MON-96 - Updated aws monitors with inputs best practice

cloud/aws/apigateway/README.md

@@ -27,17 +27,23 @@ Inputs
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
+| artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `5` | no |
 | delay | Delay in seconds for the metric evaluation | string | `900` | no |
 | environment | Environment | string | - | yes |
-| filter_tags | Tags used for custom filtering | string | `*` | no |
+| filter_tags | Tags used for filtering | string | `*` | no |
+| http_4xx_requests_message | Custom message for API Gateway HTTP 4xx requests monitor | string | `` | no |
+| http_4xx_requests_silenced | Groups to mute for API Gateway HTTP 4xx requests monitor | map | `<map>` | no |
 | http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `30` | no |
 | http_4xx_requests_threshold_warning | Maximum warning acceptable percent of 4xx errors | string | `15` | no |
+| http_5xx_requests_message | Custom message for API Gateway HTTP 5xx requests monitor | string | `` | no |
+| http_5xx_requests_silenced | Groups to mute for API Gateway HTTP 5xx requests monitor | map | `<map>` | no |
 | http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `20` | no |
 | http_5xx_requests_threshold_warning | Maximum warning acceptable percent of 5xx errors | string | `10` | no |
+| latency_message | Custom message for API Gateway latency monitor | string | `` | no |
+| latency_silenced | Groups to mute for API Gateway latency monitor | map | `<map>` | no |
+| latency_threshold_critical | Alerting threshold in milliseconds | string | `800` | no |
+| latency_threshold_warning | Warning threshold in milliseconds | string | `400` | no |
 | message | Message sent when a monitor is triggered | string | - | yes |
-| latency_threshold_critical | Alerting threshold in miliseconds | string | `800` | no |
-| latency_threshold_warning | Warning threshold in miliseconds | string | `400` | no |
-| artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `0` | no |
 
 Related documentation
 ---------------------

cloud/aws/apigateway/inputs.tf

@@ -21,6 +21,18 @@ variable "delay" {
 ###   LATENCY VARIABLES   ###
 ###################################
 
+variable "latency_silenced" {
+  description = "Groups to mute for API Gateway latency monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "latency_message" {
+  description = "Custom message for API Gateway latency monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "latency_threshold_critical" {
   default     = 800
   description = "Alerting threshold in milliseconds"
@@ -35,6 +47,18 @@ variable "latency_threshold_warning" {
 ###   HTTP 5xx status pages   ###
 #################################
 
+variable "http_5xx_requests_silenced" {
+  description = "Groups to mute for API Gateway HTTP 5xx requests monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "http_5xx_requests_message" {
+  description = "Custom message for API Gateway HTTP 5xx requests monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "http_5xx_requests_threshold_critical" {
   default     = 20
   description = "Maximum critical acceptable percent of 5xx errors"
@@ -49,6 +73,18 @@ variable "http_5xx_requests_threshold_warning" {
 ###   HTTP 4xx status pages   ###
 #################################
 
+variable "http_4xx_requests_silenced" {
+  description = "Groups to mute for API Gateway HTTP 4xx requests monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "http_4xx_requests_message" {
+  description = "Custom message for API Gateway HTTP 4xx requests monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "http_4xx_requests_threshold_critical" {
   default     = 30
   description = "Maximum critical acceptable percent of 4xx errors"

cloud/aws/apigateway/monitors-api.tf

@@ -2,7 +2,7 @@
 resource "datadog_monitor" "API_Gateway_latency" {
   name    = "[${var.environment}] API Gateway latency {{#is_alert}}{{comparator}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
   type    = "metric alert"
-  message = "${var.message}"
+  message = "${coalesce(var.latency_message, var.message)}"
 
   query = <<EOF
     avg(last_5m): (
@@ -24,6 +24,8 @@ resource "datadog_monitor" "API_Gateway_latency" {
   timeout_h           = 0
   include_tags        = true
 
+  silenced = "${var.latency_silenced}"
+
   tags = ["env:${var.environment}", "resource:apigateway", "team:aws", "provider:aws"]
 }
 
@@ -31,7 +33,7 @@ resource "datadog_monitor" "API_Gateway_latency" {
 resource "datadog_monitor" "API_http_5xx_errors_count" {
   name    = "[${var.environment}] API Gateway HTTP 5xx errors {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
   type    = "metric alert"
-  message = "${var.message}"
+  message = "${coalesce(var.http_5xx_requests_message, var.message)}"
 
   query = <<EOF
     sum(last_5m): (
@@ -54,6 +56,8 @@ resource "datadog_monitor" "API_http_5xx_errors_count" {
   timeout_h           = 1
   include_tags        = true
 
