wbyc/terraform-datadog-old-monitors
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

MON-162 add missing enabled feature

Browse Source
This commit is contained in:
Quentin Manfroi 2018-09-14 13:25:32 +02:00
parent cf75e582c8
commit f24782e406
24 changed files with 531 additions and 106 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
cloud/gcp/big-query/README.md
View File

@ -30,12 +30,14 @@ Creates DataDog monitors with the following checks:
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| available_slots_enabled | Flag to enable GCP Big Query Available Slots monitor | string | `true` | no |
| available_slots_extra_tags | Extra tags for GCP Big Query Available Slots monitor | list | `<list>` | no |
| available_slots_message | Custom message for the Available Slots monitor | string | `` | no |
| available_slots_silenced | Groups to mute for GCP Big Query Available Slots monitor. | map | `<map>` | no |
| available_slots_threshold_critical | Available Slots (critical threshold) | string | `200` | no |
| available_slots_threshold_warning | Available Slots (warning threshold) | string | `300` | no |
| available_slots_timeframe | Timeframe for the Available Slots monitor | string | `last_5m` | no |
| concurrent_queries_enabled | Flag to enable GCP Big Query Concurrent Queries monitor | string | `true` | no |
| concurrent_queries_extra_tags | Extra tags for GCP Big Query Concurrent Queries monitor | list | `<list>` | no |
| concurrent_queries_message | Custom message for the Concurrent Queries monitor | string | `` | no |
| concurrent_queries_silenced | Groups to mute for GCP Big Query Concurrent Queries monitor | map | `<map>` | no |
@ -44,48 +46,55 @@ Creates DataDog monitors with the following checks:
| concurrent_queries_timeframe | Timeframe for the Concurrent Queries monitor | string | `last_5m` | no |
| environment | Architecture environment | string | - | yes |
| evaluation_delay | Delay in seconds for the metric evaluation | string | `900` | no |
| execution_time_enabled | Flag to enable GCP Big Query Execution Time monitor | string | `true` | no |
| execution_time_extra_tags | Extra tags for GCP Big Query Execution Time monitor | list | `<list>` | no |
| execution_time_message | Custom message for the Execution Time monitor | string | `` | no |
| execution_time_silenced | Groups to mute for GCP Big Query Execution Time monitor. Muted by default. | map | `<map>` | no |
| execution_time_silenced | Groups to mute for GCP Big Query Execution Time monitor. | map | `<map>` | no |
| execution_time_threshold_critical | Average Execution Time in seconds (critical threshold) | string | `150` | no |
| execution_time_threshold_warning | Average Execution Time in seconds (warning threshold) | string | `100` | no |
| execution_time_timeframe | Timeframe for the Execution Time monitor | string | `last_5m` | no |
| filter_tags | Tags used for filtering | string | `*` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
| new_host_delay | Delay in seconds for the new host evaluation | string | `300` | no |
| scanned_bytes_billed_enabled | Flag to enable GCP Big Query Scanned Bytes Billed monitor | string | `true` | no |
| scanned_bytes_billed_extra_tags | Extra tags for GCP Big Query Scanned Bytes Billed monitor | list | `<list>` | no |
| scanned_bytes_billed_message | Custom message for the Scanned Bytes Billed monitor | string | `` | no |
| scanned_bytes_billed_silenced | Groups to mute for GCP Big Query Scanned Bytes Billed monitor. Muted by default. | map | `<map>` | no |
| scanned_bytes_billed_silenced | Groups to mute for GCP Big Query Scanned Bytes Billed monitor. | map | `<map>` | no |
| scanned_bytes_billed_threshold_critical | Scanned Bytes Billed (critical threshold) | string | `1` | no |
| scanned_bytes_billed_threshold_warning | Scanned Bytes Billed (warning threshold) | string | `0` | no |
| scanned_bytes_billed_timeframe | Timeframe for the Scanned Bytes Billed monitor | string | `last_4h` | no |
| scanned_bytes_enabled | Flag to enable GCP Big Query Scanned Bytes monitor | string | `true` | no |
| scanned_bytes_extra_tags | Extra tags for GCP Big Query Scanned Bytes monitor | list | `<list>` | no |
| scanned_bytes_message | Custom message for the Scanned Bytes monitor | string | `` | no |
| scanned_bytes_silenced | Groups to mute for GCP Big Query Scanned Bytes monitor. Muted by default. | map | `<map>` | no |
| scanned_bytes_silenced | Groups to mute for GCP Big Query Scanned Bytes monitor. | map | `<map>` | no |
| scanned_bytes_threshold_critical | Scanned Bytes (critical threshold) | string | `1` | no |
| scanned_bytes_threshold_warning | Scanned Bytes (warning threshold) | string | `0` | no |
| scanned_bytes_timeframe | Timeframe for the Scanned Bytes monitor | string | `last_4h` | no |
| stored_bytes_enabled | Flag to enable GCP Big Query Stored Bytes monitor | string | `true` | no |
| stored_bytes_extra_tags | Extra tags for GCP Big Query Stored Bytes monitor | list | `<list>` | no |
| stored_bytes_message | Custom message for the Stored Bytes monitor | string | `` | no |
| stored_bytes_silenced | Groups to mute for GCP Big Query Stored Bytes monitor. Muted by default. | map | `<map>` | no |
| stored_bytes_silenced | Groups to mute for GCP Big Query Stored Bytes monitor. | map | `<map>` | no |
| stored_bytes_threshold_critical | Stored Bytes in fraction (critical threshold) | string | `1` | no |
| stored_bytes_threshold_warning | Stored Bytes in fraction (warning threshold) | string | `0` | no |
| stored_bytes_timeframe | Timeframe for the Stored Bytes monitor | string | `last_5m` | no |
| table_count_enabled | Flag to enable GCP Big Query Table Count monitor | string | `true` | no |
| table_count_extra_tags | Extra tags for GCP Big Query Table Count monitor | list | `<list>` | no |
| table_count_message | Custom message for the Table Count monitor | string | `` | no |
| table_count_silenced | Groups to mute for GCP Big Query Table Count monitor. Muted by default. | map | `<map>` | no |
| table_count_silenced | Groups to mute for GCP Big Query Table Count monitor. | map | `<map>` | no |
| table_count_threshold_critical | Table Count (critical threshold) | string | `1` | no |
| table_count_threshold_warning | Table Count (warning threshold) | string | `0` | no |
| table_count_timeframe | Timeframe for the Table Count monitor | string | `last_4h` | no |
| uploaded_bytes_billed_enabled | Flag to enable GCP Big Query Uploaded Bytes Billed monitor | string | `true` | no |
| uploaded_bytes_billed_extra_tags | Extra tags for GCP Big Query Scanned Bytes monitor | list | `<list>` | no |
| uploaded_bytes_billed_message | Custom message for the Uploaded Bytes Billed monitor | string | `` | no |
| uploaded_bytes_billed_silenced | Groups to mute for GCP Big Query Uploaded Bytes Billed monitor. Muted by default. | map | `<map>` | no |
| uploaded_bytes_billed_silenced | Groups to mute for GCP Big Query Uploaded Bytes Billed monitor. | map | `<map>` | no |
| uploaded_bytes_billed_threshold_critical | Uploaded Bytes Billed (critical threshold) | string | `1` | no |
| uploaded_bytes_billed_threshold_warning | Uploaded Bytes Billed (warning threshold) | string | `0` | no |
| uploaded_bytes_billed_timeframe | Timeframe for the Uploaded Bytes Billed monitor | string | `last_4h` | no |
| uploaded_bytes_enabled | Flag to enable GCP Big Query Uploaded Bytes monitor | string | `true` | no |
| uploaded_bytes_extra_tags | Extra tags for GCP Big Query Uploaded Bytes monitor | list | `<list>` | no |
| uploaded_bytes_message | Custom message for the Uploaded Bytes monitor | string | `` | no |
| uploaded_bytes_silenced | Groups to mute for GCP Big Query Uploaded Bytes monitor. Muted by default. | map | `<map>` | no |
| uploaded_bytes_silenced | Groups to mute for GCP Big Query Uploaded Bytes monitor. | map | `<map>` | no |
| uploaded_bytes_threshold_critical | Uploaded Bytes (critical threshold) | string | `1` | no |
| uploaded_bytes_threshold_warning | Uploaded Bytes (warning threshold) | string | `0` | no |
| uploaded_bytes_timeframe | Timeframe for the Uploaded Bytes monitor | string | `last_4h` | no |

