From 7d2ad5114edbc7f75c0aa957e5712b560041658f Mon Sep 17 00:00:00 2001
From: vincent EL KHATIB <vincent.elkhatib@morea.fr>
Date: Mon, 30 Oct 2017 15:04:49 +0100
Subject: [PATCH 1/5] MON-81 fix delta from nexperience

MON-81 fix strconv.ParseInt

MON-81 fix hardcoded env

MON-81 added custom cpu tag & variabilize cpu threshold

MON-81 fixed dd_custom missing

MON-81 added region
---
 inputs.tf                    |  9 +++++++++
 monitors-linux-basics.tf     | 38 +++++++++++++++++++++++++++---------
 monitors-rds_mysql-basics.tf |  4 ++--
 monitors_fpm.tf              |  2 +-
 4 files changed, 41 insertions(+), 12 deletions(-)

diff --git a/inputs.tf b/inputs.tf
index 03b1829..5e6720b 100644
--- a/inputs.tf
+++ b/inputs.tf
@@ -23,6 +23,15 @@ variable "dd_custom_cpu" {
   }
 }
 
+#cpu threshold
+
+variable "cpu_5_critical" {
+  default = 95
+}
+
+variable "cpu_15_critical" {
+  default = 80
+}
 
 ## RDS
 variable "dd_aws_rds" {
diff --git a/monitors-linux-basics.tf b/monitors-linux-basics.tf
index f854caf..961a070 100644
--- a/monitors-linux-basics.tf
+++ b/monitors-linux-basics.tf
@@ -1,11 +1,15 @@
 resource "datadog_monitor" "cpu_80_15min" {
-  name    = "[${var.env}] CPU High > 80% for 15 min on {{host.name}}"
+  name    = "[${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}"
 
-  query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} > 80"
+  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"
 
+  thresholds {
+    critical = "${var.cpu_15_critical}"
+  }
+
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
   new_host_delay      = "${var.linux_basics_config["delay"]}"
@@ -19,13 +23,17 @@ resource "datadog_monitor" "cpu_80_15min" {
 }
 
 resource "datadog_monitor" "cpu_95_5min" {
-  name    = "[${var.env}] CPU High > 95% for 5 min on {{host.name}}"
+  name    = "[${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}}"
 
-  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,!dd_custom_cpu:enabled} by {host,region,stack} > 95"
+  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${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}"
 
+  thresholds {
+    critical = "${var.cpu_5_critical}"
+  }
+
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
   new_host_delay      = "${var.linux_basics_config["delay"]}"
@@ -42,10 +50,14 @@ 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}}"
 
-  query   = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,!dd_custom_cpu:enabled} by {host,device,region,stack} * 100 < 5"
+  query   = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${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}"
 
+  thresholds {
+    critical = 5
+  }
+
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
   new_host_delay      = "${var.linux_basics_config["delay"]}"
@@ -62,7 +74,7 @@ resource "datadog_monitor" "datadog_free_disk_space_10" {
   name    = "[${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}}"
 
-  query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} * 100 < 10"
+  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}"
 
@@ -87,10 +99,14 @@ 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:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} * 100 < 5"
+  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
+  }
+
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
   new_host_delay      = "${var.linux_basics_config["delay"]}"
@@ -107,7 +123,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
   name    = "[${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,stack} * 100 < 10"
+  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}"
 
@@ -154,10 +170,14 @@ 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:${var.env},!dd_custom_memory:enabled} by {host,region,stack} / avg:system.mem.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region,stack} * 100 < 5"
+  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
+  }
+
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
   new_host_delay      = "${var.linux_basics_config["delay"]}"
diff --git a/monitors-rds_mysql-basics.tf b/monitors-rds_mysql-basics.tf
index 0d1bbf3..9d81b7c 100644
--- a/monitors-rds_mysql-basics.tf
+++ b/monitors-rds_mysql-basics.tf
@@ -8,7 +8,7 @@ resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
   count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
 
