From 92833feff788d16b3831623690d676b88448e006 Mon Sep 17 00:00:00 2001
From: Ahmed Fourti <ahmed.fourti@fr.clara.net>
Date: Wed, 13 Dec 2017 12:11:15 +0100
Subject: [PATCH 01/11] MON-96 Update non-cloud resource tags

---
 middleware/apache/monitors-apache.tf  |  2 +-
 middleware/nginx/monitors-nginx.tf    |  2 +-
 middleware/php-fpm/monitors-fpm.tf    |  4 ++--
 system/linux/monitors-linux-basics.tf | 14 +++++++-------
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/middleware/apache/monitors-apache.tf b/middleware/apache/monitors-apache.tf
index 49b31d4..b542aa4 100644
--- a/middleware/apache/monitors-apache.tf
+++ b/middleware/apache/monitors-apache.tf
@@ -23,5 +23,5 @@ resource "datadog_monitor" "Apache_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:apache"]
 }
diff --git a/middleware/nginx/monitors-nginx.tf b/middleware/nginx/monitors-nginx.tf
index e09c010..03595bf 100644
--- a/middleware/nginx/monitors-nginx.tf
+++ b/middleware/nginx/monitors-nginx.tf
@@ -23,5 +23,5 @@ resource "datadog_monitor" "Nginx_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:nginx"]
 }
diff --git a/middleware/php-fpm/monitors-fpm.tf b/middleware/php-fpm/monitors-fpm.tf
index 97e7ff8..8bf654e 100644
--- a/middleware/php-fpm/monitors-fpm.tf
+++ b/middleware/php-fpm/monitors-fpm.tf
@@ -23,7 +23,7 @@ resource "datadog_monitor" "php-fpm_process_idle" {
   renotify_interval   = 0
   no_data_timeframe   = 20
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:php-fpm"]
 }
 
 resource "datadog_monitor" "FPM_process" {
@@ -51,5 +51,5 @@ resource "datadog_monitor" "FPM_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:php-fpm"]
 }
diff --git a/system/linux/monitors-linux-basics.tf b/system/linux/monitors-linux-basics.tf
index 459122d..6260aed 100644
--- a/system/linux/monitors-linux-basics.tf
+++ b/system/linux/monitors-linux-basics.tf
@@ -10,7 +10,7 @@ resource "datadog_monitor" "cpu_80_15min" {
     critical = "${var.cpu_15_critical}"
   }
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:system"]
 
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
@@ -36,7 +36,7 @@ resource "datadog_monitor" "cpu_95_5min" {
     critical = "${var.cpu_5_critical}"
   }
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:system"]
 
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
@@ -62,7 +62,7 @@ resource "datadog_monitor" "datadog_free_disk_space_5" {
     critical = 5
   }
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:system"]
 
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
@@ -89,7 +89,7 @@ resource "datadog_monitor" "datadog_free_disk_space_10" {
     critical = 10
   }
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:system"]
 
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
@@ -115,7 +115,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_5" {
     critical = 5
   }
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:system"]
 
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
@@ -142,7 +142,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
     critical = 10
   }
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:system"]
 
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
@@ -188,7 +188,7 @@ resource "datadog_monitor" "datadog_free_memory" {
     critical = 5
   }
 
-  tags = ["*"]
+  tags = ["env:${var.env}", "type:system"]
 
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"

From 86b999d7f328296f82500c0ae07f96e6570c0c9d Mon Sep 17 00:00:00 2001
From: Guillaume Kerivel <guillaume.kerivel@fr.clara.net>
Date: Tue, 16 Jan 2018 16:08:45 +0100
Subject: [PATCH 02/11] MON-96 Update basics RDS monitors

---
 cloud/aws/rds-mysql/inputs.tf                 |  1 -
 .../rds-mysql/monitors-rds_mysql-basics.tf    | 54 ---------------
 cloud/aws/rds/README.md                       | 45 ++++++++++++
 cloud/aws/rds/inputs.tf                       | 57 +++++++++++++++
 cloud/aws/rds/monitors-rds-basics.tf          | 69 +++++++++++++++++++
 5 files changed, 171 insertions(+), 55 deletions(-)
 delete mode 120000 cloud/aws/rds-mysql/inputs.tf
 delete mode 100644 cloud/aws/rds-mysql/monitors-rds_mysql-basics.tf
 create mode 100644 cloud/aws/rds/README.md
 create mode 100644 cloud/aws/rds/inputs.tf
 create mode 100644 cloud/aws/rds/monitors-rds-basics.tf

diff --git a/cloud/aws/rds-mysql/inputs.tf b/cloud/aws/rds-mysql/inputs.tf
deleted file mode 120000
index a68ace3..0000000
--- a/cloud/aws/rds-mysql/inputs.tf
+++ /dev/null
@@ -1 +0,0 @@
-../../../inputs.tf
\ No newline at end of file
diff --git a/cloud/aws/rds-mysql/monitors-rds_mysql-basics.tf b/cloud/aws/rds-mysql/monitors-rds_mysql-basics.tf
deleted file mode 100644
index 87e0746..0000000
--- a/cloud/aws/rds-mysql/monitors-rds_mysql-basics.tf
+++ /dev/null
@@ -1,54 +0,0 @@
-resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
-  name    = "[${var.env}] rds Cpu high > 90% for 15 min on {{host.identifier}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
-
-  count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
-
-  query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} > 90"
-  type  = "query alert"
-
-  thresholds {
-    warning  = "${var.rds_cpu_threshold["warning"]}"
-    critical = "${var.rds_cpu_threshold["critical"]}"
-  }
-
-  tags = ["*"]
-
-  notify_no_data      = "${var.rds_config["notify_no_data"]}"
-  evaluation_delay    = "${var.rds_config["delay"]}"
-  renotify_interval   = 60
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  new_host_delay      = "${var.rds_config["delay"]}"
-  no_data_timeframe   = 20
-}
-
-resource "datadog_monitor" "mysql_rds_free_space_low" {
-  name    = "[${var.env}] rds free space low < 10 % on {{host.identifier}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
-
-  type  = "query alert"
-  query = "avg(last_15m):avg:aws.rds.free_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} * 100 < 10"
-  count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
-
-  thresholds {
-    warning  = "${var.rds_mem_threshold["warning"]}"
-    critical = "${var.rds_mem_threshold["critical"]}"
-  }
-
-  tags = ["*"]
-
-  notify_no_data      = "${var.rds_config["notify_no_data"]}"
-  evaluation_delay    = "${var.rds_config["delay"]}"
-  renotify_interval   = 60
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  new_host_delay      = "${var.rds_config["delay"]}"
-  no_data_timeframe   = 20
-}
diff --git a/cloud/aws/rds/README.md b/cloud/aws/rds/README.md
new file mode 100644
index 0000000..36e8780
--- /dev/null
+++ b/cloud/aws/rds/README.md
@@ -0,0 +1,45 @@
+AWS RDS Instance DataDog monitors
+=================================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-aws-rds" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/rds?ref={revision}"
+
+  message     = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+```
+
+Purpose
+-------
+Creates a DataDog monitors with the following checks :
+
+* CPU High
+* Free disk space low
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
+| cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
+| diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |
+| diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no |
+| environment | Architecture Environment | string | - | yes |
+| evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
+| filter_tags_custom | Tags used 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 an alert is triggered | string | - | yes |
+| notify_no_data | Enable 'No Data' alert | string | `true` | no |
+| renotify_interval | The number of minutes after the last notification before a monitor will re-notify on the current status | string | `60` | no |
+
+Related documentation
+---------------------
+
+DataDog documentation: [https://docs.datadoghq.com/integrations/amazon_rds/](https://docs.datadoghq.com/integrations/amazon_rds/)
+
+AWS RDS Instance metrics documentation: [https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html)
diff --git a/cloud/aws/rds/inputs.tf b/cloud/aws/rds/inputs.tf
new file mode 100644
index 0000000..8e6d89a
--- /dev/null
+++ b/cloud/aws/rds/inputs.tf
@@ -0,0 +1,57 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "notify_no_data" {
+  description = "Enable 'No Data' alert"
+  default = true
+}
+
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 600
+}
+
+variable "renotify_interval" {
+  description = "The number of minutes after the last notification before a monitor will re-notify on the current status"
+  default     = 60
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+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     = "*"
+}
+
+# AWS RDS instance specific
+
+variable "cpu_threshold_warning" {
+  description = "CPU usage in percent (warning threshold)"
+  default     = "80"
+}
+
+variable "cpu_threshold_critical" {
+  description = "CPU usage in percent (critical threshold)"
+  default     = "90"
+}
+
+variable "diskspace_threshold_warning" {
+  description = "Disk free space in percent (warning threshold)"
+  default     = "20"
+}
+
+variable "diskspace_threshold_critical" {
+  description = "Disk free space in percent (critical threshold)"
+  default     = "10"
+}
diff --git a/cloud/aws/rds/monitors-rds-basics.tf b/cloud/aws/rds/monitors-rds-basics.tf
new file mode 100644
index 0000000..bb83b46
--- /dev/null
+++ b/cloud/aws/rds/monitors-rds-basics.tf
@@ -0,0 +1,69 @@
+data "template_file" "filter" {
+  template = "$${filter}"
+
+  vars {
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+  }
+}
+
+### RDS instance CPU monitor ###
+resource "datadog_monitor" "rds_cpu_90_15min" {
+  name    = "[${var.environment}] RDS instance CPU high > ${var.cpu_threshold_critical}% for 15 min on {{host.identifier}}"
+  message = "${var.message}"
+
+  type  = "metric alert"
+  query = <<EOF
+    avg(last_15m): (
+      avg:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
+    ) > ${var.cpu_threshold_critical}
+EOF
+
+  thresholds {
+    warning  = "${var.cpu_threshold_warning}"
+    critical = "${var.cpu_threshold_critical}"
+  }
+
+  notify_no_data      = "${var.notify_no_data}"
+  evaluation_delay    = "${var.evaluation_delay}"
+  renotify_interval   = "${var.renotify_interval}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.evaluation_delay}"
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:rds", "team:aws", "provider:aws"]
+}
+
+### RDS instance free space monitor ###
+resource "datadog_monitor" "rds_free_space_low" {
+  name    = "[${var.environment}] RDS instance free space < ${var.diskspace_threshold_critical}% on {{host.identifier}}"
+  message = "${var.message}"
+
+  type  = "metric alert"
+  query = <<EOF
+  avg(last_15m): (
+    avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} / avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
+  ) < ${var.diskspace_threshold_critical}
+EOF
+
+  thresholds {
+    warning  = "${var.diskspace_threshold_warning}"
+    critical = "${var.diskspace_threshold_critical}"
+  }
+
+  notify_no_data      = "${var.notify_no_data}"
+  evaluation_delay    = "${var.evaluation_delay}"
+  renotify_interval   = "${var.renotify_interval}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  new_host_delay      = "${var.evaluation_delay}"
+  no_data_timeframe   = 20
+
+  tags = ["env:${var.environment}", "resource:rds", "team:aws", "provider:aws"]
+}

