From fd485019da935076697abffbde92c97caf9df9bc Mon Sep 17 00:00:00 2001 From: Ashwin A Nayar Date: Sat, 16 Nov 2024 15:22:49 +0530 Subject: [PATCH 1/3] feat: Natively support runner job started/completed hooks (#4260) Pre and post job hooks were added to github actions to help administrators run custom scripts at the beginning and end of every job. As of today the module doesn't support these options out of the box. Add variables to accept these optional scripts and register the hook in user-data. Also enrich linux-arm64 example in multi-runner with pre/post hooks Related to: https://github.com/philips-labs/terraform-aws-github-runner/issues/3854 --- .../templates/runner-configs/linux-arm64.yaml | 9 +++++++++ examples/multi-runner/templates/user-data.sh | 14 ++++++++++++++ main.tf | 2 ++ modules/multi-runner/runners.tf | 16 +++++++++------- modules/multi-runner/variables.tf | 4 ++++ modules/runners/main.tf | 4 +++- modules/runners/templates/user-data.sh | 16 ++++++++++++++++ modules/runners/variables.tf | 12 ++++++++++++ variables.tf | 12 ++++++++++++ 9 files changed, 81 insertions(+), 8 deletions(-) diff --git a/examples/multi-runner/templates/runner-configs/linux-arm64.yaml b/examples/multi-runner/templates/runner-configs/linux-arm64.yaml index 7cfe859242..3699ae823e 100644 --- a/examples/multi-runner/templates/runner-configs/linux-arm64.yaml +++ b/examples/multi-runner/templates/runner-configs/linux-arm64.yaml @@ -18,3 +18,12 @@ runner_config: runners_maximum_count: 1 delay_webhook_event: 0 scale_down_schedule_expression: cron(* * * * ? *) + runner_hook_job_started: | + echo "Running pre job hook as \$(whoami)" + + # Clean github workspace from previous runs + if [[ -n "\$GITHUB_WORKSPACE" ]]; do + rm -rf "\$GITHUB_WORKSPACE" + done + runner_hook_job_completed: | + echo "Running post job hook as \$(whoami)" diff --git a/examples/multi-runner/templates/user-data.sh b/examples/multi-runner/templates/user-data.sh index 752a0de0e3..2d9a605362 100644 --- a/examples/multi-runner/templates/user-data.sh +++ b/examples/multi-runner/templates/user-data.sh @@ -81,4 +81,18 @@ ${post_install} cd /opt/actions-runner +%{ if hook_job_started != "" } +cat > /opt/actions-runner/hook_job_started.sh << EOF +${hook_job_started} +EOF +echo ACTIONS_RUNNER_HOOK_JOB_STARTED=/opt/actions-runner/hook_job_started.sh | tee -a /opt/actions-runner/.env +%{ endif } + +%{ if hook_job_completed != "" } +cat > /opt/actions-runner/hook_job_completed.sh << EOF +${hook_job_completed} +EOF +echo ACTIONS_RUNNER_HOOK_JOB_COMPLETED=/opt/actions-runner/hook_job_completed.sh | tee -a /opt/actions-runner/.env +%{ endif } + ${start_runner} diff --git a/main.tf b/main.tf index 8a02e470e3..1051d497be 100644 --- a/main.tf +++ b/main.tf @@ -249,6 +249,8 @@ module "runners" { userdata_content = var.userdata_content userdata_pre_install = var.userdata_pre_install userdata_post_install = var.userdata_post_install + runner_hook_job_started = var.runner_hook_job_started + runner_hook_job_completed = var.runner_hook_job_completed key_name = var.key_name runner_ec2_tags = var.runner_ec2_tags diff --git a/modules/multi-runner/runners.tf b/modules/multi-runner/runners.tf index 02df61a47b..52f268a167 100644 --- a/modules/multi-runner/runners.tf +++ b/modules/multi-runner/runners.tf @@ -86,13 +86,15 @@ module "runners" { role_path = var.role_path role_permissions_boundary = var.role_permissions_boundary - enable_userdata = each.value.runner_config.enable_userdata - userdata_template = each.value.runner_config.userdata_template - userdata_content = each.value.runner_config.userdata_content - userdata_pre_install = each.value.runner_config.userdata_pre_install - userdata_post_install = each.value.runner_config.userdata_post_install - key_name = var.key_name - runner_ec2_tags = each.value.runner_config.runner_ec2_tags + enable_userdata = each.value.runner_config.enable_userdata + userdata_template = each.value.runner_config.userdata_template + userdata_content = each.value.runner_config.userdata_content + userdata_pre_install = each.value.runner_config.userdata_pre_install + userdata_post_install = each.value.runner_config.userdata_post_install + runner_hook_job_started = each.value.runner_config.runner_hook_job_started + runner_hook_job_completed = each.value.runner_config.runner_hook_job_completed + key_name = var.key_name + runner_ec2_tags = each.value.runner_config.runner_ec2_tags create_service_linked_role_spot = each.value.runner_config.create_service_linked_role_spot diff --git a/modules/multi-runner/variables.tf b/modules/multi-runner/variables.tf index d1d31b211c..243a482dd0 100644 --- a/modules/multi-runner/variables.tf +++ b/modules/multi-runner/variables.tf @@ -78,6 +78,8 @@ variable "multi_runner_config" { 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) @@ -180,6 +182,8 @@ variable "multi_runner_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`." diff --git a/modules/runners/main.tf b/modules/runners/main.tf index 625ebd4ed0..051d6713cd 100644 --- a/modules/runners/main.tf +++ b/modules/runners/main.tf @@ -54,7 +54,9 @@ locals { S3_LOCATION_RUNNER_DISTRIBUTION = local.s3_location_runner_distribution RUNNER_ARCHITECTURE = var.runner_architecture }) - post_install = var.userdata_post_install + post_install = var.userdata_post_install + hook_job_started = var.runner_hook_job_started + hook_job_completed = var.runner_hook_job_completed start_runner = templatefile(local.userdata_start_runner[var.runner_os], { metadata_tags = var.metadata_options != null ? var.metadata_options.instance_metadata_tags : "enabled" }) diff --git a/modules/runners/templates/user-data.sh b/modules/runners/templates/user-data.sh index 68edb79b0a..321cbc4e02 100644 --- a/modules/runners/templates/user-data.sh +++ b/modules/runners/templates/user-data.sh @@ -62,4 +62,20 @@ ${install_runner} ${post_install} +# Register runner job hooks +# Ref: https://github.com/actions/runner/blob/main/docs/adrs/1751-runner-job-hooks.md +%{ if hook_job_started != "" } +cat > /opt/actions-runner/hook_job_started.sh << EOF +${hook_job_started} +EOF +echo ACTIONS_RUNNER_HOOK_JOB_STARTED=/opt/actions-runner/hook_job_started.sh | tee -a /opt/actions-runner/.env +%{ endif } + +%{ if hook_job_completed != "" } +cat > /opt/actions-runner/hook_job_completed.sh << EOF +${hook_job_completed} +EOF +echo ACTIONS_RUNNER_HOOK_JOB_COMPLETED=/opt/actions-runner/hook_job_completed.sh | tee -a /opt/actions-runner/.env +%{ endif } + ${start_runner} diff --git a/modules/runners/variables.tf b/modules/runners/variables.tf index d39601cfce..4d55a479b5 100644 --- a/modules/runners/variables.tf +++ b/modules/runners/variables.tf @@ -172,6 +172,18 @@ variable "userdata_post_install" { default = "" } +variable "runner_hook_job_started" { + description = "Script to be ran in the runner environment at the beginning of every job" + type = string + default = "" +} + +variable "runner_hook_job_completed" { + description = "Script to be ran in the runner environment at the end of every job" + type = string + default = "" +} + variable "sqs_build_queue" { description = "SQS queue to consume accepted build events." type = object({ diff --git a/variables.tf b/variables.tf index a7d4267a1d..c0379d6194 100644 --- a/variables.tf +++ b/variables.tf @@ -280,6 +280,18 @@ variable "userdata_post_install" { description = "Script to be ran after the GitHub Actions runner is installed on the EC2 instances" } +variable "runner_hook_job_started" { + type = string + default = "" + description = "Script to be ran in the runner environment at the beginning of every job" +} + +variable "runner_hook_job_completed" { + type = string + default = "" + description = "Script to be ran in the runner environment at the end of every job" +} + variable "idle_config" { description = "List of time periods, defined as a 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." type = list(object({ From 31fdaa864e61dff6c72c6db7325226ff253ab320 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Thu, 21 Nov 2024 18:59:32 +0000 Subject: [PATCH 2/3] docs: auto update terraform docs --- README.md | 2 ++ modules/multi-runner/README.md | 2 +- modules/runners/README.md | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index b63bd8f609..df0ab67663 100644 --- a/README.md +++ b/README.md @@ -212,6 +212,8 @@ Talk to the forestkeepers in the `runners-channel` on Slack. | [runner\_egress\_rules](#input\_runner\_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 | | [runner\_extra\_labels](#input\_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 `enable_workflow_job_labels_check`. GitHub read-only labels should not be provided. | `list(string)` | `[]` | no | | [runner\_group\_name](#input\_runner\_group\_name) | Name of the runner group. | `string` | `"Default"` | no | +| [runner\_hook\_job\_completed](#input\_runner\_hook\_job\_completed) | Script to be ran in the runner environment at the end of every job | `string` | `""` | no | +| [runner\_hook\_job\_started](#input\_runner\_hook\_job\_started) | Script to be ran in the runner environment at the beginning of every job | `string` | `""` | no | | [runner\_iam\_role\_managed\_policy\_arns](#input\_runner\_iam\_role\_managed\_policy\_arns) | Attach AWS or customer-managed IAM policies (by ARN) to the runner IAM role | `list(string)` | `[]` | no | | [runner\_log\_files](#input\_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. | 
list(object({
    log_group_name   = string
    prefix_log_group = bool
    file_path        = string
    log_stream_name  = string
  }))
| `null` | no | | [runner\_metadata\_options](#input\_runner\_metadata\_options) | Metadata options for the ec2 runner instances. By default, the module uses metadata tags for bootstrapping the runner, only disable `instance_metadata_tags` when using custom scripts for starting the runner. | `map(any)` | 
{
  "http_endpoint": "enabled",
  "http_put_response_hop_limit": 1,
  "http_tokens": "required",
  "instance_metadata_tags": "enabled"
}
| no | diff --git a/modules/multi-runner/README.md b/modules/multi-runner/README.md index 625e865117..6fbbc868f7 100644 --- a/modules/multi-runner/README.md +++ b/modules/multi-runner/README.md @@ -150,7 +150,7 @@ module "multi-runner" { | [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 | | [metrics\_namespace](#input\_metrics\_namespace) | The namespace for the metrics created by the module. Merics will only be created if explicit enabled. | `string` | `null` | 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\_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."
