Merged in TER-209-add-bitbucket-pipelines-to-suppo (pull request #40)

TER-209 add bitbucket pipelines to suppo

Approved-by: Adrien Bréfort <adrien.brefort@fr.clara.net>

.gitignore

@@ -1,10 +1,3 @@
-# Ignore all volatile files
-**/.terraform/modules
-**/.terraform/plugins
-**/terraform.tfstate*.backup
-
-# Ignore all credentials files
-**/terraform.tfvars
-
-# Ignore all but root state files
-**/terraform.tfstate
+.terraform
+main.tf
+terraform.tfvars

bitbucket-pipelines.yml

@@ -0,0 +1,15 @@
+image: hashicorp/terraform:0.10.8
+
+pipelines:
+  default:
+    - step:
+        name: Format
+        script:
+          - terraform fmt -write=false -diff -check
+    - step:
+        name: Validate
+        script:
+          - mv main.tf.ci main.tf
+          - mv terraform.tfvars.ci terraform.tfvars
+          - terraform init
+          - terraform validate

cloud/aws/elasticsearch/monitors-elasticsearch.tf

@@ -12,6 +12,7 @@ resource "datadog_monitor" "es_cluster_status" {
   message = "${var.message}"
 
   type = "query alert"
+
   query = <<EOF
   max(last_30m): (
     avg:aws.es.cluster_statusred{${data.template_file.filter.rendered}} by {region,name} * 2 +
@@ -45,6 +46,7 @@ resource "datadog_monitor" "es_free_space_low" {
   message = "${var.message}"
 
   type = "query alert"
+
   query = <<EOF
   avg(last_15m): (
     avg:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} / (${var.es_cluster_volume_size}*1000) * 100
@@ -76,6 +78,7 @@ resource "datadog_monitor" "es_cpu_90_15min" {
   message = "${var.message}"
 
   type = "query alert"
+
   query = <<EOF
   avg(last_15m): (
     avg:aws.es.cpuutilization{${data.template_file.filter.rendered}} by {region,name}

cloud/azure/apimanagement/monitors-azure-apimanagement.tf

@@ -15,6 +15,7 @@ resource "datadog_monitor" "apimgt_status" {
   query = <<EOF
       avg(last_5m):avg:azure.apimanagement_service.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
       EOF
+
   type = "metric alert"
 
   thresholds {

cloud/azure/eventhub/monitors-eventhub.tf

@@ -13,6 +13,7 @@ resource "datadog_monitor" "eventhub_status" {
   query = <<EOF
       avg(last_5m): avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
       EOF
+
   type = "metric alert"
 
   notify_no_data      = true
@@ -41,6 +42,7 @@ resource "datadog_monitor" "eventhub_failed_requests" {
           avg:azure.eventhub_namespaces.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
         ) * 100 > ${var.failed_requests_rate_thresold_critical}
         EOF
+
   type = "metric alert"
 
   thresholds {
@@ -78,6 +80,7 @@ resource "datadog_monitor" "eventhub_errors" {
           avg:azure.eventhub_namespaces.other_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
         ) * 100 > ${var.errors_rate_thresold_critical}
         EOF
+
   type = "metric alert"
 
   thresholds {

cloud/azure/storage/inputs.tf

@@ -69,4 +69,3 @@ variable "authorization_error_requests_threshold_critical" {
   description = "Maximum acceptable percent of authorization error requests for a storage"
   default     = 15
 }
-

cloud/azure/storage/monitors-azure-storage.tf

@@ -122,7 +122,6 @@ EOF
   tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
 }
 
-
 resource "datadog_monitor" "network_error_requests" {
   name    = "[${var.environment}] Azure Storage {{value}}% of network error requests on {{name}}"
   message = "${var.message}"
@@ -152,7 +151,6 @@ EOF
   tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
 }
 
-
 resource "datadog_monitor" "throttling_error_requests" {
   name    = "[${var.environment}] Azure Storage {{value}}% of throttling error requests on {{name}}"
   message = "${var.message}"
@@ -182,7 +180,6 @@ EOF
   tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
 }
 
