MON-554 - Add first version of Velero monitors

caas/kubernetes/velero/inputs.tf

@@ -0,0 +1,206 @@
+# Datadog global variables
+
+variable "environment" {
+  description = "Architecture environment"
+}
+
+variable "filter_tags_use_defaults" {
+  description = "Use default filter tags convention"
+  default     = "true"
+}
+
+variable "filter_tags_custom" {
+  description = "Tags used for custom filtering when filter_tags_use_defaults is false"
+  default     = "*"
+}
+
+variable "filter_tags_custom_excluded" {
+  description = "Tags excluded for custom filtering when filter_tags_use_defaults is false"
+  default     = ""
+}
+
+variable "filter_tags_scheduled_backup_use_defaults" {
+  description = "Use default filter tags scheduled backup convention"
+  default     = null
+}
+
+variable "filter_tags_scheduled_backup_custom" {
+  description = "Tags used for scheduled backup custom filtering when filter_tags_scheduled_backup_use_defaults is false"
+  default     = null
+}
+
+variable "filter_tags_scheduled_backup_custom_excluded" {
+  description = "Tags excluded for scheduled backup custom filtering when filter_tags_scheduled_backup_use_defaults is false"
+  default     = null
+}
+
+variable "message" {
+  description = "Message sent when a monitor is triggered"
+}
+
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 15
+}
+
+variable "new_host_delay" {
+  description = "Delay in seconds before monitor new resource"
+  default     = 300
+}
+
+variable "prefix_slug" {
+  description = "Prefix string to prepend between brackets on every monitors names"
+  default     = ""
+}
+
+variable "notify_no_data" {
+  description = "Will raise no data alert if set to true"
+  default     = true
+}
+
+# Datadog monitors variables
+
+variable "velero_scheduled_backup_missing_monitor_message" {
+  description = "Custom message for Velero scheduled backup missing monitor"
+  type        = string
+  default     = ""
+}
+
+variable "velero_scheduled_backup_missing_monitor_timeframe" {
+  description = "Monitor timeframe for Velero scheduled backup missing monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1d"
+}
+
+variable "velero_scheduled_backup_missing_enabled" {
+  description = "Flag to enable Velero scheduled backup missing monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "velero_scheduled_backup_missing_extra_tags" {
+  description = "Extra tags for Velero scheduled backup missing monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "velero_scheduled_backup_missing_monitor_no_data_timeframe" {
+  description = "No data timeframe in minutes"
+  default     = 1440
+}
+
+variable "velero_backup_failure_monitor_message" {
+  description = "Custom message for Velero backup failure monitor"
+  type        = string
+  default     = ""
+}
+
+variable "velero_backup_failure_monitor_timeframe" {
+  description = "Monitor timeframe for Velero backup failure monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1d"
+}
+
+variable "velero_backup_failure_enabled" {
+  description = "Flag to enable Velero backup failure monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "velero_backup_failure_extra_tags" {
+  description = "Extra tags for Velero backup failure monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "velero_backup_failure_monitor_no_data_timeframe" {
+  description = "No data timeframe in minutes"
+  default     = 1440
+}
+
+variable "velero_backup_partial_failure_monitor_message" {
+  description = "Custom message for Velero backup partial failure monitor"
+  type        = string
+  default     = ""
+}
+
+variable "velero_backup_partial_failure_monitor_timeframe" {
+  description = "Monitor timeframe for Velero backup partial failure monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1d"
+}
+
+variable "velero_backup_partial_failure_enabled" {
+  description = "Flag to enable Velero backup partial failure monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "velero_backup_partial_failure_extra_tags" {
+  description = "Extra tags for Velero backup partial failure monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "velero_backup_partial_failure_monitor_no_data_timeframe" {
+  description = "No data timeframe in minutes"
+  default     = 1440
+}
+
+variable "velero_backup_deletion_failure_monitor_message" {
+  description = "Custom message for Velero backup deletion failure monitor"
+  type        = string
+  default     = ""
+}
+
+variable "velero_backup_deletion_failure_monitor_timeframe" {
+  description = "Monitor timeframe for Velero backup deletion failure monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1d"
+}
+
+variable "velero_backup_deletion_failure_enabled" {
+  description = "Flag to enable Velero backup deletion failure monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "velero_backup_deletion_failure_extra_tags" {
+  description = "Extra tags for Velero backup deletion failure monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "velero_backup_deletion_failure_monitor_no_data_timeframe" {
+  description = "No data timeframe in minutes"
+  default     = 1440
+}
+
+variable "velero_volume_snapshot_failure_monitor_message" {
+  description = "Custom message for Velero volume snapshot failure monitor"
+  type        = string
+  default     = ""
+}
+
+variable "velero_volume_snapshot_failure_monitor_timeframe" {
+  description = "Monitor timeframe for Velero volume snapshot failure monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
+  type        = string
+  default     = "last_1d"
+}
+
+variable "velero_volume_snapshot_failure_enabled" {
+  description = "Flag to enable Velero volume snapshot failure monitor"
+  type        = string
+  default     = "true"
+}
+
+variable "velero_volume_snapshot_failure_extra_tags" {
+  description = "Extra tags for Velero volume snapshot failure monitor"
+  type        = list(string)
+  default     = []
+}
+
+variable "velero_volume_snapshot_failure_monitor_no_data_timeframe" {
+  description = "No data timeframe in minutes"
+  default     = 1440
+}

