Merge branch 'master' into integration_gcp-cloud-sql-postgresql

docs/severity.md

@@ -66,6 +66,7 @@
 - [integration_azure-virtual-machine-scaleset](#integration_azure-virtual-machine-scaleset)
 - [integration_azure-virtual-machine](#integration_azure-virtual-machine)
 - [integration_gcp-bigquery](#integration_gcp-bigquery)
+- [integration_gcp-cloud-run](#integration_gcp-cloud-run)
 - [integration_gcp-cloud-sql-common](#integration_gcp-cloud-sql-common)
 - [integration_gcp-cloud-sql-failover](#integration_gcp-cloud-sql-failover)
 - [integration_gcp-cloud-sql-mysql](#integration_gcp-cloud-sql-mysql)
@@ -79,9 +80,11 @@
 - [organization_usage](#organization_usage)
 - [otel-collector_kubernetes-common](#otel-collector_kubernetes-common)
 - [prometheus-exporter_active-directory](#prometheus-exporter_active-directory)
+- [prometheus-exporter_dnsmasq](#prometheus-exporter_dnsmasq)
 - [prometheus-exporter_docker-state](#prometheus-exporter_docker-state)
 - [prometheus-exporter_kong](#prometheus-exporter_kong)
 - [prometheus-exporter_oracledb](#prometheus-exporter_oracledb)
+- [prometheus-exporter_postfix](#prometheus-exporter_postfix)
 - [prometheus-exporter_squid](#prometheus-exporter_squid)
 - [prometheus-exporter_varnish](#prometheus-exporter_varnish)
 - [prometheus-exporter_wallix-bastion](#prometheus-exporter_wallix-bastion)
@@ -738,6 +741,15 @@
 |GCP BigQuery uploaded bytes billed|X|X|-|-|-|
 
 
+## integration_gcp-cloud-run
+
+|Detector|Critical|Major|Minor|Warning|Info|
+|---|---|---|---|---|---|
+|GCP Cloud Run container count|X|-|-|-|-|
+|GCP Cloud Run cpu utilizations|X|X|-|-|-|
+|GCP Cloud Run memory utilizations|X|X|-|-|-|
+
+
 ## integration_gcp-cloud-sql-common
 
 |Detector|Critical|Major|Minor|Warning|Info|
@@ -871,6 +883,15 @@
 |Active-directory active directory services|X|-|-|-|-|
 
 
+## prometheus-exporter_dnsmasq
+
+|Detector|Critical|Major|Minor|Warning|Info|
+|---|---|---|---|---|---|
+|Dnsmasq heartbeat|X|-|-|-|-|
+|Dnsmasq hits|X|-|-|-|-|
+|Dnsmasq hit rate|-|X|X|-|-|
+
+
 ## prometheus-exporter_docker-state
 
 |Detector|Critical|Major|Minor|Warning|Info|
@@ -897,6 +918,17 @@
 |Oracle database status|X|-|-|-|-|
 
 
+## prometheus-exporter_postfix
+
+|Detector|Critical|Major|Minor|Warning|Info|
+|---|---|---|---|---|---|
+|Postfix heartbeat|X|-|-|-|-|
+|Postfix size postfix queue deferred|X|X|-|-|-|
+|Postfix size postfix queue hold|X|X|-|-|-|
+|Postfix size postfix queue maildrop|X|X|-|-|-|
+|Postfix size postfix delivery delay|X|X|-|-|-|
+
+
 ## prometheus-exporter_squid
 
 |Detector|Critical|Major|Minor|Warning|Info|

modules/integration_aws-elasticsearch/conf/01-jvm-memory-pressure.yaml

@@ -1,7 +1,6 @@
 module: AWS Elasticsearch
 name: JVM Memory Pressure
 
-transformation: ".min(over='15m')"
 aggregation: true
 filtering: "filter('namespace', 'AWS/ES') and filter('stat', 'upper') and filter('NodeId', '*')"
 value_unit: "%"
@@ -15,7 +14,9 @@ rules:
   critical:
     threshold: 90
     comparator: ">"
+    lasting_duration: "15m"
   major:
     threshold: 80
     comparator: ">"
     dependency: critical
+    lasting_duration: "15m"

modules/integration_aws-elasticsearch/conf/05-cluster-status.yaml

@@ -1,7 +1,6 @@
 module: AWS Elasticsearch
 name: Cluster status
 
-aggregation: ".min(over='15m')"
 filtering: "filter('namespace', 'AWS/ES') and filter('stat', 'upper')"
 
 signals:
@@ -18,8 +17,10 @@ rules:
     comparator: ">="
     description: "is red"
     signal: red
+    lasting_duration: "15m"
   major:
     threshold: 1
     comparator: ">="
     description: "is yellow"
     signal: yellow
+    lasting_duration: "15m"

modules/integration_aws-elasticsearch/conf/08-cluster-cpu.yaml

@@ -2,7 +2,6 @@ module: AWS Elasticsearch
 id: "cluster_cpu"
 name: "CPU utilization"
 
