Merge branch 'MON-554-monitor-velero' into 'master'

Monitors for K8S Velero See merge request claranet/pt-monitoring/projects/datadog/terraform/monitors!153
2020-01-17 16:46:51 +01:00 · 2020-01-17 16:46:51 +01:00 · f6a2f3e795
commit f6a2f3e795
parent 0c3fde1432 266b93381e
6 changed files with 516 additions and 0 deletions
--- a/README.md
+++ b/README.md
@ -131,6 +131,7 @@ module "datadog-monitors-system-generic" {
 			- [vts](https://github.com/claranet/terraform-datadog-monitors/tree/master/caas/kubernetes/ingress/vts/)
 		- [node](https://github.com/claranet/terraform-datadog-monitors/tree/master/caas/kubernetes/node/)
 		- [pod](https://github.com/claranet/terraform-datadog-monitors/tree/master/caas/kubernetes/pod/)
+		- [velero](https://github.com/claranet/terraform-datadog-monitors/tree/master/caas/kubernetes/velero/)
 		- [workload](https://github.com/claranet/terraform-datadog-monitors/tree/master/caas/kubernetes/workload/)
 - [cloud](https://github.com/claranet/terraform-datadog-monitors/tree/master/cloud/)
 	- [aws](https://github.com/claranet/terraform-datadog-monitors/tree/master/cloud/aws/)
--- a/caas/kubernetes/velero/README.md
+++ b/caas/kubernetes/velero/README.md
@ -0,0 +1,134 @@
+# CAAS KUBERNETES VELERO DataDog monitors
+
+## How to use this module
+
+```
+module "datadog-monitors-caas-kubernetes-velero" {
+  source = "claranet/monitors/datadog//caas/kubernetes/velero"
+  version = "{revision}"
+
+  environment = var.environment
+  message     = module.datadog-message-alerting.alerting-message
+}
+
+```
+
+## Purpose
+
+Creates DataDog monitors with the following checks:
+
+- Velero backup deletion failure
+- Velero backup failure
+- Velero backup partial failure
+- Velero scheduled backup missing
+- Velero volume snapshot failure
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| environment | Architecture environment | string | n/a | yes |
+| evaluation\_delay | Delay in seconds for the metric evaluation | string | `"15"` | no |
+| filter\_tags\_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `"*"` | no |
+| filter\_tags\_custom\_excluded | Tags excluded for custom filtering when filter_tags_use_defaults is false | string | `""` | no |
+| filter\_tags\_use\_defaults | Use default filter tags convention | string | `"true"` | no |
+| message | Message sent when a monitor is triggered | string | n/a | yes |
+| new\_host\_delay | Delay in seconds before monitor new resource | string | `"300"` | no |
+| notify\_no\_data | Will raise no data alert if set to true | string | `"true"` | no |
+| prefix\_slug | Prefix string to prepend between brackets on every monitors names | string | `""` | no |
+| velero\_backup\_deletion\_failure\_enabled | Flag to enable Velero backup deletion failure monitor | string | `"true"` | no |
+| velero\_backup\_deletion\_failure\_extra\_tags | Extra tags for Velero backup deletion failure monitor | list(string) | `[]` | no |
+| velero\_backup\_deletion\_failure\_monitor\_message | Custom message for Velero backup deletion failure monitor | string | `""` | no |
+| velero\_backup\_deletion\_failure\_monitor\_timeframe | 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`] | string | `"last_1d"` | no |
+| velero\_backup\_failure\_enabled | Flag to enable Velero backup failure monitor | string | `"true"` | no |
+| velero\_backup\_failure\_extra\_tags | Extra tags for Velero backup failure monitor | list(string) | `[]` | no |
+| velero\_backup\_failure\_monitor\_message | Custom message for Velero backup failure monitor | string | `""` | no |
+| velero\_backup\_failure\_monitor\_timeframe | 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`] | string | `"last_1d"` | no |
+| velero\_backup\_partial\_failure\_enabled | Flag to enable Velero backup partial failure monitor | string | `"true"` | no |
+| velero\_backup\_partial\_failure\_extra\_tags | Extra tags for Velero backup partial failure monitor | list(string) | `[]` | no |
+| velero\_backup\_partial\_failure\_monitor\_message | Custom message for Velero backup partial failure monitor | string | `""` | no |
+| velero\_backup\_partial\_failure\_monitor\_timeframe | 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`] | string | `"last_1d"` | no |
+| velero\_scheduled\_backup\_missing\_enabled | Flag to enable Velero scheduled backup missing monitor | string | `"true"` | no |
+| velero\_scheduled\_backup\_missing\_extra\_tags | Extra tags for Velero scheduled backup missing monitor | list(string) | `[]` | no |
+| velero\_scheduled\_backup\_missing\_monitor\_message | Custom message for Velero scheduled backup missing monitor | string | `""` | no |
+| velero\_scheduled\_backup\_missing\_monitor\_no\_data\_timeframe | No data timeframe in minutes | string | `"2880"` | no |
+| velero\_scheduled\_backup\_missing\_monitor\_timeframe | 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`] | string | `"last_1d"` | no |
+| velero\_volume\_snapshot\_failure\_enabled | Flag to enable Velero volume snapshot failure monitor | string | `"true"` | no |
+| velero\_volume\_snapshot\_failure\_extra\_tags | Extra tags for Velero volume snapshot failure monitor | list(string) | `[]` | no |
+| velero\_volume\_snapshot\_failure\_monitor\_message | Custom message for Velero volume snapshot failure monitor | string | `""` | no |
+| velero\_volume\_snapshot\_failure\_monitor\_timeframe | 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`] | string | `"last_1d"` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| velero\_backup\_deletion\_failure\_id | id for monitor velero_backup_deletion_failure |
+| velero\_backup\_failure\_id | id for monitor velero_backup_failure |
+| velero\_backup\_partial\_failure\_id | id for monitor velero_backup_partial_failure |
+| velero\_scheduled\_backup\_missing\_id | id for monitor velero_scheduled_backup_missing |
+| velero\_volume\_snapshot\_failure\_id | id for monitor velero_volume_snapshot_failure |
+
+## Related documentation
+
+Documentation for Datadog prometheus intergration: https://docs.datadoghq.com/integrations/prometheus/
+Documentation for Datadog OpenMetrics integration: https://docs.datadoghq.com/integrations/openmetrics/
+Documentation for Datadog autodiscovery: https://docs.datadoghq.com/agent/autodiscovery/clusterchecks/
+
+### How to configure Datadog agent for these monitors ?
