convert processes detector using generator (#354)

* add disabled at rule level for generator

* convert processes detector using generator

* rebase on generator_disabled_rule

docs/severity.md

@@ -965,7 +965,7 @@
 
 |Detector|Critical|Major|Minor|Warning|Info|
 |---|---|---|---|---|---|
-|Processes aliveness|X|X|-|-|-|
+|Processes aliveness count|X|X|-|-|-|
 
 
 ## rabbitmq-node

modules/smart-agent_processes/README.md

@@ -58,7 +58,7 @@ Note the following parameters:
 
 These 3 parameters alongs with all variables defined in [common-variables.tf](common-variables.tf) are common to all
 [modules](../) in this repository. Other variables, specific to this module, are available in
-[variables.tf](variables.tf).
+[variables-gen.tf](variables-gen.tf).
 In general, the default configuration "works" but all of these Terraform
 [variables](https://www.terraform.io/docs/configuration/variables.html) make it possible to
 customize the detectors behavior to better fit your needs.
@@ -76,7 +76,7 @@ This module creates the following SignalFx detectors which could contain one or
 
 |Detector|Critical|Major|Minor|Warning|Info|
 |---|---|---|---|---|---|
-|Processes aliveness|X|X|-|-|-|
+|Processes aliveness count|X|X|-|-|-|
 
 ## How to collect required metrics?
 

modules/smart-agent_processes/conf/01-count.yaml

@@ -0,0 +1,16 @@
+module: processes
+name: "aliveness count"
+id: processes
+transformation: ".max(over='15m')"
+signals:
+  signal:
+    metric: ps_count.processes
+rules:
+  critical:
+    threshold: 1
+    comparator: "<"
+  major:
+    threshold: 2
+    comparator: "<"
+    dependency: critical
+    disabled: true

modules/smart-agent_processes/detectors-processes.tf → modules/smart-agent_processes/detectors-gen.tf

@@ -1,18 +1,18 @@
 resource "signalfx_detector" "processes" {
-  name = format("%s %s", local.detector_name_prefix, "Processes aliveness")
+  name = format("%s %s", local.detector_name_prefix, "Processes aliveness count")
 
   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('ps_count.processes', filter=${module.filtering.signalflow})${var.processes_aggregation_function}${var.processes_transformation_function}.publish('signal')
-        detect(when(signal < 1)).publish('CRIT')
-        detect(when(signal < ${var.processes_threshold_major}) and when (signal >= 1)).publish('MAJOR')
+    signal = data('ps_count.processes', filter=${module.filtering.signalflow})${var.processes_aggregation_function}${var.processes_transformation_function}.publish('signal')
+    detect(when(signal < ${var.processes_threshold_critical}, lasting=%{if var.processes_lasting_duration_critical == null}None%{else}'${var.processes_lasting_duration_critical}'%{endif}, at_least=${var.processes_at_least_percentage_critical})).publish('CRIT')
+    detect(when(signal < ${var.processes_threshold_major}, lasting=%{if var.processes_lasting_duration_major == null}None%{else}'${var.processes_lasting_duration_major}'%{endif}, at_least=${var.processes_at_least_percentage_major}) and (not when(signal < ${var.processes_threshold_critical}, lasting=%{if var.processes_lasting_duration_critical == null}None%{else}'${var.processes_lasting_duration_critical}'%{endif}, at_least=${var.processes_at_least_percentage_critical}))).publish('MAJOR')
 EOF
 
   rule {
-    description           = "count is too low < 1"
+    description           = "is too low < ${var.processes_threshold_critical}"
     severity              = "Critical"
     detect_label          = "CRIT"
     disabled              = coalesce(var.processes_disabled_critical, var.processes_disabled, var.detectors_disabled)
@@ -24,7 +24,7 @@ EOF
   }
 
   rule {
-    description           = "count is too low < ${var.processes_threshold_major}"
+    description           = "is too low < ${var.processes_threshold_major}"
     severity              = "Major"
     detect_label          = "MAJOR"
     disabled              = coalesce(var.processes_disabled_major, var.processes_disabled, var.detectors_disabled)
@@ -35,3 +35,4 @@ EOF
     parameterized_body    = var.message_body == "" ? local.rule_body : var.message_body
   }
 }
+

modules/smart-agent_processes/variables.tf → modules/smart-agent_processes/variables-gen.tf

@@ -1,7 +1,23 @@
-# Module specific
-
 # processes detector
 
+variable "processes_notifications" {
+  description = "Notification recipients list per severity overridden for processes detector"
+  type        = map(list(string))
+  default     = {}
+}
+
+variable "processes_aggregation_function" {
+  description = "Aggregation function and group by for processes detector (i.e. \".mean(by=['host'])\")"
+  type        = string
+  default     = ""
+}
+
+variable "processes_transformation_function" {
+  description = "Transformation function for processes detector (i.e. \".mean(over='5m')\")"
+  type        = string
+  default     = ".max(over='15m')"
+}
+
 variable "processes_tip" {
   description = "Suggested first course of action or any note useful for incident handling"
   type        = string
@@ -32,27 +48,37 @@ variable "processes_disabled_major" {
   default     = true
 }
 
-variable "processes_notifications" {
-  description = "Notification recipients list per severity overridden for processes detector"
-  type        = map(list(string))
-  default     = {}
+variable "processes_threshold_critical" {
+  description = "Critical threshold for processes detector"
+  type        = number
+  default     = 1
 }
 
-variable "processes_aggregation_function" {
-  description = "Aggregation function and group by for processes detector (i.e. \".mean(by=['host'])\")"
+variable "processes_lasting_duration_critical" {
+  description = "Minimum duration that conditions must be true before raising alert"
   type        = string
-  default     = ""
+  default     = null
 }
 
-variable "processes_transformation_function" {
-  description = "Transformation function for processes detector (i.e. \".mean(over='5m')\")"
-  type        = string
-  default     = ".max(over='15m')"
+variable "processes_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 "processes_threshold_major" {
   description = "Major threshold for processes detector"
   type        = number
   default     = 2
 }
 
+variable "processes_lasting_duration_major" {
+  description = "Minimum duration that conditions must be true before raising alert"
+  type        = string
+  default     = null
+}
+
+variable "processes_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
+}