MON-46 Monitors on number of errors, percentage of errors, number of invocations and number of throttles. No date enabled for the one on invocations.

cloud/aws/lambda/inputs.tf

@@ -0,0 +1,211 @@
+# Datadog global variables
+
+variable "environment" {
+  description = "Architecture environment"
+  type        = string
+}
+
+variable "filter_tags_use_defaults" {
+  description = "Use default filter tags convention"
+  default     = "true"
+}
+
+variable "filter_tags_custom" {
+  description = "Tags used for custom filtering when filter_tags_use_defaults is false"
+  default     = "*"
+}
+
+variable "filter_tags_custom_excluded" {
+  description = "Tags excluded for custom filtering when filter_tags_use_defaults is false"
+  default     = ""
+}
+
+variable "message" {
+  description = "Message sent when a monitor is triggered"
+}
+
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 900
+}
+
+variable "new_host_delay" {
+  description = "Delay in seconds before monitor new resource"
+  default     = 300
+}
+
+variable "prefix_slug" {
+  description = "Prefix string to prepend between brackets on every monitors names"
+  default     = ""
+}
+
+# Datadog monitors variables
+
+# Percentage of errors
+variable "pct_errors_enabled" {
+  description = "Flag to enable Percentage of errors monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "pct_errors_extra_tags" {
+  description = "Extra tags for Percentage of errors monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "pct_errors_message" {
+  description = "Custom message for Percentage of errors monitor"
+  type        = string
+  default     = ""
+}
+
+variable "pct_errors_time_aggregator" {
+  description = "Monitor aggregator for Percentage of errors [available values: min, max or avg]"
+  type        = string
+  default     = "sum"
+}
+
+variable "pct_errors_timeframe" {
+  description = "Monitor timeframe for Percentage of errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1h"
+}
+
+variable "pct_errors_threshold_critical" {
+  default     = 30
+  description = "Alerting threshold in percentage"
+}
+
+variable "pct_errors_threshold_warning" {
+  default     = 20
+  description = "Warning threshold in percentage"
+}
+
+# Errors count
+variable "errors_enabled" {
+  description = "Flag to enable Errors monitor"
+  type        = string
+  default     = "false"
+}
+
+variable "errors_extra_tags" {
+  description = "Extra tags for Errors monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "errors_message" {
+  description = "Custom message for Errors monitor"
+  type        = string
+  default     = ""
+}
+
+variable "errors_time_aggregator" {
+  description = "Monitor aggregator for Errors [available values: min, max or avg]"
+  type        = string
+  default     = "sum"
+}
+
+variable "errors_timeframe" {
+  description = "Monitor timeframe for Errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1h"
+}
+
+variable "errors_threshold_critical" {
+  default     = 3
+  description = "Alerting threshold in milliseconds"
+}
+
+variable "errors_threshold_warning" {
+  default     = 1
+  description = "Warning threshold in milliseconds"
+}
+
+# Throttles count
+variable "throttles_enabled" {
+  description = "Flag to enable Throttles monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "throttles_extra_tags" {
+  description = "Extra tags for Throttles monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "throttles_message" {
+  description = "Custom message for Throttles monitor"
+  type        = string
+  default     = ""
+}
+
+variable "throttles_time_aggregator" {
+  description = "Monitor aggregator for Throttles [available values: min, max or avg]"
+  type        = string
+  default     = "sum"
+}
+
+variable "throttles_timeframe" {
+  description = "Monitor timeframe for Throttles [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1h"
+}
+
+variable "throttles_threshold_critical" {
+  default     = 3
+  description = "Alerting threshold in number of throttles"
+}
+
+variable "throttles_threshold_warning" {
+  default     = 1
+  description = "Warning threshold in number of throttles"
+}
+
+# Invocations
+variable "invocations_enabled" {
+  description = "Flag to enable Invocations monitor"
+  type        = string
+  default     = "false"
+}
+
+variable "invocations_extra_tags" {
+  description = "Extra tags for Invocations monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "invocations_message" {
+  description = "Custom message for Invocations monitor"
+  type        = string
+  default     = ""
+}
+
+variable "invocations_time_aggregator" {
+  description = "Monitor aggregator for Invocations [available values: min, max or avg]"
+  type        = string
+  default     = "sum"
+}
+
+variable "invocations_timeframe" {
+  description = "Monitor timeframe for Invocations [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1h"
+}
+
+variable "invocations_threshold_critical" {
+  default     = 1
+  description = "Alerting threshold in number of invocations"
+}
+
+variable "invocations_threshold_warning" {
+  default     = 2
+  description = "Warning threshold in number of invocations"
+}
+
+variable "invocations_no_data_timeframe" {
+  default     = 120
+  description = "Timeframe to check before alerting on no data in minutes"
+}