 
-  query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {name,region} > 90"
+  query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} > 90"
   type  = "query alert"
 
   thresholds {
@@ -33,7 +33,7 @@ resource "datadog_monitor" "mysql_rds_free_space_low" {
   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:${var.env}} by {name,region} /  avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_rds-mysql_basics:enabled,env:${var.env},!dd_custom_rds-mysql:enabled} by {identifier,region}  * 100 < 10"
+  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 }"
 
 
diff --git a/monitors_fpm.tf b/monitors_fpm.tf
index cff10a0..0218212 100644
--- a/monitors_fpm.tf
+++ b/monitors_fpm.tf
@@ -4,7 +4,7 @@ resource "datadog_monitor" "php-fpm_process_idle" {
 
 
   type  = "query alert"
-  query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,app} / ( avg:php_fpm.processes.idle{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,app} + avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,stack} ) > 0.90"
+  query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${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 }"
 
   thresholds {

From 272ab84244d8057fbaeb344bacdf8c6d1e38d265 Mon Sep 17 00:00:00 2001
From: vincent EL KHATIB <vincent.elkhatib@morea.fr>
Date: Tue, 31 Oct 2017 16:00:47 +0100
Subject: [PATCH 2/5] MON-81 added stack

---
 monitors-linux-basics.tf     | 14 +++++++-------
 monitors-rds_mysql-basics.tf |  4 ++--
 monitors_elb.tf              | 10 +++++-----
 monitors_fpm.tf              |  2 +-
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/monitors-linux-basics.tf b/monitors-linux-basics.tf
index 961a070..223c6ef 100644
--- a/monitors-linux-basics.tf
+++ b/monitors-linux-basics.tf
@@ -3,7 +3,7 @@ resource "datadog_monitor" "cpu_80_15min" {
   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}"
 
-  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} > ${var.cpu_15_critical}"
+  query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, stack} > ${var.cpu_15_critical}"
   type  = "query alert"
 
   thresholds {
@@ -26,7 +26,7 @@ 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}}"
 
-  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} > ${var.cpu_5_critical}"
+  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, stack} > ${var.cpu_5_critical}"
   type  = "query alert"
   count   = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -50,7 +50,7 @@ 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}}"
 
-  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"
+  query   = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} * 100 < 5"
   type  = "query alert"
   count   = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -74,7 +74,7 @@ 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}}"
 
-  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"
+  query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} * 100 < 10"
   type  = "query alert"
   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -99,7 +99,7 @@ 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"
+  query = "sum(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} * 100 < 5"
   type  = "query alert"
   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -123,7 +123,7 @@ 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"
+  query = "max(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} * 100 < 10"
   type  = "query alert"
   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -170,7 +170,7 @@ 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"
+  query = "sum(last_1m):avg:system.mem.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region,stack} / avg:system.mem.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region,stack} * 100 < 5"
   type  = "query alert"
   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
diff --git a/monitors-rds_mysql-basics.tf b/monitors-rds_mysql-basics.tf
index 9d81b7c..e45cc1b 100644
--- a/monitors-rds_mysql-basics.tf
+++ b/monitors-rds_mysql-basics.tf
@@ -8,7 +8,7 @@ resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
   count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
 
 
-  query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} > 90"
+  query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} > 90"
   type  = "query alert"
 
   thresholds {
@@ -33,7 +33,7 @@ resource "datadog_monitor" "mysql_rds_free_space_low" {
   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"
+  query = "avg(last_15m):avg:aws.rds.free_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} * 100 < 10"
   count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
 
 
diff --git a/monitors_elb.tf b/monitors_elb.tf
index a66fb84..ccb72fb 100644
--- a/monitors_elb.tf
+++ b/monitors_elb.tf
@@ -3,7 +3,7 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
   message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} == 0"
+  query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} == 0"
   type  = "query alert"
 
   notify_no_data      = "${var.elb_config["notify_no_data"]}"
@@ -23,7 +23,7 @@ resource "datadog_monitor" "ELB_unhealthy_instances" {
   message = "{{#is_alert}}\n${var.ho_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.ho_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m):avg:aws.elb.un_healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > 0"
+  query = "avg(last_5m):avg:aws.elb.un_healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} > 0"
   type  = "query alert"
 
   notify_no_data      = "${var.elb_config["notify_no_data"]}"
@@ -43,7 +43,7 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
   message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m): avg:aws.elb.httpcode_backend_5xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_5xx_threshold["critical"]}"
+  query = "avg(last_5m): avg:aws.elb.httpcode_backend_5xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} * 100 > ${var.elb_5xx_threshold["critical"]}"
   type  = "query alert"
 