caas/kubernetes/velero/modules.tf

@@ -0,0 +1,19 @@
+module "filter-tags" {
+  source = "../../../common/filter-tags"
+
+  environment                 = var.environment
+  resource                    = "velero"
+  filter_tags_use_defaults    = var.filter_tags_use_defaults
+  filter_tags_custom          = var.filter_tags_custom
+  filter_tags_custom_excluded = var.filter_tags_custom_excluded
+}
+
+module "filter-tags-scheduled-backup" {
+  source = "../../../common/filter-tags"
+
+  environment                 = var.environment
+  resource                    = "velero"
+  filter_tags_use_defaults    = var.filter_tags_scheduled_backup_use_defaults != null ? var.filter_tags_scheduled_backup_use_defaults : var.filter_tags_use_defaults
+  filter_tags_custom          = var.filter_tags_scheduled_backup_custom != null ? var.filter_tags_scheduled_backup_custom : var.filter_tags_custom
+  filter_tags_custom_excluded = var.filter_tags_scheduled_backup_custom_excluded != null ? var.filter_tags_scheduled_backup_custom_excluded : var.filter_tags_custom_excluded
+}

caas/kubernetes/velero/monitors-velero.tf

@@ -0,0 +1,169 @@
+resource "datadog_monitor" "velero_scheduled_backup_missing" {
+  count   = var.velero_scheduled_backup_missing_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Velero scheduled backup missing"
+  type    = "query alert"
+  message = coalesce(var.velero_scheduled_backup_missing_monitor_message, var.message)
+
+  query = <<EOQ
+    sum(${var.velero_scheduled_backup_missing_monitor_timeframe}):sum:velero.velero_backup_success_total${module.filter-tags-scheduled-backup.query_alert} by {cluster-name,schedule}.as_count() < 1
+EOQ
+
+  thresholds = {
+    critical = 1
+  }
+
+  evaluation_delay  = var.evaluation_delay
+  new_host_delay    = var.new_host_delay
+  no_data_timeframe = var.velero_scheduled_backup_missing_monitor_no_data_timeframe
+
+  notify_no_data      = var.notify_no_data
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:prometheus", "resource:velero", "team:claranet", "created-by:terraform"], var.velero_scheduled_backup_missing_extra_tags)
+
+  lifecycle {
+    ignore_changes = [silenced]
+  }
+}
+
+resource "datadog_monitor" "velero_backup_failure" {
+  count   = var.velero_backup_failure_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Velero backup failure"
+  type    = "query alert"
+  message = coalesce(var.velero_backup_failure_monitor_message, var.message)
+
+  query = <<EOQ
+    sum(${var.velero_backup_failure_monitor_timeframe}):min:velero.velero_backup_failure_total${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay  = var.evaluation_delay
+  new_host_delay    = var.new_host_delay
+  no_data_timeframe = var.velero_backup_failure_monitor_no_data_timeframe
+
+  notify_no_data      = var.notify_no_data
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:prometheus", "resource:velero", "team:claranet", "created-by:terraform"], var.velero_backup_failure_extra_tags)
+
+  lifecycle {
+    ignore_changes = [silenced]
+  }
+}
+
+resource "datadog_monitor" "velero_backup_partial_failure" {
+  count   = var.velero_backup_partial_failure_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Velero backup partial failure"
+  type    = "query alert"
+  message = coalesce(var.velero_backup_partial_failure_monitor_message, var.message)
+
+  query = <<EOQ
