MON-224 Monitors imported from the Actualys ones using the exported json

cloud/gcp/cloud-sql/instance/inputs.tf

@@ -45,19 +45,19 @@ variable "cpu_utilization_message" {
 variable "cpu_utilization_timeframe" {
   description = "Timeframe for the CPU Utilization monitor"
   type        = "string"
-  default     = "last_30m"
+  default     = "last_15m"
 }
 
 variable "cpu_utilization_threshold_warning" {
-  description = "CPU Utilization in fraction (warning threshold)"
+  description = "CPU Utilization in percentage (warning threshold)"
   type        = "string"
-  default     = 0.8
+  default     = 80
 }
 
 variable "cpu_utilization_threshold_critical" {
-  description = "CPU Utilization in fraction (critical threshold)"
+  description = "CPU Utilization in percentage (critical threshold)"
   type        = "string"
-  default     = 0.9
+  default     = 90
 }
 
 variable "cpu_utilization_silenced" {
@@ -73,7 +73,7 @@ variable "cpu_utilization_extra_tags" {
 }
 
 #
-# DISK
+# DISK Utilization
 #
 variable "disk_utilization_message" {
   description = "Custom message for the Disk Utilization monitor"
@@ -88,15 +88,15 @@ variable "disk_utilization_timeframe" {
 }
 
 variable "disk_utilization_threshold_warning" {
-  description = "Disk Utilization in fraction (warning threshold)"
+  description = "Disk Utilization in percentage (warning threshold)"
   type        = "string"
-  default     = 0.8
+  default     = 80
 }
 
 variable "disk_utilization_threshold_critical" {
-  description = "Disk Utilization in fraction (critical threshold)"
+  description = "Disk Utilization in percentage (critical threshold)"
   type        = "string"
-  default     = 0.9
+  default     = 90
 }
 
 variable "disk_utilization_silenced" {
@@ -111,6 +111,45 @@ variable "disk_utilization_extra_tags" {
   default     = []
 }
 
+#
+# DISK Utilization Forecast
+#
+variable "disk_utilization_forecast_message" {
+  description = "Custom message for the Disk Utilization monitor"
+  type        = "string"
+  default     = ""
+}
+
+variable "disk_utilization_forecast_timeframe" {
+  description = "Timeframe for the Disk Utilization monitor"
+  type        = "string"
+  default     = "next_1w"
+}
+
+variable "disk_utilization_forecast_threshold_critical" {
+  description = "Disk Utilization in percentage (critical threshold)"
+  type        = "string"
+  default     = 80
+}
+
+variable "disk_utilization_forecast_threshold_critical_recovery" {
+  description = "Disk Utilization in percentage (recovery threshold)"
+  type        = "string"
+  default     = 72
+}
+
+variable "disk_utilization_forecast_silenced" {
+  description = "Groups to mute for GCP Cloud SQL Disk Utilization monitor"
+  type        = "map"
+  default     = {}
+}
+
+variable "disk_utilization_forecast_extra_tags" {
+  description = "Extra tags for GCP Cloud SQL CPU Utilization monitor"
+  type        = "list"
+  default     = []
+}
+
 #
 # Memory Utilization
 #
@@ -125,13 +164,13 @@ variable "memory_utilization_timeframe" {
 }
 
 variable "memory_utilization_threshold_warning" {
-  description = "Memory Utilization in fraction (warning threshold)"
+  description = "Memory Utilization in percentage (warning threshold)"
-  default     = 0.8
+  default     = 80
 }
 
 variable "memory_utilization_threshold_critical" {
-  description = "Memory Utilization in fraction (critical threshold)"
+  description = "Memory Utilization in percentage (critical threshold)"
-  default     = 0.9
+  default     = 90
 }
 
 variable "memory_utilization_silenced" {
@@ -169,14 +208,14 @@ variable "memory_utilization_forecast_history" {
   default     = "12h"
 }
 