From 2323db0639cbf2cae12446ea2801bd132f3acf17 Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Wed, 21 Feb 2018 16:10:51 +0100
Subject: [PATCH 03/11] MON-96 - Rename file and terraform fmt

---
 cloud/aws/rds/{monitors-rds-basics.tf => monitors-rds.tf} | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename cloud/aws/rds/{monitors-rds-basics.tf => monitors-rds.tf} (100%)

diff --git a/cloud/aws/rds/monitors-rds-basics.tf b/cloud/aws/rds/monitors-rds.tf
similarity index 100%
rename from cloud/aws/rds/monitors-rds-basics.tf
rename to cloud/aws/rds/monitors-rds.tf

From 8f9bf61d19d36c76c82617f5fa68c6ca5935e272 Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Wed, 21 Feb 2018 16:18:07 +0100
Subject: [PATCH 04/11] MON-96 - Apply best practice and recommandations

---
 cloud/aws/rds/README.md       |  2 --
 cloud/aws/rds/inputs.tf       | 10 ----------
 cloud/aws/rds/monitors-rds.tf | 19 ++++++++++---------
 3 files changed, 10 insertions(+), 21 deletions(-)

diff --git a/cloud/aws/rds/README.md b/cloud/aws/rds/README.md
index 36e8780..b6337a1 100644
--- a/cloud/aws/rds/README.md
+++ b/cloud/aws/rds/README.md
@@ -34,8 +34,6 @@ Inputs
 | filter_tags_custom | Tags used 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 an alert is triggered | string | - | yes |
-| notify_no_data | Enable 'No Data' alert | string | `true` | no |
-| renotify_interval | The number of minutes after the last notification before a monitor will re-notify on the current status | string | `60` | no |
 
 Related documentation
 ---------------------
diff --git a/cloud/aws/rds/inputs.tf b/cloud/aws/rds/inputs.tf
index 8e6d89a..cac076f 100644
--- a/cloud/aws/rds/inputs.tf
+++ b/cloud/aws/rds/inputs.tf
@@ -5,21 +5,11 @@ variable "environment" {
 }
 
 # Global DataDog
-variable "notify_no_data" {
-  description = "Enable 'No Data' alert"
-  default = true
-}
-
 variable "evaluation_delay" {
   description = "Delay in seconds for the metric evaluation"
   default     = 600
 }
 
-variable "renotify_interval" {
-  description = "The number of minutes after the last notification before a monitor will re-notify on the current status"
-  default     = 60
-}
-
 variable "message" {
   description = "Message sent when an alert is triggered"
 }
diff --git a/cloud/aws/rds/monitors-rds.tf b/cloud/aws/rds/monitors-rds.tf
index bb83b46..dffb178 100644
--- a/cloud/aws/rds/monitors-rds.tf
+++ b/cloud/aws/rds/monitors-rds.tf
@@ -8,10 +8,11 @@ data "template_file" "filter" {
 
 ### RDS instance CPU monitor ###
 resource "datadog_monitor" "rds_cpu_90_15min" {
-  name    = "[${var.environment}] RDS instance CPU high > ${var.cpu_threshold_critical}% for 15 min on {{host.identifier}}"
+  name    = "[${var.environment}] RDS instance CPU high {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
   message = "${var.message}"
 
-  type  = "metric alert"
+  type = "metric alert"
+
   query = <<EOF
     avg(last_15m): (
       avg:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
@@ -23,9 +24,8 @@ EOF
     critical = "${var.cpu_threshold_critical}"
   }
 
-  notify_no_data      = "${var.notify_no_data}"
+  notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
-  renotify_interval   = "${var.renotify_interval}"
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -39,13 +39,15 @@ EOF
 
 ### RDS instance free space monitor ###
 resource "datadog_monitor" "rds_free_space_low" {
-  name    = "[${var.environment}] RDS instance free space < ${var.diskspace_threshold_critical}% on {{host.identifier}}"
+  name    = "[${var.environment}] RDS instance free space {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
   message = "${var.message}"
 
-  type  = "metric alert"
+  type = "metric alert"
+
   query = <<EOF
   avg(last_15m): (
-    avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} / avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
+    avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
+    avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
   ) < ${var.diskspace_threshold_critical}
 EOF
 
@@ -54,9 +56,8 @@ EOF
     critical = "${var.diskspace_threshold_critical}"
   }
 
-  notify_no_data      = "${var.notify_no_data}"
+  notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
-  renotify_interval   = "${var.renotify_interval}"
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true

From febc38eec7e284dedc92f6629612b5e0da210a49 Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Wed, 21 Feb 2018 16:55:06 +0100
Subject: [PATCH 05/11] MON-96 - Apply conventions and update middleware
 directory

---
 .../elasticsearch/monitors-elasticsearch.tf   |  7 ++-
 middleware/apache/README.md                   | 30 ++++++++++
 middleware/apache/inputs.tf                   | 22 +++++++-
 middleware/apache/monitors-apache.tf          | 15 +++--
 middleware/nginx/README.md                    | 30 ++++++++++
 middleware/nginx/inputs.tf                    | 22 +++++++-
 middleware/nginx/monitors-nginx.tf            | 15 +++--
 middleware/php-fpm/README.md                  | 35 ++++++++++++
 middleware/php-fpm/inputs.tf                  | 43 ++++++++++++++-
 middleware/php-fpm/monitors-fpm.tf            | 55 +++++++++++--------
 10 files changed, 230 insertions(+), 44 deletions(-)
 create mode 100644 middleware/apache/README.md
 mode change 120000 => 100644 middleware/apache/inputs.tf
 create mode 100644 middleware/nginx/README.md
 mode change 120000 => 100644 middleware/nginx/inputs.tf
 create mode 100644 middleware/php-fpm/README.md
 mode change 120000 => 100644 middleware/php-fpm/inputs.tf

diff --git a/cloud/aws/elasticsearch/monitors-elasticsearch.tf b/cloud/aws/elasticsearch/monitors-elasticsearch.tf
index 7ba3aa2..8880a02 100644
--- a/cloud/aws/elasticsearch/monitors-elasticsearch.tf
+++ b/cloud/aws/elasticsearch/monitors-elasticsearch.tf
@@ -42,14 +42,15 @@ EOF
 
 ### Elasticsearch cluster free storage space monitor ###
 resource "datadog_monitor" "es_free_space_low" {
-  name    = "[${var.environment}] ElasticSearch cluster free storage space < ${var.diskspace_threshold_critical}%"
+  name    = "[${var.environment}] ElasticSearch cluster free storage space {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
   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
+    avg:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
+    (${var.es_cluster_volume_size}*1000) * 100
   ) < ${var.diskspace_threshold_critical}
 EOF
 
@@ -74,7 +75,7 @@ EOF
 
 ### Elasticsearch cluster CPU monitor ###
 resource "datadog_monitor" "es_cpu_90_15min" {
-  name    = "[${var.environment}] ElasticSearch cluster CPU high > ${var.cpu_threshold_critical}%"
+  name    = "[${var.environment}] ElasticSearch cluster CPU high {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
   message = "${var.message}"
 
   type = "query alert"
diff --git a/middleware/apache/README.md b/middleware/apache/README.md
new file mode 100644
index 0000000..4d9c00f
--- /dev/null
+++ b/middleware/apache/README.md
@@ -0,0 +1,30 @@
+Apache Middleware DataDog monitors
+==================================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-apache-middleware" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//middleware/apache?ref={revision}"
+
+  message     = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+```
+
+Purpose
+-------
+Creates a DataDog monitors with the following checks :
+
+* Apache process
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| dd_apache |  | string | `disabled` | no |
+| environment | Architecture Environment | string | - | yes |
+| evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
+| message | Message sent when an alert is triggered | string | - | yes |
diff --git a/middleware/apache/inputs.tf b/middleware/apache/inputs.tf
deleted file mode 120000
index cdfc6c6..0000000
--- a/middleware/apache/inputs.tf
+++ /dev/null
@@ -1 +0,0 @@
-../../inputs.tf
\ No newline at end of file
diff --git a/middleware/apache/inputs.tf b/middleware/apache/inputs.tf
new file mode 100644
index 0000000..0c3b10e
--- /dev/null
+++ b/middleware/apache/inputs.tf
@@ -0,0 +1,21 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 15
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+# Apache Middleware specific
+
+variable "dd_apache" {
+  default = "disabled"
+}
diff --git a/middleware/apache/monitors-apache.tf b/middleware/apache/monitors-apache.tf
index b542aa4..11f4624 100644
--- a/middleware/apache/monitors-apache.tf
+++ b/middleware/apache/monitors-apache.tf
@@ -1,10 +1,9 @@
 resource "datadog_monitor" "Apache_process" {
-  name    = "[${var.env}] Apache process is down on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
+  name    = "[${var.environment}] Apache process is down on {{host.name}}"
+  message = "${var.message}"
 
   type  = "service check"
-  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
-  count = "${var.dd_apache == "enabled" ? 1 : 0 }"
+  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -12,9 +11,9 @@ resource "datadog_monitor" "Apache_process" {
     critical = 4
   }
 
