Merge branch 'MON-531_Add_time_aggregator_on_replica_lag_monitor' into 'master'

MON-531: Add replicalag time aggregator input variable

Closes MON-531

See merge request claranet/pt-monitoring/projects/datadog/terraform/monitors!139

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

@@ -27,6 +27,7 @@ Creates DataDog monitors with the following checks:
 | aurora\_replicalag\_message | Custom message for RDS Aurora replica lag monitor | string | `""` | no |
 | aurora\_replicalag\_threshold\_critical | Aurora replica lag in milliseconds (critical threshold) | string | `"200"` | no |
 | aurora\_replicalag\_threshold\_warning | Aurora replica lag in milliseconds (warning threshold) | string | `"100"` | no |
+| aurora\_replicalag\_time\_aggregator | Monitor aggregator for RDS Aurora replica lag [available values: min, max or avg] | string | `"min"` | no |
 | aurora\_replicalag\_timeframe | Monitor timeframe for RDS Aurora 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 |
 | environment | Architecture Environment | string | n/a | yes |
 | evaluation\_delay | Delay in seconds for the metric evaluation | string | `"900"` | no |
@@ -45,3 +46,6 @@ Creates DataDog monitors with the following checks:
 
 ## Related documentation
 
+DataDog documentation: [https://docs.datadoghq.com/integrations/amazon_rds/](https://docs.datadoghq.com/integrations/amazon_rds/)
+
+AWS RDS Instance metrics documentation: [https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/MonitoringOverview.html#monitoring-cloudwatch](https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/MonitoringOverview.html#monitoring-cloudwatch)

cloud/aws/rds/aurora/mysql/inputs.tf

@@ -59,6 +59,12 @@ variable "aurora_replicalag_message" {
   default     = ""
 }
 
+variable "aurora_replicalag_time_aggregator" {
+  description = "Monitor aggregator for RDS Aurora replica lag [available values: min, max or avg]"
+  type        = string
+  default     = "min"
+}
+
 variable "aurora_replicalag_timeframe" {
   description = "Monitor timeframe for RDS Aurora replica lag monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
   type        = string
@@ -74,4 +80,3 @@ variable "aurora_replicalag_threshold_critical" {
   description = "Aurora replica lag in milliseconds (critical threshold)"
   default     = "200"
 }
-

cloud/aws/rds/aurora/mysql/monitors-rds-aurora-mysql.tf

@@ -6,7 +6,7 @@ resource "datadog_monitor" "rds_aurora_mysql_replica_lag" {
   type    = "query alert"
 
   query = <<EOQ
-  avg(${var.aurora_replicalag_timeframe}): (
+  ${var.aurora_replicalag_time_aggregator}(${var.aurora_replicalag_timeframe}): (
     avg:aws.rds.aurora_replica_lag${module.filter-tags.query_alert} by {region,name}
   ) > ${var.aurora_replicalag_threshold_critical}
 EOQ

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

@@ -27,6 +27,7 @@ Creates DataDog monitors with the following checks:
 | aurora\_replicalag\_message | Custom message for RDS Aurora replica lag monitor | string | `""` | no |
 | aurora\_replicalag\_threshold\_critical | Aurora replica lag in milliseconds (critical threshold) | string | `"200"` | no |
 | aurora\_replicalag\_threshold\_warning | Aurora replica lag in milliseconds (warning threshold) | string | `"100"` | no |
+| aurora\_replicalag\_time\_aggregator | Monitor aggregator for RDS Aurora replica lag [available values: min, max or avg] | string | `"min"` | no |
 | aurora\_replicalag\_timeframe | Monitor timeframe for RDS Aurora 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 |
 | environment | Architecture Environment | string | n/a | yes |
 | evaluation\_delay | Delay in seconds for the metric evaluation | string | `"900"` | no |
@@ -45,3 +46,6 @@ Creates DataDog monitors with the following checks:
 
 ## Related documentation
 
+DataDog documentation: [https://docs.datadoghq.com/integrations/amazon_rds/](https://docs.datadoghq.com/integrations/amazon_rds/)
+
+AWS RDS Instance metrics documentation: [https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/MonitoringOverview.html#monitoring-cloudwatch](https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/MonitoringOverview.html#monitoring-cloudwatch)

cloud/aws/rds/aurora/postgresql/inputs.tf

@@ -59,6 +59,12 @@ variable "aurora_replicalag_message" {
   default     = ""
 }
 
+variable "aurora_replicalag_time_aggregator" {
+  description = "Monitor aggregator for RDS Aurora replica lag [available values: min, max or avg]"
+  type        = string
+  default     = "min"
+}
+
 variable "aurora_replicalag_timeframe" {
   description = "Monitor timeframe for RDS Aurora replica lag monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
   type        = string
@@ -74,4 +80,3 @@ variable "aurora_replicalag_threshold_critical" {
   description = "Aurora replica lag in milliseconds (critical threshold)"
   default     = "200"
 }
-

cloud/aws/rds/aurora/postgresql/monitors-rds-aurora-postgresql.tf

@@ -6,7 +6,7 @@ resource "datadog_monitor" "rds_aurora_postgresql_replica_lag" {
   type    = "query alert"
 
   query = <<EOQ
-  avg(${var.aurora_replicalag_timeframe}): (
+  ${var.aurora_replicalag_time_aggregator}(${var.aurora_replicalag_timeframe}): (
     avg:aws.rds.rdsto_aurora_postgre_sqlreplica_lag${module.filter-tags.query_alert} by {region,name}
   ) > ${var.aurora_replicalag_threshold_critical}
 EOQ

cloud/aws/rds/common/README.md

@@ -51,6 +51,7 @@ Creates DataDog monitors with the following checks:
 | replicalag\_message | Custom message for RDS replica lag monitor | string | `""` | 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\_time\_aggregator | Monitor aggregator for RDS replica lag [available values: min, max or avg] | string | `"min"` | 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
@@ -65,5 +66,4 @@ Creates DataDog monitors with the following checks:
 
 DataDog documentation: [https://docs.datadoghq.com/integrations/amazon_rds/](https://docs.datadoghq.com/integrations/amazon_rds/)
 
-AWS RDS Instance metrics documentation: [https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html)
-
+AWS RDS Instance metrics documentation: [https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/MonitoringOverview.html#monitoring-cloudwatch](https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/MonitoringOverview.html#monitoring-cloudwatch)

cloud/aws/rds/common/inputs.tf

@@ -139,6 +139,12 @@ variable "replicalag_message" {
   default     = ""
 }
 
+variable "replicalag_time_aggregator" {
+  description = "Monitor aggregator for RDS replica lag [available values: min, max or avg]"
+  type        = string
+  default     = "min"
+}
+
 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
@@ -154,4 +160,3 @@ variable "replicalag_threshold_critical" {
   description = "replica lag in seconds (critical threshold)"
   default     = "300"
 }
-

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

@@ -75,7 +75,7 @@ resource "datadog_monitor" "rds_replica_lag" {
   type    = "query alert"
 
   query = <<EOQ
-  avg(${var.replicalag_timeframe}): (
+  ${var.replicalag_time_aggregator}(${var.replicalag_timeframe}): (
     avg:aws.rds.replica_lag${module.filter-tags.query_alert} by {region,name}
   ) > ${var.replicalag_threshold_critical}
 EOQ