+  silenced = "${var.http_5xx_requests_silenced}"
+
   tags = ["env:${var.environment}", "resource:apigateway", "team:aws", "provider:aws"]
 }
 
@@ -61,7 +65,7 @@ resource "datadog_monitor" "API_http_5xx_errors_count" {
 resource "datadog_monitor" "API_http_4xx_errors_count" {
   name    = "[${var.environment}] API Gateway HTTP 4xx errors {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
   type    = "metric alert"
-  message = "${var.message}"
+  message = "${coalesce(var.http_4xx_requests_message, var.message)}"
 
   query = <<EOF
     sum(last_5m): (
@@ -84,5 +88,7 @@ resource "datadog_monitor" "API_http_4xx_errors_count" {
   timeout_h           = 1
   include_tags        = true
 
+  silenced = "${var.http_4xx_requests_silenced}"
+
   tags = ["env:${var.environment}", "resource:apigateway", "team:aws", "provider:aws"]
 }

cloud/aws/elasticsearch/README.md

@@ -29,11 +29,17 @@ Inputs
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
+| cpu_message | Custom message for ES cluster cpu monitor | string | `` | no |
+| cpu_silenced | Groups to mute for ES cluster cpu monitor | map | `<map>` | no |
 | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
 | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
+| diskspace_message | Custom message for ES cluster diskspace monitor | string | `` | no |
+| diskspace_silenced | Groups to mute for ES cluster diskspace monitor | map | `<map>` | no |
 | diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |
 | diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no |
 | environment | Architecture Environment | string | - | yes |
+| es_cluster_status_message | Custom message for ES cluster status monitor | string | `` | no |
+| es_cluster_status_silenced | Groups to mute for ES cluster status monitor | map | `<map>` | no |
 | es_cluster_volume_size | ElasticSearch Domain volume size (in GB) | string | - | yes |
 | evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
 | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |

cloud/aws/elasticsearch/inputs.tf

@@ -25,10 +25,35 @@ variable "filter_tags_custom" {
 }
 
 # AWS ElasticSearch Service specific
+
+variable "es_cluster_status_silenced" {
+  description = "Groups to mute for ES cluster status monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "es_cluster_status_message" {
+  description = "Custom message for ES cluster status monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "es_cluster_volume_size" {
   description = "ElasticSearch Domain volume size (in GB)"
 }
 
+variable "diskspace_silenced" {
+  description = "Groups to mute for ES cluster diskspace monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "diskspace_message" {
+  description = "Custom message for ES cluster diskspace monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "diskspace_threshold_warning" {
   description = "Disk free space in percent (warning threshold)"
   default     = "20"
@@ -39,6 +64,18 @@ variable "diskspace_threshold_critical" {
   default     = "10"
 }
 
+variable "cpu_silenced" {
+  description = "Groups to mute for ES cluster cpu monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "cpu_message" {
+  description = "Custom message for ES cluster cpu monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "cpu_threshold_warning" {
   description = "CPU usage in percent (warning threshold)"
   default     = "80"

cloud/aws/elasticsearch/monitors-elasticsearch.tf

@@ -9,7 +9,7 @@ data "template_file" "filter" {
 ### Elasticsearch cluster status monitor ###
 resource "datadog_monitor" "es_cluster_status" {
   name    = "[${var.environment}] ElasticSearch cluster status is not green"
-  message = "${var.message}"
+  message = "${coalesce(var.es_cluster_status_message, var.message)}"
 
   type = "query alert"
 
@@ -37,13 +37,15 @@ EOF
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.es_cluster_status_silenced}"
+
   tags = ["env:${var.environment}", "resource:elasticsearch", "team:aws", "provider:aws"]
 }
 
 ### Elasticsearch cluster free storage space monitor ###
 resource "datadog_monitor" "es_free_space_low" {
   name    = "[${var.environment}] ElasticSearch cluster free storage space {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.diskspace_message, var.message)}"
 
   type = "query alert"
 
@@ -70,13 +72,15 @@ EOF
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.diskspace_silenced}"
+
   tags = ["env:${var.environment}", "resource:elasticsearch", "team:aws", "provider:aws"]
 }
 
