refactor: remove custom friom variable and add default values

Author: edersonbrilhante

README.md

@@ -117,7 +117,7 @@ Join our discord community via [this invite link](https://discord.gg/bxgXW8jJGh)
 | <a name="input_block_device_mappings"></a> [block\_device\_mappings](#input\_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`. | <pre>list(object({<br/>    delete_on_termination = optional(bool, true)<br/>    device_name           = optional(string, "/dev/xvda")<br/>    encrypted             = optional(bool, true)<br/>    iops                  = optional(number)<br/>    kms_key_id            = optional(string)<br/>    snapshot_id           = optional(string)<br/>    throughput            = optional(number)<br/>    volume_size           = number<br/>    volume_type           = optional(string, "gp3")<br/>  }))</pre> | <pre>[<br/>  {<br/>    "volume_size": 30<br/>  }<br/>]</pre> | no |
 | <a name="input_cloudwatch_config"></a> [cloudwatch\_config](#input\_cloudwatch\_config) | (optional) Replaces the module's default cloudwatch log config. See https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch-Agent-Configuration-File-Details.html for details. | `string` | `null` | no |
 | <a name="input_create_service_linked_role_spot"></a> [create\_service\_linked\_role\_spot](#input\_create\_service\_linked\_role\_spot) | (optional) create the service linked role for spot instances that is required by the scale-up lambda. | `bool` | `false` | no |
-| <a name="input_custom_scale_errors"></a> [custom\_scale\_errors](#input\_custom\_scale\_errors) | List of aws error codesthat should trigger retry during scale up. This list will replace the default errors defined in the variable `defaultScaleErrors` in https://github.com/github-aws-runners/terraform-aws-github-runner/blob/main/lambdas/functions/control-plane/src/aws/runners.ts | `list(string)` | `[]` | no |
+| <a name="input_scale_errors"></a> [custom\_scale\_errors](#input\_custom\_scale\_errors) | List of aws error codesthat should trigger retry during scale up. This list will replace the default errors defined in the variable `defaultScaleErrors` in https://github.com/github-aws-runners/terraform-aws-github-runner/blob/main/lambdas/functions/control-plane/src/aws/runners.ts | `list(string)` | `[]` | no |
 | <a name="input_delay_webhook_event"></a> [delay\_webhook\_event](#input\_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. | `number` | `30` | no |
 | <a name="input_disable_runner_autoupdate"></a> [disable\_runner\_autoupdate](#input\_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/) | `bool` | `false` | no |
 | <a name="input_enable_ami_housekeeper"></a> [enable\_ami\_housekeeper](#input\_enable\_ami\_housekeeper) | Option to disable the lambda to clean up old AMIs. | `bool` | `false` | no |

lambdas/functions/control-plane/src/aws/runners.d.ts

@@ -44,5 +44,5 @@ export interface RunnerInputParameters {
   amiIdSsmParameterName?: string;
   tracingEnabled?: boolean;
   onDemandFailoverOnError?: string[];
-  customScaleErrors?: string[];
+  scaleErrors: string[];
 }

lambdas/functions/control-plane/src/aws/runners.test.ts

@@ -458,19 +458,6 @@ describe('create runner with errors', () => {
     expect(mockSSMClient).not.toHaveReceivedCommand(PutParameterCommand);
   });
 
-  it('test ScaleError with custom scale error.', async () => {
-    createFleetMockWithErrors(['CustomAWSError']);
-
-    await expect(
-      createRunner(createRunnerConfig({ ...defaultRunnerConfig, customScaleErrors: ['CustomAWSError'] })),
-    ).rejects.toBeInstanceOf(ScaleError);
-    expect(mockEC2Client).toHaveReceivedCommandWith(
-      CreateFleetCommand,
-      expectedCreateFleetRequest(defaultExpectedFleetRequestValues),
-    );
-    expect(mockSSMClient).not.toHaveReceivedCommand(PutParameterCommand);
-  });
-
   it('test ScaleError with multiple error.', async () => {
     createFleetMockWithErrors(['UnfulfillableCapacity', 'MaxSpotInstanceCountExceeded', 'NotMappedError']);
 
@@ -713,7 +700,7 @@ interface RunnerConfig {
   amiIdSsmParameterName?: string;
   tracingEnabled?: boolean;
   onDemandFailoverOnError?: string[];
-  customScaleErrors?: string[];
+  scaleErrors: string[];
 }
 
 function createRunnerConfig(runnerConfig: RunnerConfig): RunnerInputParameters {
@@ -733,7 +720,7 @@ function createRunnerConfig(runnerConfig: RunnerConfig): RunnerInputParameters {
     amiIdSsmParameterName: runnerConfig.amiIdSsmParameterName,
     tracingEnabled: runnerConfig.tracingEnabled,
     onDemandFailoverOnError: runnerConfig.onDemandFailoverOnError,
-    customScaleErrors: runnerConfig.customScaleErrors,
+    scaleErrors: runnerConfig.scaleErrors,
   };
 }
 

lambdas/functions/control-plane/src/aws/runners.ts

@@ -196,23 +196,7 @@ async function processFleetResult(
     return instances;
   }
 
