Merge branch 'master' into add_loadbalancer_standard_healthprobe_status

Author: haedri

docs/severity.md

@@ -176,6 +176,7 @@
 |---|---|---|---|---|---|
 |Azure VPN heartbeat|X|-|-|-|-|
 |Azure VPN total flow count|X|-|-|-|-|
+|Azure VPN ipsec tunnel status|X|X|-|-|-|
 
 
 ## integration_aws-alb

modules/fame_azure-vpn/README.md

@@ -77,6 +77,7 @@ This module creates the following SignalFx detectors which could contain one or
 |---|---|---|---|---|---|
 |Azure VPN heartbeat|X|-|-|-|-|
 |Azure VPN total flow count|X|-|-|-|-|
+|Azure VPN ipsec tunnel status|X|X|-|-|-|
 
 ## How to collect required metrics?
 
@@ -97,6 +98,7 @@ Check the [Related documentation](#related-documentation) section for more detai
 Here is the list of required metrics for detectors in this module.
 
 * `fame.azure.virtual_network_gateway.total_flow_count`
+* `fame.azure.virtual_network_gateway.tunnel_status`
 
 
 

modules/fame_azure-vpn/conf/00-heartbeat.yaml

@@ -6,7 +6,7 @@ aggregation: true
 
 signals:
   signal:
-    metric: fame.azure.virtual_network_gateway.total_flow_count
+    metric: fame.azure.virtual_network_gateway.tunnel_status
 
 rules:
   critical:

modules/fame_azure-vpn/conf/01-total-flow-count.yaml

@@ -9,6 +9,8 @@ signals:
   signal:
     metric: fame.azure.virtual_network_gateway.total_flow_count
 
+disabled: true
+
 rules:
   critical:
     threshold: 0

modules/fame_azure-vpn/conf/02-tunnel-status.yaml

@@ -0,0 +1,21 @@
+module: Azure VPN
+name: IPSEC Tunnel Status
+id: tunnel_status
+
+transformation: true
+aggregation: ".mean(by=['azure_resource_group', 'azure_resource_name', 'remote_ip'])"
+
+signals:
+  signal:
+    metric: fame.azure.virtual_network_gateway.tunnel_status
+
+rules:
+  critical:
+    threshold: 0
+    comparator: "=="
+    lasting_duration: '20m'
+  major:
+    threshold: 0
+    comparator: "=="
+    lasting_duration: '10m'
+    dependency: critical

modules/fame_azure-vpn/detectors-gen.tf

@@ -7,7 +7,7 @@ resource "signalfx_detector" "heartbeat" {
 
   program_text = <<-EOF
     from signalfx.detectors.not_reporting import not_reporting
-    signal = data('fame.azure.virtual_network_gateway.total_flow_count', filter=${module.filtering.signalflow})${var.heartbeat_aggregation_function}${var.heartbeat_transformation_function}.publish('signal')
+    signal = data('fame.azure.virtual_network_gateway.tunnel_status', filter=${module.filtering.signalflow})${var.heartbeat_aggregation_function}${var.heartbeat_transformation_function}.publish('signal')
     not_reporting.detector(stream=signal, resource_identifier=None, duration='${var.heartbeat_timeframe}', auto_resolve_after='${local.heartbeat_auto_resolve_after}').publish('CRIT')
 EOF
 
@@ -53,3 +53,43 @@ EOF
   max_delay = var.totalflowcount_max_delay
 }
 
+resource "signalfx_detector" "tunnel_status" {
+  name = format("%s %s", local.detector_name_prefix, "Azure VPN ipsec tunnel status")
+
+  authorized_writer_teams = var.authorized_writer_teams
+  teams                   = try(coalescelist(var.teams, var.authorized_writer_teams), null)
+  tags                    = compact(concat(local.common_tags, local.tags, var.extra_tags))
+
+  program_text = <<-EOF
+    signal = data('fame.azure.virtual_network_gateway.tunnel_status', filter=${module.filtering.signalflow})${var.tunnel_status_aggregation_function}${var.tunnel_status_transformation_function}.publish('signal')
+    detect(when(signal == ${var.tunnel_status_threshold_critical}%{if var.tunnel_status_lasting_duration_critical != null}, lasting='${var.tunnel_status_lasting_duration_critical}', at_least=${var.tunnel_status_at_least_percentage_critical}%{endif})).publish('CRIT')
+    detect(when(signal == ${var.tunnel_status_threshold_major}%{if var.tunnel_status_lasting_duration_major != null}, lasting='${var.tunnel_status_lasting_duration_major}', at_least=${var.tunnel_status_at_least_percentage_major}%{endif}) and (not when(signal == ${var.tunnel_status_threshold_critical}%{if var.tunnel_status_lasting_duration_critical != null}, lasting='${var.tunnel_status_lasting_duration_critical}', at_least=${var.tunnel_status_at_least_percentage_critical}%{endif}))).publish('MAJOR')
+EOF
+
+  rule {
+    description           = "is == ${var.tunnel_status_threshold_critical}"
+    severity              = "Critical"
+    detect_label          = "CRIT"
+    disabled              = coalesce(var.tunnel_status_disabled_critical, var.tunnel_status_disabled, var.detectors_disabled)
+    notifications         = try(coalescelist(lookup(var.tunnel_status_notifications, "critical", []), var.notifications.critical), null)
+    runbook_url           = try(coalesce(var.tunnel_status_runbook_url, var.runbook_url), "")
+    tip                   = var.tunnel_status_tip
+    parameterized_subject = var.message_subject == "" ? local.rule_subject : var.message_subject
+    parameterized_body    = var.message_body == "" ? local.rule_body : var.message_body
+  }
+
+  rule {
+    description           = "is == ${var.tunnel_status_threshold_major}"
+    severity              = "Major"
+    detect_label          = "MAJOR"
+    disabled              = coalesce(var.tunnel_status_disabled_major, var.tunnel_status_disabled, var.detectors_disabled)
+    notifications         = try(coalescelist(lookup(var.tunnel_status_notifications, "major", []), var.notifications.major), null)
+    runbook_url           = try(coalesce(var.tunnel_status_runbook_url, var.runbook_url), "")
+    tip                   = var.tunnel_status_tip
+    parameterized_subject = var.message_subject == "" ? local.rule_subject : var.message_subject
+    parameterized_body    = var.message_body == "" ? local.rule_body : var.message_body
+  }
+
+  max_delay = var.tunnel_status_max_delay
+}
+