75
cloud/gcp/big-query/inputs.tf
View File

@ -60,6 +60,12 @@ variable "concurrent_queries_silenced" {
default = {}
}
variable "concurrent_queries_enabled" {
description = "Flag to enable GCP Big Query Concurrent Queries monitor"
type = "string"
default = "true"
}
variable "concurrent_queries_extra_tags" {
description = "Extra tags for GCP Big Query Concurrent Queries monitor"
type = "list"
@ -95,10 +101,15 @@ variable "execution_time_threshold_critical" {
}
variable "execution_time_silenced" {
description = "Groups to mute for GCP Big Query Execution Time monitor. Muted by default."
description = "Groups to mute for GCP Big Query Execution Time monitor."
type = "map"
default = {}
}
default = {}
variable "execution_time_enabled" {
description = "Flag to enable GCP Big Query Execution Time monitor"
type = "string"
default = "true"
}
variable "execution_time_extra_tags" {
@ -136,10 +147,15 @@ variable "scanned_bytes_threshold_critical" {
}
variable "scanned_bytes_silenced" {
description = "Groups to mute for GCP Big Query Scanned Bytes monitor. Muted by default."
description = "Groups to mute for GCP Big Query Scanned Bytes monitor."
type = "map"
default = {}
}
default = {}
variable "scanned_bytes_enabled" {
description = "Flag to enable GCP Big Query Scanned Bytes monitor"
type = "string"
default = "true"
}
variable "scanned_bytes_extra_tags" {
@ -177,10 +193,15 @@ variable "scanned_bytes_billed_threshold_critical" {
}
variable "scanned_bytes_billed_silenced" {
description = "Groups to mute for GCP Big Query Scanned Bytes Billed monitor. Muted by default."
description = "Groups to mute for GCP Big Query Scanned Bytes Billed monitor."
type = "map"
default = {}
}
default = {}
variable "scanned_bytes_billed_enabled" {
description = "Flag to enable GCP Big Query Scanned Bytes Billed monitor"
type = "string"
default = "true"
}
variable "scanned_bytes_billed_extra_tags" {
@ -223,6 +244,12 @@ variable "available_slots_silenced" {
default = {}
}
variable "available_slots_enabled" {
description = "Flag to enable GCP Big Query Available Slots monitor"
type = "string"
default = "true"
}
variable "available_slots_extra_tags" {
description = "Extra tags for GCP Big Query Available Slots monitor"
type = "list"
@ -258,10 +285,15 @@ variable "stored_bytes_threshold_critical" {
}
variable "stored_bytes_silenced" {
description = "Groups to mute for GCP Big Query Stored Bytes monitor. Muted by default."
description = "Groups to mute for GCP Big Query Stored Bytes monitor."
type = "map"
default = {}
}
default = {}
variable "stored_bytes_enabled" {
description = "Flag to enable GCP Big Query Stored Bytes monitor"
type = "string"
default = "true"
}
variable "stored_bytes_extra_tags" {
@ -299,10 +331,15 @@ variable "table_count_threshold_critical" {
}
variable "table_count_silenced" {
description = "Groups to mute for GCP Big Query Table Count monitor. Muted by default."
description = "Groups to mute for GCP Big Query Table Count monitor."
type = "map"
default = {}
}
default = {}
variable "table_count_enabled" {
description = "Flag to enable GCP Big Query Table Count monitor"
type = "string"
default = "true"
}
variable "table_count_extra_tags" {
@ -340,10 +377,15 @@ variable "uploaded_bytes_threshold_critical" {
}
variable "uploaded_bytes_silenced" {
description = "Groups to mute for GCP Big Query Uploaded Bytes monitor. Muted by default."
description = "Groups to mute for GCP Big Query Uploaded Bytes monitor."
type = "map"
default = {}
}
default = {}
variable "uploaded_bytes_enabled" {
description = "Flag to enable GCP Big Query Uploaded Bytes monitor"
type = "string"
default = "true"
}
variable "uploaded_bytes_extra_tags" {
@ -381,10 +423,15 @@ variable "uploaded_bytes_billed_threshold_critical" {
}
variable "uploaded_bytes_billed_silenced" {
description = "Groups to mute for GCP Big Query Uploaded Bytes Billed monitor. Muted by default."
description = "Groups to mute for GCP Big Query Uploaded Bytes Billed monitor."
type = "map"
default = {}
}
default = {}
variable "uploaded_bytes_billed_enabled" {
description = "Flag to enable GCP Big Query Uploaded Bytes Billed monitor"
type = "string"
default = "true"
}
variable "uploaded_bytes_billed_extra_tags" {

9
cloud/gcp/big-query/monitors-big-query.tf
View File

@ -2,6 +2,7 @@
# Concurrent queries
#
resource "datadog_monitor" "concurrent_queries" {
count = "${var.concurrent_queries_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Concurrent Queries {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.concurrent_queries_message, var.message)}"
@ -37,6 +38,7 @@ EOF
# Execution Time
#
resource "datadog_monitor" "execution_time" {
count = "${var.execution_time_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Execution Time {{#is_alert}}{{{comparator}}} {{threshold}}s ({{value}}s){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}s ({{value}}s){{/is_warning}}"
message = "${coalesce(var.execution_time_message, var.message)}"
@ -72,6 +74,7 @@ EOF
# Scanned Bytes
#
resource "datadog_monitor" "scanned_bytes" {
count = "${var.scanned_bytes_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Scanned Bytes {{#is_alert}}{{{comparator}}} {{threshold}}B/mn ({{value}}B/mn){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}B/mn ({{value}}B/mn){{/is_warning}}"
message = "${coalesce(var.scanned_bytes_message, var.message)}"
@ -107,6 +110,7 @@ EOF
# Scanned Bytes Billed
#
resource "datadog_monitor" "scanned_bytes_billed" {
count = "${var.scanned_bytes_billed_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Scanned Bytes Billed {{#is_alert}}{{{comparator}}} {{threshold}}B/mn ({{value}}B/mn){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}B/mn ({{value}}B/mn){{/is_warning}}"
message = "${coalesce(var.scanned_bytes_billed_message, var.message)}"
@ -142,6 +146,7 @@ EOF
# Available Slots
#
resource "datadog_monitor" "available_slots" {
count = "${var.available_slots_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Available Slots {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.available_slots_message, var.message)}"
@ -177,6 +182,7 @@ EOF
# Stored Bytes
#
resource "datadog_monitor" "stored_bytes" {
count = "${var.stored_bytes_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Stored Bytes {{#is_alert}}{{{comparator}}} {{threshold}}B ({{value}}B){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}B ({{value}}B){{/is_warning}}"
message = "${coalesce(var.stored_bytes_message, var.message)}"
@ -212,6 +218,7 @@ EOF
# Table Count
#
resource "datadog_monitor" "table_count" {
count = "${var.table_count_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Table Count {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.table_count_message, var.message)}"
@ -247,6 +254,7 @@ EOF
# Uploaded Bytes
#
resource "datadog_monitor" "uploaded_bytes" {
count = "${var.uploaded_bytes_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Uploaded Bytes {{#is_alert}}{{{comparator}}} {{threshold}}B/mn ({{value}}B/mn){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}B/mn ({{value}}B/mn){{/is_warning}}"
message = "${coalesce(var.uploaded_bytes_message, var.message)}"
@ -282,6 +290,7 @@ EOF
# Uploaded Bytes Billed
#
resource "datadog_monitor" "uploaded_bytes_billed" {
count = "${var.uploaded_bytes_billed_enabled ? 1 : 0}"
name = "[${var.environment}] GCP Big Query Uploaded Bytes Billed {{#is_alert}}{{{comparator}}} {{threshold}}B/mn ({{value}}B/mn){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}B/mn ({{value}}B/mn){{/is_warning}}"
message = "${coalesce(var.uploaded_bytes_billed_message, var.message)}"

