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

Merged in MON-96-update-alb-monitors-with-new-inputs-best-practice (pull request #64)

Browse Source 
MON-96 - Update ALB monitors with inputs best practice

Approved-by: Quentin Manfroi <quentin.manfroi@yahoo.fr>
Approved-by: Alexandre Gaillet <alexandre.gaillet@fr.clara.net>
This commit is contained in:
Alexandre Gaillet 2018-03-22 19:38:37 +00:00 committed by Quentin Manfroi
commit a8fc9279ab
3 changed files with 125 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
cloud/aws/alb/README.md
View File

@ -30,21 +30,33 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| alb_no_healthy_instances_message | Custom message for ALB no healthy instances monitor | string | `` | no |
| alb_no_healthy_instances_silenced | Groups to mute for ALB no healthy instances monitor | map | `<map>` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| environment | Architecture environment | string | - | yes |
| 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 | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| httpcode_elb_4xx_message | Custom message for ALB httpcode 4xx monitor | string | `` | no |
| httpcode_elb_4xx_silenced | Groups to mute for ALB httpcode 4xx monitor | map | `<map>` | no |
| httpcode_elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `80` | no |
| httpcode_elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `60` | no |
| httpcode_elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `80` | no |
| httpcode_elb_5xx_message | Custom message for ALB httpcode 5xx monitor | string | `` | no |
| httpcode_elb_5xx_silenced | Groups to mute for ALB httpcode 5xx monitor | map | `<map>` | no |
| httpcode_elb_5xx_threshold_critical | loadbalancer 5xxcritical threshold in percentage | string | `80` | no |
| httpcode_elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `60` | no |
| httpcode_target_4xx_message | Custom message for ALB target httpcode 4xx monitor | string | `` | no |
| httpcode_target_4xx_silenced | Groups to mute for ALB target httpcode 4xx monitor | map | `<map>` | no |
| httpcode_target_4xx_threshold_critical | target 4xx critical threshold in percentage | string | `80` | no |
| httpcode_target_4xx_threshold_warning | target 4xx warning threshold in percentage | string | `60` | no |
| httpcode_target_5xx_message | Custom message for ALB target httpcode 5xx monitor | string | `` | no |
| httpcode_target_5xx_silenced | Groups to mute for ALB target httpcode 5xx monitor | map | `<map>` | no |
| httpcode_target_5xx_threshold_critical | target 5xx critical threshold in percentage | string | `80` | no |
| httpcode_target_5xx_threshold_warning | target 5xx warning threshold in percentage | string | `60` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
| latency_message | Custom message for ALB latency monitor | string | `` | no |
| latency_silenced | Groups to mute for ALB latency monitor | map | `<map>` | no |
| latency_threshold_critical | latency critical threshold in milliseconds | string | `1000` | no |
| latency_threshold_warning | latency warning threshold in milliseconds | string | `500` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
Related documentation
---------------------

72
cloud/aws/alb/inputs.tf
View File

@ -26,6 +26,30 @@ variable "delay" {
# Datadog monitors variables
variable "alb_no_healthy_instances_silenced" {
description = "Groups to mute for ALB no healthy instances monitor"
type = "map"
default = {}
}
variable "alb_no_healthy_instances_message" {
description = "Custom message for ALB no healthy instances monitor"
type = "string"
default = ""
}
variable "latency_silenced" {
description = "Groups to mute for ALB latency monitor"
type = "map"
default = {}
}
variable "latency_message" {
description = "Custom message for ALB latency monitor"
type = "string"
default = ""
}
variable "latency_threshold_critical" {
default = 1000
description = "latency critical threshold in milliseconds"
@ -36,6 +60,18 @@ variable "latency_threshold_warning" {
description = "latency warning threshold in milliseconds"
}
variable "httpcode_elb_4xx_silenced" {
description = "Groups to mute for ALB httpcode 4xx monitor"
type = "map"
default = {}
}
variable "httpcode_elb_4xx_message" {
description = "Custom message for ALB httpcode 4xx monitor"
type = "string"
default = ""
}
variable "httpcode_elb_4xx_threshold_critical" {
default = 80
description = "loadbalancer 4xx critical threshold in percentage"
@ -46,6 +82,18 @@ variable "httpcode_elb_4xx_threshold_warning" {
description = "loadbalancer 4xx warning threshold in percentage"
}
variable "httpcode_target_4xx_silenced" {
description = "Groups to mute for ALB target httpcode 4xx monitor"
type = "map"
default = {}
}
variable "httpcode_target_4xx_message" {
description = "Custom message for ALB target httpcode 4xx monitor"
type = "string"
default = ""
}
variable "httpcode_target_4xx_threshold_critical" {
default = 80
description = "target 4xx critical threshold in percentage"
@ -56,6 +104,18 @@ variable "httpcode_target_4xx_threshold_warning" {
description = "target 4xx warning threshold in percentage"
}
variable "httpcode_elb_5xx_silenced" {
description = "Groups to mute for ALB httpcode 5xx monitor"
type = "map"
default = {}
}
variable "httpcode_elb_5xx_message" {
description = "Custom message for ALB httpcode 5xx monitor"
type = "string"
default = ""
}
variable "httpcode_elb_5xx_threshold_critical" {
default = 80
description = "loadbalancer 5xxcritical threshold in percentage"
@ -66,6 +126,18 @@ variable "httpcode_elb_5xx_threshold_warning" {
description = "loadbalancer 5xx warning threshold in percentage"
}
variable "httpcode_target_5xx_silenced" {
description = "Groups to mute for ALB target httpcode 5xx monitor"
type = "map"
default = {}
}
variable "httpcode_target_5xx_message" {
description = "Custom message for ALB target httpcode 5xx monitor"
type = "string"
default = ""
}
variable "httpcode_target_5xx_threshold_critical" {
default = 80
description = "target 5xx critical threshold in percentage"