-  notify_no_data      = "${var.apache_nginx_fpm_config["notify_no_data"]}"
-  evaluation_delay    = "${var.apache_nginx_fpm_config["delay"]}"
-  new_host_delay      = "${var.apache_nginx_fpm_config["delay"]}"
+  notify_no_data      = false
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
   renotify_interval   = 60
   notify_audit        = false
   timeout_h           = 0
@@ -23,5 +22,5 @@ resource "datadog_monitor" "Apache_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.env}", "type:apache"]
+  tags = ["env:${var.environment}", "type:apache"]
 }
diff --git a/middleware/nginx/README.md b/middleware/nginx/README.md
new file mode 100644
index 0000000..435dde6
--- /dev/null
+++ b/middleware/nginx/README.md
@@ -0,0 +1,30 @@
+Nginx Middleware DataDog monitors
+=================================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-nginx-middleware" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//middleware/nginx?ref={revision}"
+
+  message     = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+```
+
+Purpose
+-------
+Creates a DataDog monitors with the following checks :
+
+* Nginx process
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| dd_nginx |  | string | `disabled` | no |
+| environment | Architecture Environment | string | - | yes |
+| evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
+| message | Message sent when an alert is triggered | string | - | yes |
diff --git a/middleware/nginx/inputs.tf b/middleware/nginx/inputs.tf
deleted file mode 120000
index cdfc6c6..0000000
--- a/middleware/nginx/inputs.tf
+++ /dev/null
@@ -1 +0,0 @@
-../../inputs.tf
\ No newline at end of file
diff --git a/middleware/nginx/inputs.tf b/middleware/nginx/inputs.tf
new file mode 100644
index 0000000..f823913
--- /dev/null
+++ b/middleware/nginx/inputs.tf
@@ -0,0 +1,21 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 15
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+# Nginx Middleware specific
+
+variable "dd_nginx" {
+  default = "disabled"
+}
diff --git a/middleware/nginx/monitors-nginx.tf b/middleware/nginx/monitors-nginx.tf
index 03595bf..b018ec3 100644
--- a/middleware/nginx/monitors-nginx.tf
+++ b/middleware/nginx/monitors-nginx.tf
@@ -1,10 +1,9 @@
 resource "datadog_monitor" "Nginx_process" {
-  name    = "[${var.env}] Nginx process is down on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
+  name    = "[${var.environment}] Nginx process is down on {{host.name}}"
+  message = "${var.message}"
 
   type  = "service check"
-  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
-  count = "${var.dd_nginx == "enabled" ? 1 : 0 }"
+  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -12,9 +11,9 @@ resource "datadog_monitor" "Nginx_process" {
     critical = 4
   }
 
-  notify_no_data      = "${var.apache_nginx_fpm_config["notify_no_data"]}"
-  evaluation_delay    = "${var.apache_nginx_fpm_config["delay"]}"
-  new_host_delay      = "${var.apache_nginx_fpm_config["delay"]}"
+  notify_no_data      = false
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
   renotify_interval   = 60
   notify_audit        = false
   timeout_h           = 0
@@ -23,5 +22,5 @@ resource "datadog_monitor" "Nginx_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.env}", "type:nginx"]
+  tags = ["env:${var.environment}", "type:nginx"]
 }
diff --git a/middleware/php-fpm/README.md b/middleware/php-fpm/README.md
new file mode 100644
index 0000000..f15a56e
--- /dev/null
+++ b/middleware/php-fpm/README.md
@@ -0,0 +1,35 @@
+PHP FPM Middleware DataDog monitors
+===================================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-php-fpm-middleware" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//middleware/php-fpm?ref={revision}"
+
+  message     = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+```
+
+Purpose
+-------
+Creates a DataDog monitors with the following checks :
+
+* PHP FPM process
+* PHP FPM load
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| environment | Architecture Environment | string | - | yes |
+| evaluation_delay_metric | Delay in seconds for the metric evaluation | string | `600` | no |
+| evaluation_delay_service | 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_use_defaults | Use default filter tags convention | string | `true` | no |
+| message | Message sent when an alert is triggered | string | - | yes |
+| php_fpm_busy_threshold_critical | php fpm busy critical threshold | string | `0.9` | no |
+| php_fpm_busy_threshold_warning | php fpm busy warning threshold | string | `0.8` | no |
diff --git a/middleware/php-fpm/inputs.tf b/middleware/php-fpm/inputs.tf
deleted file mode 120000
index cdfc6c6..0000000
--- a/middleware/php-fpm/inputs.tf
+++ /dev/null
@@ -1 +0,0 @@
-../../inputs.tf
\ No newline at end of file
diff --git a/middleware/php-fpm/inputs.tf b/middleware/php-fpm/inputs.tf
new file mode 100644
index 0000000..726bd04
--- /dev/null
+++ b/middleware/php-fpm/inputs.tf
@@ -0,0 +1,42 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "evaluation_delay_service" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 15
+}
+
+variable "evaluation_delay_metric" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 600
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+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     = "*"
+}
+
+# PHP FPM Middleware specific
+
+variable "php_fpm_busy_threshold_warning" {
+  description = "php fpm busy warning threshold"
+  default     = 0.8
+}
+
+variable "php_fpm_busy_threshold_critical" {
+  description = "php fpm busy critical threshold"
+  default     = 0.9
+}
diff --git a/middleware/php-fpm/monitors-fpm.tf b/middleware/php-fpm/monitors-fpm.tf
index 8bf654e..95289e8 100644
--- a/middleware/php-fpm/monitors-fpm.tf
+++ b/middleware/php-fpm/monitors-fpm.tf
@@ -1,38 +1,49 @@
-resource "datadog_monitor" "php-fpm_process_idle" {
-  name    = "[${var.env}] php_fpm busy worker > 90% on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
+data "template_file" "filter" {
+  template = "$${filter}"
 
-  type  = "query alert"
-  query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} / ( avg:php_fpm.processes.idle{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} + avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} ) > 0.9"
-  count = "${var.dd_php_fpm == "enabled" ? 1 : 0 }"
+  vars {
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+  }
+}
+
+resource "datadog_monitor" "php-fpm_process_idle" {
+  name    = "[${var.environment}] php_fpm busy worker {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "${var.message}"
+
+  type = "metric alert"
+
+  query = <<EOF
+    avg(last_10m): (
+      avg:php_fpm.processes.active{${data.template_file.filter.rendered}} by {region, host} /
+      ( avg:php_fpm.processes.idle{${data.template_file.filter.rendered}} by {region, host} +
+       avg:php_fpm.processes.active{${data.template_file.filter.rendered}} by {region, host} )
+    ) > ${var.php_fpm_busy_threshold_critical}
+  EOF
 
   thresholds {
-    warning  = "${var.php_fpm_busy_threshold["warning"]}"
-    critical = "${var.php_fpm_busy_threshold["critical"]}"
+    warning  = "${var.php_fpm_busy_threshold_warning}"
+    critical = "${var.php_fpm_busy_threshold_critical}"
   }
 
-  notify_no_data      = "${var.apache_nginx_fpm_config["notify_no_data"]}"
-  evaluation_delay    = "${var.apache_nginx_fpm_config["delay"]}"
-  new_host_delay      = "${var.apache_nginx_fpm_config["delay"]}"
-  renotify_interval   = 60
+  notify_no_data      = false
+  evaluation_delay    = "${var.evaluation_delay_metric}"
+  new_host_delay      = "${var.evaluation_delay_metric}"
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
   locked              = false
   require_full_window = true
-  renotify_interval   = 0
   no_data_timeframe   = 20
 
-  tags = ["env:${var.env}", "type:php-fpm"]
+  tags = ["env:${var.environment}", "type:php-fpm"]
 }
 
 resource "datadog_monitor" "FPM_process" {
-  name    = "[${var.env}] FPM process is down on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
+  name    = "[${var.environment}] FPM process is down on {{host.name}}"
+  message = "${var.message}"
 
   type  = "service check"
-  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
-  count = "${var.dd_nginx == "enabled" ? 1 : 0 }"
+  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -40,9 +51,9 @@ resource "datadog_monitor" "FPM_process" {
     critical = 4
   }
 
-  notify_no_data      = "${var.apache_nginx_fpm_config["notify_no_data"]}"
-  evaluation_delay    = "${var.apache_nginx_fpm_config["delay"]}"
-  new_host_delay      = "${var.apache_nginx_fpm_config["delay"]}"
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay_service}"
+  new_host_delay      = "${var.evaluation_delay_service}"
   renotify_interval   = 60
   notify_audit        = false
   timeout_h           = 0
@@ -51,5 +62,5 @@ resource "datadog_monitor" "FPM_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.env}", "type:php-fpm"]
+  tags = ["env:${var.environment}", "type:php-fpm"]
 }

From dd729b90e5dbd3d28b4dd56f696e84dbc3077836 Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Wed, 21 Feb 2018 17:34:17 +0100
Subject: [PATCH 06/11] MON-96 - Update system directory and update
 inputs-declaration sample

---
 datadog-samples/inputs-declaration.sample |  68 +++++---
 system/generic/README.md                  |  34 ++++
 system/generic/inputs.tf                  |  43 ++++-
 system/generic/monitors-custom-cpu.tf     |  35 ++--
 system/linux/README.md                    |  43 +++++
 system/linux/inputs.tf                    |  73 +++++++-
 system/linux/monitors-linux-basics.tf     | 204 +++++++++-------------
 7 files changed, 333 insertions(+), 167 deletions(-)
 create mode 100644 system/generic/README.md
 mode change 120000 => 100644 system/generic/inputs.tf
 create mode 100644 system/linux/README.md
 mode change 120000 => 100644 system/linux/inputs.tf

diff --git a/datadog-samples/inputs-declaration.sample b/datadog-samples/inputs-declaration.sample
index a82030e..01e8c8d 100644
--- a/datadog-samples/inputs-declaration.sample
+++ b/datadog-samples/inputs-declaration.sample
@@ -1,35 +1,47 @@
-variable environment {}
-
-variable region {}
-
-variable "critical_escalation_group" {
-  default = "@pagerduty_HODummy"
-}
-variable "warning_escalation_group" {
-  default = "@pagerduty_HNODummy"
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
 }
 
-variable "datadog_api_key" {}
-variable "datadog_app_key" {}
-
-variable "dd_linux_basics" {
-  default = "enabled"
+# Global DataDog
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 600
 }
 
-variable "dd_aws_rds" {
-  default = "enabled"
+variable "message" {
+  description = "Message sent when an alert is triggered"
 }
 