6
cloud/gcp/cloud-sql/common/README.md
View File

@ -27,6 +27,7 @@ Creates DataDog monitors with the following checks:
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| cpu_utilization_enabled | Flag to enable GCP Cloud SQL CPU Utilization monitor | string | `true` | no |
| cpu_utilization_extra_tags | Extra tags for GCP Cloud SQL CPU Utilization monitor | list | `<list>` | no |
| cpu_utilization_message | Custom message for the CPU Utilization monitor | string | `` | no |
| cpu_utilization_silenced | Groups to mute for GCP Cloud SQL CPU Utilization monitor | map | `<map>` | no |
@ -34,9 +35,11 @@ Creates DataDog monitors with the following checks:
| cpu_utilization_threshold_warning | CPU Utilization in percentage (warning threshold) | string | `80` | no |
| cpu_utilization_time_aggregator | Time aggregator for the CPU Utilization monitor | string | `avg` | no |
| cpu_utilization_timeframe | Timeframe for the CPU Utilization monitor | string | `last_15m` | no |
| disk_utilization_enabled | Flag to enable GCP Cloud SQL Disk Utilization monitor | string | `true` | no |
| disk_utilization_extra_tags | Extra tags for GCP Cloud SQL CPU Utilization monitor | list | `<list>` | no |
| disk_utilization_forecast_algorithm | Algorithm for the Disk Utilization Forecast monitor | string | `linear` | no |
| disk_utilization_forecast_deviations | Deviations for the Disk Utilization Forecast monitor | string | `1` | no |
| disk_utilization_forecast_enabled | Flag to enable GCP Cloud SQL Disk Utilization Forecast monitor | string | `true` | no |
| disk_utilization_forecast_extra_tags | Extra tags for GCP Cloud SQL Disk Utilization Forecast monitor | list | `<list>` | no |
| disk_utilization_forecast_interval | Interval for the Disk Utilization Forecast monitor | string | `60m` | no |
| disk_utilization_forecast_linear_history | History for the Disk Utilization Forecast monitor | string | `3d` | no |
@ -56,6 +59,7 @@ Creates DataDog monitors with the following checks:
| disk_utilization_timeframe | Timeframe for the Disk Utilization monitor | string | `last_5m` | no |
| environment | Architecture environment | string | - | yes |
| evaluation_delay | Delay in seconds for the metric evaluation | string | `900` | no |
| failover_unavailable_enabled | Flag to enable GCP Cloud SQL Failover Unavailable monitor | string | `true` | no |
| failover_unavailable_extra_tags | Extra tags for GCP Cloud SQL Failover Unavailable monitor | list | `<list>` | no |
| failover_unavailable_message | Custom message for the Failover Unavailable monitor | string | `` | no |
| failover_unavailable_silenced | Groups to mute for GCP Cloud SQL Failover Unavailable monitor | map | `<map>` | no |
@ -63,9 +67,11 @@ Creates DataDog monitors with the following checks:
| failover_unavailable_time_aggregator | Time aggreggator for the Failover Unavailable monitor | string | `max` | no |
| failover_unavailable_timeframe | Timeframe for the Failover Unavailable monitor | string | `last_5m` | no |
| filter_tags | Tags used for filtering | string | `*` | no |
| memory_utilization_enabled | Flag to enable GCP Cloud SQL Memory Utilization monitor | string | `true` | no |
| memory_utilization_extra_tags | Extra tags for GCP Cloud SQL Memory Utilization monitor | list | `<list>` | no |
| memory_utilization_forecast_algorithm | Algorithm for the Memory Utilization Forecast monitor | string | `linear` | no |
| memory_utilization_forecast_deviations | Deviations for the Memory Utilization Forecast monitor | string | `1` | no |
| memory_utilization_forecast_enabled | Flag to enable GCP Cloud SQL Memory Utilization Forecast monitor | string | `true` | no |
| memory_utilization_forecast_extra_tags | Extra tags for GCP Cloud SQL Memory Utilization Forecast monitor | list | `<list>` | no |
| memory_utilization_forecast_interval | Interval for the Memory Utilization Forecast monitor | string | `30m` | no |
| memory_utilization_forecast_linear_history | History for the Memory Utilization Forecast monitor | string | `12h` | no |

36
cloud/gcp/cloud-sql/common/inputs.tf
View File

@ -65,6 +65,12 @@ variable "cpu_utilization_silenced" {
default = {}
}
variable "cpu_utilization_enabled" {
description = "Flag to enable GCP Cloud SQL CPU Utilization monitor"
type = "string"
default = "true"
}
variable "cpu_utilization_extra_tags" {
description = "Extra tags for GCP Cloud SQL CPU Utilization monitor"
type = "list"
@ -111,6 +117,12 @@ variable "disk_utilization_silenced" {
default = {}
}
variable "disk_utilization_enabled" {
description = "Flag to enable GCP Cloud SQL Disk Utilization monitor"
type = "string"
default = "true"
}
variable "disk_utilization_extra_tags" {
description = "Extra tags for GCP Cloud SQL CPU Utilization monitor"
type = "list"
@ -193,6 +205,12 @@ variable "disk_utilization_forecast_silenced" {
default = {}
}
variable "disk_utilization_forecast_enabled" {
description = "Flag to enable GCP Cloud SQL Disk Utilization Forecast monitor"
type = "string"
default = "true"
}
variable "disk_utilization_forecast_extra_tags" {
description = "Extra tags for GCP Cloud SQL Disk Utilization Forecast monitor"
type = "list"
@ -234,6 +252,12 @@ variable "memory_utilization_silenced" {
default = {}
}
variable "memory_utilization_enabled" {
description = "Flag to enable GCP Cloud SQL Memory Utilization monitor"
type = "string"
default = "true"
}
variable "memory_utilization_extra_tags" {
description = "Extra tags for GCP Cloud SQL Memory Utilization monitor"
type = "list"
@ -311,6 +335,12 @@ variable "memory_utilization_forecast_silenced" {
default = {}
}
variable "memory_utilization_forecast_enabled" {
description = "Flag to enable GCP Cloud SQL Memory Utilization Forecast monitor"
type = "string"
default = "true"
}
variable "memory_utilization_forecast_extra_tags" {
description = "Extra tags for GCP Cloud SQL Memory Utilization Forecast monitor"
type = "list"
@ -351,6 +381,12 @@ variable "failover_unavailable_silenced" {
default = {}
}
variable "failover_unavailable_enabled" {
description = "Flag to enable GCP Cloud SQL Failover Unavailable monitor"
type = "string"
default = "true"
}
variable "failover_unavailable_extra_tags" {
description = "Extra tags for GCP Cloud SQL Failover Unavailable monitor"
type = "list"

6
cloud/gcp/cloud-sql/common/monitors-cloud-sql-common.tf
View File

@ -2,6 +2,7 @@
# CPU Utilization
#
resource "datadog_monitor" "cpu_utilization" {
count = "${var.cpu_utilization_enabled ? 1 : 0}"
name = "[${var.environment}] Cloud SQL CPU Utilization {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.cpu_utilization_message, var.message)}"
@ -39,6 +40,7 @@ EOF
# Disk Utilization
#
resource "datadog_monitor" "disk_utilization" {
count = "${var.disk_utilization_enabled ? 1 : 0}"
name = "[${var.environment}] Cloud SQL Disk Utilization {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.disk_utilization_message, var.message)}"
@ -76,6 +78,7 @@ EOF
# Disk Utilization Forecast
#
resource "datadog_monitor" "disk_utilization_forecast" {
count = "${var.disk_utilization_forecast_enabled ? 1 : 0}"
name = "[${var.environment}] Cloud SQL Disk Utilization could reach {{#is_alert}}{{threshold}}%{{/is_alert}} in a near future"
message = "${coalesce(var.disk_utilization_forecast_message, var.message)}"
@ -119,6 +122,7 @@ EOF
# Memory Utilization
#
resource "datadog_monitor" "memory_utilization" {
count = "${var.memory_utilization_enabled ? 1 : 0}"
name = "[${var.environment}] Cloud SQL Memory Utilization {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.memory_utilization_message, var.message)}"
@ -156,6 +160,7 @@ EOF
# Memory Utilization Forecast
#
resource "datadog_monitor" "memory_utilization_forecast" {
count = "${var.memory_utilization_forecast_enabled ? 1 : 0}"
name = "[${var.environment}] Cloud SQL Memory Utilization could reach {{#is_alert}}{{threshold}}%{{/is_alert}} in a near future"
message = "${coalesce(var.memory_utilization_forecast_message, var.message)}"
@ -199,6 +204,7 @@ EOF
# Failover Unavailable
#
resource "datadog_monitor" "failover_unavailable" {
count = "${var.failover_unavailable_enabled ? 1 : 0}"
name = "[${var.environment}] Cloud SQL Failover Unavailable"
message = "${coalesce(var.failover_unavailable_message, var.message)}"