modules/fame_azure-vpn/outputs.tf

@@ -8,3 +8,8 @@ output "totalflowcount" {
   value       = signalfx_detector.totalflowcount
 }
 
+output "tunnel_status" {
+  description = "Detector resource for tunnel_status"
+  value       = signalfx_detector.tunnel_status
+}
+

modules/fame_azure-vpn/variables-gen.tf

@@ -89,7 +89,7 @@ variable "totalflowcount_runbook_url" {
 variable "totalflowcount_disabled" {
   description = "Disable all alerting rules for totalflowcount detector"
   type        = bool
-  default     = null
+  default     = true
 }
 
 variable "totalflowcount_threshold_critical" {
@@ -109,3 +109,93 @@ variable "totalflowcount_at_least_percentage_critical" {
   type        = number
   default     = 1
 }
+# tunnel_status detector
+
+variable "tunnel_status_notifications" {
+  description = "Notification recipients list per severity overridden for tunnel_status detector"
+  type        = map(list(string))
+  default     = {}
+}
+
+variable "tunnel_status_aggregation_function" {
+  description = "Aggregation function and group by for tunnel_status detector (i.e. \".mean(by=['host'])\")"
+  type        = string
+  default     = ".mean(by=['azure_resource_group', 'azure_resource_name', 'remote_ip'])"
+}
+
+variable "tunnel_status_transformation_function" {
+  description = "Transformation function for tunnel_status detector (i.e. \".mean(over='5m')\")"
+  type        = string
+  default     = ""
+}
+
+variable "tunnel_status_max_delay" {
+  description = "Enforce max delay for tunnel_status detector (use \"0\" or \"null\" for \"Auto\")"
+  type        = number
+  default     = null
+}
+
+variable "tunnel_status_tip" {
+  description = "Suggested first course of action or any note useful for incident handling"
+  type        = string
+  default     = ""
+}
+
+variable "tunnel_status_runbook_url" {
+  description = "URL like SignalFx dashboard or wiki page which can help to troubleshoot the incident cause"
+  type        = string
+  default     = ""
+}
+
+variable "tunnel_status_disabled" {
+  description = "Disable all alerting rules for tunnel_status detector"
+  type        = bool
+  default     = null
+}
+
+variable "tunnel_status_disabled_critical" {
+  description = "Disable critical alerting rule for tunnel_status detector"
+  type        = bool
+  default     = null
+}
+
+variable "tunnel_status_disabled_major" {
+  description = "Disable major alerting rule for tunnel_status detector"
+  type        = bool
+  default     = null
+}
+
+variable "tunnel_status_threshold_critical" {
+  description = "Critical threshold for tunnel_status detector"
+  type        = number
+  default     = 0
+}
+
+variable "tunnel_status_lasting_duration_critical" {
+  description = "Minimum duration that conditions must be true before raising alert"
+  type        = string
+  default     = "20m"
+}
+
+variable "tunnel_status_at_least_percentage_critical" {
+  description = "Percentage of lasting that conditions must be true before raising alert (>= 0.0 and <= 1.0)"
+  type        = number
+  default     = 1
+}
+variable "tunnel_status_threshold_major" {
+  description = "Major threshold for tunnel_status detector"
+  type        = number
+  default     = 0
+}
+
+variable "tunnel_status_lasting_duration_major" {
+  description = "Minimum duration that conditions must be true before raising alert"
+  type        = string
+  default     = "10m"
+}
+
+variable "tunnel_status_at_least_percentage_major" {
+  description = "Percentage of lasting that conditions must be true before raising alert (>= 0.0 and <= 1.0)"
+  type        = number
+  default     = 1
+}