56
cloud/aws/alb/monitors-alb.tf
View File

@ -11,7 +11,7 @@ data "template_file" "filter" {
resource "datadog_monitor" "ALB_no_healthy_instances" {
name = "[${var.environment}] ALB no healthy instances"
type = "metric alert"
message = "${var.message}"
message = "${coalesce(var.alb_no_healthy_instances_message, var.message)}"
query = <<EOF
min(last_1m): (
@ -32,13 +32,15 @@ resource "datadog_monitor" "ALB_no_healthy_instances" {
timeout_h = 0
include_tags = true
silenced = "${var.alb_no_healthy_instances_silenced}"
tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "ALB_latency" {
name = "[${var.environment}] ALB latency {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
type = "metric alert"
message = "${var.message}"
message = "${coalesce(var.latency_message, var.message)}"
query = <<EOF
min(last_5m): (
@ -60,18 +62,22 @@ resource "datadog_monitor" "ALB_latency" {
timeout_h = 0
include_tags = true
silenced = "${var.latency_silenced}"
tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "ALB_httpcode_elb_5xx" {
name = "[${var.environment}] ALB HTTP code 5xx {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
type = "metric alert"
message = "${var.message}"
message = "${coalesce(var.httpcode_elb_5xx_message, var.message)}"
query = <<EOF
sum(last_5m): (
avg:aws.applicationelb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() * 100
default(
avg:aws.applicationelb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count(),
0) * 100
) > ${var.httpcode_elb_5xx_threshold_critical}
EOF
@ -86,21 +92,25 @@ resource "datadog_monitor" "ALB_httpcode_elb_5xx" {
notify_no_data = false
renotify_interval = 0
require_full_window = false
timeout_h = 1
timeout_h = 0
include_tags = true
silenced = "${var.httpcode_elb_5xx_silenced}"
tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "ALB_httpcode_elb_4xx" {
name = "[${var.environment}] ALB HTTP code 4xx {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
type = "metric alert"
message = "${var.message}"
message = "${coalesce(var.httpcode_elb_4xx_message, var.message)}"
query = <<EOF
sum(last_5m): (
avg:aws.applicationelb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() * 100
default(
avg:aws.applicationelb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count(),
0) * 100
) > ${var.httpcode_elb_4xx_threshold_critical}
EOF
@ -115,21 +125,25 @@ resource "datadog_monitor" "ALB_httpcode_elb_4xx" {
notify_no_data = false
renotify_interval = 0
require_full_window = false
timeout_h = 1
timeout_h = 0
include_tags = true
silenced = "${var.httpcode_elb_4xx_silenced}"
tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "ALB_httpcode_target_5xx" {
name = "[${var.environment}] ALB target HTTP code 5xx {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
type = "metric alert"
message = "${var.message}"
message = "${coalesce(var.httpcode_target_5xx_message, var.message)}"
query = <<EOF
sum(last_5m): (
avg:aws.applicationelb.httpcode_target_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() * 100
default(
avg:aws.applicationelb.httpcode_target_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count(),
0) * 100
) > ${var.httpcode_target_5xx_threshold_critical}
EOF
@ -144,21 +158,25 @@ resource "datadog_monitor" "ALB_httpcode_target_5xx" {
notify_no_data = false
renotify_interval = 0
require_full_window = false
timeout_h = 1
timeout_h = 0
include_tags = true
silenced = "${var.httpcode_target_5xx_silenced}"
tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "ALB_httpcode_target_4xx" {
name = "[${var.environment}] ALB target HTTP code 4xx {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
type = "metric alert"
message = "${var.message}"
message = "${coalesce(var.httpcode_target_4xx_message, var.message)}"
query = <<EOF
sum(last_5m): (
avg:aws.applicationelb.httpcode_target_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() * 100
default(
avg:aws.applicationelb.httpcode_target_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
avg:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count(),
0) * 100
) > ${var.httpcode_target_4xx_threshold_critical}
EOF
@ -173,8 +191,10 @@ resource "datadog_monitor" "ALB_httpcode_target_4xx" {
notify_no_data = false
renotify_interval = 0
require_full_window = false
timeout_h = 1
timeout_h = 0
include_tags = true
silenced = "${var.httpcode_target_4xx_silenced}"
tags = ["env:${var.environment}", "resource:alb", "team:aws", "provider:aws"]
}