1
cloud/gcp/cloud-sql/mysql/README.md
View File

@ -27,6 +27,7 @@ Creates DataDog monitors with the following checks:
| filter_tags | Tags used for filtering | string | `*` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
| new_host_delay | Delay in seconds for the new host evaluation | string | `300` | no |
| replication_lag_enabled | Flag to enable GCP Cloud SQL Replication Lag monitor | string | `true` | no |
| replication_lag_extra_tags | Extra tags for GCP Cloud SQL SQL Replication monitor | list | `<list>` | no |
| replication_lag_message | Custom message for the Replication Lag monitor | string | `` | no |
| replication_lag_silenced | Groups to mute for GCP Cloud SQL Replication Lag monitor | map | `<map>` | no |

6
cloud/gcp/cloud-sql/mysql/inputs.tf
View File

@ -65,6 +65,12 @@ variable "replication_lag_silenced" {
default = {}
}
variable "replication_lag_enabled" {
description = "Flag to enable GCP Cloud SQL Replication Lag monitor"
type = "string"
default = "true"
}
variable "replication_lag_extra_tags" {
description = "Extra tags for GCP Cloud SQL SQL Replication monitor"
type = "list"

1
cloud/gcp/cloud-sql/mysql/monitors-cloudsql-mysql.tf
View File

@ -2,6 +2,7 @@
# Replication Lag
#
resource "datadog_monitor" "replication_lag" {
count = "${var.replication_lag_enabled ? 1 : 0}"
name = "[${var.environment}] Cloud SQL MySQL Replication Lag {{#is_alert}}{{{comparator}}} {{threshold}}s ({{value}}s){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}s ({{value}}s){{/is_warning}}"
message = "${coalesce(var.replication_lag_message, var.message)}"

5
cloud/gcp/lb/README.md
View File

@ -26,6 +26,7 @@ Creates DataDog monitors with the following checks:
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| backend_latency_bucket_enabled | Flag to enable GCP LB Backend Latency monitor | string | `true` | no |
| backend_latency_bucket_extra_tags | Extra tags for GCP LB Backend Latency monitor | list | `<list>` | no |
| backend_latency_bucket_message | Custom message for the GCP LB Backend Latency monitor | string | `` | no |
| backend_latency_bucket_silenced | Groups to mute for GCP LB Backend Latency monitor | map | `<map>` | no |
@ -33,6 +34,7 @@ Creates DataDog monitors with the following checks:
| backend_latency_bucket_threshold_warning | Latency in milliseconds (warning threshold) | string | `4000` | no |
| backend_latency_bucket_time_aggregator | Timeframe for the GCP LB Backend Latency monitor | string | `min` | no |
| backend_latency_bucket_timeframe | Timeframe for the GCP LB Backend Latency monitor | string | `last_10m` | no |
| backend_latency_service_enabled | Flag to enable GCP LB Backend Latency monitor | string | `true` | no |
| backend_latency_service_extra_tags | Extra tags for GCP LB Backend Latency monitor | list | `<list>` | no |
| backend_latency_service_message | Custom message for the GCP LB Backend Latency monitor | string | `` | no |
| backend_latency_service_silenced | Groups to mute for GCP LB Backend Latency monitor | map | `<map>` | no |
@ -42,6 +44,7 @@ Creates DataDog monitors with the following checks:
| backend_latency_service_timeframe | Timeframe for the GCP LB Backend Latency monitor | string | `last_10m` | no |
| environment | Architecture environment | string | - | yes |
| error_rate_4xx_artificial_request | Divisor Delta for the GCP LB 4XX Errors monitor | string | `5` | no |
| error_rate_4xx_enabled | Flag to enable GCP LB 4XX Errors monitor | string | `true` | no |
| error_rate_4xx_extra_tags | Extra tags for GCP LB 4XX Errors monitor | list | `<list>` | no |
| error_rate_4xx_message | Custom message for the GCP LB 4XX Errors monitor | string | `` | no |
| error_rate_4xx_silenced | Groups to mute for GCP LB 4XX Errors monitor | map | `<map>` | no |
@ -50,6 +53,7 @@ Creates DataDog monitors with the following checks:
| error_rate_4xx_time_aggregator | Timeframe for the GCP LB 4XX Errors monitor | string | `sum` | no |
| error_rate_4xx_timeframe | Timeframe for the GCP LB 4XX Errors monitor | string | `last_5m` | no |
| error_rate_5xx_artificial_request | Divisor Delta for the GCP LB 5XX Errors monitor | string | `5` | no |
| error_rate_5xx_enabled | Flag to enable GCP LB 5XX Errors monitor | string | `true` | no |
| error_rate_5xx_extra_tags | Extra tags for GCP LB 5XX Errors monitor | list | `<list>` | no |
| error_rate_5xx_message | Custom message for the GCP LB 5XX Errors monitor | string | `` | no |
| error_rate_5xx_silenced | Groups to mute for GCP LB 5XX Errors monitor | map | `<map>` | no |
@ -61,6 +65,7 @@ Creates DataDog monitors with the following checks:
| filter_tags | Tags used for filtering | string | `*` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
| new_host_delay | Delay in seconds for the new host evaluation | string | `300` | no |
| request_count_enabled | Flag to enable GCP LB Request Count monitor | string | `true` | no |
| request_count_extra_tags | Extra tags for GCP LB Request Count monitor | list | `<list>` | no |
| request_count_message | Custom message for the GCP LB Request Count monitor | string | `` | no |
| request_count_silenced | Groups to mute for GCP LB Request Count monitor | map | `<map>` | no |

30
cloud/gcp/lb/inputs.tf
View File

@ -70,6 +70,12 @@ variable "error_rate_4xx_silenced" {
default = {}
}
variable "error_rate_4xx_enabled" {
description = "Flag to enable GCP LB 4XX Errors monitor"
type = "string"
default = "true"
}
variable "error_rate_4xx_extra_tags" {
description = "Extra tags for GCP LB 4XX Errors monitor"
type = "list"
@ -121,6 +127,12 @@ variable "error_rate_5xx_silenced" {
default = {}
}
variable "error_rate_5xx_enabled" {
description = "Flag to enable GCP LB 5XX Errors monitor"
type = "string"
default = "true"
}
variable "error_rate_5xx_extra_tags" {
description = "Extra tags for GCP LB 5XX Errors monitor"
type = "list"
@ -166,6 +178,12 @@ variable "backend_latency_service_silenced" {
default = {}
}
variable "backend_latency_service_enabled" {
description = "Flag to enable GCP LB Backend Latency monitor"
type = "string"
default = "true"
}
variable "backend_latency_service_extra_tags" {
description = "Extra tags for GCP LB Backend Latency monitor"
type = "list"
@ -211,6 +229,12 @@ variable "backend_latency_bucket_silenced" {
default = {}
}
variable "backend_latency_bucket_enabled" {
description = "Flag to enable GCP LB Backend Latency monitor"
type = "string"
default = "true"
}
variable "backend_latency_bucket_extra_tags" {
description = "Extra tags for GCP LB Backend Latency monitor"
type = "list"
@ -262,6 +286,12 @@ variable "request_count_silenced" {
default = {}
}
variable "request_count_enabled" {
description = "Flag to enable GCP LB Request Count monitor"
type = "string"
default = "true"
}
variable "request_count_extra_tags" {
description = "Extra tags for GCP LB Request Count monitor"
type = "list"

5
cloud/gcp/lb/monitors-lb.tf
View File

@ -2,6 +2,7 @@
# 4XX Errors
#
resource "datadog_monitor" "error_rate_4xx" {
count = "${var.error_rate_4xx_enabled ? 1 : 0}"
name = "[${var.environment}] GCP LB 4xx errors {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.error_rate_4xx_message, var.message)}"
@ -40,6 +41,7 @@ EOF
# 5XX Errors
#
resource "datadog_monitor" "error_rate_5xx" {
count = "${var.error_rate_5xx_enabled ? 1 : 0}"
name = "[${var.environment}] GCP LB 5xx errors {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.error_rate_5xx_message, var.message)}"
@ -78,6 +80,7 @@ EOF
# Backend Latency for service
#
resource "datadog_monitor" "backend_latency_service" {
count = "${var.backend_latency_service_enabled ? 1 : 0}"
name = "[${var.environment}] GCP LB service backend latency {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.backend_latency_service_message, var.message)}"
@ -114,6 +117,7 @@ EOF
# Backend Latency for bucket
#
resource "datadog_monitor" "backend_latency_bucket" {
count = "${var.backend_latency_bucket_enabled ? 1 : 0}"
name = "[${var.environment}] GCP LB bucket backend latency {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.backend_latency_bucket_message, var.message)}"
@ -150,6 +154,7 @@ EOF
# Request Count
#
resource "datadog_monitor" "request_count" {
count = "${var.request_count_enabled ? 1 : 0}"
name = "[${var.environment}] GCP LB Requests count increased abruptly {{#is_alert}}{{value}}%{{/is_alert}}{{#is_warning}}{{value}}%{{/is_warning}}"
message = "${coalesce(var.request_count_message, var.message)}"

