2_types
ENABLE_JIT_CONFIG = var.enable_jit_config
ENABLE_JOB_QUEUED_CHECK = local.enable_job_queued_check
ENABLE_METRIC_GITHUB_APP_RATE_LIMIT = var.metrics.enable && var.metrics.metric.enable_github_app_rate_limit
diff --git a/modules/runners/variables.tf b/modules/runners/variables.tf
index 08109008fd..1127411dfa 100644
--- a/modules/runners/variables.tf
+++ b/modules/runners/variables.tf
@@ -526,6 +526,12 @@ variable "enable_ephemeral_runners" {
default = false
}
+variable "enable_dynamic_ec2_types" {
+ description = "Enable dynamic EC2 instance types based on workflow job labels. When enabled, jobs can request specific instance types via the 'gh:ec2:instance-type' label."
+ type = bool
+ default = false
+}
+
variable "enable_job_queued_check" {
description = "Only scale if the job event received by the scale up lambda is is in the state queued. By default enabled for non ephemeral runners and disabled for ephemeral. Set this variable to overwrite the default behavior."
type = bool
diff --git a/variables.tf b/variables.tf
index cb30dcef5d..14f97af78f 100644
--- a/variables.tf
+++ b/variables.tf
@@ -647,6 +647,12 @@ variable "enable_ephemeral_runners" {
default = false
}
+variable "enable_dynamic_ec2_types" {
+ description = "Enable dynamic EC2 instance types based on workflow job labels. When enabled, jobs can request specific instance types via the 'gh-ec2-instance-type' label (e.g., 'gh-ec2-t3.large')."
+ type = bool
+ default = false
+}
+
variable "enable_job_queued_check" {
description = "Only scale if the job event received by the scale up lambda is in the queued state. By default enabled for non ephemeral runners and disabled for ephemeral. Set this variable to overwrite the default behavior."
type = bool