 ### Elasticsearch cluster CPU monitor ###
 resource "datadog_monitor" "es_cpu_90_15min" {
   name    = "[${var.environment}] ElasticSearch cluster CPU high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.cpu_message, var.message)}"
 
   type = "query alert"
 
@@ -102,5 +106,7 @@ EOF
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.cpu_silenced}"
+
   tags = ["env:${var.environment}", "resource:elasticsearch", "team:aws", "provider:aws"]
 }

cloud/aws/elb/README.md

@@ -31,16 +31,28 @@ Inputs
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
 | dd_aws_elb | # ELB | string | `disable` | no |
+| elb_4xx_message | Custom message for ELB 4xx errors monitor | string | `` | no |
+| elb_4xx_silenced | Groups to mute for ELB 4xx errors monitor | map | `<map>` | no |
 | elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `10` | no |
 | elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `5` | no |
+| elb_5xx_message | Custom message for ELB 5xx errors monitor | string | `` | no |
+| elb_5xx_silenced | Groups to mute for ELB 5xx errors monitor | map | `<map>` | no |
 | elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `10` | no |
 | elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `5` | no |
+| elb_backend_4xx_message | Custom message for ELB backend 4xx errors monitor | string | `` | no |
+| elb_backend_4xx_silenced | Groups to mute for ELB backend 4xx errors monitor | map | `<map>` | no |
 | elb_backend_4xx_threshold_critical | loadbalancer backend 4xx critical threshold in percentage | string | `10` | no |
 | elb_backend_4xx_threshold_warning | loadbalancer backend 4xx warning threshold in percentage | string | `5` | no |
+| elb_backend_5xx_message | Custom message for ELB backend 5xx errors monitor | string | `` | no |
+| elb_backend_5xx_silenced | Groups to mute for ELB backend 5xx errors monitor | map | `<map>` | no |
 | elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no |
 | elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no |
 | elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no |
+| elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no |
+| elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `<map>` | no |
 | elb_backend_latency_warning | latency warning threshold in seconds | string | `1` | no |
+| elb_no_healthy_instance_message | Custom message for ELB no healty instance monitor | string | `` | no |
+| elb_no_healthy_instance_silenced | Groups to mute for ELB no healty instance monitor | map | `<map>` | no |
 | environment | Architecture Environment | string | - | yes |
 | evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
 | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |

cloud/aws/elb/inputs.tf

@@ -29,6 +29,30 @@ variable "dd_aws_elb" {
   default = "disable"
 }
 
+variable "elb_no_healthy_instance_silenced" {
+  description = "Groups to mute for ELB no healty instance monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "elb_no_healthy_instance_message" {
+  description = "Custom message for ELB no healty instance monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "elb_4xx_silenced" {
+  description = "Groups to mute for ELB 4xx errors monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "elb_4xx_message" {
+  description = "Custom message for ELB 4xx errors monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "elb_4xx_threshold_warning" {
   description = "loadbalancer 4xx warning threshold in percentage"
   default     = 5
@@ -39,6 +63,18 @@ variable "elb_4xx_threshold_critical" {
   default     = 10
 }
 
+variable "elb_5xx_silenced" {
+  description = "Groups to mute for ELB 5xx errors monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "elb_5xx_message" {
+  description = "Custom message for ELB 5xx errors monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "elb_5xx_threshold_warning" {
   description = "loadbalancer 5xx warning threshold in percentage"
   default     = 5
@@ -49,6 +85,18 @@ variable "elb_5xx_threshold_critical" {
   default     = 10
 }
 
+variable "elb_backend_4xx_silenced" {
+  description = "Groups to mute for ELB backend 4xx errors monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "elb_backend_4xx_message" {
+  description = "Custom message for ELB backend 4xx errors monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "elb_backend_4xx_threshold_warning" {
   description = "loadbalancer backend 4xx warning threshold in percentage"
   default     = 5
@@ -59,6 +107,18 @@ variable "elb_backend_4xx_threshold_critical" {
   default     = 10
 }
 
+variable "elb_backend_5xx_silenced" {
+  description = "Groups to mute for ELB backend 5xx errors monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "elb_backend_5xx_message" {
+  description = "Custom message for ELB backend 5xx errors monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "elb_backend_5xx_threshold_warning" {
   description = "loadbalancer backend 5xx warning threshold in percentage"
   default     = 5
@@ -69,6 +129,18 @@ variable "elb_backend_5xx_threshold_critical" {
   default     = 10
 }
 