2
cloud/gcp/pubsub/README.md
View File

@ -28,12 +28,14 @@ Creates DataDog monitors with the following checks:
| filter_tags | Tags used for filtering | string | `*` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
| new_host_delay | Delay in seconds for the new host evaluation | string | `300` | no |
| sending_operations_count_enabled | Flag to enable GCP Pub/Sub Unavailable Sending Operations Count monitor | string | `true` | no |
| sending_operations_count_extra_tags | Extra tags for GCP Pub/Sub Sending Operations Count monitor | list | `<list>` | no |
| sending_operations_count_message | Custom message for the GCP Pub/Sub Sending Operations Count monitor | string | `` | no |
| sending_operations_count_silenced | Groups to mute for GCP Pub/Sub Sending Operations Count monitor | map | `<map>` | no |
| sending_operations_count_threshold_critical | Critical threshold for the number of sending operations. | string | `0` | no |
| sending_operations_count_time_aggregator | Timeframe for the GCP Pub/Sub Sending Operations Count monitor | string | `sum` | no |
| sending_operations_count_timeframe | Timeframe for the GCP Pub/Sub Sending Operations Count monitor | string | `last_30m` | no |
| unavailable_sending_operations_count_enabled | Flag to enable GCP Pub/Sub Unavailable Sending Operations Count monitor | string | `true` | no |
| unavailable_sending_operations_count_extra_tags | Extra tags for GCP Pub/Sub Unavailable Sending Operations Count monitor | list | `<list>` | no |
| unavailable_sending_operations_count_message | Custom message for the GCP Pub/Sub Unavailable Sending Operations Count monitor | string | `` | no |
| unavailable_sending_operations_count_silenced | Groups to mute for GCP Pub/Sub Unavailable Sending Operations Count monitor | map | `<map>` | no |

12
cloud/gcp/pubsub/inputs.tf
View File

@ -58,6 +58,12 @@ variable "sending_operations_count_silenced" {
default = {}
}
variable "sending_operations_count_enabled" {
description = "Flag to enable GCP Pub/Sub Unavailable Sending Operations Count monitor"
type = "string"
default = "true"
}
variable "sending_operations_count_extra_tags" {
description = "Extra tags for GCP Pub/Sub Sending Operations Count monitor"
type = "list"
@ -103,6 +109,12 @@ variable "unavailable_sending_operations_count_silenced" {
default = {}
}
variable "unavailable_sending_operations_count_enabled" {
description = "Flag to enable GCP Pub/Sub Unavailable Sending Operations Count monitor"
type = "string"
default = "true"
}
variable "unavailable_sending_operations_count_extra_tags" {
description = "Extra tags for GCP Pub/Sub Unavailable Sending Operations Count monitor"
type = "list"

2
cloud/gcp/pubsub/monitors-pubsub.tf
View File

@ -2,6 +2,7 @@
# Sending Operations Count
#
resource "datadog_monitor" "sending_operations_count" {
count = "${var.sending_operations_count_enabled ? 1 : 0}"
name = "[${var.environment}] GCP pubsub sending messages operations {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.sending_operations_count_message, var.message)}"
@ -37,6 +38,7 @@ EOF
# Unavailable Sending Operations Count
#
resource "datadog_monitor" "unavailable_sending_operations_count" {
count = "${var.unavailable_sending_operations_count_enabled ? 1 : 0}"
name = "[${var.environment}] GCP pubsub sending messages with result unavailable {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.unavailable_sending_operations_count_message, var.message)}"

