From c6d629309a43fff6d3e4b3f15b31fa7fa5b73764 Mon Sep 17 00:00:00 2001
From: Florent DELAHAYE <Tulux@users.noreply.github.com>
Date: Thu, 19 Sep 2024 11:08:42 +0200
Subject: [PATCH] feat: variabilize (cron)jobs groups (#59)

* feat: variabilize (cron)jobs groups

* doc: update readme

---------

Co-authored-by: Florent DELAHAYE <florent.delahaye@fr.clara.net>
---
 caas/kubernetes/workload/README.md                | 2 ++
 caas/kubernetes/workload/inputs.tf                | 8 ++++++++
 caas/kubernetes/workload/locals.tf                | 6 ++++--
 caas/kubernetes/workload/monitors-k8s-workload.tf | 4 ++--
 4 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/caas/kubernetes/workload/README.md b/caas/kubernetes/workload/README.md
index d8476911..3f7650c1 100644
--- a/caas/kubernetes/workload/README.md
+++ b/caas/kubernetes/workload/README.md
@@ -61,6 +61,7 @@ Creates DataDog monitors with the following checks:
 | <a name="input_cronjob_extra_tags"></a> [cronjob\_extra\_tags](#input\_cronjob\_extra\_tags) | Extra tags for Cronjob monitor | `list(string)` | `[]` | no |
 | <a name="input_cronjob_message"></a> [cronjob\_message](#input\_cronjob\_message) | Custom message for Cronjob monitor | `string` | `""` | no |
 | <a name="input_cronjob_threshold_warning"></a> [cronjob\_threshold\_warning](#input\_cronjob\_threshold\_warning) | Cronjob monitor (warning threshold) | `string` | `3` | no |
+| <a name="input_cronjobfailed_group_by"></a> [cronjobfailed\_group\_by](#input\_cronjobfailed\_group\_by) | n/a | `list` | <pre>[<br>  "kube_cronjob"<br>]</pre> | no |
 | <a name="input_deployment_group_by"></a> [deployment\_group\_by](#input\_deployment\_group\_by) | Select group by element on deployment monitors | `list` | <pre>[<br>  "kube_namespace",<br>  "kube_deployment",<br>  "kube_cluster_name"<br>]</pre> | no |
 | <a name="input_environment"></a> [environment](#input\_environment) | Architecture Environment | `string` | n/a | yes |
 | <a name="input_evaluation_delay"></a> [evaluation\_delay](#input\_evaluation\_delay) | Delay in seconds for the metric evaluation | `number` | `15` | no |
@@ -72,6 +73,7 @@ Creates DataDog monitors with the following checks:
 | <a name="input_job_extra_tags"></a> [job\_extra\_tags](#input\_job\_extra\_tags) | Extra tags for Job monitor | `list(string)` | `[]` | no |
 | <a name="input_job_message"></a> [job\_message](#input\_job\_message) | Custom message for Job monitor | `string` | `""` | no |
 | <a name="input_job_threshold_warning"></a> [job\_threshold\_warning](#input\_job\_threshold\_warning) | Job monitor (warning threshold) | `string` | `3` | no |
+| <a name="input_jobfailed_group_by"></a> [jobfailed\_group\_by](#input\_jobfailed\_group\_by) | n/a | `list` | <pre>[<br>  "kube_job",<br>  "kube_cluster_name"<br>]</pre> | no |
 | <a name="input_message"></a> [message](#input\_message) | Message sent when a monitor is triggered | `any` | n/a | yes |
 | <a name="input_new_group_delay"></a> [new\_group\_delay](#input\_new\_group\_delay) | Delay in seconds before monitor new resource | `number` | `300` | no |
 | <a name="input_new_host_delay"></a> [new\_host\_delay](#input\_new\_host\_delay) | Delay in seconds before monitor new resource | `number` | `300` | no |
diff --git a/caas/kubernetes/workload/inputs.tf b/caas/kubernetes/workload/inputs.tf
index 00b2f034..338cb9e3 100644
--- a/caas/kubernetes/workload/inputs.tf
+++ b/caas/kubernetes/workload/inputs.tf
@@ -223,3 +223,11 @@ variable "deployment_group_by" {
   default     = ["kube_namespace", "kube_deployment", "kube_cluster_name"]
   description = "Select group by element on deployment monitors"
 }
+
+variable "jobfailed_group_by" {
+  default = ["kube_job", "kube_cluster_name"]
+}
+
+variable "cronjobfailed_group_by" {
+  default = ["kube_cronjob"]
+}
diff --git a/caas/kubernetes/workload/locals.tf b/caas/kubernetes/workload/locals.tf
index ca4bbf6a..a4b621c1 100644
--- a/caas/kubernetes/workload/locals.tf
+++ b/caas/kubernetes/workload/locals.tf
@@ -1,4 +1,6 @@
 locals {
-  replica_group_by    = join(", ", var.replica_group_by)
-  deployment_group_by = join(", ", var.deployment_group_by)
+  replica_group_by       = join(", ", var.replica_group_by)
+  deployment_group_by    = join(", ", var.deployment_group_by)
+  jobfailed_group_by     = join(", ", [for i in var.jobfailed_group_by : format("%q", i)])
+  cronjobfailed_group_by = join(", ", [for i in var.cronjobfailed_group_by : format("%q", i)])
 }
diff --git a/caas/kubernetes/workload/monitors-k8s-workload.tf b/caas/kubernetes/workload/monitors-k8s-workload.tf
index 128aa543..7cceb884 100644
--- a/caas/kubernetes/workload/monitors-k8s-workload.tf
+++ b/caas/kubernetes/workload/monitors-k8s-workload.tf
@@ -5,7 +5,7 @@ resource "datadog_monitor" "job" {
   type    = "service check"
 
   query = <<EOQ
-    "kubernetes_state.job.complete"${module.filter-tags.service_check}.by("kube_job", "kube_cluster_name").last(6).count_by_status()
+    "kubernetes_state.job.complete"${module.filter-tags.service_check}.by(${local.jobfailed_group_by}).last(6).count_by_status()
 EOQ
 
   monitor_thresholds {
@@ -32,7 +32,7 @@ resource "datadog_monitor" "cronjob" {
   type    = "service check"
 
   query = <<EOQ
-    "kubernetes_state.cronjob.on_schedule_check"${module.filter-tags.service_check}.by("kube_cronjob").last(6).count_by_status()
+    "kubernetes_state.cronjob.on_schedule_check"${module.filter-tags.service_check}.by(${local.cronjobfailed_group_by}).last(6).count_by_status()
 EOQ
 
   monitor_thresholds {