-variable "memory_utilization_forecast_threshold_warning" {
+variable "memory_utilization_forecast_threshold_critical" {
-  description = "Memory Utilization Forecast in fraction (warning threshold)"
+  description = "Memory Utilization Forecast in percentage (warning threshold)"
-  default     = 0.8
+  default     = 90
 }
 
-variable "memory_utilization_forecast_threshold_critical" {
+variable "memory_utilization_forecast_threshold_critical_recovery" {
-  description = "Memory Utilization Forecast in fraction (critical threshold)"
+  description = "Memory Utilization Forecast in percentage (recovery threshold)"
-  default     = 0.9
+  default     = 81
 }
 
 variable "memory_utilization_forecast_silenced" {

cloud/gcp/cloud-sql/instance/monitors-cloud-sql-instance.tf

@@ -15,7 +15,7 @@ data "template_file" "filter" {
 # CPU Utilization
 #
 resource "datadog_monitor" "cpu_utilization" {
-  name    = "[${var.environment}] Cloud SQL CPU Utilization {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  name    = "[${var.environment}] Cloud SQL CPU utilization {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
   message = "${coalesce(var.cpu_utilization_message, var.message)}"
 
   type = "metric alert"
@@ -23,7 +23,7 @@ resource "datadog_monitor" "cpu_utilization" {
   query = <<EOF
   avg(${var.cpu_utilization_timeframe}):
     avg:gcp.cloudsql.database.cpu.utilization{${data.template_file.filter.rendered}}
-  by {database_id}
+    by {database_id} * 100
   > ${var.cpu_utilization_threshold_critical}
 EOF
 
@@ -32,15 +32,18 @@ EOF
     critical = "${var.cpu_utilization_threshold_critical}"
   }
 
-  notify_no_data      = true
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  no_data_timeframe   = 30
+  require_full_window = false
+  notify_no_data      = true
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.cpu_utilization_silenced}"
 
   tags = [
@@ -56,7 +59,7 @@ EOF
 # Disk Utilization
 #
 resource "datadog_monitor" "disk_utilization" {
-  name    = "[${var.environment}] Cloud SQL Disk Utilization {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  name    = "[${var.environment}] Cloud SQL Disk utilization {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
   message = "${coalesce(var.disk_utilization_message, var.message)}"
 
   type = "metric alert"
@@ -64,7 +67,7 @@ resource "datadog_monitor" "disk_utilization" {
   query = <<EOF
   avg(${var.disk_utilization_timeframe}):
     avg:gcp.cloudsql.database.disk.utilization{${data.template_file.filter.rendered}}
-    by {database_id}
+    by {database_id} *100
     > ${var.disk_utilization_threshold_critical}
 EOF
 
@@ -73,15 +76,18 @@ EOF
     critical = "${var.disk_utilization_threshold_critical}"
   }
 
-  notify_no_data      = true
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  no_data_timeframe   = 20
+  require_full_window = false
+  notify_no_data      = true
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.disk_utilization_silenced}"
 
