Merged in MON-96-update-monitors-tags (pull request #35)
MON-96 Update legacy monitors to new best practices Approved-by: Laurent Piroelle <laurent.piroelle@fr.clara.net> Approved-by: Jérôme Respaut <shr3ps@gmail.com> Approved-by: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
This commit is contained in:
Ahmed Fourti
Quentin Manfroi
commit
55e0c50bf7
@ -33,7 +33,7 @@ EOF
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = true
|
||||
require_full_window = false
|
||||
new_host_delay = "${var.evaluation_delay}"
|
||||
no_data_timeframe = 20
|
||||
|
||||
@ -42,14 +42,15 @@ EOF
|
||||
|
||||
### Elasticsearch cluster free storage space monitor ###
|
||||
resource "datadog_monitor" "es_free_space_low" {
|
||||
name = "[${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
|
||||
) < ${var.diskspace_threshold_critical}
|
||||
EOF
|
||||
|
||||
@ -65,7 +66,7 @@ EOF
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = true
|
||||
require_full_window = false
|
||||
new_host_delay = "${var.evaluation_delay}"
|
||||
no_data_timeframe = 20
|
||||
|
||||
@ -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 = "${var.message}"
|
||||
|
||||
type = "query alert"
|
||||
@ -97,7 +98,7 @@ EOF
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = true
|
||||
require_full_window = false
|
||||
new_host_delay = "${var.evaluation_delay}"
|
||||
no_data_timeframe = 20
|
||||
|
||||
|
||||
@ -1 +0,0 @@
|
||||
../../../inputs.tf
|
||||
@ -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 = "${var.rds_config["delay"]}"
|
||||
no_data_timeframe = 20
|
||||
}
|
||||
43
cloud/aws/rds/README.md
Normal file
43
cloud/aws/rds/README.md
Normal file
@ -0,0 +1,43 @@
|
||||
AWS RDS Instance DataDog monitors
|
||||
=================================
|
||||
|
||||
How to use this module
|
||||
----------------------
|
||||
|
||||
```
|
||||
module "datadog-monitors-aws-rds" {
|
||||
source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/rds?ref={revision}"
|
||||
|
||||
message = "${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 |
|
||||
|
||||
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)
|
||||
47
cloud/aws/rds/inputs.tf
Normal file
47
cloud/aws/rds/inputs.tf
Normal file
@ -0,0 +1,47 @@
|
||||
# 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 = "*"
|
||||
}
|
||||
|
||||
# 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"
|
||||
}
|
||||
70
cloud/aws/rds/monitors-rds.tf
Normal file
70
cloud/aws/rds/monitors-rds.tf
Normal file
@ -0,0 +1,70 @@
|
||||
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 {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
|
||||
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 = true
|
||||
evaluation_delay = "${var.evaluation_delay}"
|
||||
notify_audit = false
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = false
|
||||
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 {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
|
||||
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 = true
|
||||
evaluation_delay = "${var.evaluation_delay}"
|
||||
notify_audit = false
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = false
|
||||
new_host_delay = "${var.evaluation_delay}"
|
||||
no_data_timeframe = 20
|
||||
|
||||
tags = ["env:${var.environment}", "resource:rds", "team:aws", "provider:aws"]
|
||||
}
|
||||
@ -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"
|
||||
}
|
||||
|
||||
29
middleware/apache/README.md
Normal file
29
middleware/apache/README.md
Normal file
@ -0,0 +1,29 @@
|
||||
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 |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| 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 |
|
||||
@ -1 +0,0 @@
|
||||
../../inputs.tf
|
||||
18
middleware/apache/inputs.tf
Normal file
18
middleware/apache/inputs.tf
Normal file
@ -0,0 +1,18 @@
|
||||
# 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
|
||||
|
||||
@ -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}}"
|
||||
resource "datadog_monitor" "datadog_apache_process" {
|
||||
name = "[${var.environment}] Can't connect to apache vhost status"
|
||||
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 = "\"apache.can_connect\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
|
||||
|
||||
thresholds = {
|
||||
ok = 1
|
||||
@ -12,10 +11,10 @@ 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"]}"
|
||||
renotify_interval = 60
|
||||
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
|
||||
@ -23,5 +22,5 @@ resource "datadog_monitor" "Apache_process" {
|
||||
require_full_window = true
|
||||
no_data_timeframe = 20
|
||||
|
||||
tags = ["*"]
|
||||
tags = ["env:${var.environment}", "resource:apache"]
|
||||
}
|
||||
|
||||
29
middleware/nginx/README.md
Normal file
29
middleware/nginx/README.md
Normal file
@ -0,0 +1,29 @@
|
||||
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 |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| 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 |
|
||||
@ -1 +0,0 @@
|
||||