+variable "elb_backend_latency_silenced" {
+  description = "Groups to mute for ELB backend latency monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "elb_backend_latency_message" {
+  description = "Custom message for ELB backend latency monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "elb_backend_latency_warning" {
   description = "latency warning threshold in seconds"
   default     = 1

cloud/aws/elb/monitors-elb.tf

@@ -8,7 +8,7 @@ data "template_file" "filter" {
 
 resource "datadog_monitor" "ELB_no_healthy_instances" {
   name    = "[${var.environment}] ELB no healthy instances"
-  message = "${var.message}"
+  message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}"
 
   query = <<EOF
     avg(last_5m): (
@@ -29,12 +29,14 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.elb_no_healthy_instance_silenced}"
+
   tags = ["env:${var.environment}", "resource:elb", "team:aws", "provider:aws"]
 }
 
 resource "datadog_monitor" "ELB_too_much_4xx" {
   name    = "[${var.environment}] ELB 4xx errors too high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.elb_4xx_message, var.message)}"
 
   query = <<EOF
     avg(last_5m): (
@@ -61,12 +63,14 @@ resource "datadog_monitor" "ELB_too_much_4xx" {
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.elb_4xx_silenced}"
+
   tags = ["env:${var.environment}", "resource:elb", "team:aws", "provider:aws"]
 }
 
 resource "datadog_monitor" "ELB_too_much_5xx" {
   name    = "[${var.environment}] ELB 5xx errors too high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.elb_5xx_message, var.message)}"
 
   query = <<EOF
     avg(last_5m): (
@@ -93,12 +97,14 @@ resource "datadog_monitor" "ELB_too_much_5xx" {
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.elb_5xx_silenced}"
+
   tags = ["env:${var.environment}", "resource:elb", "team:aws", "provider:aws"]
 }
 
 resource "datadog_monitor" "ELB_too_much_4xx_backend" {
   name    = "[${var.environment}] ELB backend 4xx errors too high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.elb_backend_4xx_message, var.message)}"
 
   query = <<EOF
     avg(last_5m): (
@@ -125,12 +131,14 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.elb_backend_4xx_silenced}"
+
   tags = ["env:${var.environment}", "resource:elb", "team:aws", "provider:aws"]
 }
 
 resource "datadog_monitor" "ELB_too_much_5xx_backend" {
   name    = "[${var.environment}] ELB backend 5xx errors too high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.elb_backend_5xx_message, var.message)}"
 
   query = <<EOF
     avg(last_5m): (
@@ -157,12 +165,14 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.elb_backend_5xx_silenced}"
+
   tags = ["env:${var.environment}", "resource:elb", "team:aws", "provider:aws"]
 }
 
 resource "datadog_monitor" "ELB_backend_latency" {
   name    = "[${var.environment}] ELB latency too high {{#is_alert}}{{comparator}} {{threshold}}s ({{value}}s){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}s ({{value}}s){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.elb_backend_latency_message, var.message)}"
 
   query = <<EOF
     min(last_5m): (
@@ -188,5 +198,7 @@ resource "datadog_monitor" "ELB_backend_latency" {
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.elb_backend_latency_silenced}"
+
   tags = ["env:${var.environment}", "resource:elb", "team:aws", "provider:aws"]
 }

cloud/aws/kinesis-firehose/README.md

@@ -28,6 +28,8 @@ Inputs
 | environment | Environment | string | - | yes |
 | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
 | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
+| incoming_records_message | Custom message for Kinesis Firehorse incoming records monitor | string | `` | no |
+| incoming_records_silenced | Groups to mute for Kinesis Firehorse incoming records monitor | map | `<map>` | no |
 | incoming_records_timeframe | Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
 

cloud/aws/kinesis-firehose/inputs.tf

@@ -25,6 +25,19 @@ variable "filter_tags_custom" {
 }
 
 # Kinesis-Firehose
+
+variable "incoming_records_silenced" {
+  description = "Groups to mute for Kinesis Firehorse incoming records monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "incoming_records_message" {
+  description = "Custom message for Kinesis Firehorse incoming records monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "incoming_records_timeframe" {
   description = "Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
   default     = "last_15m"

cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf

@@ -9,7 +9,7 @@ data "template_file" "filter" {
 ### Kinesis Firehose Incoming records ###
 resource "datadog_monitor" "firehose_incoming_records" {
   name    = "[${var.environment}] Kinesis Firehose No incoming records"
-  message = "${var.message}"
+  message = "${coalesce(var.incoming_records_message, var.message)}"
 
   type = "metric alert"
 