22
database/elasticsearch/README.md
View File

@ -43,6 +43,7 @@ Creates DataDog monitors with the following checks:
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| cluster_initializing_shards_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| cluster_initializing_shards_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| cluster_initializing_shards_message | Custom message for the Cluster Status monitor | string | `` | no |
| cluster_initializing_shards_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -50,6 +51,7 @@ Creates DataDog monitors with the following checks:
| cluster_initializing_shards_threshold_warning | Cluster Status warning threshold | string | `1` | no |
| cluster_initializing_shards_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| cluster_initializing_shards_timeframe | Timeframe for the Cluster Status monitor | string | `last_5m` | no |
| cluster_relocating_shards_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| cluster_relocating_shards_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| cluster_relocating_shards_message | Custom message for the Cluster Status monitor | string | `` | no |
| cluster_relocating_shards_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -57,6 +59,7 @@ Creates DataDog monitors with the following checks:
| cluster_relocating_shards_threshold_warning | Cluster Status warning threshold | string | `1` | no |
| cluster_relocating_shards_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| cluster_relocating_shards_timeframe | Timeframe for the Cluster Status monitor | string | `last_5m` | no |
| cluster_status_not_green_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| cluster_status_not_green_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| cluster_status_not_green_message | Custom message for the Cluster Status monitor | string | `` | no |
| cluster_status_not_green_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -64,6 +67,7 @@ Creates DataDog monitors with the following checks:
| cluster_status_not_green_threshold_warning | Cluster Status warning threshold | string | `1` | no |
| cluster_status_not_green_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| cluster_status_not_green_timeframe | Timeframe for the Cluster Status monitor | string | `last_5m` | no |
| cluster_unassigned_shards_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| cluster_unassigned_shards_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| cluster_unassigned_shards_message | Custom message for the Cluster Status monitor | string | `` | no |
| cluster_unassigned_shards_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -73,6 +77,7 @@ Creates DataDog monitors with the following checks:
| cluster_unassigned_shards_timeframe | Timeframe for the Cluster Status monitor | string | `last_5m` | no |
| environment | Architecture environment | string | - | yes |
| evaluation_delay | Delay in seconds for the metric evaluation | string | `15` | no |
| fetch_change_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| fetch_change_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| fetch_change_message | Custom message for the Cluster Status monitor | string | `` | no |
| fetch_change_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -81,6 +86,7 @@ Creates DataDog monitors with the following checks:
| fetch_change_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| fetch_change_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| fetch_change_timeshift | Timeshift for the Cluster Status monitor | string | `last_10m` | no |
| fetch_latency_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| fetch_latency_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| fetch_latency_message | Custom message for the Cluster Status monitor | string | `` | no |
| fetch_latency_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -88,6 +94,7 @@ Creates DataDog monitors with the following checks:
| fetch_latency_threshold_warning | Cluster Status warning threshold | string | `2` | no |
| fetch_latency_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| fetch_latency_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| field_data_evictions_change_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| field_data_evictions_change_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| field_data_evictions_change_message | Custom message for the Cluster Status monitor | string | `` | no |
| field_data_evictions_change_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -98,6 +105,7 @@ Creates DataDog monitors with the following checks:
| field_data_evictions_change_timeshift | Timeframe for the Cluster Status monitor | string | `last_15m` | no |
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| flush_latency_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| flush_latency_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| flush_latency_message | Custom message for the Cluster Status monitor | string | `` | no |
| flush_latency_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -110,6 +118,7 @@ Creates DataDog monitors with the following checks:
| http_connections_anomaly_detection_algorithm | Anomaly Detection Algorithm used | string | `agile` | no |
| http_connections_anomaly_deviations | Deviations to detect the anomaly | string | `2` | no |
| http_connections_anomaly_direction | Direction of the anomaly. It can be both, below or above. | string | `above` | no |
| http_connections_anomaly_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| http_connections_anomaly_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| http_connections_anomaly_interval | Interval. | string | `60` | no |
| http_connections_anomaly_message | Custom message for the Cluster Status monitor | string | `` | no |
@ -119,6 +128,7 @@ Creates DataDog monitors with the following checks:
| http_connections_anomaly_threshold_warning | Cluster Status warning threshold | string | `0.75` | no |
| http_connections_anomaly_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| http_connections_anomaly_timeframe | Timeframe for the Cluster Status monitor | string | `last_4h` | no |
| indexing_latency_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| indexing_latency_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| indexing_latency_message | Custom message for the Cluster Status monitor | string | `` | no |
| indexing_latency_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -126,6 +136,7 @@ Creates DataDog monitors with the following checks:
| indexing_latency_threshold_warning | Cluster Status warning threshold | string | `10` | no |
| indexing_latency_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| indexing_latency_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| jvm_gc_old_collection_latency_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| jvm_gc_old_collection_latency_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| jvm_gc_old_collection_latency_message | Custom message for the Cluster Status monitor | string | `` | no |
| jvm_gc_old_collection_latency_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -133,6 +144,7 @@ Creates DataDog monitors with the following checks:
| jvm_gc_old_collection_latency_threshold_warning | Cluster Status warning threshold | string | `160` | no |
| jvm_gc_old_collection_latency_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| jvm_gc_old_collection_latency_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| jvm_gc_young_collection_latency_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| jvm_gc_young_collection_latency_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| jvm_gc_young_collection_latency_message | Custom message for the Cluster Status monitor | string | `` | no |
| jvm_gc_young_collection_latency_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -140,6 +152,7 @@ Creates DataDog monitors with the following checks:
| jvm_gc_young_collection_latency_threshold_warning | Cluster Status warning threshold | string | `20` | no |
| jvm_gc_young_collection_latency_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| jvm_gc_young_collection_latency_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| jvm_heap_memory_usage_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| jvm_heap_memory_usage_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| jvm_heap_memory_usage_message | Custom message for the Cluster Status monitor | string | `` | no |
| jvm_heap_memory_usage_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -147,6 +160,7 @@ Creates DataDog monitors with the following checks:
| jvm_heap_memory_usage_threshold_warning | Cluster Status warning threshold | string | `80` | no |
| jvm_heap_memory_usage_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| jvm_heap_memory_usage_timeframe | Timeframe for the Cluster Status monitor | string | `last_5m` | no |
| jvm_memory_old_usage_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| jvm_memory_old_usage_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| jvm_memory_old_usage_message | Custom message for the Cluster Status monitor | string | `` | no |
| jvm_memory_old_usage_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -154,6 +168,7 @@ Creates DataDog monitors with the following checks:
| jvm_memory_old_usage_threshold_warning | Cluster Status warning threshold | string | `80` | no |
| jvm_memory_old_usage_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| jvm_memory_old_usage_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| jvm_memory_young_usage_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| jvm_memory_young_usage_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| jvm_memory_young_usage_message | Custom message for the Cluster Status monitor | string | `` | no |
| jvm_memory_young_usage_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -163,6 +178,7 @@ Creates DataDog monitors with the following checks:
| jvm_memory_young_usage_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
| new_host_delay | Delay in seconds before begin to monitor new host | string | `300` | no |
| node_free_space_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| node_free_space_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| node_free_space_message | Custom message for the Cluster Status monitor | string | `` | no |
| node_free_space_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -170,11 +186,13 @@ Creates DataDog monitors with the following checks:
| node_free_space_threshold_warning | Cluster Status warning threshold | string | `20` | no |
| node_free_space_time_aggregator | Time aggregator for the Cluster Status monitor | string | `sum` | no |
| node_free_space_timeframe | Timeframe for the Cluster Status monitor | string | `last_5m` | no |
| not_responding_enabled | Flag to enable Elasticsearch does not respond monitor | string | `true` | no |
| not_responding_extra_tags | Extra tags for Elasticsearch does not respond monitor | list | `<list>` | no |
| not_responding_message | Custom message for Elasticsearch does not respond monitor | string | `` | no |
| not_responding_no_data_timeframe | Elasticsearch not responding monitor no data timeframe | string | `10` | no |
| not_responding_silenced | Groups to mute for Elasticsearch does not respond monitor | map | `<map>` | no |
| not_responding_threshold_warning | Elasticsearch not responding limit (warning threshold) | string | `3` | no |
| query_cache_evictions_change_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| query_cache_evictions_change_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| query_cache_evictions_change_message | Custom message for the Cluster Status monitor | string | `` | no |
| query_cache_evictions_change_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -183,6 +201,7 @@ Creates DataDog monitors with the following checks:
| query_cache_evictions_change_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| query_cache_evictions_change_timeframe | Timeframe for the Cluster Status monitor | string | `last_15m` | no |
| query_cache_evictions_change_timeshift | Timeframe for the Cluster Status monitor | string | `last_15m` | no |
| request_cache_evictions_change_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| request_cache_evictions_change_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| request_cache_evictions_change_message | Custom message for the Cluster Status monitor | string | `` | no |
| request_cache_evictions_change_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -191,6 +210,7 @@ Creates DataDog monitors with the following checks:
| request_cache_evictions_change_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| request_cache_evictions_change_timeframe | Timeframe for the Cluster Status monitor | string | `last_15m` | no |
| request_cache_evictions_change_timeshift | Timeshift for the Cluster Status monitor | string | `last_15m` | no |
| search_query_change_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| search_query_change_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| search_query_change_message | Custom message for the Cluster Status monitor | string | `` | no |
| search_query_change_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -199,6 +219,7 @@ Creates DataDog monitors with the following checks:
| search_query_change_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| search_query_change_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| search_query_change_timeshift | Timeshift for the Cluster Status monitor | string | `last_10m` | no |
| search_query_latency_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| search_query_latency_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| search_query_latency_message | Custom message for the Cluster Status monitor | string | `` | no |
| search_query_latency_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |
@ -206,6 +227,7 @@ Creates DataDog monitors with the following checks:
| search_query_latency_threshold_warning | Cluster Status warning threshold | string | `0.5` | no |
| search_query_latency_time_aggregator | Time aggregator for the Cluster Status monitor | string | `avg` | no |
| search_query_latency_timeframe | Timeframe for the Cluster Status monitor | string | `last_10m` | no |
| task_time_in_queue_change_enabled | Flag to enable Cluster Status monitor | string | `true` | no |
| task_time_in_queue_change_extra_tags | Extra tags for Cluster Status monitor | list | `<list>` | no |
| task_time_in_queue_change_message | Custom message for the Cluster Status monitor | string | `` | no |
| task_time_in_queue_change_silenced | Groups to mute for Cluster Status monitor | map | `<map>` | no |

132
database/elasticsearch/inputs.tf
View File

@ -69,6 +69,12 @@ variable "cluster_status_not_green_silenced" {
default = {}
}
variable "cluster_status_not_green_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "cluster_status_not_green_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -114,6 +120,12 @@ variable "cluster_initializing_shards_silenced" {
default = {}
}
variable "cluster_initializing_shards_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "cluster_initializing_shards_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -159,6 +171,12 @@ variable "cluster_relocating_shards_silenced" {
default = {}
}
variable "cluster_relocating_shards_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "cluster_relocating_shards_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -204,6 +222,12 @@ variable "cluster_unassigned_shards_silenced" {
default = {}
}
variable "cluster_unassigned_shards_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "cluster_unassigned_shards_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -249,6 +273,12 @@ variable "node_free_space_silenced" {
default = {}
}
variable "node_free_space_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "node_free_space_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -294,6 +324,12 @@ variable "jvm_heap_memory_usage_silenced" {
default = {}
}
variable "jvm_heap_memory_usage_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "jvm_heap_memory_usage_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -339,6 +375,12 @@ variable "jvm_memory_young_usage_silenced" {
default = {}
}
variable "jvm_memory_young_usage_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "jvm_memory_young_usage_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -384,6 +426,12 @@ variable "jvm_memory_old_usage_silenced" {
default = {}
}
variable "jvm_memory_old_usage_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "jvm_memory_old_usage_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -429,6 +477,12 @@ variable "jvm_gc_old_collection_latency_silenced" {
default = {}
}
variable "jvm_gc_old_collection_latency_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "jvm_gc_old_collection_latency_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -474,6 +528,12 @@ variable "jvm_gc_young_collection_latency_silenced" {
default = {}
}
variable "jvm_gc_young_collection_latency_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "jvm_gc_young_collection_latency_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -519,6 +579,12 @@ variable "indexing_latency_silenced" {
default = {}
}
variable "indexing_latency_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "indexing_latency_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -564,6 +630,12 @@ variable "flush_latency_silenced" {
default = {}
}
variable "flush_latency_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "flush_latency_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -651,6 +723,12 @@ variable "http_connections_anomaly_silenced" {
default = {}
}
variable "http_connections_anomaly_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "http_connections_anomaly_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -696,6 +774,12 @@ variable "search_query_latency_silenced" {
default = {}
}
variable "search_query_latency_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "search_query_latency_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -741,6 +825,12 @@ variable "fetch_latency_silenced" {
default = {}
}
variable "fetch_latency_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "fetch_latency_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -792,6 +882,12 @@ variable "search_query_change_silenced" {
default = {}
}
variable "search_query_change_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "search_query_change_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -843,6 +939,12 @@ variable "fetch_change_silenced" {
default = {}
}
variable "fetch_change_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "fetch_change_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -894,6 +996,12 @@ variable "field_data_evictions_change_silenced" {
default = {}
}
variable "field_data_evictions_change_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "field_data_evictions_change_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -945,6 +1053,12 @@ variable "query_cache_evictions_change_silenced" {
default = {}
}
variable "query_cache_evictions_change_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "query_cache_evictions_change_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -996,6 +1110,12 @@ variable "request_cache_evictions_change_silenced" {
default = {}
}
variable "request_cache_evictions_change_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "request_cache_evictions_change_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -1047,6 +1167,12 @@ variable "task_time_in_queue_change_silenced" {
default = {}
}
variable "task_time_in_queue_change_enabled" {
description = "Flag to enable Cluster Status monitor"
type = "string"
default = "true"
}
variable "task_time_in_queue_change_extra_tags" {
description = "Extra tags for Cluster Status monitor"
type = "list"
@ -1062,6 +1188,12 @@ variable "not_responding_silenced" {
default = {}
}
variable "not_responding_enabled" {
description = "Flag to enable Elasticsearch does not respond monitor"
type = "string"
default = "true"
}
variable "not_responding_message" {
description = "Custom message for Elasticsearch does not respond monitor"
type = "string"