-  // Educated guess of errors that would make sense to retry based on the list
-  // https://docs.aws.amazon.com/AWSEC2/latest/APIReference/errors-overview.html
-  const defaultScaleErrors = [
-    'UnfulfillableCapacity',
-    'MaxSpotInstanceCountExceeded',
-    'TargetCapacityLimitExceededException',
-    'RequestLimitExceeded',
-    'ResourceLimitExceeded',
-    'MaxSpotInstanceCountExceeded',
-    'MaxSpotFleetRequestCountExceeded',
-    'InsufficientInstanceCapacity',
-  ];
-
-  const scaleErrors =
-    runnerParameters.customScaleErrors && runnerParameters.customScaleErrors.length > 0
-      ? runnerParameters.customScaleErrors
-      : defaultScaleErrors;
+  const scaleErrors = runnerParameters.scaleErrors;
 
   const failedCount = countScaleErrors(errors, scaleErrors);
   if (failedCount > 0) {

lambdas/functions/control-plane/src/modules.d.ts

@@ -3,7 +3,7 @@ declare namespace NodeJS {
     AWS_REGION: string;
     ENABLE_METRIC_GITHUB_APP_RATE_LIMIT: string;
     ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS: string;
-    CUSTOM_SCALE_ERRORS: string;
+    SCALE_ERRORS: string;
     ENVIRONMENT: string;
     GHES_URL: string;
     JOB_RETRY_CONFIG: string;

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

@@ -41,9 +41,7 @@ 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 customScaleErrors = process.env.CUSTOM_SCALE_ERRORS
-    ? (JSON.parse(process.env.CUSTOM_SCALE_ERRORS) as [string])
-    : [];
+  const scaleErrors = JSON.parse(process.env.SCALE_ERRORS) as [string];
 
   const { ghesApiUrl, ghesBaseUrl } = getGitHubEnterpriseApiUrl();
 
@@ -98,7 +96,7 @@ export async function adjust(event: PoolEvent): Promise<void> {
         amiIdSsmParameterName,
         tracingEnabled,
         onDemandFailoverOnError,
-        customScaleErrors,
+        scaleErrors,
       },
       topUp,
       githubInstallationClient,

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

@@ -105,7 +105,7 @@ const EXPECTED_RUNNER_PARAMS: RunnerInputParameters = {
   subnets: ['subnet-123'],
   tracingEnabled: false,
   onDemandFailoverOnError: [],
-  customScaleErrors: [],
+  scaleErrors: ['UnfulfillableCapacity', 'MaxSpotInstanceCountExceeded', 'TargetCapacityLimitExceededException'],
 };
 let expectedRunnerParams: RunnerInputParameters;
 
@@ -123,7 +123,8 @@ function setDefaults() {
   process.env.INSTANCE_TYPES = 'm5.large';
   process.env.INSTANCE_TARGET_CAPACITY_TYPE = 'spot';
   process.env.ENABLE_ON_DEMAND_FAILOVER = undefined;
-  process.env.CUSTOM_SCALE_ERRORS = undefined;
+  process.env.SCALE_ERRORS =
+    '["UnfulfillableCapacity","MaxSpotInstanceCountExceeded","TargetCapacityLimitExceededException"]';
 }
 
 beforeEach(() => {
@@ -813,11 +814,11 @@ describe('scaleUp with public GH', () => {
 
     it('creates a runner with correct config and labels and custom scale errors enabled.', async () => {
       process.env.RUNNER_LABELS = 'label1,label2';
-      process.env.CUSTOM_SCALE_ERRORS = JSON.stringify(['RequestLimitExceeded']);
+      process.env.SCALE_ERRORS = JSON.stringify(['RequestLimitExceeded']);
       await scaleUpModule.scaleUp(TEST_DATA);
       expect(createRunner).toBeCalledWith({
         ...expectedRunnerParams,
-        customScaleErrors: ['RequestLimitExceeded'],
+        scaleErrors: ['RequestLimitExceeded'],
       });
     });
 

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

@@ -62,7 +62,7 @@ interface CreateEC2RunnerConfig {
   amiIdSsmParameterName?: string;
   tracingEnabled?: boolean;
   onDemandFailoverOnError?: string[];
-  customScaleErrors?: string[];
+  scaleErrors: string[];
 }
 
 function generateRunnerServiceConfig(githubRunnerConfig: CreateGitHubRunnerConfig, token: string) {
@@ -256,9 +256,7 @@ export async function scaleUp(payloads: ActionRequestMessageSQS[]): Promise<stri
   const onDemandFailoverOnError = process.env.ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS
     ? (JSON.parse(process.env.ENABLE_ON_DEMAND_FAILOVER_FOR_ERRORS) as [string])
     : [];
-  const customScaleErrors = process.env.CUSTOM_SCALE_ERRORS
-    ? (JSON.parse(process.env.CUSTOM_SCALE_ERRORS) as [string])
-    : [];
+  const scaleErrors = JSON.parse(process.env.SCALE_ERRORS) as [string];
 
   const { ghesApiUrl, ghesBaseUrl } = getGitHubEnterpriseApiUrl();
 
@@ -435,7 +433,7 @@ export async function scaleUp(payloads: ActionRequestMessageSQS[]): Promise<stri
         amiIdSsmParameterName,
         tracingEnabled,
         onDemandFailoverOnError,
-        customScaleErrors,
+        scaleErrors,
       },
       newRunners,
       githubInstallationClient,

main.tf

@@ -187,7 +187,7 @@ module "runners" {
   enable_jit_config                    = var.enable_jit_config
   enable_job_queued_check              = var.enable_job_queued_check
   enable_on_demand_failover_for_errors = var.enable_runner_on_demand_failover_for_errors
-  custom_scale_errors                  = var.custom_scale_errors
+  scale_errors                         = var.scale_errors
   disable_runner_autoupdate            = var.disable_runner_autoupdate
   enable_managed_runner_security_group = var.enable_managed_runner_security_group
   enable_runner_detailed_monitoring    = var.enable_runner_detailed_monitoring