Add initial monitors

Author: rhynix

.terraform-version

@@ -0,0 +1 @@
+1.0.3

.terraform.lock.hcl

@@ -0,0 +1,48 @@
+variable "batches_compiled_percent_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "batches_compiled_percent_warning" {
+  type    = number
+  default = 10
+}
+
+variable "batches_compiled_percent_critical" {
+  type    = number
+  default = 20
+}
+
+variable "batches_compiled_percent_evaluation_period" {
+  type    = string
+  default = "last_1d"
+}
+
+variable "batches_compiled_percent_note" {
+  type    = string
+  default = ""
+}
+
+variable "batches_compiled_percent_docs" {
+  type    = string
+  default = <<-EOT
+    When this metric is high, a lot of queries need to be recompiled. Consider parameterizing more queries by using stored procedures, using forced parameterization or allocating more memory.
+  EOT
+}
+
+variable "batches_compiled_percent_filter_override" {
+  type    = string
+  default = ""
+}
+
+variable "batches_compiled_percent_alerting_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "batches_compiled_percent_priority" {
+  description = "Number from 1 (high) to 5 (low)."
+
+  type    = number
+  default = 4
+}

batches-compiled-percent-variables.tf

@@ -0,0 +1,34 @@
+locals {
+  batches_compiled_percent_filter = coalesce(
+    var.batches_compiled_percent_filter_override,
+    var.filter_str
+  )
+}
+
+module "batches_compiled_percent" {
+  source = "[email protected]:kabisa/terraform-datadog-generic-monitor.git?ref=0.6.2"
+
+  name  = "SQL Server - Percentage of batches requiring compilation"
+  query = "avg(${var.batches_compiled_percent_evaluation_period}):(max:sqlserver.stats.sql_compilations{${local.batches_compiled_percent_filter}} by {host} / max:sqlserver.stats.batch_requests{${local.batches_compiled_percent_filter}} by {host}) * 100 >= ${var.batches_compiled_percent_critical}"
+
+  alert_message    = "Database {{database.name}} on {{host.name}} has a high percent of batches requiring compilation"
+  recovery_message = "Database {{database.name}} on {{host.name}} has a normal percent of batches requiring compilation"
+
+  # monitor level vars
+  enabled            = var.batches_compiled_percent_enabled
+  alerting_enabled   = var.batches_compiled_percent_alerting_enabled
+  warning_threshold  = var.batches_compiled_percent_warning
+  critical_threshold = var.batches_compiled_percent_critical
+  priority           = var.batches_compiled_percent_priority
+  docs               = var.batches_compiled_percent_docs
+  note               = var.batches_compiled_percent_note
+
+  # module level vars
+  env                  = var.alert_env
+  service              = var.service
+  notification_channel = var.notification_channel
+  additional_tags      = var.additional_tags
+  locked               = var.locked
+  name_prefix          = var.name_prefix
+  name_suffix          = var.name_suffix
+}

batches-compiled-percent.tf

@@ -0,0 +1,48 @@
+variable "buffer_cache_hit_ratio_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "buffer_cache_hit_ratio_warning" {
+  type    = number
+  default = 90
+}
+
+variable "buffer_cache_hit_ratio_critical" {
+  type    = number
+  default = 75
+}
+
+variable "buffer_cache_hit_ratio_evaluation_period" {
+  type    = string
+  default = "last_1d"
+}
+
+variable "buffer_cache_hit_ratio_note" {
+  type    = string
+  default = ""
+}
+
+variable "buffer_cache_hit_ratio_docs" {
+  type    = string
+  default = <<-EOT
+    When this metric is low, pages are often read from disk. Consider allocating more memory.
+  EOT
+}
+
+variable "buffer_cache_hit_ratio_filter_override" {
+  type    = string
+  default = ""
+}
+
+variable "buffer_cache_hit_ratio_alerting_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "buffer_cache_hit_ratio_priority" {
+  description = "Number from 1 (high) to 5 (low)."
+
+  type    = number
+  default = 4
+}