   tags = [
@@ -93,6 +99,55 @@ EOF
   ]
 }
 
+#
+# Disk Utilization Forecast
+#
+resource "datadog_monitor" "disk_utilization_forecast" {
+  name    = "[${var.environment}] Cloud SQL Disk utilization could reach {{#is_alert}}{{threshold}}%{{/is_alert}} in a near future"
+  message = "${coalesce(var.disk_utilization_forecast_message, var.message)}"
+
+  type = "metric alert"
+
+  query = <<EOF
+  max(${var.disk_utilization_forecast_timeframe}):
+    forecast(
+      avg:gcp.cloudsql.database.disk.utilization{${data.template_file.filter.rendered}} by {database_id} * 100,
+      'linear',
+      1,
+      interval='60m',
+      history='3d',
+      model='default'
+    )
+  >= ${var.disk_utilization_forecast_threshold_critical}
+EOF
+
+  thresholds {
+    critical          = "${var.disk_utilization_forecast_threshold_critical}"
+    critical_recovery = "${var.disk_utilization_forecast_threshold_critical_recovery}"
+  }
+
+  notify_audit        = false
+  locked              = false
+  timeout_h           = 0
+  include_tags        = true
+  require_full_window = false
+  notify_no_data      = false
+  renotify_interval   = 0
+
+  evaluation_delay = "${var.delay}"
+  new_host_delay   = "${var.delay}"
+
+  silenced = "${var.disk_utilization_forecast_silenced}"
+
+  tags = [
+    "team:gcp",
+    "provider:gcp",
+    "env:${var.environment}",
+    "resource:cloud-sql",
+    "${var.disk_utilization_forecast_extra_tags}",
+  ]
+}
+
 #
 # Memory Utilization
 #
@@ -105,7 +160,7 @@ resource "datadog_monitor" "memory_utilization" {
   query = <<EOF
   avg(${var.memory_utilization_timeframe}):
     avg:gcp.cloudsql.database.memory.utilization{${data.template_file.filter.rendered}}
-    by {database_id}
+    by {database_id} * 100
   > ${var.memory_utilization_threshold_critical}
 EOF
 
@@ -114,15 +169,18 @@ EOF
     critical = "${var.memory_utilization_threshold_critical}"
   }
 
-  notify_no_data      = true
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  no_data_timeframe   = 20
+  require_full_window = false
+  notify_no_data      = true
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.memory_utilization_silenced}"
 
   tags = [
@@ -138,7 +196,7 @@ EOF
 # Memory Utilization Forecast
 #
 resource "datadog_monitor" "memory_utilization_forecast" {
-  name    = "[${var.environment}] Cloud SQL Memory Utilization Forecast {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  name    = "[${var.environment}] Cloud SQL Memory Utilization could reach {{#is_alert}}{{threshold}}%{{/is_alert}} in a near future"
   message = "${coalesce(var.memory_utilization_forecast_message, var.message)}"
 
   type = "query alert"
@@ -146,30 +204,32 @@ resource "datadog_monitor" "memory_utilization_forecast" {
   query = <<EOF
   max(${var.memory_utilization_forecast_timeframe}):
     forecast(
-      avg:gcp.cloudsql.database.memory.utilization{${data.template_file.filter.rendered}} by {database_id},
+      avg:gcp.cloudsql.database.memory.utilization{${data.template_file.filter.rendered}} by {database_id} * 100,
       'linear',
       1,
       interval='${var.memory_utilization_forecast_interval}',
       history='${var.memory_utilization_forecast_history}',
       model='default'
       )
-    > ${var.memory_utilization_forecast_threshold_critical}
+    >= ${var.memory_utilization_forecast_threshold_critical}
 EOF
 
   thresholds {
-    warning  = "${var.memory_utilization_forecast_threshold_warning}"
     critical          = "${var.memory_utilization_forecast_threshold_critical}"
+    critical_recovery = "${var.memory_utilization_forecast_threshold_critical_recovery}"
   }
 
-  notify_no_data      = true
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  require_full_window = false
+  notify_no_data      = false
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.memory_utilization_forecast_silenced}"
 
   tags = [
@@ -185,7 +245,7 @@ EOF
 # Failover Unavailable
 #
 resource "datadog_monitor" "failover_unavailable" {
-  name    = "[${var.environment}] Cloud SQL Failover Unavailable {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
+  name    = "[${var.environment}] Cloud SQL Failover Unavailable"
   message = "${coalesce(var.failover_unavailable_message, var.message)}"
 
   type = "metric alert"
@@ -201,15 +261,18 @@ EOF
     critical = "${var.failover_unavailable_threshold_critical}"
   }
 