   thresholds {
@@ -68,7 +68,7 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
   message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m): avg:aws.elb.httpcode_backend_4xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_4xx_threshold["critical"]}"
+  query = "avg(last_5m): avg:aws.elb.httpcode_backend_4xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} * 100 > ${var.elb_4xx_threshold["critical"]}"
   type  = "query alert"
 
   thresholds {
@@ -93,7 +93,7 @@ resource "datadog_monitor" "ELB_backend_latency" {
   message = "{{#is_alert}}\n${var.ho_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.ho_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m):avg:aws.elb.latency{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > ${var.elb_backend_latency["critical"]}"
+  query = "avg(last_5m):avg:aws.elb.latency{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} > ${var.elb_backend_latency["critical"]}"
   type  = "query alert"
 
   thresholds {
diff --git a/monitors_fpm.tf b/monitors_fpm.tf
index 0218212..9929229 100644
--- a/monitors_fpm.tf
+++ b/monitors_fpm.tf
@@ -4,7 +4,7 @@ resource "datadog_monitor" "php-fpm_process_idle" {
 
 
   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:${var.env}} by {host,region} ) > 0.9"
+  query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,stack} / ( 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,stack} ) > 0.9"
   count = "${var.dd_php_fpm == "enabled" ? 1 : 0 }"
 
   thresholds {

From 7481485da1d6d91b8396a8ea506367d4abb4b6e4 Mon Sep 17 00:00:00 2001
From: vincent EL KHATIB <vincent.elkhatib@morea.fr>
Date: Tue, 31 Oct 2017 16:27:25 +0100
Subject: [PATCH 3/5] MON-81 remove space

---
 monitors-linux-basics.tf | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/monitors-linux-basics.tf b/monitors-linux-basics.tf
index 223c6ef..1ed76a8 100644
--- a/monitors-linux-basics.tf
+++ b/monitors-linux-basics.tf
@@ -3,7 +3,7 @@ resource "datadog_monitor" "cpu_80_15min" {
   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}"
 
-  query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, stack} > ${var.cpu_15_critical}"
+  query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} > ${var.cpu_15_critical}"
   type  = "query alert"
 
   thresholds {
@@ -26,7 +26,7 @@ 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}}"
 
-  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, stack} > ${var.cpu_5_critical}"
+  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} > ${var.cpu_5_critical}"
   type  = "query alert"
   count   = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -50,7 +50,7 @@ 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}}"
 
-  query   = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} * 100 < 5"
+  query   = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 5"
   type  = "query alert"
   count   = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -74,7 +74,7 @@ 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}}"
 
-  query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} * 100 < 10"
+  query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 10"
   type  = "query alert"
   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 
@@ -99,7 +99,7 @@ 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:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region, device,stack} * 100 < 5"
+  query = "sum(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 5"
   type  = "query alert"
   count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
 

From 64be248b9eff70649c9cb2d6b1d0f5381adc5110 Mon Sep 17 00:00:00 2001
From: vincent EL KHATIB <vincent.elkhatib@morea.fr>
Date: Thu, 2 Nov 2017 15:47:47 +0100
Subject: [PATCH 4/5] MON-81 added tag *

---
 monitors-linux-basics.tf     | 14 ++++++++++++++
 monitors-rds_mysql-basics.tf |  4 ++++
 monitors_apache.tf           |  2 ++
 monitors_elb.tf              | 10 ++++++++++
 monitors_fpm.tf              |  4 ++++
 monitors_nginx.tf            |  2 ++
 6 files changed, 36 insertions(+)

diff --git a/monitors-linux-basics.tf b/monitors-linux-basics.tf
index 1ed76a8..d23a02e 100644
--- a/monitors-linux-basics.tf
+++ b/monitors-linux-basics.tf
@@ -10,6 +10,8 @@ resource "datadog_monitor" "cpu_80_15min" {
     critical = "${var.cpu_15_critical}"
   }
 
+  tags = ["*"]
+
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
   new_host_delay      = "${var.linux_basics_config["delay"]}"
@@ -34,6 +36,8 @@ resource "datadog_monitor" "cpu_95_5min" {
     critical = "${var.cpu_5_critical}"
   }
 
+  tags = ["*"]
+
   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"]}"
@@ -58,6 +62,8 @@ resource "datadog_monitor" "datadog_free_disk_space_5" {
     critical = 5
   }
 
+  tags = ["*"]
+
   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"]}"
@@ -83,6 +89,8 @@ resource "datadog_monitor" "datadog_free_disk_space_10" {
     critical = 10
   }
 
