CCM-14044 Setting prod defaults

Author: aidenvaines-cgi

infrastructure/terraform/components/api/README.md

@@ -21,8 +21,12 @@ No requirements.
 | <a name="input_enable_api_data_trace"></a> [enable\_api\_data\_trace](#input\_enable\_api\_data\_trace) | Enable API Gateway data trace logging | `bool` | `false` | no |
 | <a name="input_enable_backups"></a> [enable\_backups](#input\_enable\_backups) | Enable backups | `bool` | `false` | no |
 | <a name="input_enable_event_cache"></a> [enable\_event\_cache](#input\_enable\_event\_cache) | Enable caching of events to an S3 bucket | `bool` | `true` | no |
+| <a name="input_enable_event_publishing_anomaly_detection"></a> [enable\_event\_publishing\_anomaly\_detection](#input\_enable\_event\_publishing\_anomaly\_detection) | Enable CloudWatch anomaly detection alarm for SNS message publishing. Detects abnormal drops or spikes in event publishing volume. | `bool` | `true` | no |
 | <a name="input_enable_sns_delivery_logging"></a> [enable\_sns\_delivery\_logging](#input\_enable\_sns\_delivery\_logging) | Enable SNS Delivery Failure Notifications | `bool` | `true` | no |
 | <a name="input_environment"></a> [environment](#input\_environment) | The name of the tfscaffold environment | `string` | n/a | yes |
+| <a name="input_event_publishing_anomaly_band_width"></a> [event\_publishing\_anomaly\_band\_width](#input\_event\_publishing\_anomaly\_band\_width) | The width of the anomaly detection band. Higher values (e.g. 4-6) reduce sensitivity and noise, lower values (e.g. 2-3) increase sensitivity. Recommended: 2-4. | `number` | `5` | no |
+| <a name="input_event_publishing_anomaly_evaluation_periods"></a> [event\_publishing\_anomaly\_evaluation\_periods](#input\_event\_publishing\_anomaly\_evaluation\_periods) | Number of evaluation periods for the publishing anomaly alarm. Each period is defined by event\_publishing\_anomaly\_period. | `number` | `3` | no |
+| <a name="input_event_publishing_anomaly_period"></a> [event\_publishing\_anomaly\_period](#input\_event\_publishing\_anomaly\_period) | The period in seconds over which the specified statistic is applied for anomaly detection. Minimum 300 seconds (5 minutes). Recommended: 300-600. | `number` | `300` | no |
 | <a name="input_eventpub_control_plane_bus_arn"></a> [eventpub\_control\_plane\_bus\_arn](#input\_eventpub\_control\_plane\_bus\_arn) | ARN of the EventBridge control plane bus for eventpub | `string` | `""` | no |
 | <a name="input_eventpub_data_plane_bus_arn"></a> [eventpub\_data\_plane\_bus\_arn](#input\_eventpub\_data\_plane\_bus\_arn) | ARN of the EventBridge data plane bus for eventpub | `string` | `""` | no |
 | <a name="input_force_destroy"></a> [force\_destroy](#input\_force\_destroy) | Flag to force deletion of S3 buckets | `bool` | `false` | no |
@@ -52,7 +56,7 @@ No requirements.
 | <a name="module_ddb_alarms_mi"></a> [ddb\_alarms\_mi](#module\_ddb\_alarms\_mi) | ../../modules/alarms-ddb | n/a |
 | <a name="module_ddb_alarms_suppliers"></a> [ddb\_alarms\_suppliers](#module\_ddb\_alarms\_suppliers) | ../../modules/alarms-ddb | n/a |
 | <a name="module_domain_truststore"></a> [domain\_truststore](#module\_domain\_truststore) | https://github.com/NHSDigital/nhs-notify-shared-modules/releases/download/v2.0.26/terraform-s3bucket.zip | n/a |
-| <a name="module_eventpub"></a> [eventpub](#module\_eventpub) | https://github.com/NHSDigital/nhs-notify-shared-modules/releases/download/v2.0.31/terraform-eventpub.zip | n/a |
+| <a name="module_eventpub"></a> [eventpub](#module\_eventpub) | git::https://github.com/NHSDigital/nhs-notify-shared-modules.git//infrastructure/terraform/modules/eventpub | 3.0.4 |
 | <a name="module_eventsub"></a> [eventsub](#module\_eventsub) | ../../modules/eventsub | n/a |
 | <a name="module_get_letter"></a> [get\_letter](#module\_get\_letter) | https://github.com/NHSDigital/nhs-notify-shared-modules/releases/download/v2.0.29/terraform-lambda.zip | n/a |
 | <a name="module_get_letter_data"></a> [get\_letter\_data](#module\_get\_letter\_data) | https://github.com/NHSDigital/nhs-notify-shared-modules/releases/download/v2.0.29/terraform-lambda.zip | n/a |

infrastructure/terraform/components/api/modules_eventpub.tf

@@ -1,5 +1,5 @@
 module "eventpub" {
-  source = "https://github.com/NHSDigital/nhs-notify-shared-modules/releases/download/v2.0.31/terraform-eventpub.zip"
+  source = "git::https://github.com/NHSDigital/nhs-notify-shared-modules.git//infrastructure/terraform/modules/eventpub?ref=3.0.4"
 
   name = "eventpub"
 