}
fifo: "Enable a FIFO queue to remain the order of events received by the webhook. Suggest to set to true for repo level runners."
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_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)
    })
    fifo = optional(bool, false)
    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\_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."
}
fifo: "Enable a FIFO queue to remain the order of events received by the webhook. Suggest to set to true for repo level runners."
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)
    })
    fifo = optional(bool, false)
    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/runners/README.md b/modules/runners/README.md index df16693009..0603796472 100644 --- a/modules/runners/README.md +++ b/modules/runners/README.md @@ -203,6 +203,8 @@ yarn run dist | [runner\_disable\_default\_labels](#input\_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`. | `bool` | `false` | no | | [runner\_ec2\_tags](#input\_runner\_ec2\_tags) | Map of tags that will be added to the launch template instance tag specifications. | `map(string)` | `{}` | no | | [runner\_group\_name](#input\_runner\_group\_name) | Name of the runner group. | `string` | `"Default"` | no | +| [runner\_hook\_job\_completed](#input\_runner\_hook\_job\_completed) | Script to be ran in the runner environment at the end of every job | `string` | `""` | no | +| [runner\_hook\_job\_started](#input\_runner\_hook\_job\_started) | Script to be ran in the runner environment at the beginning of every job | `string` | `""` | no | | [runner\_iam\_role\_managed\_policy\_arns](#input\_runner\_iam\_role\_managed\_policy\_arns) | Attach AWS or customer-managed IAM policies (by ARN) to the runner IAM role | `list(string)` | `[]` | no | | [runner\_labels](#input\_runner\_labels) | All the labels for the runners (GitHub) including the default one's(e.g: self-hosted, linux, x64, label1, label2). Separate each label by a comma | `list(string)` | n/a | yes | | [runner\_log\_files](#input\_runner\_log\_files) | (optional) List of logfiles to send to CloudWatch, will only be used if `enable_cloudwatch_agent` is set to true. Object description: `log_group_name`: Name of the log group, `prefix_log_group`: If true, the log group name will be prefixed with `/github-self-hosted-runners/`, `file_path`: path to the log file, `log_stream_name`: name of the log stream. | 
list(object({
    log_group_name   = string
    prefix_log_group = bool
    file_path        = string
    log_stream_name  = string
  }))
| `null` | no | From 8d87c135a3d6f08d0737e1f70c2d660632acdd32 Mon Sep 17 00:00:00 2001 From: Niek Palm Date: Fri, 20 Dec 2024 13:43:46 +0100 Subject: [PATCH 3/3] chore: simplify broken script --- .../multi-runner/templates/runner-configs/linux-arm64.yaml | 5 ----- 1 file changed, 5 deletions(-) diff --git a/examples/multi-runner/templates/runner-configs/linux-arm64.yaml b/examples/multi-runner/templates/runner-configs/linux-arm64.yaml index 3699ae823e..34817cc36c 100644 --- a/examples/multi-runner/templates/runner-configs/linux-arm64.yaml +++ b/examples/multi-runner/templates/runner-configs/linux-arm64.yaml @@ -20,10 +20,5 @@ runner_config: scale_down_schedule_expression: cron(* * * * ? *) runner_hook_job_started: | echo "Running pre job hook as \$(whoami)" - - # Clean github workspace from previous runs - if [[ -n "\$GITHUB_WORKSPACE" ]]; do - rm -rf "\$GITHUB_WORKSPACE" - done runner_hook_job_completed: | echo "Running post job hook as \$(whoami)"