-
 resource "datadog_monitor" "server_other_error_requests" {
   name    = "[${var.environment}] Azure Storage {{value}}% of server_other error requests on {{name}}"
   message = "${var.message}"
@@ -212,7 +209,6 @@ EOF
   tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
 }
 
-
 resource "datadog_monitor" "client_other_error_requests" {
   name    = "[${var.environment}] Azure Storage {{value}}% of client_other error requests on {{name}}"
   message = "${var.message}"
@@ -242,7 +238,6 @@ EOF
   tags = ["env:${var.environment}", "resource:storage", "team:azure", "provider:azure"]
 }
 
-
 resource "datadog_monitor" "authorization_error_requests" {
   name    = "[${var.environment}] Azure Storage {{value}}% of authorization error requests on {{name}}"
   message = "${var.message}"

cloud/azure/stream-analytics/monitors-stream-analytics.tf

@@ -13,6 +13,7 @@ resource "datadog_monitor" "status" {
   query = <<EOF
     avg(last_5m):avg:azure.streamanalytics_streamingjobs.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
   EOF
+
   type = "metric alert"
 
   notify_no_data      = true
@@ -38,6 +39,7 @@ resource "datadog_monitor" "su_utilization" {
       avg:azure.streamanalytics_streamingjobs.resource_utilization{${data.template_file.filter.rendered}} by {resource_group,region,name}
     ) > ${var.su_utilization_threshold_critical}
   EOF
+
   type = "metric alert"
 
   notify_no_data      = false
@@ -50,6 +52,7 @@ resource "datadog_monitor" "su_utilization" {
   require_full_window = true
   new_host_delay      = "${var.delay}"
   no_data_timeframe   = 20
+
   thresholds {
     warning  = "${var.su_utilization_threshold_warning}"
     critical = "${var.su_utilization_threshold_critical}"
@@ -68,6 +71,7 @@ resource "datadog_monitor" "failed_function_requests" {
        avg:azure.streamanalytics_streamingjobs.aml_callout_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
     ) * 100 > ${var.failed_function_requests_threshold_critical}
   EOF
+
   type = "metric alert"
 
   notify_no_data      = false
@@ -80,6 +84,7 @@ resource "datadog_monitor" "failed_function_requests" {
   require_full_window = true
   new_host_delay      = "${var.delay}"
   no_data_timeframe   = 20
+
   thresholds {
     warning  = "${var.function_requests_threshold_warning}"
     critical = "${var.failed_function_requests_threshold_critical}"
@@ -97,6 +102,7 @@ resource "datadog_monitor" "conversion_errors" {
       avg:azure.streamanalytics_streamingjobs.conversion_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
     ) > ${var.conversion_errors_threshold_critical}
   EOF
+
   type = "metric alert"
 
   notify_no_data      = false
@@ -109,6 +115,7 @@ resource "datadog_monitor" "conversion_errors" {
   require_full_window = true
   new_host_delay      = "${var.delay}"
   no_data_timeframe   = 20
+
   thresholds {
     warning  = "${var.conversion_errors_threshold_warning}"
     critical = "${var.conversion_errors_threshold_critical}"
@@ -126,6 +133,7 @@ resource "datadog_monitor" "runtime_errors" {
       avg:azure.streamanalytics_streamingjobs.errors{${data.template_file.filter.rendered}} by {resource_group,region,name}
     ) > ${var.runtime_errors_threshold_critical}
   EOF
+
   type = "metric alert"
 
   notify_no_data      = false
@@ -138,6 +146,7 @@ resource "datadog_monitor" "runtime_errors" {
   require_full_window = true
   new_host_delay      = "${var.delay}"
   no_data_timeframe   = 20
+
   thresholds {
     warning  = "${var.runtime_errors_threshold_warning}"
     critical = "${var.runtime_errors_threshold_critical}"

