MON-122 add replication lag for rds

cloud/aws/rds/aurora/mysql/README.md

@@ -22,8 +22,8 @@ Creates DataDog monitors with the following checks:
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
-| aurora_replicalag_enabled | Flag to enable RDS CPU usage monitor | string | `true` | no |
+| aurora_replicalag_enabled | Flag to enable RDS Aurora replica lag monitor | string | `true` | no |
-| aurora_replicalag_extra_tags | Extra tags for RDS CPU usage monitor | list | `<list>` | no |
+| aurora_replicalag_extra_tags | Extra tags for RDS Aurora replica lag monitor | list | `<list>` | no |
 | aurora_replicalag_message | Custom message for RDS Aurora replica lag monitor | string | `` | no |
 | aurora_replicalag_silenced | Groups to mute for RDS Aurora replica lag monitor | map | `<map>` | no |
 | aurora_replicalag_threshold_critical | Aurora replica lag in milliseconds (critical threshold) | string | `200` | no |

cloud/aws/rds/aurora/postgresql/README.md

@@ -22,8 +22,8 @@ Creates DataDog monitors with the following checks:
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
-| aurora_replicalag_enabled | Flag to enable RDS CPU usage monitor | string | `true` | no |
+| aurora_replicalag_enabled | Flag to enable RDS Aurora replica lag monitor | string | `true` | no |
-| aurora_replicalag_extra_tags | Extra tags for RDS CPU usage monitor | list | `<list>` | no |
+| aurora_replicalag_extra_tags | Extra tags for RDS Aurora replica lag monitor | list | `<list>` | no |
 | aurora_replicalag_message | Custom message for RDS Aurora replica lag monitor | string | `` | no |
 | aurora_replicalag_silenced | Groups to mute for RDS Aurora replica lag monitor | map | `<map>` | no |
 | aurora_replicalag_threshold_critical | Aurora replica lag in milliseconds (critical threshold) | string | `200` | no |

cloud/aws/rds/common/README.md

@@ -18,6 +18,7 @@ Creates DataDog monitors with the following checks:
 
 - RDS instance CPU high
 - RDS instance free space
+- RDS replica lag
 
 ## Inputs
 
@@ -45,6 +46,13 @@ Creates DataDog monitors with the following checks:
 | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
 | new_host_delay | Delay in seconds before monitor new resource | string | `300` | no |
+| replicalag_enabled | Flag to enable RDS replica lag monitor | string | `true` | no |
+| replicalag_extra_tags | Extra tags for RDS replica lag monitor | list | `<list>` | no |
+| replicalag_message | Custom message for RDS replica lag monitor | string | `` | no |
+| replicalag_silenced | Groups to mute for RDS replica lag monitor | map | `<map>` | no |
+| replicalag_threshold_critical | replica lag in seconds (critical threshold) | string | `300` | no |
+| replicalag_threshold_warning | replica lag in seconds (warning threshold) | string | `200` | no |
+| replicalag_timeframe | Monitor timeframe for RDS replica lag monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
 
 ## Outputs
 
@@ -52,6 +60,7 @@ Creates DataDog monitors with the following checks:
 |------|-------------|
 | rds_cpu_90_15min_id | id for monitor rds_cpu_90_15min |
 | rds_free_space_low_id | id for monitor rds_free_space_low |
+| rds_replica_lag_id | id for monitor rds_replica_lag |
 
 ## Related documentation
 

cloud/aws/rds/common/inputs.tf

@@ -122,3 +122,43 @@ variable "diskspace_threshold_critical" {
   description = "Disk free space in percent (critical threshold)"
   default     = "10"
 }
+
+variable "replicalag_silenced" {
+  description = "Groups to mute for RDS replica lag monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "replicalag_enabled" {
+  description = "Flag to enable RDS replica lag monitor"
+  type        = "string"
+  default     = "true"
+}
+
+variable "replicalag_extra_tags" {
+  description = "Extra tags for RDS replica lag monitor"
+  type        = "list"
+  default     = []
+}
+
+variable "replicalag_message" {
+  description = "Custom message for RDS replica lag monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "replicalag_timeframe" {
+  description = "Monitor timeframe for RDS replica lag monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = "string"
+  default     = "last_5m"
+}
+
+variable "replicalag_threshold_warning" {
+  description = "replica lag in seconds (warning threshold)"
+  default     = "200"
+}
+
+variable "replicalag_threshold_critical" {
+  description = "replica lag in seconds (critical threshold)"
+  default     = "300"
+}

cloud/aws/rds/common/monitors-rds-common.tf

@@ -64,3 +64,36 @@ EOF
 
   tags = ["env:${var.environment}", "type:cloud", "provider:aws", "resource:rds", "team:claranet", "created-by:terraform", "${var.diskspace_extra_tags}"]
 }
+
+### RDS Replica Lag monitor ###
+resource "datadog_monitor" "rds_replica_lag" {
+  count   = "${var.replicalag_enabled ? 1 : 0}"
+  name    = "[${var.environment}] RDS replica lag {{#is_alert}}{{{comparator}}} {{threshold}} ms ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ms ({{value}}%){{/is_warning}}"
+  message = "${coalesce(var.replicalag_message, var.message)}"
+
+  type = "metric alert"
+
+  query = <<EOF
+  avg(${var.replicalag_timeframe}): (
+    avg:aws.rds.replica_lag${module.filter-tags.query_alert} by {region,name}
+  ) > ${var.replicalag_threshold_critical}
+EOF
+
+  thresholds {
+    warning  = "${var.replicalag_threshold_warning}"
+    critical = "${var.replicalag_threshold_critical}"
+  }
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+  new_host_delay      = "${var.new_host_delay}"
+
+  silenced = "${var.replicalag_silenced}"
+
+  tags = ["env:${var.environment}", "type:cloud", "provider:aws", "resource:rds", "team:claranet", "created-by:terraform", "${var.replicalag_extra_tags}"]
+}

cloud/aws/rds/common/outputs.tf

@@ -7,3 +7,8 @@ output "rds_free_space_low_id" {
   description = "id for monitor rds_free_space_low"
   value       = "${datadog_monitor.rds_free_space_low.*.id}"
 }
+
+output "rds_replica_lag_id" {
+  description = "id for monitor rds_replica_lag"
+  value       = "${datadog_monitor.rds_replica_lag.*.id}"
+}