Improve various AWS detectors

docs/severity.md

@@ -269,11 +269,11 @@
 |Detector|Critical|Major|Minor|Warning|Info|
 |---|---|---|---|---|---|
 |AWS EFS used space|X|X|-|-|-|
-|AWS EFS percent of io limit|-|X|X|-|-|
-|AWS EFS percent of read throughput|-|-|X|X|-|
-|AWS EFS percent of write throughput|-|-|X|X|-|
-|AWS EFS percent of permitted throughput|-|X|X|-|-|
-|AWS EFS burst credit balance|-|X|-|-|-|
+|AWS EFS percent of io limit|X|X|-|-|-|
+|AWS EFS percent of read throughput|X|X|-|-|-|
+|AWS EFS percent of write throughput|X|X|-|-|-|
+|AWS EFS percent of permitted throughput|X|X|-|-|-|
+|AWS EFS burst credit balance|X|-|-|-|-|
 
 
 ## integration_aws-elasticache-common

modules/integration_aws-alb/conf/00-heartbeat.yaml

@@ -4,6 +4,7 @@ name: heartbeat
 transformation: false
 aggregation: ".mean(by=['LoadBalancer'])"
 filtering: "filter('namespace', 'AWS/ApplicationELB')"
+condition: "var.heartbeat_detector_enabled"
 
 signals:
   signal:

modules/integration_aws-alb/conf/01-latency.yaml

@@ -6,6 +6,7 @@ transformation: true
 aggregation: true
 filtering: "filter('namespace', 'AWS/ApplicationELB')"
 value_unit: "Second"
+condition: "var.latency_detector_enabled"
 
 signals:
   signal:

modules/integration_aws-alb/conf/02-lb-5xx.yaml

@@ -6,6 +6,7 @@ transformation: true
 aggregation: true
 filtering: "filter('namespace', 'AWS/ApplicationELB') and filter('stat', 'sum') and (not filter('AvailabilityZone', '*'))"
 value_unit: "%"
+condition: "var.lb_5xx_detector_enabled"
 
 signals:
   errors:

modules/integration_aws-alb/conf/03-lb-4xx.yaml

@@ -6,6 +6,7 @@ transformation: true
 aggregation: true
 filtering: "filter('namespace', 'AWS/ApplicationELB') and filter('stat', 'sum') and (not filter('AvailabilityZone', '*'))"
 value_unit: "%"
+condition: "var.lb_4xx_detector_enabled"
 
 signals:
   errors:
@@ -25,7 +26,6 @@ rules:
     lasting_duration: 15m
     lasting_at_least: 0.9
     append_condition: and when(requests > ${var.minimum_traffic})
-    disabled: true
   major:
     threshold: 95
     comparator: ">"

modules/integration_aws-alb/conf/04-target-5xx.yaml

@@ -6,6 +6,7 @@ transformation: true
 aggregation: true
 filtering: "filter('namespace', 'AWS/ApplicationELB') and filter('stat', 'sum') and filter('TargetGroup', '*') and (not filter('AvailabilityZone', '*'))"
 value_unit: "%"
+condition: "var.target_5xx_detector_enabled"
 
 signals:
   errors:

modules/integration_aws-alb/conf/05-target-4xx.yaml

@@ -6,6 +6,7 @@ transformation: true
 aggregation: true
 filtering: "filter('namespace', 'AWS/ApplicationELB') and filter('stat', 'sum') and filter('TargetGroup', '*') and (not filter('AvailabilityZone', '*'))"
 value_unit: "%"
+condition: "var.target_4xx_detector_enabled"
 
 signals:
   errors:
@@ -25,7 +26,6 @@ rules:
     lasting_duration: 15m
     lasting_at_least: 0.9
     append_condition: and when(requests > ${var.minimum_traffic})
-    disabled: true
   major:
     threshold: 95
     comparator: ">"

modules/integration_aws-alb/conf/06-healthy.yaml

@@ -6,6 +6,7 @@ transformation: true
 aggregation: true
 filtering: "filter('namespace', 'AWS/ApplicationELB') and (not filter('AvailabilityZone', '*'))"
 value_unit: "%"
+condition: "var.healthy_detector_enabled"
 
 signals:
   healthy:

modules/integration_aws-alb/detectors-gen.tf

@@ -1,4 +1,6 @@
 resource "signalfx_detector" "heartbeat" {
+  count = (var.heartbeat_detector_enabled) ? 1 : 0
+
   name = format("%s %s", local.detector_name_prefix, "AWS ALB heartbeat")
 
   authorized_writer_teams = var.authorized_writer_teams
@@ -28,6 +30,8 @@ EOF
 }
 
 resource "signalfx_detector" "latency" {
+  count = (var.latency_detector_enabled) ? 1 : 0
+
   name = format("%s %s", local.detector_name_prefix, "AWS ALB target response time")
 