@@ -34,5 +34,7 @@ EOF
   new_host_delay      = "${var.delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.incoming_records_silenced}"
+
   tags = ["env:${var.environment}", "resource:kinesis-firehose", "team:aws", "provider:aws"]
 }

cloud/aws/rds/README.md

@@ -25,8 +25,12 @@ Inputs
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
+| cpu_message | Custom message for RDS CPU usage monitor | string | `` | no |
+| cpu_silenced | Groups to mute for RDS CPU usage monitor | map | `<map>` | no |
 | cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
 | cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
+| diskspace_message | Custom message for RDS free diskspace monitor | string | `` | no |
+| diskspace_silenced | Groups to mute for RDS free diskspace monitor | map | `<map>` | no |
 | diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |
 | diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no |
 | environment | Architecture Environment | string | - | yes |

cloud/aws/rds/inputs.tf

@@ -26,6 +26,18 @@ variable "filter_tags_custom" {
 
 # AWS RDS instance specific
 
+variable "cpu_silenced" {
+  description = "Groups to mute for RDS CPU usage monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "cpu_message" {
+  description = "Custom message for RDS CPU usage monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "cpu_threshold_warning" {
   description = "CPU usage in percent (warning threshold)"
   default     = "80"
@@ -36,6 +48,18 @@ variable "cpu_threshold_critical" {
   default     = "90"
 }
 
+variable "diskspace_silenced" {
+  description = "Groups to mute for RDS free diskspace monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "diskspace_message" {
+  description = "Custom message for RDS free diskspace monitor"
+  type        = "string"
+  default     = ""
+}
+
 variable "diskspace_threshold_warning" {
   description = "Disk free space in percent (warning threshold)"
   default     = "20"

cloud/aws/rds/monitors-rds.tf

@@ -9,7 +9,7 @@ data "template_file" "filter" {
 ### RDS instance CPU monitor ###
 resource "datadog_monitor" "rds_cpu_90_15min" {
   name    = "[${var.environment}] RDS instance CPU high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.cpu_message, var.message)}"
 
   type = "metric alert"
 
@@ -34,13 +34,15 @@ EOF
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.cpu_silenced}"
+
   tags = ["env:${var.environment}", "resource:rds", "team:aws", "provider:aws"]
 }
 
 ### RDS instance free space monitor ###
 resource "datadog_monitor" "rds_free_space_low" {
   name    = "[${var.environment}] RDS instance free space {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
-  message = "${var.message}"
+  message = "${coalesce(var.diskspace_message, var.message)}"
 
   type = "metric alert"
 
@@ -66,5 +68,7 @@ EOF
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
+  silenced = "${var.diskspace_silenced}"
+
   tags = ["env:${var.environment}", "resource:rds", "team:aws", "provider:aws"]
 }

cloud/aws/vpn/README.md

@@ -29,3 +29,5 @@ Inputs
 | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
 | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
+| vpn_status_message | Custom message for VPN status monitor | string | `` | no |
+| vpn_status_silenced | Groups to mute for VPN status monitor | map | `<map>` | no |

cloud/aws/vpn/inputs.tf

@@ -23,3 +23,15 @@ variable "filter_tags_custom" {
   description = "Tags used for custom filtering when filter_tags_use_defaults is false"
   default     = "*"
 }
+
+variable "vpn_status_silenced" {
+  description = "Groups to mute for VPN status monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "vpn_status_message" {
+  description = "Custom message for VPN status monitor"
+  type        = "string"
+  default     = ""
+}

cloud/aws/vpn/monitors-vpn.tf

@@ -8,7 +8,7 @@ data "template_file" "filter" {
 
 resource "datadog_monitor" "VPN_status" {
   name    = "[${var.environment}] VPN Down"
-  message = "${var.message}"
+  message = "${coalesce(var.vpn_status_message, var.message)}"
 
   query = <<EOF
         avg(last_5m): (
@@ -27,5 +27,7 @@ resource "datadog_monitor" "VPN_status" {
   include_tags        = true
   require_full_window = false
 
+  silenced = "${var.vpn_status_silenced}"
+
   tags = ["env: ${var.environment}", "resource:vpn", "team:aws", "provider:aws"]
 }