MON-96 Update basics RDS monitors

This commit is contained in:
Guillaume Kerivel 2018-01-16 16:08:45 +01:00 committed by Alexandre Gaillet
parent 92833feff7
commit 86b999d7f3
5 changed files with 171 additions and 55 deletions

View File

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

View File

@ -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
}

45
cloud/aws/rds/README.md Normal file
View File

@ -0,0 +1,45 @@
AWS RDS Instance DataDog monitors
=================================
How to use this module
----------------------
```
module "datadog-monitors-aws-rds" {
source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git//cloud/aws/rds?ref={revision}"
message = "${module.datadog-message-alerting.alerting-message}"
environment = "${var.environment}"
}
```
Purpose
-------
Creates a DataDog monitors with the following checks :
* CPU High
* Free disk space low
Inputs
------
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
| cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
| diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |
| diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no |
| environment | Architecture Environment | string | - | yes |
| evaluation_delay | Delay in seconds for the metric evaluation | string | `600` | no |
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| message | Message sent when an alert is triggered | string | - | yes |
| notify_no_data | Enable 'No Data' alert | string | `true` | no |
| renotify_interval | The number of minutes after the last notification before a monitor will re-notify on the current status | string | `60` | no |
Related documentation
---------------------
DataDog documentation: [https://docs.datadoghq.com/integrations/amazon_rds/](https://docs.datadoghq.com/integrations/amazon_rds/)
AWS RDS Instance metrics documentation: [https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html](https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/rds-metricscollected.html)

57
cloud/aws/rds/inputs.tf Normal file
View File

@ -0,0 +1,57 @@
# Global Terraform
variable "environment" {
description = "Architecture Environment"
type = "string"
}
# Global DataDog
variable "notify_no_data" {
description = "Enable 'No Data' alert"
default = true
}
variable "evaluation_delay" {
description = "Delay in seconds for the metric evaluation"
default = 600
}
variable "renotify_interval" {
description = "The number of minutes after the last notification before a monitor will re-notify on the current status"
default = 60
}
variable "message" {
description = "Message sent when an alert is triggered"
}
variable "filter_tags_use_defaults" {
description = "Use default filter tags convention"
default = "true"
}
variable "filter_tags_custom" {
description = "Tags used for custom filtering when filter_tags_use_defaults is false"
default = "*"
}
# AWS RDS instance specific
variable "cpu_threshold_warning" {
description = "CPU usage in percent (warning threshold)"
default = "80"
}
variable "cpu_threshold_critical" {
description = "CPU usage in percent (critical threshold)"
default = "90"
}
variable "diskspace_threshold_warning" {
description = "Disk free space in percent (warning threshold)"
default = "20"
}
variable "diskspace_threshold_critical" {
description = "Disk free space in percent (critical threshold)"
default = "10"
}

View File

@ -0,0 +1,69 @@
data "template_file" "filter" {
template = "$${filter}"
vars {
filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_rds:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
}
}
### RDS instance CPU monitor ###
resource "datadog_monitor" "rds_cpu_90_15min" {
name = "[${var.environment}] RDS instance CPU high > ${var.cpu_threshold_critical}% for 15 min on {{host.identifier}}"
message = "${var.message}"
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
) > ${var.cpu_threshold_critical}
EOF
thresholds {
warning = "${var.cpu_threshold_warning}"
critical = "${var.cpu_threshold_critical}"
}
notify_no_data = "${var.notify_no_data}"
evaluation_delay = "${var.evaluation_delay}"
renotify_interval = "${var.renotify_interval}"
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.evaluation_delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}", "resource:rds", "team:aws", "provider:aws"]
}
### RDS instance free space monitor ###
resource "datadog_monitor" "rds_free_space_low" {
name = "[${var.environment}] RDS instance free space < ${var.diskspace_threshold_critical}% on {{host.identifier}}"
message = "${var.message}"
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} / avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
) < ${var.diskspace_threshold_critical}
EOF
thresholds {
warning = "${var.diskspace_threshold_warning}"
critical = "${var.diskspace_threshold_critical}"
}
notify_no_data = "${var.notify_no_data}"
evaluation_delay = "${var.evaluation_delay}"
renotify_interval = "${var.renotify_interval}"
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.evaluation_delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}", "resource:rds", "team:aws", "provider:aws"]
}