-
-variable "dd_custom_cpu" {
-  type = "map"
-  default = {
-    status = "enabled"
-    name   = "CPU High > 95% during 1 hour"
-
-    period = "last_1h"
-
-    critical_threshold = 95
-    warning_threshold  = 90
-  }
+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     = "*"
+}
+
+# instance specific
+
+variable "cpu_threshold_warning" {
+  description = "CPU usage in percent (warning threshold)"
+  default     = "80"
+}
+
+variable "cpu_threshold_critical" {
+  description = "CPU usage in percent (critical threshold)"
+  default     = "90"
+}
+
+variable "diskspace_threshold_warning" {
+  description = "Disk free space in percent (warning threshold)"
+  default     = "20"
+}
+
+variable "diskspace_threshold_critical" {
+  description = "Disk free space in percent (critical threshold)"
+  default     = "10"
 }
diff --git a/system/generic/README.md b/system/generic/README.md
new file mode 100644
index 0000000..eb85357
--- /dev/null
+++ b/system/generic/README.md
@@ -0,0 +1,34 @@
+System Generic DataDog monitors
+===============================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-system-generic" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//system/generic?ref={revision}"
+
+  message     = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+```
+
+Purpose
+-------
+Creates a DataDog monitors with the following checks :
+
+* System CPU High
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| custom_cpu_period | Set up period for the query | string | `last_5m` | no |
+| custom_cpu_threshold_critical | Custom CPU critical threshold | string | `95` | no |
+| custom_cpu_threshold_warning | Custom CPU warning threshold | string | `80` | no |
+| environment | Architecture Environment | string | - | yes |
+| evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
+| filter_tags_custom | Tags used 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 an alert is triggered | string | - | yes |
diff --git a/system/generic/inputs.tf b/system/generic/inputs.tf
deleted file mode 120000
index cdfc6c6..0000000
--- a/system/generic/inputs.tf
+++ /dev/null
@@ -1 +0,0 @@
-../../inputs.tf
\ No newline at end of file
diff --git a/system/generic/inputs.tf b/system/generic/inputs.tf
new file mode 100644
index 0000000..06a118e
--- /dev/null
+++ b/system/generic/inputs.tf
@@ -0,0 +1,42 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 600
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+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     = "*"
+}
+
+# Custom CPU instance specific
+
+variable "custom_cpu_period" {
+  description = "Set up period for the query"
+  default     = "last_5m"
+}
+
+variable "custom_cpu_threshold_warning" {
+  description = "Custom CPU warning threshold"
+  default     = 80
+}
+
+variable "custom_cpu_threshold_critical" {
+  description = "Custom CPU critical threshold"
+  default     = 95
+}
diff --git a/system/generic/monitors-custom-cpu.tf b/system/generic/monitors-custom-cpu.tf
index ef2d695..57b9b03 100644
--- a/system/generic/monitors-custom-cpu.tf
+++ b/system/generic/monitors-custom-cpu.tf
@@ -1,19 +1,32 @@
-resource "datadog_monitor" "cpu_custom" {
-  name    = "${var.dd_custom_cpu["name"]}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group}\n{{/is_warning}}\n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
-  count   = "${var.dd_custom_cpu["status"] == "enabled" ? 1 : 0}"
+data "template_file" "filter" {
+  template = "$${filter}"
 
-  query = "min(${var.dd_custom_cpu["period"]}):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,!dd_custom_cpu.monitoring:enabled} by {host} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,!dd_custom_cpu:enabled} by {host} > ${var.dd_custom_cpu["critical_threshold"]}"
-  type  = "query alert"
+  vars {
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+  }
+}
+
+resource "datadog_monitor" "cpu_custom" {
+  name    = "[${var.environment}] CPU too High {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "${var.message}"
+
+  query = <<EOF
+    min(${var.custom_cpu_period}): (
+      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host} +
+      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host}
+    ) > ${var.custom_cpu_threshold_critical}"
+  EOF
+
+  type = "metric alert"
 
   thresholds = {
-    warning  = "${var.dd_custom_cpu["warning_threshold"]}"
-    critical = "${var.dd_custom_cpu["critical_threshold"]}"
+    warning  = "${var.custom_cpu_threshold_warning}"
+    critical = "${var.custom_cpu_threshold_critical}"
   }
 
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
   renotify_interval   = 60
   notify_audit        = false
   timeout_h           = 0
diff --git a/system/linux/README.md b/system/linux/README.md
new file mode 100644
index 0000000..54aac37
--- /dev/null
+++ b/system/linux/README.md
@@ -0,0 +1,43 @@
+System Linux DataDog monitors
+=============================
+
+How to use this module
+----------------------
+
+```
+module "datadog-monitors-system-generic" {
+  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//system/linux?ref={revision}"
+
+  message     = "${module.datadog-message-alerting.alerting-message}"
+  environment = "${var.environment}"
+}
+```
+
+Purpose
+-------
+Creates a DataDog monitors with the following checks :
+
+* System CPU High
+* System Free disk space
+* System Free disk inodes
+* System Free memory
+
+Inputs
+------
+
+| Name | Description | Type | Default | Required |
+|------|-------------|:----:|:-----:|:-----:|
+| cpu_high_threshold_critical | CPU high critical threshold | string | `95` | no |
+| cpu_high_threshold_warning | CPU high warning threshold | string | `80` | no |
+| custom_cpu_period | Set up period for the query | string | `last_5m` | no |
+| environment | Architecture Environment | string | - | yes |
+| evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
+| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
+| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
+| free_disk_inodes_threshold_critical | Free disk space critical threshold | string | `5` | no |
+| free_disk_inodes_threshold_warning | Free disk space warning threshold | string | `10` | no |
+| free_disk_space_threshold_critical | Free disk space critical threshold | string | `5` | no |
+| free_disk_space_threshold_warning | Free disk space warning threshold | string | `10` | no |
+| free_memory_threshold_critical | Free disk space critical threshold | string | `5` | no |
+| free_memory_threshold_warning | Free disk space warning threshold | string | `10` | no |
+| message | Message sent when an alert is triggered | string | - | yes |
\ No newline at end of file
diff --git a/system/linux/inputs.tf b/system/linux/inputs.tf
deleted file mode 120000
index cdfc6c6..0000000
--- a/system/linux/inputs.tf
+++ /dev/null
@@ -1 +0,0 @@
-../../inputs.tf
\ No newline at end of file
diff --git a/system/linux/inputs.tf b/system/linux/inputs.tf
new file mode 100644
index 0000000..de67079
--- /dev/null
+++ b/system/linux/inputs.tf
@@ -0,0 +1,72 @@
+# Global Terraform
+variable "environment" {
+  description = "Architecture Environment"
+  type        = "string"
+}
+
+# Global DataDog
+variable "evaluation_delay" {
+  description = "Delay in seconds for the metric evaluation"
+  default     = 600
+}
+
+variable "message" {
+  description = "Message sent when an alert is triggered"
+}
+
+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     = "*"
+}
+
+# Custom CPU instance specific
+
+variable "custom_cpu_period" {
+  description = "Set up period for the query"
+  default     = "last_5m"
+}
+
+variable "cpu_high_threshold_warning" {
+  description = "CPU high warning threshold"
+  default     = 80
+}
+
+variable "cpu_high_threshold_critical" {
+  description = "CPU high critical threshold"
+  default     = 95
+}
+
+variable "free_disk_space_threshold_warning" {
+  description = "Free disk space warning threshold"
+  default     = 10
+}
+
+variable "free_disk_space_threshold_critical" {
+  description = "Free disk space critical threshold"
+  default     = 5
+}
+
+variable "free_disk_inodes_threshold_warning" {
+  description = "Free disk space warning threshold"
+  default     = 10
+}
+
+variable "free_disk_inodes_threshold_critical" {
+  description = "Free disk space critical threshold"
+  default     = 5
+}
+
+variable "free_memory_threshold_warning" {
+  description = "Free disk space warning threshold"
+  default     = 10
+}
+
+variable "free_memory_threshold_critical" {
+  description = "Free disk space critical threshold"
+  default     = 5
+}
diff --git a/system/linux/monitors-linux-basics.tf b/system/linux/monitors-linux-basics.tf
index 6260aed..6bd173d 100644
--- a/system/linux/monitors-linux-basics.tf
+++ b/system/linux/monitors-linux-basics.tf
@@ -1,21 +1,34 @@
-resource "datadog_monitor" "cpu_80_15min" {
-  name    = "[${var.env}] CPU High > ${var.cpu_15_critical} for 15 min on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
-  count   = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
+data "template_file" "filter" {
+  template = "$${filter}"
 
-  query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} > ${var.cpu_15_critical}"
-  type  = "query alert"
+  vars {
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+  }
+}
+
+resource "datadog_monitor" "datadog_cpu_too_high" {
+  name    = "[${var.environment}] CPU High {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "${var.message}"
+
+  query = <<EOF
+    min(last_15m): (
+      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host} +
+      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host}
+    ) > ${var.cpu_high_threshold_critical}
+  EOF
+
+  type = "metric alert"
 
   thresholds {
-    critical = "${var.cpu_15_critical}"
+    warning  = "${var.cpu_high_threshold_warning}"
+    critical = "${var.cpu_high_threshold_critical}"
   }
 
-  tags = ["env:${var.env}", "type:system"]
+  tags = ["env:${var.environment}", "type:system"]
 
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
-  renotify_interval   = 60
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -24,24 +37,29 @@ resource "datadog_monitor" "cpu_80_15min" {
   no_data_timeframe   = 20
 }
 
-resource "datadog_monitor" "cpu_95_5min" {
-  name    = "[${var.env}] CPU High > ${var.cpu_5_critical} for 5 min on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
+resource "datadog_monitor" "datadog_free_disk_space_too_low" {
+  name    = "[${var.environment}] Free disk space {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "${var.message}"
 
-  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} > ${var.cpu_5_critical}"
-  type  = "query alert"
-  count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
+  query = <<EOF
+    sum(last_5m): (
+      avg:system.disk.free{${data.template_file.filter.rendered}} by {region,host,device} /
+      avg:system.disk.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
+    ) < ${var.free_disk_space_threshold_critical}
+  EOF
+
+  type = "metric alert"
 
   thresholds {
-    critical = "${var.cpu_5_critical}"
+    warning  = "${var.free_disk_space_threshold_warning}"
+    critical = "${var.free_disk_space_threshold_critical}"
   }
 
-  tags = ["env:${var.env}", "type:system"]
+  tags = ["env:${var.environment}", "type:system"]
 
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
-  renotify_interval   = 60
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -50,24 +68,29 @@ resource "datadog_monitor" "cpu_95_5min" {
   no_data_timeframe   = 20
 }
 
-resource "datadog_monitor" "datadog_free_disk_space_5" {
-  name    = "[${var.env}] Free disk space < 5%  on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
+resource "datadog_monitor" "datadog_free_disk_space_inodes_too_low" {
+  name    = "[${var.environment}] Free disk inodes {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "${var.message}"
 
-  query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 5"
-  type  = "query alert"
-  count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
+  query = <<EOF
+    sum(last_5m): (
+      avg:system.fs.inodes.free{${data.template_file.filter.rendered}} by {region,host,device} /
+      avg:system.fs.inodes.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
+    ) < ${var.free_disk_inodes_threshold_critical}
+  EOF
+
+  type = "metric alert"
 
   thresholds {
-    critical = 5
+    warning  = "${var.free_disk_inodes_threshold_warning}"
+    critical = "${var.free_disk_inodes_threshold_critical}"
   }
 