@@ -31,7 +31,14 @@ module "eventpub" {
   additional_policies_for_event_cache_bucket = [
     data.aws_iam_policy_document.eventcache[0].json
   ]
+
+  # CloudWatch Anomaly Detection for publishing
+  enable_event_publishing_anomaly_detection   = var.enable_event_publishing_anomaly_detection
+  event_publishing_anomaly_band_width         = var.event_publishing_anomaly_band_width
+  event_publishing_anomaly_evaluation_periods = var.event_publishing_anomaly_evaluation_periods
+  event_publishing_anomaly_period             = var.event_publishing_anomaly_period
 }
+
 data "aws_iam_policy_document" "eventcache" {
   count = local.event_cache_bucket_name != null ? 1 : 0
   statement {

infrastructure/terraform/components/api/variables.tf

@@ -199,3 +199,27 @@ variable "enable_alarms" {
   description = "Enable CloudWatch alarms for this deployed environment"
   default     = true
 }
+
+variable "enable_event_publishing_anomaly_detection" {
+  type        = bool
+  description = "Enable CloudWatch anomaly detection alarm for SNS message publishing. Detects abnormal drops or spikes in event publishing volume."
+  default     = true
+}
+
+variable "event_publishing_anomaly_evaluation_periods" {
+  type        = number
+  description = "Number of evaluation periods for the publishing anomaly alarm. Each period is defined by event_publishing_anomaly_period."
+  default     = 3
+}
+
+variable "event_publishing_anomaly_period" {
+  type        = number
+  description = "The period in seconds over which the specified statistic is applied for anomaly detection. Minimum 300 seconds (5 minutes). Recommended: 300-600."
+  default     = 300
+}
+
+variable "event_publishing_anomaly_band_width" {
+  type        = number
+  description = "The width of the anomaly detection band. Higher values (e.g. 4-6) reduce sensitivity and noise, lower values (e.g. 2-3) increase sensitivity. Recommended: 2-4."
+  default     = 5
+}

infrastructure/terraform/modules/eventsub/README.md

@@ -14,10 +14,14 @@
 | <a name="input_aws_account_id"></a> [aws\_account\_id](#input\_aws\_account\_id) | The AWS Account ID (numeric) | `string` | n/a | yes |
 | <a name="input_component"></a> [component](#input\_component) | The name of the terraformscaffold component calling this module | `string` | n/a | yes |
 | <a name="input_default_tags"></a> [default\_tags](#input\_default\_tags) | Default tag map for application to all taggable resources in the module | `map(string)` | `{}` | no |
+| <a name="input_enable_event_anomaly_detection"></a> [enable\_event\_anomaly\_detection](#input\_enable\_event\_anomaly\_detection) | Enable CloudWatch anomaly detection alarm for SNS topic message publishing | `bool` | `true` | no |
 | <a name="input_enable_event_cache"></a> [enable\_event\_cache](#input\_enable\_event\_cache) | Enable caching of events to an S3 bucket | `bool` | `true` | no |
 | <a name="input_enable_firehose_raw_message_delivery"></a> [enable\_firehose\_raw\_message\_delivery](#input\_enable\_firehose\_raw\_message\_delivery) | Enables raw message delivery on firehose subscription | `bool` | `false` | no |
 | <a name="input_enable_sns_delivery_logging"></a> [enable\_sns\_delivery\_logging](#input\_enable\_sns\_delivery\_logging) | Enable SNS Delivery Failure Notifications | `bool` | `true` | no |
 | <a name="input_environment"></a> [environment](#input\_environment) | The name of the terraformscaffold environment the module is called for | `string` | n/a | yes |
+| <a name="input_event_anomaly_band_width"></a> [event\_anomaly\_band\_width](#input\_event\_anomaly\_band\_width) | The width of the anomaly detection band. Higher values (e.g. 4-6) reduce sensitivity and noise, lower values (e.g. 2-3) increase sensitivity. Recommended: 2-4. | `number` | `3` | no |
+| <a name="input_event_anomaly_evaluation_periods"></a> [event\_anomaly\_evaluation\_periods](#input\_event\_anomaly\_evaluation\_periods) | Number of evaluation periods for the anomaly alarm. Each period is defined by event\_anomaly\_period. | `number` | `2` | no |
+| <a name="input_event_anomaly_period"></a> [event\_anomaly\_period](#input\_event\_anomaly\_period) | The period in seconds over which the specified statistic is applied for anomaly detection. Minimum 300 seconds (5 minutes). Recommended: 300-600. | `number` | `300` | no |
 | <a name="input_event_cache_buffer_interval"></a> [event\_cache\_buffer\_interval](#input\_event\_cache\_buffer\_interval) | The buffer interval for data firehose | `number` | `500` | no |
 | <a name="input_event_cache_expiry_days"></a> [event\_cache\_expiry\_days](#input\_event\_cache\_expiry\_days) | s3 archiving expiry in days | `number` | `30` | no |
 | <a name="input_force_destroy"></a> [force\_destroy](#input\_force\_destroy) | When enabled will force destroy event-cache S3 bucket | `bool` | `false` | no |
@@ -42,6 +46,7 @@
 |------|-------------|
 | <a name="output_s3_bucket_event_cache"></a> [s3\_bucket\_event\_cache](#output\_s3\_bucket\_event\_cache) | S3 Bucket ARN and Name for event cache |
 | <a name="output_sns_topic"></a> [sns\_topic](#output\_sns\_topic) | SNS Topic ARN and Name |
+| <a name="output_subscriber_anomaly_alarm"></a> [subscriber\_anomaly\_alarm](#output\_subscriber\_anomaly\_alarm) | Subscriber anomaly detection alarm details |
 <!-- vale on -->
 <!-- markdownlint-enable -->
 <!-- END_TF_DOCS -->