   authorized_writer_teams = var.authorized_writer_teams
@@ -74,6 +78,8 @@ EOF
 }
 
 resource "signalfx_detector" "alb_5xx" {
+  count = (var.lb_5xx_detector_enabled) ? 1 : 0
+
   name = format("%s %s", local.detector_name_prefix, "AWS ALB 5xx error rate")
 
   authorized_writer_teams = var.authorized_writer_teams
@@ -122,6 +128,8 @@ EOF
 }
 
 resource "signalfx_detector" "alb_4xx" {
+  count = (var.lb_4xx_detector_enabled) ? 1 : 0
+
   name = format("%s %s", local.detector_name_prefix, "AWS ALB 4xx error rate")
 
   authorized_writer_teams = var.authorized_writer_teams
@@ -183,6 +191,8 @@ EOF
 }
 
 resource "signalfx_detector" "target_5xx" {
+  count = (var.target_5xx_detector_enabled) ? 1 : 0
+
   name = format("%s %s", local.detector_name_prefix, "AWS ALB target 5xx error rate")
 
   authorized_writer_teams = var.authorized_writer_teams
@@ -231,6 +241,8 @@ EOF
 }
 
 resource "signalfx_detector" "target_4xx" {
+  count = (var.target_4xx_detector_enabled) ? 1 : 0
+
   name = format("%s %s", local.detector_name_prefix, "AWS ALB target 4xx error rate")
 
   authorized_writer_teams = var.authorized_writer_teams
@@ -292,6 +304,8 @@ EOF
 }
 
 resource "signalfx_detector" "healthy" {
+  count = (var.healthy_detector_enabled) ? 1 : 0
+
   name = format("%s %s", local.detector_name_prefix, "AWS ALB healthy instances percentage")
 
   authorized_writer_teams = var.authorized_writer_teams

modules/integration_aws-alb/variables-gen.tf

@@ -269,7 +269,7 @@ variable "alb_4xx_disabled" {
 variable "alb_4xx_disabled_critical" {
   description = "Disable critical alerting rule for alb_4xx detector"
   type        = bool
-  default     = true
+  default     = null
 }
 
 variable "alb_4xx_disabled_major" {
@@ -472,7 +472,7 @@ variable "target_4xx_disabled" {
 variable "target_4xx_disabled_critical" {
   description = "Disable critical alerting rule for target_4xx detector"
   type        = bool
-  default     = true
+  default     = null
 }
 
 variable "target_4xx_disabled_major" {

modules/integration_aws-alb/variables.tf

@@ -1,3 +1,45 @@
+variable "heartbeat_detector_enabled" {
+  description = "Enable heartbeat detector"
+  type        = bool
+  default     = true
+}
+
+variable "latency_detector_enabled" {
+  description = "Enable latency detector"
+  type        = bool
+  default     = true
+}
+
+variable "lb_5xx_detector_enabled" {
+  description = "Enable lb 5xx detector"
+  type        = bool
+  default     = true
+}
+
+variable "lb_4xx_detector_enabled" {
+  description = "Enable lb 4xx detector"
+  type        = bool
+  default     = true
+}
+
+variable "target_5xx_detector_enabled" {
+  description = "Enable target 5xx detector"
+  type        = bool
+  default     = true
+}
+
+variable "target_4xx_detector_enabled" {
+  description = "Enable target 4xx detector"
+  type        = bool
+  default     = true
+}
+
+variable "healthy_detector_enabled" {
+  description = "Enable healthy detector"
+  type        = bool
+  default     = true
+}
+
 # Module specific
 
 variable "minimum_traffic" {

modules/integration_aws-efs/README.md

@@ -28,14 +28,10 @@ existing [stack](https://github.com/claranet/terraform-signalfx-detectors/wiki/G
 module "signalfx-detectors-integration-aws-efs" {
   source = "github.com/claranet/terraform-signalfx-detectors.git//modules/integration_aws-efs?ref={revision}"
 