+  tags = ["*"]
+
   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"]}"
@@ -107,6 +115,8 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_5" {
     critical = 5
   }
 
+  tags = ["*"]
+
   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"]}"
@@ -132,6 +142,8 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
     critical = 10
   }
 
+  tags = ["*"]
+
   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"]}"
@@ -178,6 +190,8 @@ resource "datadog_monitor" "datadog_free_memory" {
     critical = 5
   }
 
+  tags = ["*"]
+
   notify_no_data      = "${var.linux_basics_config["notify_no_data"]}"
   evaluation_delay    = "${var.linux_basics_config["delay"]}"
   new_host_delay      = "${var.linux_basics_config["delay"]}"
diff --git a/monitors-rds_mysql-basics.tf b/monitors-rds_mysql-basics.tf
index e45cc1b..c0c44d1 100644
--- a/monitors-rds_mysql-basics.tf
+++ b/monitors-rds_mysql-basics.tf
@@ -16,6 +16,8 @@ resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
     critical = "${var.rds_cpu_threshold["critical"]}"
   }
 
+  tags = ["*"]
+
   notify_no_data      = "${var.rds_config["notify_no_data"]}"
   evaluation_delay    = "${var.rds_config["delay"]}"
   renotify_interval   = 60
@@ -42,6 +44,8 @@ resource "datadog_monitor" "mysql_rds_free_space_low" {
     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
diff --git a/monitors_apache.tf b/monitors_apache.tf
index b318de2..d807312 100644
--- a/monitors_apache.tf
+++ b/monitors_apache.tf
@@ -23,4 +23,6 @@ resource "datadog_monitor" "Apache_process" {
   locked              = false
   require_full_window = true
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
diff --git a/monitors_elb.tf b/monitors_elb.tf
index ccb72fb..788037a 100644
--- a/monitors_elb.tf
+++ b/monitors_elb.tf
@@ -16,6 +16,8 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
   require_full_window = true
   new_host_delay      = "${var.elb_config["delay"]}"
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
 
 resource "datadog_monitor" "ELB_unhealthy_instances" {
@@ -36,6 +38,8 @@ resource "datadog_monitor" "ELB_unhealthy_instances" {
   require_full_window = true
   new_host_delay      = "${var.elb_config["delay"]}"
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
 
 resource "datadog_monitor" "ELB_too_much_5xx_backend" {
@@ -61,6 +65,8 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
   require_full_window = true
   new_host_delay      = "${var.elb_config["delay"]}"
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
 
 resource "datadog_monitor" "ELB_too_much_4xx_backend" {
@@ -86,6 +92,8 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
   require_full_window = true
   new_host_delay      = "${var.elb_config["delay"]}"
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
 
 resource "datadog_monitor" "ELB_backend_latency" {
@@ -111,6 +119,8 @@ resource "datadog_monitor" "ELB_backend_latency" {
   require_full_window = true
   new_host_delay      = "${var.elb_config["delay"]}"
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
 
 
diff --git a/monitors_fpm.tf b/monitors_fpm.tf
index 9929229..957e1b9 100644
--- a/monitors_fpm.tf
+++ b/monitors_fpm.tf
@@ -23,6 +23,8 @@ resource "datadog_monitor" "php-fpm_process_idle" {
   require_full_window = true
   renotify_interval   = 0
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
 
 
@@ -51,4 +53,6 @@ resource "datadog_monitor" "FPM_process" {
   locked              = false
   require_full_window = true
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }
diff --git a/monitors_nginx.tf b/monitors_nginx.tf
index 01a95fe..8baf1cc 100644
--- a/monitors_nginx.tf
+++ b/monitors_nginx.tf
@@ -23,4 +23,6 @@ resource "datadog_monitor" "Nginx_process" {
   locked              = false
   require_full_window = true
   no_data_timeframe   = 20
+
+  tags = ["*"]
 }

From 63ba5e54d1cc439ca15bf5c34ee3767b3c9b0931 Mon Sep 17 00:00:00 2001
From: vincent EL KHATIB <vincent.elkhatib@morea.fr>
Date: Thu, 2 Nov 2017 15:54:51 +0100
Subject: [PATCH 5/5] MON-81 remove stack

