MON-114 add kubernetes cluster monitors
This commit is contained in:
parent
2df9ff2706
commit
c2c98581fa
@ -77,6 +77,7 @@ The `//` is very important, it's a terraform specific syntax used to separate gi
|
||||
- [caas](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/)
|
||||
- [kubernetes](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/)
|
||||
- [ark](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/ark/)
|
||||
- [cluster](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/cluster/)
|
||||
- [ingress](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/ingress/)
|
||||
- [vts](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/caas/kubernetes/ingress/vts/)
|
||||
- [cloud](https://git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors/tree/master/cloud/)
|
||||
|
||||
48
caas/kubernetes/cluster/README.md
Normal file
48
caas/kubernetes/cluster/README.md
Normal file
@ -0,0 +1,48 @@
|
||||
# CAAS KUBERNETES CLUSTER DataDog monitors
|
||||
|
||||
## How to use this module
|
||||
|
||||
```
|
||||
module "datadog-monitors-caas-kubernetes-cluster" {
|
||||
source = "git::ssh://git@git.fr.clara.net/claranet/pt-monitoring/projects/datadog/terraform/monitors.git//caas/kubernetes/cluster?ref={revision}"
|
||||
|
||||
environment = "${var.environment}"
|
||||
message = "${module.datadog-message-alerting.alerting-message}"
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
## Purpose
|
||||
|
||||
Creates DataDog monitors with the following checks:
|
||||
|
||||
- Kubernetes API server does not respond
|
||||
|
||||
## Inputs
|
||||
|
||||
| Name | Description | Type | Default | Required |
|
||||
|------|-------------|:----:|:-----:|:-----:|
|
||||
| apiserver\_enabled | Flag to enable API server monitor | string | `"true"` | no |
|
||||
| apiserver\_extra\_tags | Extra tags for API server monitor | list | `[]` | no |
|
||||
| apiserver\_message | Custom message for API server monitor | string | `""` | no |
|
||||
| apiserver\_silenced | Groups to mute for API server monitor | map | `{}` | no |
|
||||
| apiserver\_threshold\_warning | API server monitor (warning threshold) | string | `"3"` | no |
|
||||
| environment | Architecture environment | string | n/a | yes |
|
||||
| evaluation\_delay | 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\_custom\_excluded | Tags excluded 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 a monitor is triggered | string | n/a | yes |
|
||||
| new\_host\_delay | Delay in seconds before monitor new resource | string | `"300"` | no |
|
||||
|
||||
## Outputs
|
||||
|
||||
| Name | Description |
|
||||
|------|-------------|
|
||||
| apiserver\_id | id for monitor apiserver |
|
||||
|
||||
## Related documentation
|
||||
|
||||
* [Datadog metrics](https://docs.datadoghq.com/agent/kubernetes/metrics/)
|
||||
* [Datadog documentation](https://docs.datadoghq.com/integrations/kubernetes/)
|
||||
* [Datadog Blog](https://www.datadoghq.com/blog/monitor-kubernetes-docker/)
|
||||
66
caas/kubernetes/cluster/inputs.tf
Normal file
66
caas/kubernetes/cluster/inputs.tf
Normal file
@ -0,0 +1,66 @@
|
||||
# Datadog global variables
|
||||
|
||||
variable "environment" {
|
||||
description = "Architecture environment"
|
||||
}
|
||||
|
||||
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 = "*"
|
||||
}
|
||||
|
||||
variable "filter_tags_custom_excluded" {
|
||||
description = "Tags excluded for custom filtering when filter_tags_use_defaults is false"
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "message" {
|
||||
description = "Message sent when a monitor is triggered"
|
||||
}
|
||||
|
||||
variable "evaluation_delay" {
|
||||
description = "Delay in seconds for the metric evaluation"
|
||||
default = 15
|
||||
}
|
||||
|
||||
variable "new_host_delay" {
|
||||
description = "Delay in seconds before monitor new resource"
|
||||
default = 300
|
||||
}
|
||||
|
||||
# Datadog monitors variables
|
||||
|
||||
variable "apiserver_silenced" {
|
||||
description = "Groups to mute for API server monitor"
|
||||
type = "map"
|
||||
default = {}
|
||||
}
|
||||
|
||||
variable "apiserver_enabled" {
|
||||
description = "Flag to enable API server monitor"
|
||||
type = "string"
|
||||
default = "true"
|
||||
}
|
||||
|
||||
variable "apiserver_extra_tags" {
|
||||
description = "Extra tags for API server monitor"
|
||||
type = "list"
|
||||
default = []
|
||||
}
|
||||
|
||||
variable "apiserver_message" {
|
||||
description = "Custom message for API server monitor"
|
||||
type = "string"
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "apiserver_threshold_warning" {
|
||||
description = "API server monitor (warning threshold)"
|
||||
type = "string"
|
||||
default = 3
|
||||
}
|
||||
9
caas/kubernetes/cluster/modules.tf
Normal file
9
caas/kubernetes/cluster/modules.tf
Normal file
@ -0,0 +1,9 @@
|
||||
module "filter-tags" {
|
||||
source = "../../../common/filter-tags"
|
||||
|
||||
environment = "${var.environment}"
|
||||
resource = "kubernetes"
|
||||
filter_tags_use_defaults = "${var.filter_tags_use_defaults}"
|
||||
filter_tags_custom = "${var.filter_tags_custom}"
|
||||
filter_tags_custom_excluded = "${var.filter_tags_custom_excluded}"
|
||||
}
|
||||
29
caas/kubernetes/cluster/monitors-k8s-cluster.tf
Normal file
29
caas/kubernetes/cluster/monitors-k8s-cluster.tf
Normal file
@ -0,0 +1,29 @@
|
||||
resource "datadog_monitor" "apiserver" {
|
||||
count = "${var.apiserver_enabled == "true" ? 1 : 0}"
|
||||
name = "[${var.environment}] Kubernetes API server does not respond"
|
||||
message = "${coalesce(var.apiserver_message, var.message)}"
|
||||
|
||||
type = "service check"
|
||||
|
||||
query = <<EOQ
|
||||
"kube_apiserver_controlplane.up"${module.filter-tags.service_check}.by("apiserver_name").last(6).count_by_status()
|
||||
EOQ
|
||||
|
||||
thresholds = {
|
||||
warning = "${var.apiserver_threshold_warning}"
|
||||
critical = 5
|
||||
}
|
||||
|
||||
new_host_delay = "${var.new_host_delay}"
|
||||
notify_no_data = true
|
||||
renotify_interval = 0
|
||||
notify_audit = false
|
||||
timeout_h = 0
|
||||
include_tags = true
|
||||
locked = false
|
||||
require_full_window = true
|
||||
|
||||
silenced = "${var.apiserver_silenced}"
|
||||
|
||||
tags = ["env:${var.environment}", "type:caas", "provider:kubernetes", "resource:kubernetes-node", "team:claranet", "created-by:terraform", "${var.apiserver_extra_tags}"]
|
||||
}
|
||||
4
caas/kubernetes/cluster/outputs.tf
Normal file
4
caas/kubernetes/cluster/outputs.tf
Normal file
@ -0,0 +1,4 @@
|
||||
output "apiserver_id" {
|
||||
description = "id for monitor apiserver"
|
||||
value = "${datadog_monitor.apiserver.*.id}"
|
||||
}
|
||||
Loading…
x
Reference in New Issue
Block a user