../../inputs.tf
|
||||
18
middleware/nginx/inputs.tf
Normal file
18
middleware/nginx/inputs.tf
Normal file
@ -0,0 +1,18 @@
|
||||
# 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
|
||||
|
||||
@ -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}}"
|
||||
resource "datadog_monitor" "datadog_nginx_process" {
|
||||
name = "[${var.environment}] Can't connect to nginx vhost status"
|
||||
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 = "\"nginx.can_connect\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
|
||||
|
||||
thresholds = {
|
||||
ok = 1
|
||||
@ -12,10 +11,10 @@ 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"]}"
|
||||
renotify_interval = 60
|
||||
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
|
||||
@ -23,5 +22,5 @@ resource "datadog_monitor" "Nginx_process" {
|
||||
require_full_window = true
|
||||
no_data_timeframe = 20
|
||||
|
||||
tags = ["*"]
|
||||
tags = ["env:${var.environment}", "resource:nginx"]
|
||||
}
|
||||
|
||||
35
middleware/php-fpm/README.md
Normal file
35
middleware/php-fpm/README.md
Normal file
@ -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 |
|
||||
@ -1 +0,0 @@
|
||||
../../inputs.tf
|
||||
42
middleware/php-fpm/inputs.tf
Normal file
42
middleware/php-fpm/inputs.tf
Normal file
@ -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
|
||||
}
|
||||
@ -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 }"
|
||||
|
||||
thresholds {
|
||||
warning = "${var.php_fpm_busy_threshold["warning"]}"
|
||||
critical = "${var.php_fpm_busy_threshold["critical"]}"
|
||||
vars {
|
||||
filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_php_fpm:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
|
||||
}
|
||||
}
|
||||
|
||||
notify_no_data = "${var.apache_nginx_fpm_config["notify_no_data"]}"
|
||||
evaluation_delay = "${var.apache_nginx_fpm_config["delay"]}"
|
||||
new_host_delay = "${var.apache_nginx_fpm_config["delay"]}"
|
||||
renotify_interval = 60
|
||||
resource "datadog_monitor" "datadog_php_fpm_process_idle" {
|
||||
name = "[${var.environment}] php_fpm busy worker {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
|
||||
message = "${var.message}"
|
||||
|
||||
type = "metric alert"
|
||||
|
||||
query = <<EOF
|
||||
avg(last_10m): (
|
||||
avg:php_fpm.processes.active{${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 = "${var.php_fpm_busy_threshold_critical}"
|
||||
}
|
||||
|
||||
notify_no_data = true
|
||||
evaluation_delay = "${var.evaluation_delay_metric}"
|
||||
new_host_delay = "${var.evaluation_delay_metric}"
|
||||
notify_audit = false
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = true
|
||||
renotify_interval = 0
|
||||
no_data_timeframe = 20
|
||||
|
||||
tags = ["*"]
|
||||
tags = ["env:${var.environment}", "resource: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${var.ho_escalation_group}\n{{/is_warning_recovery}}"
|
||||
resource "datadog_monitor" "datadog_fpm_process" {
|
||||
name = "[${var.environment}] Can't connect to php-fpm"
|
||||
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 = "${var.dd_nginx == "enabled" ? 1 : 0 }"
|
||||
query = "\"php_fpm.can_ping\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"env:${var.environment}\").by(\"host\",\"port\").last(6).count_by_status()"
|
||||
|
||||
thresholds = {
|
||||
ok = 1
|
||||
@ -40,10 +51,10 @@ 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 = "${var.apache_nginx_fpm_config["delay"]}"
|
||||
renotify_interval = 60
|
||||
notify_no_data = true
|
||||
evaluation_delay = "${var.evaluation_delay_service}"
|
||||
new_host_delay = "${var.evaluation_delay_service}"
|
||||
renotify_interval = 0
|
||||
notify_audit = false
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
@ -51,5 +62,5 @@ resource "datadog_monitor" "FPM_process" {
|
||||
require_full_window = true
|
||||
no_data_timeframe = 20
|
||||
|
||||
tags = ["*"]
|
||||
tags = ["env:${var.environment}", "resource:php-fpm"]
|
||||
}
|
||||
|
||||
40
system/generic/README.md
Normal file
40
system/generic/README.md
Normal file
@ -0,0 +1,40 @@
|
||||
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 |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| 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 |
|
||||
@ -1 +0,0 @@
|
||||
../../inputs.tf
|
||||
72
system/generic/inputs.tf
Normal file
72
system/generic/inputs.tf
Normal file
@ -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 "cpu_high_timeframe" {
|
||||
description = "CPU high timeframe"
|
||||
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
|
||||
}
|
||||
@ -1,24 +0,0 @@
|
||||
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}"
|
||||
|
||||
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} > ${var.dd_custom_cpu["critical_threshold"]}"
|
||||
type = "query alert"
|
||||
|
||||
thresholds = {
|
||||
warning = "${var.dd_custom_cpu["warning_threshold"]}"
|
||||
critical = "${var.dd_custom_cpu["critical_threshold"]}"
|
||||
}
|
||||
|
||||
notify_no_data = "${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