-  notify_no_data      = true
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  no_data_timeframe   = 20
+  require_full_window = false
+  notify_no_data      = true
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.failover_unavailable_silenced}"
 
   tags = [

cloud/gcp/cloud-sql/mysql/inputs.tf

@@ -96,13 +96,13 @@ variable "replication_lag_timeframe" {
 variable "replication_lag_threshold_warning" {
   description = "Seconds behind the master (warning threshold)"
   type        = "string"
-  default     = 300
+  default     = 90
 }
 
 variable "replication_lag_threshold_critical" {
   description = "Seconds behind the master (critical threshold)"
   type        = "string"
-  default     = 900
+  default     = 180
 }
 
 variable "replication_lag_silenced" {
@@ -135,13 +135,13 @@ variable "queries_changing_message" {
 variable "queries_changing_timeframe" {
   description = "Timeframe for the Queries Changing mon monitor"
   type        = "string"
-  default     = "last_10m"
+  default     = "last_1h"
 }
 
 variable "queries_changing_anomaly_detection_algorithm" {
   description = "Anomaly Detection Algorithm used"
   type        = "string"
-  default     = "robust"
+  default     = "agile"
 }
 
 variable "queries_changing_deviations" {
@@ -174,6 +174,12 @@ variable "queries_changing_threshold_critical" {
   default     = 1
 }
 
+variable "queries_changing_threshold_critical_recovery" {
+  description = "Queries Changing critical recovery threshold"
+  type        = "string"
+  default     = 0.99
+}
+
 variable "queries_changing_silenced" {
   description = "Groups to mute for GCP Cloud SQL Queries Changing monitor"
   type        = "map"
@@ -198,7 +204,7 @@ variable "questions_changing_message" {
 variable "questions_changing_timeframe" {
   description = "Timeframe for the Questions Changing monitor"
   type        = "string"
-  default     = "last_10m"
+  default     = "last_1h"
 }
 
 variable "questions_changing_database_ids" {
@@ -210,7 +216,7 @@ variable "questions_changing_database_ids" {
 variable "questions_changing_anomaly_detection_algorithm" {
   description = "Anomaly Detection Algorithm used"
   type        = "string"
-  default     = "robust"
+  default     = "agile"
 }
 
 variable "questions_changing_deviations" {
@@ -243,6 +249,12 @@ variable "questions_changing_threshold_critical" {
   default     = 1
 }
 
+variable "questions_changing_threshold_critical_recovery" {
+  description = "Questions Changing critical recovery threshold"
+  type        = "string"
+  default     = 0.99
+}
+
 variable "questions_changing_silenced" {
   description = "Groups to mute for GCP Cloud SQL Questions Changing monitor"
   type        = "map"

cloud/gcp/cloud-sql/mysql/monitors-cloudsql-mysql.tf

@@ -57,7 +57,7 @@ EOF
 # Replication Lag
 #
 resource "datadog_monitor" "replication_lag" {
-  name    = "[${var.environment}] Cloud SQL MySQL Replication Lag too high"
+  name    = "[${var.environment}] Cloud SQL MySQL Replication Lag {{#is_alert}}{{{comparator}}} {{threshold}}s ({{value}}s){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}s ({{value}}s){{/is_warning}}"
   message = "${coalesce(var.replication_lag_message, var.message)}"
 
   type = "metric alert"
@@ -74,15 +74,18 @@ EOF
     warning  = "${var.replication_lag_threshold_warning}"
   }
 
-  notify_no_data      = true
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  no_data_timeframe   = 25
+  require_full_window = false
+  notify_no_data      = true
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.replication_lag_silenced}"
 
   tags = [
@@ -99,9 +102,7 @@ EOF
 # Queries Anomaly
 #
 resource "datadog_monitor" "queries_changing_anomaly" {
-  count = "${length(var.queries_changing_database_ids)}"
+  name    = "[${var.environment}] Cloud SQL MySQL Queries Count changed abnormally"
-
-  name    = "[${var.environment}] [${var.queries_changing_database_ids[count.index]}] Cloud SQL MySQL Queries Count changed abnormally {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
   message = "${coalesce(var.queries_changing_message, var.message)}"
 
