wbyc/terraform-datadog-old-monitors
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

MON-96 - Apply best practice and recommandations

Browse Source
This commit is contained in:
Alexandre Gaillet 2018-02-21 16:18:07 +01:00
parent 2323db0639
commit 8f9bf61d19
3 changed files with 10 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cloud/aws/rds/README.md
View File

@ -34,8 +34,6 @@ Inputs
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| message | Message sent when an alert is triggered | string | - | yes |
| notify_no_data | Enable 'No Data' alert | string | `true` | no |
| renotify_interval | The number of minutes after the last notification before a monitor will re-notify on the current status | string | `60` | no |
Related documentation
---------------------

10
cloud/aws/rds/inputs.tf
View File

@ -5,21 +5,11 @@ variable "environment" {
}
# Global DataDog
variable "notify_no_data" {
description = "Enable 'No Data' alert"
default = true
}
variable "evaluation_delay" {
description = "Delay in seconds for the metric evaluation"
default = 600
}
variable "renotify_interval" {
description = "The number of minutes after the last notification before a monitor will re-notify on the current status"
default = 60
}
variable "message" {
description = "Message sent when an alert is triggered"
}

15
cloud/aws/rds/monitors-rds.tf
View File

@ -8,10 +8,11 @@ data "template_file" "filter" {
### RDS instance CPU monitor ###
resource "datadog_monitor" "rds_cpu_90_15min" {
name = "[${var.environment}] RDS instance CPU high > ${var.cpu_threshold_critical}% for 15 min on {{host.identifier}}"
name = "[${var.environment}] RDS instance CPU high {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
message = "${var.message}"
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
@ -23,9 +24,8 @@ EOF
critical = "${var.cpu_threshold_critical}"
}
notify_no_data = "${var.notify_no_data}"
notify_no_data = true
evaluation_delay = "${var.evaluation_delay}"
renotify_interval = "${var.renotify_interval}"
notify_audit = false
timeout_h = 0
include_tags = true
@ -39,13 +39,15 @@ EOF
### RDS instance free space monitor ###
resource "datadog_monitor" "rds_free_space_low" {
name = "[${var.environment}] RDS instance free space < ${var.diskspace_threshold_critical}% on {{host.identifier}}"
name = "[${var.environment}] RDS instance free space {{comparator}} {{#is_alert}}{{threshold}}%{{/is_alert}}{{#is_warning}}{{warn_threshold}}%{{/is_warning}} ({{value}}%)"
message = "${var.message}"
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} / avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
) < ${var.diskspace_threshold_critical}
EOF
@ -54,9 +56,8 @@ EOF
critical = "${var.diskspace_threshold_critical}"
}
notify_no_data = "${var.notify_no_data}"
notify_no_data = true
evaluation_delay = "${var.evaluation_delay}"
renotify_interval = "${var.renotify_interval}"
notify_audit = false
timeout_h = 0
include_tags = true