-  tags = ["env:${var.env}", "type:system"]
+  tags = ["env:${var.environment}", "type:system"]
 
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
-  renotify_interval   = 60
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -76,77 +99,29 @@ resource "datadog_monitor" "datadog_free_disk_space_5" {
   no_data_timeframe   = 20
 }
 
-resource "datadog_monitor" "datadog_free_disk_space_10" {
-  name    = "[${var.env}] Free disk space < 10% on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group}\n{{/is_warning}}\n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
+resource "datadog_monitor" "datadog_free_memory" {
+  name    = "[${var.environment}] Free memory {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "Debugging alert - no escalation"
 
-  query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 10"
-  type  = "query alert"
-  count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
+  query = <<EOF
+    sum(last_1m): (
+      avg:system.mem.free{${data.template_file.filter.rendered}} by {region,host} /
+      avg:system.mem.total{${data.template_file.filter.rendered}} by {region,host} * 100
+    ) < ${var.free_memory_threshold_critical}
+  EOF
+
+  type = "metric alert"
 
   thresholds {
-    warning  = 20
-    critical = 10
+    warning  = "${var.free_memory_threshold_warning}"
+    critical = "${var.free_memory_threshold_critical}"
   }
 
-  tags = ["env:${var.env}", "type:system"]
+  tags = ["env:${var.environment}", "type:system"]
 
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
-  renotify_interval   = 60
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  no_data_timeframe   = 20
-}
-
-resource "datadog_monitor" "datadog_free_disk_space_inodes_5" {
-  name    = "[${var.env}] Free disk inodes < 5% on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group} \n{{/is_recovery}}"
-
-  query = "sum(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 5"
-  type  = "query alert"
-  count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
-
-  thresholds {
-    critical = 5
-  }
-
-  tags = ["env:${var.env}", "type:system"]
-
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
-  renotify_interval   = 60
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  no_data_timeframe   = 20
-}
-
-resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
-  name    = "[${var.env}] Free disk inodes < 10% on {{host.name}}"
-  message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group}\n{{/is_warning}}\n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
-
-  query = "max(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region} * 100 < 10"
-  type  = "query alert"
-  count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
-
-  thresholds {
-    warning  = 20
-    critical = 10
-  }
-
-  tags = ["env:${var.env}", "type:system"]
-
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
   renotify_interval   = 60
   notify_audit        = false
   timeout_h           = 0
@@ -160,10 +135,12 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
 #   name    = "CPU Load > 2"
 #   message = "Debugging alert - no escalation"
 
+
 #   query = "min(last_5m):avg:system.load.5{dd_monitoring:enabled,dd_linux_basics:enabled,!dd_custom_cpu:enabled} by {instance-id} / avg:gcp.gce.instance.cpu.reserved_cores{*} by {instance-id} > 2"
 #   type  = "query alert"
 #   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
+
 # notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
 # evaluation_delay    = "${var.linux_basics_config["delay"]}"
 # new_host_delay      = "${var.linux_basics_config["delay"]}"
@@ -176,31 +153,6 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
 # no_data_timeframe   = 20
 # }
 
-resource "datadog_monitor" "datadog_free_memory" {
-  name    = "[${var.env}] Free memory < 5% on {{host.name}}"
-  message = "Debugging alert - no escalation"
-
-  query = "sum(last_1m):avg:system.mem.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region} / avg:system.mem.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region} * 100 < 5"
-  type  = "query alert"
-  count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
-
-  thresholds {
-    critical = 5
-  }
-
-  tags = ["env:${var.env}", "type:system"]
-
-  notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-  evaluation_delay    = "${var.linux_basics_config["delay"]}"
-  new_host_delay      = "${var.linux_basics_config["delay"]}"
-  renotify_interval   = 60
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  no_data_timeframe   = 20
-}
 
 # resource "datadog_monitor" "datadog_host_unreachable" {
 #   name    = "Host unreachable"

From 8bf6f4154341218c36bc1fec21931a93d56df5d6 Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Thu, 22 Feb 2018 12:13:05 +0100
Subject: [PATCH 07/11] MON-96 - Updated all monitors to follow recommendations

---
 cloud/aws/elasticsearch/monitors-elasticsearch.tf |  4 ++--
 cloud/aws/rds/monitors-rds.tf                     |  4 ++--
 middleware/apache/README.md                       |  1 -
 middleware/apache/inputs.tf                       |  4 ----
 middleware/apache/monitors-apache.tf              |  8 ++++----
 middleware/nginx/README.md                        |  1 -
 middleware/nginx/inputs.tf                        |  4 ----
 middleware/nginx/monitors-nginx.tf                |  8 ++++----
 middleware/php-fpm/monitors-fpm.tf                | 12 ++++++------
 system/generic/monitors-custom-cpu.tf             |  8 ++++----
 system/linux/monitors-linux-basics.tf             |  4 ++--
 11 files changed, 24 insertions(+), 34 deletions(-)

diff --git a/cloud/aws/elasticsearch/monitors-elasticsearch.tf b/cloud/aws/elasticsearch/monitors-elasticsearch.tf
index 8880a02..5a55f4b 100644
--- a/cloud/aws/elasticsearch/monitors-elasticsearch.tf
+++ b/cloud/aws/elasticsearch/monitors-elasticsearch.tf
@@ -33,7 +33,7 @@ EOF
   timeout_h           = 0
   include_tags        = true
   locked              = false
-  require_full_window = true
+  require_full_window = false
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
@@ -66,7 +66,7 @@ EOF
   timeout_h           = 0
   include_tags        = true
   locked              = false
-  require_full_window = true
+  require_full_window = false
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
diff --git a/cloud/aws/rds/monitors-rds.tf b/cloud/aws/rds/monitors-rds.tf
index dffb178..430cf37 100644
--- a/cloud/aws/rds/monitors-rds.tf
+++ b/cloud/aws/rds/monitors-rds.tf
@@ -30,7 +30,7 @@ EOF
   timeout_h           = 0
   include_tags        = true
   locked              = false
-  require_full_window = true
+  require_full_window = false
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
@@ -62,7 +62,7 @@ EOF
   timeout_h           = 0
   include_tags        = true
   locked              = false
-  require_full_window = true
+  require_full_window = false
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
diff --git a/middleware/apache/README.md b/middleware/apache/README.md
index 4d9c00f..aaf5630 100644
--- a/middleware/apache/README.md
+++ b/middleware/apache/README.md
@@ -24,7 +24,6 @@ Inputs
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
-| dd_apache |  | string | `disabled` | no |
 | environment | Architecture Environment | string | - | yes |
 | evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
diff --git a/middleware/apache/inputs.tf b/middleware/apache/inputs.tf
index 0c3b10e..ca3d259 100644
--- a/middleware/apache/inputs.tf
+++ b/middleware/apache/inputs.tf
@@ -15,7 +15,3 @@ variable "message" {
 }
 
 # Apache Middleware specific
-
-variable "dd_apache" {
-  default = "disabled"
-}
diff --git a/middleware/apache/monitors-apache.tf b/middleware/apache/monitors-apache.tf
index 11f4624..2fc3126 100644
--- a/middleware/apache/monitors-apache.tf
+++ b/middleware/apache/monitors-apache.tf
@@ -3,7 +3,7 @@ resource "datadog_monitor" "Apache_process" {
   message = "${var.message}"
 
   type  = "service check"
-  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
+  query = "\"apache.can_connect\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -11,10 +11,10 @@ resource "datadog_monitor" "Apache_process" {
     critical = 4
   }
 
-  notify_no_data      = false
+  notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
   new_host_delay      = "${var.evaluation_delay}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -22,5 +22,5 @@ resource "datadog_monitor" "Apache_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:apache"]
+  tags = ["env:${var.environment}", "type:resource"]
 }
diff --git a/middleware/nginx/README.md b/middleware/nginx/README.md
index 435dde6..ccf7772 100644
--- a/middleware/nginx/README.md
+++ b/middleware/nginx/README.md
@@ -24,7 +24,6 @@ Inputs
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
-| dd_nginx |  | string | `disabled` | no |
 | environment | Architecture Environment | string | - | yes |
 | evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
diff --git a/middleware/nginx/inputs.tf b/middleware/nginx/inputs.tf
index f823913..ea23988 100644
--- a/middleware/nginx/inputs.tf
+++ b/middleware/nginx/inputs.tf
@@ -15,7 +15,3 @@ variable "message" {
 }
 
 # Nginx Middleware specific
-
-variable "dd_nginx" {
-  default = "disabled"
-}
diff --git a/middleware/nginx/monitors-nginx.tf b/middleware/nginx/monitors-nginx.tf
index b018ec3..a569c60 100644
--- a/middleware/nginx/monitors-nginx.tf
+++ b/middleware/nginx/monitors-nginx.tf
@@ -3,7 +3,7 @@ resource "datadog_monitor" "Nginx_process" {
   message = "${var.message}"
 
   type  = "service check"
-  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
+  query = "\"nginx.can_connect\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -11,10 +11,10 @@ resource "datadog_monitor" "Nginx_process" {
     critical = 4
   }
 
-  notify_no_data      = false
+  notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
   new_host_delay      = "${var.evaluation_delay}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -22,5 +22,5 @@ resource "datadog_monitor" "Nginx_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:nginx"]
+  tags = ["env:${var.environment}", "type:resource"]
 }
diff --git a/middleware/php-fpm/monitors-fpm.tf b/middleware/php-fpm/monitors-fpm.tf
index 95289e8..2b06108 100644
--- a/middleware/php-fpm/monitors-fpm.tf
+++ b/middleware/php-fpm/monitors-fpm.tf
@@ -2,7 +2,7 @@ data "template_file" "filter" {
   template = "$${filter}"
 
   vars {
-    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_php_fpm:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
   }
 }
 
@@ -25,7 +25,7 @@ resource "datadog_monitor" "php-fpm_process_idle" {
     critical = "${var.php_fpm_busy_threshold_critical}"
   }
 