incubator/monitors-gcp-cloud-sql.tf

@@ -42,10 +42,10 @@ resource "datadog_monitor" "cloud_sql_disk_space" {
 }
 
 resource "datadog_monitor" "cloud_sql_connection_80" {
-name   = "Cloud SQL MySQL connection > 80% of max connections"
-message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
-query   = "avg(last_5m):avg:gcp.cloudsql.database.network.connections{*} > 3500"
-type  = "metric alert"
+  name    = "Cloud SQL MySQL connection > 80% of max connections"
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
+  query   = "avg(last_5m):avg:gcp.cloudsql.database.network.connections{*} > 3500"
+  type    = "metric alert"
 
   notify_no_data      = false
   renotify_interval   = 60
@@ -61,10 +61,10 @@ type  = "metric alert"
 }
 
 resource "datadog_monitor" "cloud_sql_lag" {
-name   = "Cloud SQL MySQL lag > 45min"
-message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
-query   = "min(last_10m):avg:gcp.cloudsql.database.mysql.replication.seconds_behind_master{*} by {database_id} > 2700"
-type  = "metric alert"
+  name    = "Cloud SQL MySQL lag > 45min"
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
+  query   = "min(last_10m):avg:gcp.cloudsql.database.mysql.replication.seconds_behind_master{*} by {database_id} > 2700"
+  type    = "metric alert"
 
   notify_no_data      = false
   renotify_interval   = 60
@@ -77,14 +77,13 @@ type  = "metric alert"
   notify_no_data      = false
   renotify_interval   = 0
   no_data_timeframe   = 20
-
 }
 
 resource "datadog_monitor" "cloud_sql_replication" {
-name   = "Cloud SQL Failover not ready to replication"
-message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
-query   = "max(last_5m):avg:gcp.cloudsql.database.mysql.replication.available_for_failover{*} <= 0"
-type  = "metric alert"
+  name    = "Cloud SQL Failover not ready to replication"
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
+  query   = "max(last_5m):avg:gcp.cloudsql.database.mysql.replication.available_for_failover{*} <= 0"
+  type    = "metric alert"
 
   notify_no_data      = false
   renotify_interval   = 60
@@ -97,5 +96,4 @@ type  = "metric alert"
   notify_no_data      = false
   renotify_interval   = 0
   no_data_timeframe   = 20
-
 }

incubator/monitors-kubernetes.tf

@@ -48,7 +48,9 @@ resource "datadog_monitor" "kubernetes_kubelet_check" {
 
 resource "datadog_monitor" "kubernetes_kubelet_ping" {
   name    = "Kubernetes kubelet ping not ok"
-  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}\n{{#is_warning}}\n${var.warning_HO} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.warning_HO}\n{{/is_warning_recovery}}"message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}\n{{#is_warning}}\n${var.warning_HO} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.warning_HO}\n{{/is_warning_recovery}}"
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}\n{{#is_warning}}\n${var.warning_HO} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.warning_HO}\n{{/is_warning_recovery}}"
+
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}\n{{#is_warning}}\n${var.warning_HO} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.warning_HO}\n{{/is_warning_recovery}}"
   query   = "\"kubernetes.kubelet.check.ping\".over(\"goog-gke-node\").by(\"*\").last(1).pct_by_status()"
 
   thresholds {
@@ -108,7 +110,7 @@ resource "datadog_monitor" "kubernetes_node_status" {
   no_data_timeframe   = 20
 }
 
-  type  = "query alert"
+/*  type  = "query alert"
 
   thresholds {
 #    warning  = 75
@@ -126,4 +128,5 @@ resource "datadog_monitor" "kubernetes_node_status" {
   notify_no_data      = false
   renotify_interval   = 0
   no_data_timeframe   = 20
-}
+}*/
+

incubator/monitors-redis-containers.tf

@@ -1,11 +1,12 @@
 resource "datadog_monitor" "kubernetes_redis_cpu_95_5min" {
   name = "Kubernetes Redis container CPU High > 95% for 5 min"
+
   #message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}\n{{#is_warning}}\n${var.warning_HO} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.warning_HO}\n{{/is_warning_recovery}}"
   message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
   query   = "avg(last_5m):avg:gcp.container.cpu.utilization{container_name:redis} by {cluster-name} * 100 > 95"
 