|
||||
}
|
||||
131
system/generic/monitors-system.tf
Normal file
131
system/generic/monitors-system.tf
Normal file
@ -0,0 +1,131 @@
|
||||
data "template_file" "filter" {
|
||||
template = "$${filter}"
|
||||
|
||||
vars {
|
||||
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 = "[${var.environment}] CPU usage {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
|
||||
message = "${var.message}"
|
||||
|
||||
query = <<EOF
|
||||
min(${var.cpu_high_timeframe}): (
|
||||
100 - avg:system.cpu.idle{${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", "resource:cpu"]
|
||||
|
||||
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
|
||||
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
|
||||
) < ${var.free_disk_space_threshold_critical}
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
|
||||
thresholds {
|
||||
warning = "${var.free_disk_space_threshold_warning}"
|
||||
critical = "${var.free_disk_space_threshold_critical}"
|
||||
}
|
||||
|
||||
tags = ["env:${var.environment}", "type:system", "resource:disk"]
|
||||
|
||||
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
|
||||
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
|
||||
) < ${var.free_disk_inodes_threshold_critical}
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
|
||||
thresholds {
|
||||
warning = "${var.free_disk_inodes_threshold_warning}"
|
||||
critical = "${var.free_disk_inodes_threshold_critical}"
|
||||
}
|
||||
|
||||
tags = ["env:${var.environment}", "type:system", "resource:disk"]
|
||||
|
||||
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 = "[${var.environment}] Free memory {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
|
||||
message = "${var.message}"
|
||||
|
||||
query = <<EOF
|
||||
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
|
||||
) < ${var.free_memory_threshold_critical}
|
||||
EOF
|
||||
|
||||
type = "metric alert"
|
||||
|
||||
thresholds {
|
||||
warning = "${var.free_memory_threshold_warning}"
|
||||
critical = "${var.free_memory_threshold_critical}"
|
||||
}
|
||||
|
||||
tags = ["env:${var.environment}", "type:system", "resource:memory"]
|
||||
|
||||
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
|
||||
}
|
||||
@ -1 +0,0 @@
|
||||
../../inputs.tf
|
||||
@ -1,226 +0,0 @@
|
||||
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}"
|
||||
|
||||
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}"
|
||||
}
|
||||
|
||||
tags = ["*"]
|
||||
|
||||
notify_no_data = "${var.linux_basics_config["notify_no_data"]}"
|
||||
evaluation_delay = "${var.linux_basics_config["delay"]}"
|
||||
new_host_delay = "${var.linux_basics_config["delay"]}"
|
||||
renotify_interval = 60
|
||||
notify_audit = false
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = true
|
||||
no_data_timeframe = 20
|
||||
}
|
||||
|
||||
resource "datadog_monitor" "cpu_95_5min" {
|
||||
name = "[${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} > ${var.cpu_5_critical}"
|
||||
type = "query alert"
|
||||
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
|
||||
|
||||
thresholds {
|
||||
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"]}"
|
||||
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_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:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 5"
|
||||
type = "query alert"
|
||||
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
|
||||
|
||||
thresholds {
|
||||
critical = 5
|
||||
}
|
||||
|
||||
tags = ["*"]
|
||||
|
||||
notify_no_data = "${var.linux_basics_config["notify_no_data"]}"
|
||||
evaluation_delay = "${var.linux_basics_config["delay"]}"
|
||||
new_host_delay = "${var.linux_basics_config["delay"]}"
|
||||
renotify_interval = 60
|
||||
notify_audit = false
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = true
|
||||
no_data_timeframe = 20
|
||||
}
|
||||
|
||||
resource "datadog_monitor" "datadog_free_disk_space_10" {
|
||||
name = "[${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"
|
||||
type = "query alert"
|
||||
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
|
||||
|
||||
thresholds {
|
||||
warning = 20
|
||||
critical = 10
|
||||
}
|
||||
|
||||
tags = ["*"]
|
||||
|
||||
notify_no_data = "${var.linux_basics_config["notify_no_data"]}"
|
||||
evaluation_delay = "${var.linux_basics_config["delay"]}"
|
||||
new_host_delay = "${var.linux_basics_config["delay"]}"
|
||||
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 = ["*"]
|
||||
|
||||
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 = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
|
||||
|
||||
thresholds {
|
||||
warning = 20
|
||||
critical = 10
|
||||
}
|
||||
|
||||
tags = ["*"]
|
||||
|
||||
notify_no_data = "${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_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_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 = ["*"]
|
||||
|
||||
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
|
||||
# }
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user