-  notify_no_data      = false
+  notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay_metric}"
   new_host_delay      = "${var.evaluation_delay_metric}"
   notify_audit        = false
@@ -35,7 +35,7 @@ resource "datadog_monitor" "php-fpm_process_idle" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:php-fpm"]
+  tags = ["env:${var.environment}", "type:resource"]
 }
 
 resource "datadog_monitor" "FPM_process" {
@@ -43,7 +43,7 @@ resource "datadog_monitor" "FPM_process" {
   message = "${var.message}"
 
   type  = "service check"
-  query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
+  query = "\"php_fpm.can_ping\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -54,7 +54,7 @@ resource "datadog_monitor" "FPM_process" {
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay_service}"
   new_host_delay      = "${var.evaluation_delay_service}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
@@ -62,5 +62,5 @@ resource "datadog_monitor" "FPM_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:php-fpm"]
+  tags = ["env:${var.environment}", "type:resource"]
 }
diff --git a/system/generic/monitors-custom-cpu.tf b/system/generic/monitors-custom-cpu.tf
index 57b9b03..7f862cf 100644
--- a/system/generic/monitors-custom-cpu.tf
+++ b/system/generic/monitors-custom-cpu.tf
@@ -2,7 +2,7 @@ data "template_file" "filter" {
   template = "$${filter}"
 
   vars {
-    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_system:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
   }
 }
 
@@ -12,8 +12,8 @@ resource "datadog_monitor" "cpu_custom" {
 
   query = <<EOF
     min(${var.custom_cpu_period}): (
-      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host} +
-      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host}
+      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host.name,host.ip} +
+      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host.name,host.ip}
     ) > ${var.custom_cpu_threshold_critical}"
   EOF
 
@@ -27,7 +27,7 @@ resource "datadog_monitor" "cpu_custom" {
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
   new_host_delay      = "${var.evaluation_delay}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true
diff --git a/system/linux/monitors-linux-basics.tf b/system/linux/monitors-linux-basics.tf
index 6bd173d..d5762fe 100644
--- a/system/linux/monitors-linux-basics.tf
+++ b/system/linux/monitors-linux-basics.tf
@@ -2,7 +2,7 @@ data "template_file" "filter" {
   template = "$${filter}"
 
   vars {
-    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_linux:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
   }
 }
 
@@ -122,7 +122,7 @@ resource "datadog_monitor" "datadog_free_memory" {
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
   new_host_delay      = "${var.evaluation_delay}"
-  renotify_interval   = 60
+  renotify_interval   = 0
   notify_audit        = false
   timeout_h           = 0
   include_tags        = true

From 73d81d7053cfc62b3fc9afb38dc9eb74123971cf Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Thu, 22 Feb 2018 12:15:53 +0100
Subject: [PATCH 08/11] MON-96 - Renamed system's monitors

---
 middleware/apache/inputs.tf                                   | 1 +
 middleware/nginx/inputs.tf                                    | 1 +
 system/generic/{monitors-custom-cpu.tf => monitors-system.tf} | 0
 system/linux/{monitors-linux-basics.tf => monitors-linux.tf}  | 0
 4 files changed, 2 insertions(+)
 rename system/generic/{monitors-custom-cpu.tf => monitors-system.tf} (100%)
 rename system/linux/{monitors-linux-basics.tf => monitors-linux.tf} (100%)

diff --git a/middleware/apache/inputs.tf b/middleware/apache/inputs.tf
index ca3d259..1812e3d 100644
--- a/middleware/apache/inputs.tf
+++ b/middleware/apache/inputs.tf
@@ -15,3 +15,4 @@ variable "message" {
 }
 
 # Apache Middleware specific
+
diff --git a/middleware/nginx/inputs.tf b/middleware/nginx/inputs.tf
index ea23988..a82f6c2 100644
--- a/middleware/nginx/inputs.tf
+++ b/middleware/nginx/inputs.tf
@@ -15,3 +15,4 @@ variable "message" {
 }
 
 # Nginx Middleware specific
+
diff --git a/system/generic/monitors-custom-cpu.tf b/system/generic/monitors-system.tf
similarity index 100%
rename from system/generic/monitors-custom-cpu.tf
rename to system/generic/monitors-system.tf
diff --git a/system/linux/monitors-linux-basics.tf b/system/linux/monitors-linux.tf
similarity index 100%
rename from system/linux/monitors-linux-basics.tf
rename to system/linux/monitors-linux.tf

From 4fcbd5da7effa0b514714385a66d7e91b0001fdb Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Thu, 22 Feb 2018 14:56:25 +0100
Subject: [PATCH 09/11] MON-96 - Migrated system/linux monitors into
 system/generic

---
 .../elasticsearch/monitors-elasticsearch.tf   |   2 +-
 middleware/apache/monitors-apache.tf          |   8 +-
 middleware/nginx/monitors-nginx.tf            |   8 +-
 middleware/php-fpm/monitors-fpm.tf            |  14 +-
 system/generic/README.md                      |  12 +-
 system/generic/inputs.tf                      |  42 ++++-
 system/generic/monitors-system.tf             | 111 ++++++++++-
 system/linux/README.md                        |  43 -----
 system/linux/inputs.tf                        |  72 -------
 system/linux/monitors-linux.tf                | 178 ------------------
 10 files changed, 164 insertions(+), 326 deletions(-)
 delete mode 100644 system/linux/README.md
 delete mode 100644 system/linux/inputs.tf
 delete mode 100644 system/linux/monitors-linux.tf

diff --git a/cloud/aws/elasticsearch/monitors-elasticsearch.tf b/cloud/aws/elasticsearch/monitors-elasticsearch.tf
index 5a55f4b..b665926 100644
--- a/cloud/aws/elasticsearch/monitors-elasticsearch.tf
+++ b/cloud/aws/elasticsearch/monitors-elasticsearch.tf
@@ -98,7 +98,7 @@ EOF
   timeout_h           = 0
   include_tags        = true
   locked              = false
-  require_full_window = true
+  require_full_window = false
   new_host_delay      = "${var.evaluation_delay}"
   no_data_timeframe   = 20
 
diff --git a/middleware/apache/monitors-apache.tf b/middleware/apache/monitors-apache.tf
index 2fc3126..b1f8d53 100644
--- a/middleware/apache/monitors-apache.tf
+++ b/middleware/apache/monitors-apache.tf
@@ -1,9 +1,9 @@
-resource "datadog_monitor" "Apache_process" {
-  name    = "[${var.environment}] Apache process is down on {{host.name}}"
+resource "datadog_monitor" "datadog_apache_process" {
+  name    = "[${var.environment}] Can't connect to apache, process is not running on {{host.name}}"
   message = "${var.message}"
 
   type  = "service check"
-  query = "\"apache.can_connect\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
+  query = "\"apache.can_connect\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -22,5 +22,5 @@ resource "datadog_monitor" "Apache_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:resource"]
+  tags = ["env:${var.environment}", "resource:apache"]
 }
diff --git a/middleware/nginx/monitors-nginx.tf b/middleware/nginx/monitors-nginx.tf
index a569c60..f81a291 100644
--- a/middleware/nginx/monitors-nginx.tf
+++ b/middleware/nginx/monitors-nginx.tf
@@ -1,9 +1,9 @@
-resource "datadog_monitor" "Nginx_process" {
-  name    = "[${var.environment}] Nginx process is down on {{host.name}}"
+resource "datadog_monitor" "datadog_nginx_process" {
+  name    = "[${var.environment}] Can't connect to nginx, process is not running on {{host.name}}"
   message = "${var.message}"
 
   type  = "service check"
-  query = "\"nginx.can_connect\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
+  query = "\"nginx.can_connect\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -22,5 +22,5 @@ resource "datadog_monitor" "Nginx_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:resource"]
+  tags = ["env:${var.environment}", "resource:nginx"]
 }
diff --git a/middleware/php-fpm/monitors-fpm.tf b/middleware/php-fpm/monitors-fpm.tf
index 2b06108..e85f0e6 100644
--- a/middleware/php-fpm/monitors-fpm.tf
+++ b/middleware/php-fpm/monitors-fpm.tf
@@ -2,11 +2,11 @@ data "template_file" "filter" {
   template = "$${filter}"
 
   vars {
-    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_php_fpm:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_php_fpm:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
   }
 }
 
-resource "datadog_monitor" "php-fpm_process_idle" {
+resource "datadog_monitor" "datadog_php_fpm_process_idle" {
   name    = "[${var.environment}] php_fpm busy worker {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
   message = "${var.message}"
 
@@ -35,15 +35,15 @@ resource "datadog_monitor" "php-fpm_process_idle" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:resource"]
+  tags = ["env:${var.environment}", "resource:php-fpm"]
 }
 
-resource "datadog_monitor" "FPM_process" {
-  name    = "[${var.environment}] FPM process is down on {{host.name}}"
+resource "datadog_monitor" "datadog_fpm_process" {
+  name    = "[${var.environment}] Can't ping FPM, process is not running on {{host.name}}"
   message = "${var.message}"
 
   type  = "service check"
-  query = "\"php_fpm.can_ping\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
+  query = "\"php_fpm.can_ping\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
 
   thresholds = {
     ok       = 1
@@ -62,5 +62,5 @@ resource "datadog_monitor" "FPM_process" {
   require_full_window = true
   no_data_timeframe   = 20
 
-  tags = ["env:${var.environment}", "type:resource"]
+  tags = ["env:${var.environment}", "resource:php-fpm"]
 }
diff --git a/system/generic/README.md b/system/generic/README.md
index eb85357..abf80e0 100644
--- a/system/generic/README.md
+++ b/system/generic/README.md
@@ -24,11 +24,17 @@ Inputs
 
 | Name | Description | Type | Default | Required |
 |------|-------------|:----:|:-----:|:-----:|
-| custom_cpu_period | Set up period for the query | string | `last_5m` | no |
-| custom_cpu_threshold_critical | Custom CPU critical threshold | string | `95` | no |
-| custom_cpu_threshold_warning | Custom CPU warning threshold | string | `80` | no |
+| cpu_high_threshold_critical | CPU high critical threshold | string | `95` | no |
+| cpu_high_threshold_warning | CPU high warning threshold | string | `80` | no |
+| cpu_high_timeframe | CPU high timeframe | string | `last_5m` | no |
 | environment | Architecture Environment | string | - | yes |
 | evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
 | filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
 | filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
+| free_disk_inodes_threshold_critical | Free disk space critical threshold | string | `5` | no |
+| free_disk_inodes_threshold_warning | Free disk space warning threshold | string | `10` | no |
+| free_disk_space_threshold_critical | Free disk space critical threshold | string | `5` | no |
+| free_disk_space_threshold_warning | Free disk space warning threshold | string | `10` | no |
+| free_memory_threshold_critical | Free disk space critical threshold | string | `5` | no |
+| free_memory_threshold_warning | Free disk space warning threshold | string | `10` | no |
 | message | Message sent when an alert is triggered | string | - | yes |
diff --git a/system/generic/inputs.tf b/system/generic/inputs.tf
index 06a118e..5b34296 100644
--- a/system/generic/inputs.tf
+++ b/system/generic/inputs.tf
@@ -26,17 +26,47 @@ variable "filter_tags_custom" {
 