cloud/aws/lambda/modules.tf

@@ -0,0 +1,9 @@
+module "filter-tags" {
+  source = "../../../common/filter-tags"
+
+  environment                 = var.environment
+  resource                    = "aws_lambda"
+  filter_tags_use_defaults    = var.filter_tags_use_defaults
+  filter_tags_custom          = var.filter_tags_custom
+  filter_tags_custom_excluded = var.filter_tags_custom_excluded
+}

cloud/aws/lambda/monitors-lambda.tf

@@ -0,0 +1,149 @@
+# Errors Percent
+resource "datadog_monitor" "pct_errors" {
+  count   = var.pct_errors_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Lambda Percentage of errors {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  type    = "metric alert"
+  message = coalesce(var.pct_errors_message, var.message)
+
+  query = <<EOQ
+    ${var.pct_errors_time_aggregator}(${var.pct_errors_timeframe}):
+      (sum:aws.lambda.errors${module.filter-tags.query_alert} by {region,functionname}.as_count()
+      /
+      sum:aws.lambda.invocations${module.filter-tags.query_alert} by {region,functionname}.as_count())
+      * 100
+      > ${var.pct_errors_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.pct_errors_threshold_critical
+    warning  = var.pct_errors_threshold_warning
+  }
+
+  notify_no_data      = false
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+  tags = concat(["env:${var.environment}", "type:cloud", "provider:aws", "resource:lambda", "team:claranet", "created-by:terraform"], var.pct_errors_extra_tags)
+
+  lifecycle {
+    ignore_changes = ["silenced"]
+  }
+}
+
+# Errors Absolute Value
+resource "datadog_monitor" "errors" {
+  count   = var.errors_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Lambda Number of Errors {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
+  type    = "metric alert"
+  message = coalesce(var.errors_message, var.message)
+
+  query = <<EOQ
+    ${var.errors_time_aggregator}(${var.errors_timeframe}):
+      sum:aws.lambda.errors${module.filter-tags.query_alert} by {region,functionname}.as_count()
+      > ${var.errors_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.errors_threshold_critical
+    warning  = var.errors_threshold_warning
+  }
+
+  notify_no_data      = false
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+  tags = concat(["env:${var.environment}", "type:cloud", "provider:aws", "resource:lambda", "team:claranet", "created-by:terraform"], var.errors_extra_tags)
+
+  lifecycle {
+    ignore_changes = ["silenced"]
+  }
+}
+
+# Throttles
+resource "datadog_monitor" "throttles" {
+  count   = var.throttles_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Lambda Number of Throttles {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
+  type    = "metric alert"
+  message = coalesce(var.throttles_message, var.message)
+
+  query = <<EOQ
+    ${var.throttles_time_aggregator}(${var.throttles_timeframe}):
+      sum:aws.lambda.throttles${module.filter-tags.query_alert} by {region,functionname}.as_count()
+      > ${var.throttles_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.throttles_threshold_critical
+    warning  = var.throttles_threshold_warning
+  }
+
+  notify_no_data      = false
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+  tags = concat(["env:${var.environment}", "type:cloud", "provider:aws", "resource:lambda", "team:claranet", "created-by:terraform"], var.throttles_extra_tags)
+
+  lifecycle {
+    ignore_changes = ["silenced"]
+  }
+}
+
+# INVOCATIONS
+resource "datadog_monitor" "invocations" {
+  count   = var.invocations_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Lambda Number of Invocations {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
+  type    = "metric alert"
+  message = coalesce(var.invocations_message, var.message)
+
+  query = <<EOQ
+    ${var.invocations_time_aggregator}(${var.invocations_timeframe}):
+      sum:aws.lambda.invocations${module.filter-tags.query_alert} by {region,functionname}.as_count()
+      < ${var.invocations_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.invocations_threshold_critical
+    warning  = var.invocations_threshold_warning
+  }
+
+  notify_no_data      = true
+  no_data_timeframe   = var.invocations_no_data_timeframe
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+
+
+  tags = concat(["env:${var.environment}", "type:cloud", "provider:aws", "resource:lambda", "team:claranet", "created-by:terraform"], var.invocations_extra_tags)
+
+  lifecycle {
+    ignore_changes = ["silenced"]
+  }
+}

cloud/aws/lambda/outputs.tf

@@ -0,0 +1,20 @@
+output "errors_id" {
+  description = "id for monitor errors"
+  value       = datadog_monitor.errors.*.id
+}
+
+output "invocations_id" {
+  description = "id for monitor invocations"
+  value       = datadog_monitor.invocations.*.id
+}
+
+output "pct_errors_id" {
+  description = "id for monitor pct_errors"
+  value       = datadog_monitor.pct_errors.*.id
+}
+
+output "throttles_id" {
+  description = "id for monitor throttles"
+  value       = datadog_monitor.throttles.*.id
+}
+