   type = "query alert"
@@ -109,12 +110,13 @@ resource "datadog_monitor" "queries_changing_anomaly" {
   query = <<EOF
     avg(${var.queries_changing_timeframe}):
       anomalies(
-        default(
+        avg:gcp.cloudsql.database.mysql.queries{${data.template_file.filter.rendered}} by {database_id}.as_count()
-          avg:gcp.cloudsql.database.mysql.queries{project_id:${var.project_id},database_id:${var.project_id}:${var.queries_changing_database_ids[count.index]}},
-          0),
         '${var.queries_changing_anomaly_detection_algorithm}',
         ${var.queries_changing_deviations},
         direction='${var.queries_changing_direction}',
+        alert_window='last_30m',
+        interval=20,
+        count_default_zero='false',
         seasonality='${var.queries_changing_seasonality}'
       )
       > ${var.queries_changing_threshold_critical}
@@ -123,17 +125,20 @@ EOF
   thresholds {
     warning           = "${var.queries_changing_threshold_warning}"
     critical          = "${var.queries_changing_threshold_critical}"
+    critical_recovery = "${var.queries_changing_threshold_critical_recovery}"
   }
 
-  notify_no_data      = false
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  require_full_window = false
+  notify_no_data      = false
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.queries_changing_silenced}"
 
   tags = [
@@ -142,7 +147,6 @@ EOF
     "env:${var.environment}",
     "resource:cloud-sql",
     "engine:mysql",
-    "database_id:${var.project_id}:${var.queries_changing_database_ids[count.index]}}",
     "${var.queries_changing_extra_tags}",
   ]
 }
@@ -151,22 +155,21 @@ EOF
 # Questions Anomaly
 #
 resource "datadog_monitor" "questions_changing_anomaly" {
-  count = "${length(var.questions_changing_database_ids)}"
+  name    = "[${var.environment}] Cloud SQL MySQL Questions Count changed abnormally"
-
-  name    = "[${var.environment}] [${var.questions_changing_database_ids[count.index]}] Cloud SQL MySQL Questions Count changed abnormally {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
   message = "${coalesce(var.questions_changing_message, var.message)}"
 
   type = "query alert"
 
   query = <<EOF
-    avg(${var.questions_changing_timeframe}):
+    avg(last_1h):
       anomalies(
-        default(
+        avg:gcp.cloudsql.database.mysql.questions{${data.template_file.filter.rendered}} by {database_id},
-          avg:gcp.cloudsql.database.mysql.questions{project_id:${var.project_id},database_id:${var.project_id}:${var.questions_changing_database_ids[count.index]}},
-          0),
         '${var.questions_changing_anomaly_detection_algorithm}',
         ${var.questions_changing_deviations},
         direction='${var.questions_changing_direction}',
+        alert_window='last_30m',
+        interval=20,
+        count_default_zero='false',
         seasonality='${var.questions_changing_seasonality}'
       )
     > ${var.questions_changing_threshold_critical}
@@ -175,17 +178,20 @@ EOF
   thresholds {
     warning           = "${var.questions_changing_threshold_warning}"
     critical          = "${var.questions_changing_threshold_critical}"
+    critical_recovery = "${var.questions_changing_threshold_critical_recovery}"
   }
 
-  notify_no_data      = false
-  require_full_window = false
-  renotify_interval   = 0
   notify_audit        = false
+  locked              = false
   timeout_h           = 0
   include_tags        = true
-  locked              = false
+  require_full_window = false
+  notify_no_data      = false
+  renotify_interval   = 0
+
   evaluation_delay = "${var.delay}"
   new_host_delay   = "${var.delay}"
+
   silenced = "${var.questions_changing_silenced}"
 
   tags = [
@@ -194,7 +200,6 @@ EOF
     "env:${var.environment}",
     "resource:cloud-sql",
     "engine:mysql",
-    "database_id:${var.project_id}:${var.questions_changing_database_ids[count.index]}",
     "${var.questions_changing_extra_tags}",
   ]
 }