 # Custom CPU instance specific
 
-variable "custom_cpu_period" {
-  description = "Set up period for the query"
+variable "cpu_high_timeframe" {
+  description = "CPU high timeframe"
   default     = "last_5m"
 }
 
-variable "custom_cpu_threshold_warning" {
-  description = "Custom CPU warning threshold"
+variable "cpu_high_threshold_warning" {
+  description = "CPU high warning threshold"
   default     = 80
 }
 
-variable "custom_cpu_threshold_critical" {
-  description = "Custom CPU critical threshold"
+variable "cpu_high_threshold_critical" {
+  description = "CPU high critical threshold"
   default     = 95
 }
+
+variable "free_disk_space_threshold_warning" {
+  description = "Free disk space warning threshold"
+  default     = 10
+}
+
+variable "free_disk_space_threshold_critical" {
+  description = "Free disk space critical threshold"
+  default     = 5
+}
+
+variable "free_disk_inodes_threshold_warning" {
+  description = "Free disk space warning threshold"
+  default     = 10
+}
+
+variable "free_disk_inodes_threshold_critical" {
+  description = "Free disk space critical threshold"
+  default     = 5
+}
+
+variable "free_memory_threshold_warning" {
+  description = "Free disk space warning threshold"
+  default     = 10
+}
+
+variable "free_memory_threshold_critical" {
+  description = "Free disk space critical threshold"
+  default     = 5
+}
diff --git a/system/generic/monitors-system.tf b/system/generic/monitors-system.tf
index 7f862cf..473701c 100644
--- a/system/generic/monitors-system.tf
+++ b/system/generic/monitors-system.tf
@@ -6,24 +6,119 @@ data "template_file" "filter" {
   }
 }
 
-resource "datadog_monitor" "cpu_custom" {
+resource "datadog_monitor" "datadog_cpu_too_high" {
   name    = "[${var.environment}] CPU too High {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
   message = "${var.message}"
 
   query = <<EOF
-    min(${var.custom_cpu_period}): (
-      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host.name,host.ip} +
-      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host.name,host.ip}
-    ) > ${var.custom_cpu_threshold_critical}"
+    min(${var.cpu_high_timeframe}): (
+      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host} +
+      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host}
+    ) > ${var.cpu_high_threshold_critical}
   EOF
 
   type = "metric alert"
 
-  thresholds = {
-    warning  = "${var.custom_cpu_threshold_warning}"
-    critical = "${var.custom_cpu_threshold_critical}"
+  thresholds {
+    warning  = "${var.cpu_high_threshold_warning}"
+    critical = "${var.cpu_high_threshold_critical}"
   }
 
+  tags = ["env:${var.environment}", "type:system"]
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  no_data_timeframe   = 20
+}
+
+resource "datadog_monitor" "datadog_free_disk_space_too_low" {
+  name    = "[${var.environment}] Free disk space {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "${var.message}"
+
+  query = <<EOF
+    sum(last_5m): (
+      avg:system.disk.free{${data.template_file.filter.rendered}} by {region,host,device} /
+      avg:system.disk.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
+    ) < ${var.free_disk_space_threshold_critical}
+  EOF
+
+  type = "metric alert"
+
+  thresholds {
+    warning  = "${var.free_disk_space_threshold_warning}"
+    critical = "${var.free_disk_space_threshold_critical}"
+  }
+
+  tags = ["env:${var.environment}", "type:system"]
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  no_data_timeframe   = 20
+}
+
+resource "datadog_monitor" "datadog_free_disk_space_inodes_too_low" {
+  name    = "[${var.environment}] Free disk inodes {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "${var.message}"
+
+  query = <<EOF
+    sum(last_5m): (
+      avg:system.fs.inodes.free{${data.template_file.filter.rendered}} by {region,host,device} /
+      avg:system.fs.inodes.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
+    ) < ${var.free_disk_inodes_threshold_critical}
+  EOF
+
+  type = "metric alert"
+
+  thresholds {
+    warning  = "${var.free_disk_inodes_threshold_warning}"
+    critical = "${var.free_disk_inodes_threshold_critical}"
+  }
+
+  tags = ["env:${var.environment}", "type:system"]
+
+  notify_no_data      = true
+  evaluation_delay    = "${var.evaluation_delay}"
+  new_host_delay      = "${var.evaluation_delay}"
+  notify_audit        = false
+  timeout_h           = 0
+  include_tags        = true
+  locked              = false
+  require_full_window = true
+  no_data_timeframe   = 20
+}
+
+resource "datadog_monitor" "datadog_free_memory" {
+  name    = "[${var.environment}] Free memory {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  message = "Debugging alert - no escalation"
+
+  query = <<EOF
+    sum(last_1m): (
+      avg:system.mem.free{${data.template_file.filter.rendered}} by {region,host} /
+      avg:system.mem.total{${data.template_file.filter.rendered}} by {region,host} * 100
+    ) < ${var.free_memory_threshold_critical}
+  EOF
+
+  type = "metric alert"
+
+  thresholds {
+    warning  = "${var.free_memory_threshold_warning}"
+    critical = "${var.free_memory_threshold_critical}"
+  }
+
+  tags = ["env:${var.environment}", "type:system"]
+
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
   new_host_delay      = "${var.evaluation_delay}"
diff --git a/system/linux/README.md b/system/linux/README.md
deleted file mode 100644
index 54aac37..0000000
--- a/system/linux/README.md
+++ /dev/null
@@ -1,43 +0,0 @@
-System Linux DataDog monitors
-=============================
-
-How to use this module
-----------------------
-
-```
-module "datadog-monitors-system-generic" {
-  source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//system/linux?ref={revision}"
-
-  message     = "${module.datadog-message-alerting.alerting-message}"
-  environment = "${var.environment}"
-}
-```
-
-Purpose
--------
-Creates a DataDog monitors with the following checks :
-
-* System CPU High
-* System Free disk space
-* System Free disk inodes
-* System Free memory
-
-Inputs
-------
-
-| Name | Description | Type | Default | Required |
-|------|-------------|:----:|:-----:|:-----:|
-| cpu_high_threshold_critical | CPU high critical threshold | string | `95` | no |
-| cpu_high_threshold_warning | CPU high warning threshold | string | `80` | no |
-| custom_cpu_period | Set up period for the query | string | `last_5m` | no |
-| environment | Architecture Environment | string | - | yes |
-| evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
-| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
-| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
-| free_disk_inodes_threshold_critical | Free disk space critical threshold | string | `5` | no |
-| free_disk_inodes_threshold_warning | Free disk space warning threshold | string | `10` | no |
-| free_disk_space_threshold_critical | Free disk space critical threshold | string | `5` | no |
-| free_disk_space_threshold_warning | Free disk space warning threshold | string | `10` | no |
-| free_memory_threshold_critical | Free disk space critical threshold | string | `5` | no |
-| free_memory_threshold_warning | Free disk space warning threshold | string | `10` | no |
-| message | Message sent when an alert is triggered | string | - | yes |
\ No newline at end of file
diff --git a/system/linux/inputs.tf b/system/linux/inputs.tf
deleted file mode 100644
index de67079..0000000
--- a/system/linux/inputs.tf
+++ /dev/null
@@ -1,72 +0,0 @@
-# Global Terraform
-variable "environment" {
-  description = "Architecture Environment"
-  type        = "string"
-}
-
-# Global DataDog
-variable "evaluation_delay" {
-  description = "Delay in seconds for the metric evaluation"
-  default     = 600
-}
-
-variable "message" {
-  description = "Message sent when an alert is triggered"
-}
-
-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     = "*"
-}
-
-# Custom CPU instance specific
-
-variable "custom_cpu_period" {
-  description = "Set up period for the query"
-  default     = "last_5m"
-}
-
-variable "cpu_high_threshold_warning" {
-  description = "CPU high warning threshold"
-  default     = 80
-}
-
-variable "cpu_high_threshold_critical" {
-  description = "CPU high critical threshold"
-  default     = 95
-}
-
-variable "free_disk_space_threshold_warning" {
-  description = "Free disk space warning threshold"
-  default     = 10
-}
-
-variable "free_disk_space_threshold_critical" {
-  description = "Free disk space critical threshold"
-  default     = 5
-}
-
-variable "free_disk_inodes_threshold_warning" {
-  description = "Free disk space warning threshold"
-  default     = 10
-}
-
-variable "free_disk_inodes_threshold_critical" {
-  description = "Free disk space critical threshold"
-  default     = 5
-}
-
-variable "free_memory_threshold_warning" {
-  description = "Free disk space warning threshold"
-  default     = 10
-}
-
-variable "free_memory_threshold_critical" {
-  description = "Free disk space critical threshold"
-  default     = 5
-}
diff --git a/system/linux/monitors-linux.tf b/system/linux/monitors-linux.tf
deleted file mode 100644
index d5762fe..0000000
--- a/system/linux/monitors-linux.tf
+++ /dev/null
@@ -1,178 +0,0 @@
-data "template_file" "filter" {
-  template = "$${filter}"
-
-  vars {
-    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_linux:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
-  }
-}
-
-resource "datadog_monitor" "datadog_cpu_too_high" {
-  name    = "[${var.environment}] CPU High {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
-  message = "${var.message}"
-
-  query = <<EOF
-    min(last_15m): (
-      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host} +
-      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host}
-    ) > ${var.cpu_high_threshold_critical}
-  EOF
-
-  type = "metric alert"
-
-  thresholds {
-    warning  = "${var.cpu_high_threshold_warning}"
-    critical = "${var.cpu_high_threshold_critical}"
-  }
-
-  tags = ["env:${var.environment}", "type:system"]
-
-  notify_no_data      = true
-  evaluation_delay    = "${var.evaluation_delay}"
-  new_host_delay      = "${var.evaluation_delay}"
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  no_data_timeframe   = 20
-}
-
-resource "datadog_monitor" "datadog_free_disk_space_too_low" {
-  name    = "[${var.environment}] Free disk space {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
-  message = "${var.message}"
-
-  query = <<EOF
-    sum(last_5m): (
-      avg:system.disk.free{${data.template_file.filter.rendered}} by {region,host,device} /
-      avg:system.disk.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
-    ) < ${var.free_disk_space_threshold_critical}
-  EOF
-
-  type = "metric alert"
-
-  thresholds {
-    warning  = "${var.free_disk_space_threshold_warning}"
-    critical = "${var.free_disk_space_threshold_critical}"
-  }
-
-  tags = ["env:${var.environment}", "type:system"]
-
-  notify_no_data      = true
-  evaluation_delay    = "${var.evaluation_delay}"
-  new_host_delay      = "${var.evaluation_delay}"
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  no_data_timeframe   = 20
-}
-
-resource "datadog_monitor" "datadog_free_disk_space_inodes_too_low" {
-  name    = "[${var.environment}] Free disk inodes {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
-  message = "${var.message}"
-
-  query = <<EOF
-    sum(last_5m): (
-      avg:system.fs.inodes.free{${data.template_file.filter.rendered}} by {region,host,device} /
-      avg:system.fs.inodes.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
-    ) < ${var.free_disk_inodes_threshold_critical}
-  EOF
-
-  type = "metric alert"
-
-  thresholds {
-    warning  = "${var.free_disk_inodes_threshold_warning}"
-    critical = "${var.free_disk_inodes_threshold_critical}"
-  }
-
-  tags = ["env:${var.environment}", "type:system"]
-
-  notify_no_data      = true
-  evaluation_delay    = "${var.evaluation_delay}"
-  new_host_delay      = "${var.evaluation_delay}"
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  no_data_timeframe   = 20
-}
-
-resource "datadog_monitor" "datadog_free_memory" {
-  name    = "[${var.environment}] Free memory {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
-  message = "Debugging alert - no escalation"
-
-  query = <<EOF
-    sum(last_1m): (
-      avg:system.mem.free{${data.template_file.filter.rendered}} by {region,host} /
-      avg:system.mem.total{${data.template_file.filter.rendered}} by {region,host} * 100
-    ) < ${var.free_memory_threshold_critical}
-  EOF
-
-  type = "metric alert"
-
-  thresholds {
-    warning  = "${var.free_memory_threshold_warning}"
-    critical = "${var.free_memory_threshold_critical}"
-  }
-
-  tags = ["env:${var.environment}", "type:system"]
-
-  notify_no_data      = true
-  evaluation_delay    = "${var.evaluation_delay}"
-  new_host_delay      = "${var.evaluation_delay}"
-  renotify_interval   = 0
-  notify_audit        = false
-  timeout_h           = 0
-  include_tags        = true
-  locked              = false
-  require_full_window = true
-  no_data_timeframe   = 20
-}
-
-# resource "datadog_monitor" "datadog_cpu_load" {
-#   name    = "CPU Load > 2"
-#   message = "Debugging alert - no escalation"
-
-
-#   query = "min(last_5m):avg:system.load.5{dd_monitoring:enabled,dd_linux_basics:enabled,!dd_custom_cpu:enabled} by {instance-id} / avg:gcp.gce.instance.cpu.reserved_cores{*} by {instance-id} > 2"
-#   type  = "query alert"
-#   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
-
-
-# notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-# evaluation_delay    = "${var.linux_basics_config["delay"]}"
-# new_host_delay      = "${var.linux_basics_config["delay"]}"
-# renotify_interval   = 60
-# notify_audit        = false
-# timeout_h           = 0
-# include_tags        = true
-# locked              = false
-# require_full_window = true
-# no_data_timeframe   = 20
-# }
-
-
-# resource "datadog_monitor" "datadog_host_unreachable" {
-#   name    = "Host unreachable"
-#   message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group} \n{{/is_recovery}}"
-
-
-#   query = "datadog.agent.up.over(dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled).last(1).count_by_status()"
-#   type  = "service check"
-#   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
-
-
-# notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
-# evaluation_delay    = "${var.linux_basics_config["delay"]}"
-# new_host_delay      = "${var.linux_basics_config["delay"]}"
-# renotify_interval   = 60
-# notify_audit        = false
-# timeout_h           = 0
-# include_tags        = true
-# locked              = false
-# require_full_window = true
-# no_data_timeframe   = 20
-# }
-

