MON-96 - Apply conventions and update middleware directory

This commit is contained in:
Alexandre Gaillet 2018-02-21 16:55:06 +01:00
parent 8f9bf61d19
commit febc38eec7
10 changed files with 230 additions and 44 deletions

View File

@ -42,14 +42,15 @@ EOF
### Elasticsearch cluster free storage space monitor ###
resource "datadog_monitor" "es_free_space_low" {
name = "[${var.environment}] ElasticSearch cluster free storage space < ${var.diskspace_threshold_critical}%"
name = "[${var.environment}] ElasticSearch cluster free storage space {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
message = "${var.message}"
type = "query alert"
query = <<EOF
avg(last_15m): (
avg:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} / (${var.es_cluster_volume_size}*1000) * 100
avg:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
(${var.es_cluster_volume_size}*1000) * 100
) < ${var.diskspace_threshold_critical}
EOF
@ -74,7 +75,7 @@ EOF
### Elasticsearch cluster CPU monitor ###
resource "datadog_monitor" "es_cpu_90_15min" {
name = "[${var.environment}] ElasticSearch cluster CPU high > ${var.cpu_threshold_critical}%"
name = "[${var.environment}] ElasticSearch cluster CPU high {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
message = "${var.message}"
type = "query alert"

View File

@ -0,0 +1,30 @@
Apache Middleware DataDog monitors
==================================
How to use this module
----------------------
```
module "datadog-monitors-apache-middleware" {
source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//middleware/apache?ref={revision}"
message = "${module.datadog-message-alerting.alerting-message}"
environment = "${var.environment}"
}
```
Purpose
-------
Creates a DataDog monitors with the following checks :
* Apache process
Inputs
------
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| dd_apache | | string | `disabled` | no |
| environment | Architecture Environment | string | - | yes |
| evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
| message | Message sent when an alert is triggered | string | - | yes |

View File

@ -1 +0,0 @@
../../inputs.tf

View File

@ -0,0 +1,21 @@
# Global Terraform
variable "environment" {
description = "Architecture Environment"
type = "string"
}
# Global DataDog
variable "evaluation_delay" {
description = "Delay in seconds for the metric evaluation"
default = 15
}
variable "message" {
description = "Message sent when an alert is triggered"
}
# Apache Middleware specific
variable "dd_apache" {
default = "disabled"
}

View File

@ -1,10 +1,9 @@
resource "datadog_monitor" "Apache_process" {
name = "[${var.env}] Apache process is down on {{host.name}}"
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
name = "[${var.environment}] Apache process is down on {{host.name}}"
message = "${var.message}"
type = "service check"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
count = "${var.dd_apache == "enabled" ? 1 : 0 }"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
thresholds = {
ok = 1
@ -12,9 +11,9 @@ resource "datadog_monitor" "Apache_process" {
critical = 4
}
notify_no_data = "${var.apache_nginx_fpm_config["notify_no_data"]}"
evaluation_delay = "${var.apache_nginx_fpm_config["delay"]}"
new_host_delay = "${var.apache_nginx_fpm_config["delay"]}"
notify_no_data = false
evaluation_delay = "${var.evaluation_delay}"
new_host_delay = "${var.evaluation_delay}"
renotify_interval = 60
notify_audit = false
timeout_h = 0
@ -23,5 +22,5 @@ resource "datadog_monitor" "Apache_process" {
require_full_window = true
no_data_timeframe = 20
tags = ["env:${var.env}", "type:apache"]
tags = ["env:${var.environment}", "type:apache"]
}

View File

@ -0,0 +1,30 @@
Nginx Middleware DataDog monitors
=================================
How to use this module
----------------------
```
module "datadog-monitors-nginx-middleware" {
source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//middleware/nginx?ref={revision}"
message = "${module.datadog-message-alerting.alerting-message}"
environment = "${var.environment}"
}
```
Purpose
-------
Creates a DataDog monitors with the following checks :
* Nginx process
Inputs
------
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| dd_nginx | | string | `disabled` | no |
| environment | Architecture Environment | string | - | yes |
| evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
| message | Message sent when an alert is triggered | string | - | yes |

View File

@ -1 +0,0 @@
../../inputs.tf

View File

@ -0,0 +1,21 @@
# Global Terraform
variable "environment" {
description = "Architecture Environment"
type = "string"
}
# Global DataDog
variable "evaluation_delay" {
description = "Delay in seconds for the metric evaluation"
default = 15
}
variable "message" {
description = "Message sent when an alert is triggered"
}
# Nginx Middleware specific
variable "dd_nginx" {
default = "disabled"
}

View File

@ -1,10 +1,9 @@
resource "datadog_monitor" "Nginx_process" {
name = "[${var.env}] Nginx process is down on {{host.name}}"
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
name = "[${var.environment}] Nginx process is down on {{host.name}}"
message = "${var.message}"
type = "service check"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
count = "${var.dd_nginx == "enabled" ? 1 : 0 }"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
thresholds = {
ok = 1
@ -12,9 +11,9 @@ resource "datadog_monitor" "Nginx_process" {
critical = 4
}
notify_no_data = "${var.apache_nginx_fpm_config["notify_no_data"]}"
evaluation_delay = "${var.apache_nginx_fpm_config["delay"]}"
new_host_delay = "${var.apache_nginx_fpm_config["delay"]}"
notify_no_data = false
evaluation_delay = "${var.evaluation_delay}"
new_host_delay = "${var.evaluation_delay}"
renotify_interval = 60
notify_audit = false
timeout_h = 0
@ -23,5 +22,5 @@ resource "datadog_monitor" "Nginx_process" {
require_full_window = true
no_data_timeframe = 20
tags = ["env:${var.env}", "type:nginx"]
tags = ["env:${var.environment}", "type:nginx"]
}

View 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 |

View File

@ -1 +0,0 @@
../../inputs.tf

View 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
}

View File

@ -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 = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${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 = "${var.apache_nginx_fpm_config["delay"]}"
renotify_interval = 60
resource "datadog_monitor" "php-fpm_process_idle" {
name = "[${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 = "${var.php_fpm_busy_threshold_critical}"
}
notify_no_data = false
evaluation_delay = "${var.evaluation_delay_metric}"
new_host_delay = "${var.evaluation_delay_metric}"
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
renotify_interval = 0
no_data_timeframe = 20
tags = ["env:${var.env}", "type:php-fpm"]
tags = ["env:${var.environment}", "type:php-fpm"]
}
resource "datadog_monitor" "FPM_process" {
name = "[${var.env}] FPM process is down on {{host.name}}"
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
name = "[${var.environment}] FPM process is down on {{host.name}}"
message = "${var.message}"
type = "service check"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
count = "${var.dd_nginx == "enabled" ? 1 : 0 }"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.environment}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
thresholds = {
ok = 1
@ -40,9 +51,9 @@ resource "datadog_monitor" "FPM_process" {
critical = 4
}
notify_no_data = "${var.apache_nginx_fpm_config["notify_no_data"]}"
evaluation_delay = "${var.apache_nginx_fpm_config["delay"]}"
new_host_delay = "${var.apache_nginx_fpm_config["delay"]}"
notify_no_data = true
evaluation_delay = "${var.evaluation_delay_service}"
new_host_delay = "${var.evaluation_delay_service}"
renotify_interval = 60
notify_audit = false
timeout_h = 0
@ -51,5 +62,5 @@ resource "datadog_monitor" "FPM_process" {
require_full_window = true
no_data_timeframe = 20
tags = ["env:${var.env}", "type:php-fpm"]
tags = ["env:${var.environment}", "type:php-fpm"]
}