---
 monitors-linux-basics.tf     | 14 +++++++-------
 monitors-rds_mysql-basics.tf |  4 ++--
 monitors_elb.tf              | 10 +++++-----
 monitors_fpm.tf              |  2 +-
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/monitors-linux-basics.tf b/monitors-linux-basics.tf
index d23a02e..ee92cd5 100644
--- a/monitors-linux-basics.tf
+++ b/monitors-linux-basics.tf
@@ -3,7 +3,7 @@ resource "datadog_monitor" "cpu_80_15min" {
   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}"
 
-  query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} > ${var.cpu_15_critical}"
+  query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${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"
 
   thresholds {
@@ -28,7 +28,7 @@ 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}}"
 
-  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} > ${var.cpu_5_critical}"
+  query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${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}"
 
@@ -54,7 +54,7 @@ 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}}"
 
-  query   = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 5"
+  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}"
 
@@ -80,7 +80,7 @@ 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}}"
 
-  query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 10"
+  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}"
 
@@ -107,7 +107,7 @@ 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:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 5"
+  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}"
 
@@ -133,7 +133,7 @@ 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:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} * 100 < 10"
+  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}"
 
@@ -182,7 +182,7 @@ 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:${var.env},!dd_custom_memory:enabled} by {host,region,stack} / avg:system.mem.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region,stack} * 100 < 5"
+  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}"
 
diff --git a/monitors-rds_mysql-basics.tf b/monitors-rds_mysql-basics.tf
index c0c44d1..95557e0 100644
--- a/monitors-rds_mysql-basics.tf
+++ b/monitors-rds_mysql-basics.tf
@@ -8,7 +8,7 @@ resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
   count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
 
 
-  query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} > 90"
+  query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} > 90"
   type  = "query alert"
 
   thresholds {
@@ -35,7 +35,7 @@ resource "datadog_monitor" "mysql_rds_free_space_low" {
   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:${var.env}} by {region,name,stack} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} * 100 < 10"
+  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 }"
 
 
diff --git a/monitors_elb.tf b/monitors_elb.tf
index 788037a..acabd1a 100644
--- a/monitors_elb.tf
+++ b/monitors_elb.tf
@@ -3,7 +3,7 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
   message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} == 0"
+  query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} == 0"
   type  = "query alert"
 
   notify_no_data      = "${var.elb_config["notify_no_data"]}"
@@ -25,7 +25,7 @@ resource "datadog_monitor" "ELB_unhealthy_instances" {
   message = "{{#is_alert}}\n${var.ho_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.ho_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m):avg:aws.elb.un_healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} > 0"
+  query = "avg(last_5m):avg:aws.elb.un_healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > 0"
   type  = "query alert"
 
   notify_no_data      = "${var.elb_config["notify_no_data"]}"
@@ -47,7 +47,7 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
   message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m): avg:aws.elb.httpcode_backend_5xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} * 100 > ${var.elb_5xx_threshold["critical"]}"
+  query = "avg(last_5m): avg:aws.elb.httpcode_backend_5xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_5xx_threshold["critical"]}"
   type  = "query alert"
 
   thresholds {
@@ -74,7 +74,7 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
   message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m): avg:aws.elb.httpcode_backend_4xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} * 100 > ${var.elb_4xx_threshold["critical"]}"
+  query = "avg(last_5m): avg:aws.elb.httpcode_backend_4xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_4xx_threshold["critical"]}"
   type  = "query alert"
 
   thresholds {
@@ -101,7 +101,7 @@ resource "datadog_monitor" "ELB_backend_latency" {
   message = "{{#is_alert}}\n${var.ho_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.ho_escalation_group}\n{{/is_recovery}}"
 
   count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
-  query = "avg(last_5m):avg:aws.elb.latency{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} > ${var.elb_backend_latency["critical"]}"
+  query = "avg(last_5m):avg:aws.elb.latency{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > ${var.elb_backend_latency["critical"]}"
   type  = "query alert"
 
   thresholds {
diff --git a/monitors_fpm.tf b/monitors_fpm.tf
index 957e1b9..844d6ac 100644
--- a/monitors_fpm.tf
+++ b/monitors_fpm.tf
@@ -4,7 +4,7 @@ resource "datadog_monitor" "php-fpm_process_idle" {
 
 
   type  = "query alert"
-  query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,stack} / ( avg:php_fpm.processes.idle{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} + avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,stack} ) > 0.9"
+  query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${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 }"
 
   thresholds {