   thresholds {
-#    warning  = 80
+    #    warning  = 80
     critical = 95
   }
 
@@ -25,6 +26,7 @@ resource "datadog_monitor" "kubernetes_redis_cpu_95_5min" {
 
 resource "datadog_monitor" "kubernetes_redis_cpu_80_15min" {
   name = "Kubernetes Redis container CPU High > 80% for 15 min"
+
   #message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}\n{{#is_warning}}\n${var.warning_HO} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.warning_HO}\n{{/is_warning_recovery}}"
   message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
 
@@ -32,7 +34,7 @@ resource "datadog_monitor" "kubernetes_redis_cpu_80_15min" {
   type  = "query alert"
 
   thresholds {
-#    warning  = 75
+    #    warning  = 75
     critical = 80
   }
 
@@ -72,3 +74,4 @@ resource "datadog_monitor" "kubernetes_redis_cpu_80_15min" {
 #   renotify_interval   = 0
 #   no_data_timeframe   = 20
 # }
+

incubator/monitors-redis.tf

@@ -22,13 +22,11 @@ resource "datadog_monitor" "redis_connection" {
   no_data_timeframe   = 20
 }
 
-
-
 resource "datadog_monitor" "redis_eviction" {
-name   = "Redis eviction > 0"
-message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
-query   = "min(last_5m):avg:redis.keys.evicted{*} > 0"
-type  = "metric alert"
+  name    = "Redis eviction > 0"
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
+  query   = "min(last_5m):avg:redis.keys.evicted{*} > 0"
+  type    = "metric alert"
 
   notify_no_data      = false
   renotify_interval   = 60
@@ -41,15 +39,13 @@ type  = "metric alert"
   notify_no_data      = false
   renotify_interval   = 0
   no_data_timeframe   = 20
-
 }
 
-
 resource "datadog_monitor" "datadog_blocked_client" {
-name   = "Redis blocked clients > 0"
-message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
-query   = "min(last_5m):avg:redis.clients.blocked{*} > 0"
-type  = "metric alert"
+  name    = "Redis blocked clients > 0"
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
+  query   = "min(last_5m):avg:redis.clients.blocked{*} > 0"
+  type    = "metric alert"
 
   notify_no_data      = false
   renotify_interval   = 60
@@ -62,15 +58,13 @@ type  = "metric alert"
   notify_no_data      = false
   renotify_interval   = 0
   no_data_timeframe   = 20
-
 }
 
-
 resource "datadog_monitor" "redis_swap" {
-name   = "Redis begin to swap"
-message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
-query   = "avg(last_5m):avg:redis.mem.fragmentation_ratio{*} <= 0.8"
-type  = "metric alert"
+  name    = "Redis begin to swap"
+  message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
+  query   = "avg(last_5m):avg:redis.mem.fragmentation_ratio{*} <= 0.8"
+  type    = "metric alert"
 
   notify_no_data      = false
   renotify_interval   = 60
@@ -83,5 +77,4 @@ type  = "metric alert"
   notify_no_data      = false
   renotify_interval   = 0
   no_data_timeframe   = 20
-
 }

inputs.tf

@@ -96,6 +96,7 @@ variable "elb_4xx_threshold" {
 
 variable "elb_backend_latency" {
   description = "Average time elapsed after the request leaves the load balancer until a response is received. In seconds"
+
   default = {
     warning  = 1
     critical = 5

main.tf.ci

@@ -0,0 +1,7 @@
+variable "aws_region" {}
+
+provider "aws" {
+  version = "1.2.0"
+
+  region = "${var.aws_region}"
+}

terraform.tfvars.ci

@@ -0,0 +1,6 @@
+aws_region="eu-west-1"
+region="eu-west-1"
+env="test"
+hno_escalation_group="abc"
+ho_escalation_group="abc"
+