From 3d79aced742a85b95351206dbbb58a72d86bfe01 Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Thu, 22 Feb 2018 17:23:31 +0100
Subject: [PATCH 10/11] MON-96 - Fix middleware monitors names and update
 system monitors

---
 middleware/apache/monitors-apache.tf |  2 +-
 middleware/nginx/monitors-nginx.tf   |  2 +-
 middleware/php-fpm/monitors-fpm.tf   |  2 +-
 system/generic/monitors-system.tf    | 17 ++++++++---------
 4 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/middleware/apache/monitors-apache.tf b/middleware/apache/monitors-apache.tf
index b1f8d53..d31cfd6 100644
--- a/middleware/apache/monitors-apache.tf
+++ b/middleware/apache/monitors-apache.tf
@@ -1,5 +1,5 @@
 resource "datadog_monitor" "datadog_apache_process" {
-  name    = "[${var.environment}] Can't connect to apache, process is not running on {{host.name}}"
+  name    = "[${var.environment}] Can't connect to apache vhost status"
   message = "${var.message}"
 
   type  = "service check"
diff --git a/middleware/nginx/monitors-nginx.tf b/middleware/nginx/monitors-nginx.tf
index f81a291..3db1c0f 100644
--- a/middleware/nginx/monitors-nginx.tf
+++ b/middleware/nginx/monitors-nginx.tf
@@ -1,5 +1,5 @@
 resource "datadog_monitor" "datadog_nginx_process" {
-  name    = "[${var.environment}] Can't connect to nginx, process is not running on {{host.name}}"
+  name    = "[${var.environment}] Can't connect to nginx vhost status"
   message = "${var.message}"
 
   type  = "service check"
diff --git a/middleware/php-fpm/monitors-fpm.tf b/middleware/php-fpm/monitors-fpm.tf
index e85f0e6..5b1568b 100644
--- a/middleware/php-fpm/monitors-fpm.tf
+++ b/middleware/php-fpm/monitors-fpm.tf
@@ -39,7 +39,7 @@ resource "datadog_monitor" "datadog_php_fpm_process_idle" {
 }
 
 resource "datadog_monitor" "datadog_fpm_process" {
-  name    = "[${var.environment}] Can't ping FPM, process is not running on {{host.name}}"
+  name    = "[${var.environment}] Can't connect to php-fpm"
   message = "${var.message}"
 
   type  = "service check"
diff --git a/system/generic/monitors-system.tf b/system/generic/monitors-system.tf
index 473701c..43ef2cc 100644
--- a/system/generic/monitors-system.tf
+++ b/system/generic/monitors-system.tf
@@ -2,18 +2,17 @@ data "template_file" "filter" {
   template = "$${filter}"
 
   vars {
-    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_system:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
+    filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_system:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
   }
 }
 
 resource "datadog_monitor" "datadog_cpu_too_high" {
-  name    = "[${var.environment}] CPU too High {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
+  name    = "[${var.environment}] CPU usage {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
   message = "${var.message}"
 
   query = <<EOF
     min(${var.cpu_high_timeframe}): (
-      avg:system.cpu.system{${data.template_file.filter.rendered}} by {region,host} +
-      avg:system.cpu.user{${data.template_file.filter.rendered}} by {region,host}
+      100 - avg:system.cpu.idle{${data.template_file.filter.rendered}} by {region,host}
     ) > ${var.cpu_high_threshold_critical}
   EOF
 
@@ -24,7 +23,7 @@ resource "datadog_monitor" "datadog_cpu_too_high" {
     critical = "${var.cpu_high_threshold_critical}"
   }
 
-  tags = ["env:${var.environment}", "type:system"]
+  tags = ["env:${var.environment}", "type:system", "resource:cpu"]
 
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
@@ -55,7 +54,7 @@ resource "datadog_monitor" "datadog_free_disk_space_too_low" {
     critical = "${var.free_disk_space_threshold_critical}"
   }
 
-  tags = ["env:${var.environment}", "type:system"]
+  tags = ["env:${var.environment}", "type:system", "resource:disk"]
 
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
@@ -86,7 +85,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_too_low" {
     critical = "${var.free_disk_inodes_threshold_critical}"
   }
 
-  tags = ["env:${var.environment}", "type:system"]
+  tags = ["env:${var.environment}", "type:system", "resource:disk"]
 
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"
@@ -101,7 +100,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_too_low" {
 
 resource "datadog_monitor" "datadog_free_memory" {
   name    = "[${var.environment}] Free memory {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
-  message = "Debugging alert - no escalation"
+  message = "${var.message}"
 
   query = <<EOF
     sum(last_1m): (
@@ -117,7 +116,7 @@ resource "datadog_monitor" "datadog_free_memory" {
     critical = "${var.free_memory_threshold_critical}"
   }
 
-  tags = ["env:${var.environment}", "type:system"]
+  tags = ["env:${var.environment}", "type:system", "resource:memory"]
 
   notify_no_data      = true
   evaluation_delay    = "${var.evaluation_delay}"

From 5ebe18572f56ce14caa16f8d0e93edf307c4dc68 Mon Sep 17 00:00:00 2001
From: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
Date: Thu, 22 Feb 2018 17:49:34 +0100
Subject: [PATCH 11/11] MON-96 - Update queries system monitors with min()

---
 system/generic/monitors-system.tf | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/system/generic/monitors-system.tf b/system/generic/monitors-system.tf
index 43ef2cc..0a09ffd 100644
--- a/system/generic/monitors-system.tf
+++ b/system/generic/monitors-system.tf
@@ -41,7 +41,7 @@ resource "datadog_monitor" "datadog_free_disk_space_too_low" {
   message = "${var.message}"
 
   query = <<EOF
-    sum(last_5m): (
+    min(last_5m): (
       avg:system.disk.free{${data.template_file.filter.rendered}} by {region,host,device} /
       avg:system.disk.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
     ) < ${var.free_disk_space_threshold_critical}
@@ -72,7 +72,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_too_low" {
   message = "${var.message}"
 
   query = <<EOF
-    sum(last_5m): (
+    min(last_5m): (
       avg:system.fs.inodes.free{${data.template_file.filter.rendered}} by {region,host,device} /
       avg:system.fs.inodes.total{${data.template_file.filter.rendered}} by {region,host,device} * 100
     ) < ${var.free_disk_inodes_threshold_critical}
@@ -103,7 +103,7 @@ resource "datadog_monitor" "datadog_free_memory" {
   message = "${var.message}"
 
   query = <<EOF
-    sum(last_1m): (
+    min(last_1m): (
       avg:system.mem.free{${data.template_file.filter.rendered}} by {region,host} /
       avg:system.mem.total{${data.template_file.filter.rendered}} by {region,host} * 100
     ) < ${var.free_memory_threshold_critical}