+    sum(${var.velero_backup_partial_failure_monitor_timeframe}):min:velero.velero_backup_partial_failure_total${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay  = var.evaluation_delay
+  new_host_delay    = var.new_host_delay
+  no_data_timeframe = var.velero_backup_partial_failure_monitor_no_data_timeframe
+
+  notify_no_data      = var.notify_no_data
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:prometheus", "resource:velero", "team:claranet", "created-by:terraform"], var.velero_backup_partial_failure_extra_tags)
+
+  lifecycle {
+    ignore_changes = [silenced]
+  }
+}
+
+resource "datadog_monitor" "velero_backup_deletion_failure" {
+  count   = var.velero_backup_deletion_failure_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Velero backup deletion failure"
+  type    = "query alert"
+  message = coalesce(var.velero_backup_deletion_failure_monitor_message, var.message)
+
+  query = <<EOQ
+    sum(${var.velero_backup_deletion_failure_monitor_timeframe}):min:velero.velero_backup_deletion_failure_total${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay  = var.evaluation_delay
+  new_host_delay    = var.new_host_delay
+  no_data_timeframe = var.velero_backup_deletion_failure_monitor_no_data_timeframe
+
+  notify_no_data      = var.notify_no_data
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:prometheus", "resource:velero", "team:claranet", "created-by:terraform"], var.velero_backup_deletion_failure_extra_tags)
+
+  lifecycle {
+    ignore_changes = [silenced]
+  }
+}
+
+resource "datadog_monitor" "velero_volume_snapshot_failure" {
+  count   = var.velero_volume_snapshot_failure_enabled == "true" ? 1 : 0
+  name    = "${var.prefix_slug == "" ? "" : "[${var.prefix_slug}]"}[${var.environment}] Velero volume snapshot failure"
+  type    = "query alert"
+  message = coalesce(var.velero_volume_snapshot_failure_monitor_message, var.message)
+
+  query = <<EOQ
+    sum(${var.velero_volume_snapshot_failure_monitor_timeframe}):min:velero.velero_volume_snapshot_failure_total${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay  = var.evaluation_delay
+  new_host_delay    = var.new_host_delay
+  no_data_timeframe = var.velero_volume_snapshot_failure_monitor_no_data_timeframe
+
+  notify_no_data      = var.notify_no_data
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = false
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:prometheus", "resource:velero", "team:claranet", "created-by:terraform"], var.velero_volume_snapshot_failure_extra_tags)
+
+  lifecycle {
+    ignore_changes = [silenced]
+  }
+}
+

caas/kubernetes/velero/outputs.tf

@@ -0,0 +1,24 @@
+output "velero_scheduled_backup_missing_id" {
+  description = "id for monitor velero_scheduled_backup_missing"
+  value       = datadog_monitor.velero_scheduled_backup_missing.*.id
+}
+
+output "velero_backup_failure_id" {
+  description = "id for monitor velero_backup_failure"
+  value       = datadog_monitor.velero_backup_failure.*.id
+}
+
+output "velero_backup_partial_failure_id" {
+  description = "id for monitor velero_backup_partial_failure"
+  value       = datadog_monitor.velero_backup_partial_failure.*.id
+}
+
+output "velero_backup_deletion_failure_id" {
+  description = "id for monitor velero_backup_deletion_failure"
+  value       = datadog_monitor.velero_backup_deletion_failure.*.id
+}
+
+output "velero_volume_snapshot_failure_id" {
+  description = "id for monitor velero_volume_snapshot_failure"
+  value       = datadog_monitor.velero_volume_snapshot_failure.*.id
+}