Merge branch 'MON-444_fix_threshold_for_pod_error' into 'master'

MON-444 fix operator and timeframe for pod error monitor

Closes MON-444

See merge request claranet/pt-monitoring/projects/datadog/terraform/monitors!60

caas/kubernetes/pod/README.md

@@ -30,7 +30,7 @@ Creates DataDog monitors with the following checks:
 | error\_silenced | Groups to mute for Pod errors monitor | map | `{}` | no |
 | error\_threshold\_critical | error critical threshold | string | `"0.5"` | no |
 | error\_threshold\_warning | error warning threshold | string | `"0"` | no |
-| error\_time\_aggregator | Monitor aggregator for Pod errors [available values: min, max or avg] | string | `"sum"` | no |
+| error\_time\_aggregator | Monitor aggregator for Pod errors [available values: min, max or avg] | string | `"min"` | no |
 | error\_timeframe | Monitor timeframe for Pod errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `"last_15m"` | no |
 | 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 |

caas/kubernetes/pod/inputs.tf

@@ -103,7 +103,7 @@ variable "error_message" {
 variable "error_time_aggregator" {
   description = "Monitor aggregator for Pod errors [available values: min, max or avg]"
   type        = "string"
-  default     = "sum"
+  default     = "min"
 }
 
 variable "error_timeframe" {

caas/kubernetes/pod/monitors-k8s-pod.tf

@@ -37,7 +37,7 @@ resource "datadog_monitor" "error" {
   query = <<EOQ
     ${var.error_time_aggregator}(${var.error_timeframe}):
       sum:kubernetes_state.container.status_report.count.waiting${module.filter-tags-nocontainercreating.query_alert} by {namespace,pod,reason}.as_count()
-    >= ${var.error_threshold_critical}
+    > ${var.error_threshold_critical}
   EOQ
 
   thresholds {