Merge branch 'MON-46-aws-lambda-tf012' into 'master'

MON-46 AWS Lambda

See merge request claranet/pt-monitoring/projects/datadog/terraform/monitors!109

README.md

@@ -147,6 +147,7 @@ The `//` is very important, it's a terraform specific syntax used to separate gi
 		- [elasticsearch](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/elasticsearch/)
 		- [elb](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/elb/)
 		- [kinesis-firehose](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/kinesis-firehose/)
+		- [lambda](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/lambda/)
 		- [rds](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/rds/)
 			- [aurora](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/rds/aurora/)
 				- [mysql](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/aws/rds/aurora/mysql/)

cloud/aws/lambda/README.md

@@ -0,0 +1,77 @@
+# CLOUD AWS LAMBDA DataDog monitors
+
+## How to use this module
+
+```
+module "datadog-monitors-cloud-aws-lambda" {
+  source = "git::ssh://git@git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors.git//cloud/aws/lambda?ref={revision}"
+
+  environment = var.environment
+  message     = module.datadog-message-alerting.alerting-message
+}
+
+```
+
+## Purpose
+
+Creates DataDog monitors with the following checks:
+
+- Lambda Invocations throttled due to concurrent limit reached
+- Lambda Number of errors
+- Lambda Number of invocations (disabled by default)
+- Lambda Percentage of errors
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| environment | Architecture environment | string | n/a | yes |
+| errors\_enabled | Flag to enable Errors monitor | string | `"false"` | no |
+| errors\_extra\_tags | Extra tags for Errors monitor | list(string) | `[]` | no |
+| errors\_message | Custom message for Errors monitor | string | `""` | no |
+| errors\_threshold\_critical | Alerting threshold in milliseconds | string | `"3"` | no |
+| errors\_threshold\_warning | Warning threshold in milliseconds | string | `"1"` | no |
+| errors\_time\_aggregator | Monitor aggregator for Errors [available values: min, max or avg] | string | `"sum"` | no |
+| errors\_timeframe | Monitor timeframe for Errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_1h"` | no |
+| evaluation\_delay | Delay in seconds for the metric evaluation | string | `"900"` | no |
+| filter\_tags\_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `"*"` | no |
+| filter\_tags\_custom\_excluded | Tags excluded for custom filtering when filter_tags_use_defaults is false | string | `""` | no |
+| filter\_tags\_use\_defaults | Use default filter tags convention | string | `"true"` | no |
+| invocations\_enabled | Flag to enable Invocations monitor | string | `"false"` | no |
+| invocations\_extra\_tags | Extra tags for Invocations monitor | list(string) | `[]` | no |
+| invocations\_message | Custom message for Invocations monitor | string | `""` | no |
+| invocations\_no\_data\_timeframe | Timeframe to check before alerting on no data in minutes | string | `"120"` | no |
+| invocations\_threshold\_critical | Alerting threshold in number of invocations | string | `"1"` | no |
+| invocations\_threshold\_warning | Warning threshold in number of invocations | string | `"2"` | no |
+| invocations\_time\_aggregator | Monitor aggregator for Invocations [available values: min, max or avg] | string | `"sum"` | no |
+| invocations\_timeframe | Monitor timeframe for Invocations [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_30m"` | no |
+| message | Message sent when a monitor is triggered | string | n/a | yes |
+| new\_host\_delay | Delay in seconds before monitor new resource | string | `"300"` | no |
+| pct\_errors\_enabled | Flag to enable Percentage of errors monitor | string | `"true"` | no |
+| pct\_errors\_extra\_tags | Extra tags for Percentage of errors monitor | list(string) | `[]` | no |
+| pct\_errors\_message | Custom message for Percentage of errors monitor | string | `""` | no |
+| pct\_errors\_threshold\_critical | Alerting threshold in percentage | string | `"30"` | no |
+| pct\_errors\_threshold\_warning | Warning threshold in percentage | string | `"20"` | no |
+| pct\_errors\_time\_aggregator | Monitor aggregator for Percentage of errors [available values: min, max or avg] | string | `"sum"` | no |
+| pct\_errors\_timeframe | 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`] | string | `"last_1h"` | no |
+| prefix\_slug | Prefix string to prepend between brackets on every monitors names | string | `""` | no |
+| throttles\_enabled | Flag to enable Throttles monitor | string | `"true"` | no |
+| throttles\_extra\_tags | Extra tags for Throttles monitor | list(string) | `[]` | no |
+| throttles\_message | Custom message for Throttles monitor | string | `""` | no |
+| throttles\_threshold\_critical | Alerting threshold in number of throttles | string | `"3"` | no |
+| throttles\_threshold\_warning | Warning threshold in number of throttles | string | `"1"` | no |
+| throttles\_time\_aggregator | Monitor aggregator for Throttles [available values: min, max or avg] | string | `"sum"` | no |
+| throttles\_timeframe | Monitor timeframe for Throttles [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_1h"` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| errors\_id | id for monitor errors |
+| invocations\_id | id for monitor invocations |
+| pct\_errors\_id | id for monitor pct_errors |
+| throttles\_id | id for monitor throttles |
+
+## Related documentation
+* [Datadog Documentation](https://docs.datadoghq.com/integrations/amazon_lambda/)
+* [Service documentation](https://docs.aws.amazon.com/lambda/index.html)

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_30m"
+}
+
+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}):
+      default(
+        (default(sum:aws.lambda.errors${module.filter-tags.query_alert} by {region,functionname}.as_count(),0)
+        /
+        default(sum:aws.lambda.invocations${module.filter-tags.query_alert} by {region,functionname}.as_count(),1))
+        * 100,0)
+      > ${var.pct_errors_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.pct_errors_threshold_critical
+    warning  = var.pct_errors_threshold_warning
+  }
+
+  notify_no_data      = false
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+  tags = concat(["env:${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}):
+      default(sum:aws.lambda.errors${module.filter-tags.query_alert} by {region,functionname}.as_count(),0)
+      > ${var.errors_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.errors_threshold_critical
+    warning  = var.errors_threshold_warning
+  }
+
+  notify_no_data      = false
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+  tags = concat(["env:${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 Invocations throttled due to concurrent limit reached {{#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}):
+      default(sum:aws.lambda.throttles${module.filter-tags.query_alert} by {region,functionname}.as_count(),0)
+      > ${var.throttles_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.throttles_threshold_critical
+    warning  = var.throttles_threshold_warning
+  }
+
+  notify_no_data      = false
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+  tags = concat(["env:${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}):
+      default(sum:aws.lambda.invocations${module.filter-tags.query_alert} by {region,functionname}.as_count(),0)
+      <= ${var.invocations_threshold_critical}
+  EOQ
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  thresholds = {
+    critical = var.invocations_threshold_critical
+    warning  = var.invocations_threshold_warning
+  }
+
+  notify_no_data      = false
+  require_full_window = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+
+
+
+  tags = concat(["env:${var.environment}", "type:cloud", "provider:aws", "resource:lambda", "team:claranet", "created-by:terraform"], var.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
+}
+