22
database/elasticsearch/monitors-elasticsearch.tf
View File

@ -2,6 +2,7 @@
# Service Check
#
resource "datadog_monitor" "not_responding" {
count = "${var.not_responding_enabled ? 1 : 0}"
name = "[${var.environment}] ElasticSearch does not respond"
message = "${coalesce(var.not_responding_message, var.message)}"
@ -44,6 +45,7 @@ EOL
# Cluster Status Not Green
#
resource "datadog_monitor" "cluster_status_not_green" {
count = "${var.cluster_status_not_green_enabled ? 1 : 0}"
name = "[${var.environment}] ElasticSearch Cluster status not green"
message = "${coalesce(var.cluster_status_not_green_message, var.message)}"
@ -86,6 +88,7 @@ EOF
# Cluster Initializing Shards
#
resource "datadog_monitor" "cluster_initializing_shards" {
count = "${var.cluster_initializing_shards_enabled ? 1 : 0}"
name = "[${var.environment}] ElasticSearch Cluster is initializing shards"
message = "${coalesce(var.cluster_initializing_shards_message, var.message)}"
@ -127,6 +130,7 @@ EOF
# Cluster Relocating Shards
#
resource "datadog_monitor" "cluster_relocating_shards" {
count = "${var.cluster_relocating_shards_enabled ? 1 : 0}"
name = "[${var.environment}] ElasticSearch Cluster is relocating shards"
message = "${coalesce(var.cluster_relocating_shards_message, var.message)}"
@ -168,6 +172,7 @@ EOF
# Cluster Unassigned Shards
#
resource "datadog_monitor" "cluster_unassigned_shards" {
count = "${var.cluster_unassigned_shards_enabled ? 1 : 0}"
name = "[${var.environment}] ElasticSearch Cluster has unassigned shards"
message = "${coalesce(var.cluster_unassigned_shards_message, var.message)}"
@ -209,6 +214,7 @@ EOF
# Free Space in nodes
#
resource "datadog_monitor" "node_free_space" {
count = "${var.node_free_space_enabled ? 1 : 0}"
name = "[${var.environment}] ElasticSearch free space < 10%"
message = "${coalesce(var.node_free_space_message, var.message)}"
@ -253,6 +259,7 @@ EOF
# JVM Heap Memory Usage
#
resource "datadog_monitor" "jvm_heap_memory_usage" {
count = "${var.jvm_heap_memory_usage_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch JVM HEAP memory usage {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.jvm_heap_memory_usage_message, var.message)}"
@ -294,6 +301,7 @@ EOF
# JVM Memory Young Usage
#
resource "datadog_monitor" "jvm_memory_young_usage" {
count = "${var.jvm_memory_young_usage_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch JVM memory Young usage {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.jvm_memory_young_usage_message, var.message)}"
@ -335,6 +343,7 @@ EOF
# JVM Memory Old Usage
#
resource "datadog_monitor" "jvm_memory_old_usage" {
count = "${var.jvm_memory_old_usage_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch JVM memory Old usage {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.jvm_memory_old_usage_message, var.message)}"
@ -376,6 +385,7 @@ EOF
# JVM Garbace Collector Old Collection Latency
#
resource "datadog_monitor" "jvm_gc_old_collection_latency" {
count = "${var.jvm_gc_old_collection_latency_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch average Old-generation garbage collections latency {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.jvm_gc_old_collection_latency_message, var.message)}"
@ -417,6 +427,7 @@ EOF
# JVM Garbace Collector Young Collection Latency
#
resource "datadog_monitor" "jvm_gc_young_collection_latency" {
count = "${var.jvm_gc_young_collection_latency_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch average Young-generation garbage collections latency {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.jvm_gc_young_collection_latency_message, var.message)}"
@ -458,6 +469,7 @@ EOF
# Indexing Latency
#
resource "datadog_monitor" "indexing_latency" {
count = "${var.indexing_latency_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch average indexing time by document {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.indexing_latency_message, var.message)}"
@ -500,6 +512,7 @@ EOF
# Flush Latency
#
resource "datadog_monitor" "flush_latency" {
count = "${var.flush_latency_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch average index flushing to disk latency {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.flush_latency_message, var.message)}"
@ -542,6 +555,7 @@ EOF
# Open HTTP Connections Anomaly
#
resource "datadog_monitor" "http_connections_anomaly" {
count = "${var.http_connections_anomaly_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch number of current open HTTP connections anomaly detected"
message = "${coalesce(var.http_connections_anomaly_message, var.message)}"
@ -591,6 +605,7 @@ EOF
# Query Latency
#
resource "datadog_monitor" "search_query_latency" {
count = "${var.search_query_latency_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch average search query latency {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.search_query_latency_message, var.message)}"
@ -633,6 +648,7 @@ EOF
# Fetch Latency
#
resource "datadog_monitor" "fetch_latency" {
count = "${var.fetch_latency_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch average search fetch latency {{#is_alert}}{{{comparator}}} {{threshold}}ms ({{value}}ms){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}ms ({{value}}ms){{/is_warning}}"
message = "${coalesce(var.fetch_latency_message, var.message)}"
@ -675,6 +691,7 @@ EOF
# Search Query Change
#
resource "datadog_monitor" "search_query_change" {
count = "${var.search_query_change_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch change alert on the number of currently active queries"
message = "${coalesce(var.search_query_change_message, var.message)}"
@ -716,6 +733,7 @@ EOF
# Fetch Change
#
resource "datadog_monitor" "fetch_change" {
count = "${var.fetch_change_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch change alert on the number of search fetches currently running"
message = "${coalesce(var.fetch_change_message, var.message)}"
@ -757,6 +775,7 @@ EOF
# Field Data Evictions
#
resource "datadog_monitor" "field_data_evictions_change" {
count = "${var.field_data_evictions_change_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch change alert on the total number of evictions from the fielddata cache"
message = "${coalesce(var.field_data_evictions_change_message, var.message)}"
@ -799,6 +818,7 @@ EOF
# Query Cache Evictions
#
resource "datadog_monitor" "query_cache_evictions_change" {
count = "${var.query_cache_evictions_change_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch change alert on the number of query cache evictions"
message = "${coalesce(var.query_cache_evictions_change_message, var.message)}"
@ -841,6 +861,7 @@ EOF
# Request Cache Evictions
#
resource "datadog_monitor" "request_cache_evictions_change" {
count = "${var.request_cache_evictions_change_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch change alert on the number of request cache evictions"
message = "${coalesce(var.request_cache_evictions_change_message, var.message)}"
@ -883,6 +904,7 @@ EOF
# Task Time in Queue
#
resource "datadog_monitor" "task_time_in_queue_change" {
count = "${var.task_time_in_queue_change_enabled ? 1 : 0}"
name = "[${var.environment}] Elasticsearch change alert on the average time spent by tasks in the queue"
message = "${coalesce(var.task_time_in_queue_change_message, var.message)}"