infrastructure/terraform/modules/eventsub/cloudwatch_metric_alarm_subscriber_anomaly.tf

@@ -0,0 +1,40 @@
+resource "aws_cloudwatch_metric_alarm" "subscriber_anomaly" {
+  count = var.enable_event_anomaly_detection ? 1 : 0
+
+  alarm_name          = "${local.csi}-subscriber-anomaly"
+  alarm_description   = "ANOMALY: Detects anomalous patterns in messages published to the SNS fanout topic"
+  comparison_operator = "LessThanLowerOrGreaterThanUpperThreshold"
+  evaluation_periods  = var.event_anomaly_evaluation_periods
+  threshold_metric_id = "ad1"
+  treat_missing_data  = "notBreaching"
+
+  metric_query {
+    id          = "m1"
+    return_data = true
+
+    metric {
+      metric_name = "NumberOfMessagesPublished"
+      namespace   = "AWS/SNS"
+      period      = var.event_anomaly_period
+      stat        = "Sum"
+
+      dimensions = {
+        TopicName = aws_sns_topic.main.name
+      }
+    }
+  }
+
+  metric_query {
+    id          = "ad1"
+    expression  = "ANOMALY_DETECTION_BAND(m1, ${var.event_anomaly_band_width})"
+    label       = "NumberOfMessagesPublished (expected)"
+    return_data = true
+  }
+
+  tags = merge(
+    var.default_tags,
+    {
+      Name = "${local.csi}-subscriber-anomaly"
+    }
+  )
+}

infrastructure/terraform/modules/eventsub/outputs.tf

@@ -13,3 +13,12 @@ output "s3_bucket_event_cache" {
     bucket = module.s3bucket_event_cache[0].bucket
   } : {}
 }
+
+# CloudWatch Anomaly Detection Alarm
+output "subscriber_anomaly_alarm" {
+  description = "Subscriber anomaly detection alarm details"
+  value = var.enable_event_anomaly_detection ? {
+    arn  = aws_cloudwatch_metric_alarm.subscriber_anomaly[0].arn
+    name = aws_cloudwatch_metric_alarm.subscriber_anomaly[0].alarm_name
+  } : null
+}

infrastructure/terraform/modules/eventsub/variables.tf

@@ -79,6 +79,39 @@ variable "sns_success_logging_sample_percent" {
   default     = 0
 }
 
+##
+# CloudWatch Anomaly Detection Variables
+##
+
+variable "enable_event_anomaly_detection" {
+  type        = bool
+  description = "Enable CloudWatch anomaly detection alarm for SNS topic message publishing"
+  default     = true
+}
+
+variable "event_anomaly_evaluation_periods" {
+  type        = number
+  description = "Number of evaluation periods for the anomaly alarm. Each period is defined by event_anomaly_period."
+  default     = 2
+}
+
+variable "event_anomaly_period" {
+  type        = number
+  description = "The period in seconds over which the specified statistic is applied for anomaly detection. Minimum 300 seconds (5 minutes). Recommended: 300-600."
+  default     = 300
+}
+
+variable "event_anomaly_band_width" {
+  type        = number
+  description = "The width of the anomaly detection band. Higher values (e.g. 4-6) reduce sensitivity and noise, lower values (e.g. 2-3) increase sensitivity. Recommended: 2-4."
+  default     = 3
+
+  validation {
+    condition     = var.event_anomaly_band_width >= 2 && var.event_anomaly_band_width <= 10
+    error_message = "Band width must be between 2 and 10"
+  }
+}
+
 variable "log_level" {
   type        = string
   description = "The log level to be used in lambda functions within the component. Any log with a lower severity than the configured value will not be logged: https://docs.python.org/3/library/logging.html#levels"