buffer-cache-hit-ratio-variables.tf

@@ -0,0 +1,34 @@
+locals {
+  buffer_cache_hit_ratio_filter = coalesce(
+    var.buffer_cache_hit_ratio_filter_override,
+    var.filter_str
+  )
+}
+
+module "buffer_cache_hit_ratio" {
+  source = "[email protected]:kabisa/terraform-datadog-generic-monitor.git?ref=0.6.2"
+
+  name  = "SQL Server - Buffer cache hit ratio"
+  query = "avg(${var.buffer_cache_hit_ratio_evaluation_period}):min:sqlserver.buffer.cache_hit_ratio{${local.buffer_cache_hit_ratio_filter}} by {host} * 100 < ${var.buffer_cache_hit_ratio_critical}"
+
+  alert_message    = "Buffer cache hit ratio on {{host.name}} has increased above {{threshold}} ({{value}})"
+  recovery_message = "Buffer cache hit ratio on {{host.name}} has recovered ({{value}})"
+
+  # monitor level vars
+  enabled            = var.buffer_cache_hit_ratio_enabled
+  alerting_enabled   = var.buffer_cache_hit_ratio_alerting_enabled
+  warning_threshold  = var.buffer_cache_hit_ratio_warning
+  critical_threshold = var.buffer_cache_hit_ratio_critical
+  priority           = var.buffer_cache_hit_ratio_priority
+  docs               = var.buffer_cache_hit_ratio_docs
+  note               = var.buffer_cache_hit_ratio_note
+
+  # module level vars
+  env                  = var.alert_env
+  service              = var.service
+  notification_channel = var.notification_channel
+  additional_tags      = var.additional_tags
+  locked               = var.locked
+  name_prefix          = var.name_prefix
+  name_suffix          = var.name_suffix
+}

buffer-cache-hit-ratio.tf

@@ -0,0 +1,34 @@
+variable "can_connect_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "can_connect_alerting_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "can_connect_warning" {
+  type    = number
+  default = 1
+}
+
+variable "can_connect_critical" {
+  type    = number
+  default = 1
+}
+
+variable "can_connect_priority" {
+  type    = number
+  default = 1
+}
+
+variable "can_connect_docs" {
+  type    = string
+  default = ""
+}
+
+variable "can_connect_note" {
+  type    = string
+  default = ""
+}

can-connect-variables.tf

@@ -0,0 +1,30 @@
+module "can_connect" {
+  source = "[email protected]:kabisa/terraform-datadog-service-check-monitor.git?ref=1.2.0"
+
+  name         = "SQL Server - Can connect"
+  check_name   = "sqlserver.can_connect"
+  by_tags      = ["host", "db"]
+  include_tags = local.service_check_include_tags
+  exclude_tags = local.service_check_exclude_tags
+
+  alert_message    = "Can not connect to database {{database.name}} on {{host.name}}"
+  recovery_message = "Can connect to database {{database.name}} on {{host.name}}"
+
+  # monitor level vars
+  enabled            = var.can_connect_enabled
+  alerting_enabled   = var.can_connect_alerting_enabled
+  warning_threshold  = var.can_connect_warning
+  critical_threshold = var.can_connect_critical
+  priority           = var.can_connect_priority
+  docs               = var.can_connect_docs
+  note               = var.can_connect_note
+
+  # module level vars
+  env                  = var.alert_env
+  service              = var.service
+  notification_channel = var.notification_channel
+  additional_tags      = var.additional_tags
+  locked               = var.locked
+  name_prefix          = var.name_prefix
+  name_suffix          = var.name_suffix
+}

can-connect.tf

@@ -0,0 +1,46 @@
+variable "database_state_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "database_state_warning" {
+  type    = number
+  default = 1
+}
+
+variable "database_state_critical" {
+  type    = number
+  default = 5
+}
+
+variable "database_state_evaluation_period" {
+  type    = string
+  default = "last_5m"
+}
+
+variable "database_state_note" {
+  type    = string
+  default = ""
+}
+
+variable "database_state_docs" {
+  type    = string
+  default = ""
+}
+
+variable "database_state_filter_override" {
+  type    = string
+  default = ""
+}
+
+variable "database_state_alerting_enabled" {
+  type    = bool
+  default = true
+}
+
+variable "database_state_priority" {
+  description = "Number from 1 (high) to 5 (low)."
+
+  type    = number
+  default = 1
+}

database-state-variables.tf

@@ -0,0 +1,34 @@
+locals {
+  database_state_filter = coalesce(
+    var.database_state_filter_override,
+    var.filter_str
+  )
+}
+
+module "database_state" {
+  source = "[email protected]:kabisa/terraform-datadog-generic-monitor.git?ref=0.6.2"
+
+  name  = "SQL Server - Database state"
+  query = "max(${var.database_state_evaluation_period}):max:sqlserver.database.state{${local.database_state_filter}} by {host,database,database_state_desc} >= ${var.database_state_critical}"
+
+  alert_message    = "Database {{database.name}} on {{host.name}} is in abnormal state {{database_state_desc.name}}"
+  recovery_message = "Database {{database.name}} on {{host.name}} is in back in state {{database_state_desc.name}}"
+
+  # monitor level vars
+  enabled            = var.database_state_enabled
+  alerting_enabled   = var.database_state_alerting_enabled
+  warning_threshold  = var.database_state_warning
+  critical_threshold = var.database_state_critical
+  priority           = var.database_state_priority
+  docs               = var.database_state_docs
+  note               = var.database_state_note
+
+  # module level vars
+  env                  = var.alert_env
+  service              = var.service
+  notification_channel = var.notification_channel
+  additional_tags      = var.additional_tags
+  locked               = var.locked
+  name_prefix          = var.name_prefix
+  name_suffix          = var.name_suffix
+}