-transformation: ".min(over='45m')"
 aggregation: ""
 filtering: "filter('namespace', 'AWS/ES') and filter('stat', 'upper') and filter('NodeId', '*')"
 
@@ -20,6 +19,8 @@ rules:
     threshold: 80
     comparator: ">"
     dependency: critical
+    lasting_duration: "45m"
   critical:
     threshold: 90
     comparator: ">"
+    lasting_duration: "45m"

modules/integration_aws-elasticsearch/conf/09-master-cpu.yaml

@@ -2,7 +2,6 @@ module: AWS Elasticsearch
 id: "master_cpu"
 name: "Master CPU utilization"
 
-transformation: ".min(over='20m')"
 aggregation: ""
 filtering: "filter('namespace', 'AWS/ES') and filter('stat', 'upper') and filter('NodeId', '*')"
 
@@ -15,6 +14,8 @@ rules:
     threshold: 60
     comparator: ">"
     dependency: critical
+    lasting_duration: "20m"
   critical:
     threshold: 70
     comparator: ">"
+    lasting_duration: "20m"

modules/integration_aws-elasticsearch/variables-gen.tf

@@ -59,7 +59,7 @@ variable "jvm_memory_pressure_aggregation_function" {
 variable "jvm_memory_pressure_transformation_function" {
   description = "Transformation function for jvm_memory_pressure detector (i.e. \".mean(over='5m')\")"
   type        = string
-  default     = ".min(over='15m')"
+  default     = ""
 }
 
 variable "jvm_memory_pressure_max_delay" {
@@ -109,7 +109,7 @@ variable "jvm_memory_pressure_threshold_critical" {
 variable "jvm_memory_pressure_lasting_duration_critical" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "15m"
 }
 
 variable "jvm_memory_pressure_at_least_percentage_critical" {
@@ -126,7 +126,7 @@ variable "jvm_memory_pressure_threshold_major" {
 variable "jvm_memory_pressure_lasting_duration_major" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "15m"
 }
 
 variable "jvm_memory_pressure_at_least_percentage_major" {
@@ -467,7 +467,7 @@ variable "cluster_status_notifications" {
 variable "cluster_status_aggregation_function" {
   description = "Aggregation function and group by for cluster_status detector (i.e. \".mean(by=['host'])\")"
   type        = string
-  default     = ".min(over='15m')"
+  default     = ""
 }
 
 variable "cluster_status_transformation_function" {
@@ -521,7 +521,7 @@ variable "cluster_status_threshold_critical" {
 variable "cluster_status_lasting_duration_critical" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "15m"
 }
 
 variable "cluster_status_at_least_percentage_critical" {
@@ -538,7 +538,7 @@ variable "cluster_status_threshold_major" {
 variable "cluster_status_lasting_duration_major" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "15m"
 }
 
 variable "cluster_status_at_least_percentage_major" {
@@ -725,7 +725,7 @@ variable "cluster_cpu_notifications" {
 variable "cluster_cpu_transformation_function" {
   description = "Transformation function for cluster_cpu detector (i.e. \".mean(over='5m')\")"
   type        = string
-  default     = ".min(over='45m')"
+  default     = ""
 }
 
 variable "cluster_cpu_max_delay" {
@@ -773,7 +773,7 @@ variable "cluster_cpu_threshold_major" {
 variable "cluster_cpu_lasting_duration_major" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "45m"
 }
 
 variable "cluster_cpu_at_least_percentage_major" {
@@ -790,7 +790,7 @@ variable "cluster_cpu_threshold_critical" {
 variable "cluster_cpu_lasting_duration_critical" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "45m"
 }
 
 variable "cluster_cpu_at_least_percentage_critical" {
@@ -809,7 +809,7 @@ variable "master_cpu_notifications" {
 variable "master_cpu_transformation_function" {
   description = "Transformation function for master_cpu detector (i.e. \".mean(over='5m')\")"
   type        = string
-  default     = ".min(over='20m')"
+  default     = ""
 }
 
 variable "master_cpu_max_delay" {
@@ -857,7 +857,7 @@ variable "master_cpu_threshold_major" {
 variable "master_cpu_lasting_duration_major" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "20m"
 }
 
 variable "master_cpu_at_least_percentage_major" {
@@ -874,7 +874,7 @@ variable "master_cpu_threshold_critical" {
 variable "master_cpu_lasting_duration_critical" {
   description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = null
+  default     = "20m"
 }
 
 variable "master_cpu_at_least_percentage_critical" {