+You can configure Datadog agent by autodiscovery pod annotations or by configuration file.
+
+#### Configuration by autodiscovery pod annotations
+Add these annotations to Velero pods:
+
+```
+podAnnotations: {
+  "ad.datadoghq.com/velero.check_names": '["openmetrics"]',
+  "ad.datadoghq.com/velero.init_configs": '[{}]',
+  "ad.datadoghq.com/velero.instances": '[{"prometheus_url": "http://%%host%%:8085/metrics", "namespace": "velero", "metrics": ["velero*"]}]'
+}
+```
+
+#### Configuration by configuration file
+Example of `openmetrics.d/conf.yaml`:
+
+```
+init_config:
+
+instances:
+
+    ## @param prometheus_url - string - required
+    ## The URL where your application metrics are exposed by Prometheus.
+    #
+  - prometheus_url: http://velero.velero.svc.cluster.local:8085/metrics
+
+    ## @param namespace - string - required
+    ## The namespace to be prepended to all metrics.
+    #
+    namespace: "velero"
+
+    ## @param metrics - list of strings - required
+    ## List of metrics to be fetched from the prometheus endpoint, if there's a
+    ## value it'll be renamed. This list should contain at least one metric
+    #
+    metrics:
+      - velero*
+```
+
+### How to monitor multiple schedule witch have different frequencies ?
+
+If you have multiple Velero schedules with different frequencies, you must duplicate this module and disable common monitors in the others instance of module.
+
+```
+module "datadog-monitors-caas-kubernetes-velero" {
+  source = "claranet/monitors/datadog//caas/kubernetes/velero"
+  version = "{revision}"
+
+  environment = var.environment
+  message     = module.datadog-message-alerting.alerting-message
+
+  velero_backup_failure_enabled          = false
+  velero_backup_partial_failure_enabled  = false
+  velero_backup_deletion_failure_enabled = false
+  velero_volume_snapshot_failure_enabled = false
+}
+
--- a/caas/kubernetes/velero/inputs.tf
+++ b/caas/kubernetes/velero/inputs.tf
@ -0,0 +1,171 @@
+# 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 "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     = 2880
+}
+
+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_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_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_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     = []
+}
--- a/caas/kubernetes/velero/modules.tf
+++ b/caas/kubernetes/velero/modules.tf
@ -0,0 +1,20 @@
+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_use_defaults
+  filter_tags_custom          = var.filter_tags_custom
+  filter_tags_custom_excluded = var.filter_tags_custom_excluded
+  extra_tags_excluded         = ["schedule:"]
+}
--- a/caas/kubernetes/velero/monitors-velero.tf
+++ b/caas/kubernetes/velero/monitors-velero.tf
@ -0,0 +1,165 @@
+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${module.filter-tags-scheduled-backup.query_alert} by {cluster-name,schedule}.as_count() < 1
+EOQ
+
+  thresholds = {
+    critical = 1
+  }
+
+  evaluation_delay  = var.evaluation_delay
+  new_host_delay    = var.new_host_delay
+  no_data_timeframe = var.velero_scheduled_backup_missing_monitor_no_data_timeframe
+
+  notify_no_data      = var.notify_no_data
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:openmetrics", "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${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:openmetrics", "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${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:openmetrics", "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${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:openmetrics", "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${module.filter-tags.query_alert} by {schedule}.as_count() > 1
+EOQ
+
+  thresholds = {
+    critical = 1
+    warning  = 0
+  }
+
+  evaluation_delay = var.evaluation_delay
+  new_host_delay   = var.new_host_delay
+
+  notify_no_data      = false
+  renotify_interval   = 0
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+
+  tags = concat(["env:${var.environment}", "type:caas", "provider:openmetrics", "resource:velero", "team:claranet", "created-by:terraform"], var.velero_volume_snapshot_failure_extra_tags)
+
+  lifecycle {
+    ignore_changes = [silenced]
+  }
+}
+
--- a/caas/kubernetes/velero/outputs.tf
+++ b/caas/kubernetes/velero/outputs.tf
@ -0,0 +1,25 @@
+output "velero_backup_deletion_failure_id" {
+  description = "id for monitor velero_backup_deletion_failure"
+  value       = datadog_monitor.velero_backup_deletion_failure.*.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_scheduled_backup_missing_id" {
+  description = "id for monitor velero_scheduled_backup_missing"
+  value       = datadog_monitor.velero_scheduled_backup_missing.*.id
+}
+
+output "velero_volume_snapshot_failure_id" {
+  description = "id for monitor velero_volume_snapshot_failure"
+  value       = datadog_monitor.velero_volume_snapshot_failure.*.id
+}
+