-  environment                        = var.environment
-  notifications                      = local.notifications
-  used_space_threshold_major         = 42
-  write_throughput_threshold_minor   = 42
-  read_throughput_threshold_minor    = 42
-  read_throughput_threshold_warning  = 42
-  write_throughput_threshold_warning = 42
-  used_space_threshold_critical      = 42
+  environment                   = var.environment
+  notifications                 = local.notifications
+  used_space_threshold_major    = 42
+  used_space_threshold_critical = 42
 }
 ```
 
@@ -87,11 +83,11 @@ This module creates the following SignalFx detectors which could contain one or
 |Detector|Critical|Major|Minor|Warning|Info|
 |---|---|---|---|---|---|
 |AWS EFS used space|X|X|-|-|-|
-|AWS EFS percent of io limit|-|X|X|-|-|
-|AWS EFS percent of read throughput|-|-|X|X|-|
-|AWS EFS percent of write throughput|-|-|X|X|-|
-|AWS EFS percent of permitted throughput|-|X|X|-|-|
-|AWS EFS burst credit balance|-|X|-|-|-|
+|AWS EFS percent of io limit|X|X|-|-|-|
+|AWS EFS percent of read throughput|X|X|-|-|-|
+|AWS EFS percent of write throughput|X|X|-|-|-|
+|AWS EFS percent of permitted throughput|X|X|-|-|-|
+|AWS EFS burst credit balance|X|-|-|-|-|
 
 ## How to collect required metrics?
 

modules/integration_aws-efs/conf/01-used-space.yaml

@@ -2,7 +2,7 @@ module: "AWS EFS"
 name: "Used Space"
 filtering: "filter('namespace', 'AWS/EFS')"
 value_unit: "Gibibyte"
-transformation: ".max(over='15m')"
+condition: "var.used_space_detector_enabled"
 signals:
   used_space:
     metric: "StorageBytes"
@@ -13,6 +13,8 @@ signals:
 rules:
   critical:
     comparator: ">"
+    lasting_duration: "15m"
   major:
     comparator: ">"
+    lasting_duration: "15m"
     dependency: critical

modules/integration_aws-efs/conf/02-io-limit.yaml

@@ -3,17 +3,19 @@ name: "Percent of IO Limit"
 id: "io_limit"
 filtering: "filter('namespace', 'AWS/EFS')"
 value_unit: "%"
-transformation: ".mean(over='30m')"
+condition: "var.io_limit_detector_enabled"
 tip: "If you reach too often the limit with current General Purpose mode, consider moving your application to a file system using the Max I/O performance mode."
 signals:
   signal:
     metric: "PercentIOLimit"
     filter: "filter('stat', 'mean')"
 rules:
-  major:
+  critical:
     comparator: ">"
     threshold: 90
-  minor:
+    lasting_duration: "30m"
+  major:
     comparator: ">"
-    dependency: major
+    dependency: critical
     threshold: 80
+    lasting_duration: "30m"

modules/integration_aws-efs/conf/03-throughput-read.yaml

@@ -3,8 +3,7 @@ name: "Percent of read throughput"
 id: "read_throughput"
 filtering: "filter('namespace', 'AWS/EFS')"
 value_unit: "%"
-transformation: ".max(over='15m')"
-disabled: true
+condition: "var.read_throughput_detector_enabled"
 signals:
   read:
     metric: "DataReadIOBytes"
@@ -16,8 +15,12 @@ signals:
     formula:
       (read/total).scale(100)
 rules:
-  minor:
+  critical:
     comparator: ">"
-  warning:
+    threshold: 90
+    lasting_duration: "15m"
+  major:
+    lasting_duration: "15m"
     comparator: ">"
-    dependency: minor
+    threshold: 80
+    dependency: critical

modules/integration_aws-efs/conf/04-throughput-write.yaml

@@ -3,8 +3,7 @@ name: "Percent of write throughput"
 id: "write_throughput"
 filtering: "filter('namespace', 'AWS/EFS')"
 value_unit: "%"
-transformation: ".max(over='15m')"
-disabled: true
+condition: "var.write_throughput_detector_enabled"
 signals:
   write:
     metric: "DataWriteIOBytes"
@@ -16,8 +15,12 @@ signals:
     formula:
       (write/total).scale(100)
 rules:
-  minor:
+  critical:
     comparator: ">"
-  warning:
+    threshold: 90
+    lasting_duration: "15m"
+  major:
     comparator: ">"
-    dependency: minor
+    threshold: 80
+    dependency: critical
+    lasting_duration: "15m"

modules/integration_aws-efs/conf/05-permitted-throughput.yaml

@@ -2,7 +2,7 @@ module: "AWS EFS"
 name: "Percent of permitted throughput"
 filtering: "filter('namespace', 'AWS/EFS')"
 value_unit: "%"
-transformation: ".mean(over='30m')"
+condition: "var.permitted_throughput_detector_enabled"
 tip: "You are consuming the entire amount of throughput allocated to your file system, In this situation, you might consider changing the file system's throughput mode to Provisioned Throughput to get higher throughput."
 signals:
   metered:
@@ -14,10 +14,12 @@ signals:
   signal:
     formula: (metered/permitted.scale(60)).scale(100)
 rules:
-  major:
+  critical:
     comparator: ">"
     threshold: 90
-  minor:
+    lasting_duration: "30m"
+  major:
     comparator: ">"
-    dependency: major
+    dependency: critical
     threshold: 80
+    lasting_duration: "30m"

modules/integration_aws-efs/conf/06-burst-cedit-balance.yaml

@@ -2,13 +2,14 @@ module: "AWS EFS"
 name: "Burst Credit Balance"
 filtering: "filter('namespace', 'AWS/EFS')"
 value_unit: "credits"
-transformation: ".mean(over='5m')"
+condition: "var.burst_credit_balance_detector_enabled"
 tip: "See https://docs.aws.amazon.com/efs/latest/ug/performance.html#bursting"
 signals:
   signal:
     metric: "BurstCreditBalance"
     filter: "filter('stat', 'lower')"
 rules:
-  major:
+  critical:
     comparator: "<"
     threshold: 1
+    lasting_duration: "5m"