22
database/mysql/README.md
View File

@ -34,35 +34,40 @@ Creates DataDog monitors with the following checks:
| filter_tags_custom | Tags used for custom filtering when filter_tags_use_defaults is false | string | `*` | no |
| filter_tags_use_defaults | Use default filter tags convention | string | `true` | no |
| message | Message sent when an alert is triggered | string | - | yes |
| mysql_aborted_enabled | Flag to enable MySQL aborted connects monitor | string | `true` | no |
| mysql_aborted_extra_tags | Extra tags for MySQL aborted connects monitor | list | `<list>` | no |
| mysql_aborted_message | Custom message for MySQL aborted connects monitor | string | `` | no |
| mysql_aborted_silenced | Groups to mute MySQL aborted connects monitor | map | `<map>` | no |
| mysql_aborted_silenced | Groups to mute for MySQL aborted connects monitor | map | `<map>` | no |
| mysql_aborted_threshold_critical | Maximum critical acceptable percent of aborted connects | string | `10` | no |
| mysql_aborted_threshold_warning | Maximum warning acceptable percent of aborted connects | string | `5` | no |
| mysql_aborted_time_aggregator | Monitor time aggregator for MySQL aborted connects monitor [available values: min, max or avg] | string | `avg` | no |
| mysql_aborted_timeframe | Monitor timeframe for MySQL aborted connects monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_10m` | no |
| mysql_availability_enabled | Flag to enable Mysql availability monitor | string | `true` | no |
| mysql_availability_extra_tags | Extra tags for Mysql availability monitor | list | `<list>` | no |
| mysql_availability_message | Custom message for Mysql availability monitor | string | `` | no |
| mysql_availability_no_data_timeframe | Mysql availability monitor no data timeframe | string | `10` | no |
| mysql_availability_silenced | Groups to mute for Mysql availability monitor | map | `<map>` | no |
| mysql_availability_threshold_warning | Mysql availability monitor (warning threshold) | string | `3` | no |
| mysql_connection_enabled | Flag to enable MySQL connection monitor | string | `true` | no |
| mysql_connection_extra_tags | Extra tags for MySQL connection monitor | list | `<list>` | no |
| mysql_connection_message | Custom message for MySQL connection monitor | string | `` | no |
| mysql_connection_silenced | Groups to mute MySQL connection monitor | map | `<map>` | no |
| mysql_connection_silenced | Groups to mute for MySQL connection monitor | map | `<map>` | no |
| mysql_connection_threshold_critical | Maximum critical acceptable percent of connections | string | `80` | no |
| mysql_connection_threshold_warning | Maximum warning acceptable percent of connections | string | `70` | no |
| mysql_connection_time_aggregator | Monitor time aggregator for MySQL connection monitor [available values: min, max or avg] | string | `avg` | no |
| mysql_connection_timeframe | Monitor timeframe for MySQL connection monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_10m` | no |
| mysql_pool_efficiency_enabled | Flag to enable MySQL innodb buffer pool efficiency monitor | string | `true` | no |
| mysql_pool_efficiency_extra_tags | Extra tags for MySQL innodb buffer pool efficiency monitor | list | `<list>` | no |
| mysql_pool_efficiency_message | Custom message for MySQL innodb buffer pool efficiency monitor | string | `` | no |
| mysql_pool_efficiency_silenced | Groups to mute MySQL innodb buffer pool efficiency monitor | map | `<map>` | no |
| mysql_pool_efficiency_silenced | Groups to mute for MySQL innodb buffer pool efficiency monitor | map | `<map>` | no |
| mysql_pool_efficiency_threshold_critical | Maximum critical acceptable percent of innodb buffer pool efficiency | string | `20` | no |
| mysql_pool_efficiency_threshold_warning | Maximum warning acceptable percent of innodb buffer pool efficiency | string | `1` | no |
| mysql_pool_efficiency_time_aggregator | Monitor time aggregator for MySQL innodb buffer pool efficiency monitor [available values: min, max or avg] | string | `sum` | no |
| mysql_pool_efficiency_timeframe | Monitor timeframe for MySQL innodb buffer pool efficiency monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_1h` | no |
| mysql_pool_utilization_enabled | Flag to enable MySQL innodb buffer pool utilization monitor | string | `true` | no |
| mysql_pool_utilization_extra_tags | Extra tags for MySQL innodb buffer pool utilization monitor | list | `<list>` | no |
| mysql_pool_utilization_message | Custom message for MySQL innodb buffer pool utilization monitor | string | `` | no |
| mysql_pool_utilization_silenced | Groups to mute MySQL innodb buffer pool utilization monitor | map | `<map>` | no |
| mysql_pool_utilization_silenced | Groups to mute for MySQL innodb buffer pool utilization monitor | map | `<map>` | no |
| mysql_pool_utilization_threshold_critical | Maximum critical acceptable percent of innodb buffer pool utilization | string | `90` | no |
| mysql_pool_utilization_threshold_warning | Maximum warning acceptable percent of innodb buffer pool utilization | string | `75` | no |
| mysql_pool_utilization_time_aggregator | Monitor time aggregator for MySQL innodb buffer pool utilization monitor [available values: min, max or avg] | string | `min` | no |
@ -72,17 +77,19 @@ Creates DataDog monitors with the following checks:
| mysql_queries_detection_algorithm | Anomaly Detection Algorithm used | string | `agile` | no |
| mysql_queries_deviations | Deviations to detect the anomaly | string | `5` | no |
| mysql_queries_direction | Direction of the anomaly. It can be both, below or above. | string | `both` | no |
| mysql_queries_enabled | Flag to enable mysql queries monitor | string | `true` | no |
| mysql_queries_extra_tags | Extra tags for MySQL queries monitor | list | `<list>` | no |
| mysql_queries_interval | Interval. | string | `60` | no |
| mysql_queries_message | Custom message for MySQL queries monitor | string | `` | no |
| mysql_queries_seasonality | Seasonality of the algorithm | string | `daily` | no |
| mysql_queries_silenced | Groups to mute mysql queries monitor | map | `<map>` | no |
| mysql_queries_silenced | Groups to mute for mysql queries monitor | map | `<map>` | no |
| mysql_queries_threshold_critical | Maximum critical acceptable number of queries | string | `1` | no |
| mysql_queries_time_aggregator | Monitor time aggregator for MySQL queries monitor [available values: min, max or avg] | string | `avg` | no |
| mysql_queries_timeframe | Monitor timeframe for MySQL queries monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_4h` | no |
| mysql_slow_enabled | Flag to enable MySQL slow queries monitor | string | `true` | no |
| mysql_slow_extra_tags | Extra tags for MySQL slow queries monitor | list | `<list>` | no |
| mysql_slow_message | Custom message for MySQL slow queries monitor | string | `` | no |
| mysql_slow_silenced | Groups to mute MySQL slow queries monitor | map | `<map>` | no |
| mysql_slow_silenced | Groups to mute for MySQL slow queries monitor | map | `<map>` | no |
| mysql_slow_threshold_critical | Maximum critical acceptable percent of slow queries | string | `20` | no |
| mysql_slow_threshold_warning | Maximum warning acceptable percent of slow queries | string | `5` | no |
| mysql_slow_time_aggregator | Monitor time aggregator for MySQL slow queries monitor [available values: min, max or avg] | string | `avg` | no |
@ -92,11 +99,12 @@ Creates DataDog monitors with the following checks:
| mysql_threads_detection_algorithm | Anomaly Detection Algorithm used | string | `basic` | no |
| mysql_threads_deviations | Deviations to detect the anomaly | string | `2` | no |
| mysql_threads_direction | Direction of the anomaly. It can be both, below or above. | string | `above` | no |
| mysql_threads_enabled | Flag to enable mysql threads monitor | string | `true` | no |
| mysql_threads_extra_tags | Extra tags for MySQL threads monitor | list | `<list>` | no |
| mysql_threads_interval | Interval. | string | `60` | no |
| mysql_threads_message | Custom message for MySQL threads monitor | string | `` | no |
| mysql_threads_seasonality | Seasonality of the algorithm | string | `daily` | no |
| mysql_threads_silenced | Groups to mute mysql threads monitor | map | `<map>` | no |
| mysql_threads_silenced | Groups to mute for mysql threads monitor | map | `<map>` | no |
| mysql_threads_threshold_critical | Maximum critical acceptable number of threads | string | `1` | no |
| mysql_threads_time_aggregator | Monitor time aggregator for MySQL threads monitor [available values: min, max or avg] | string | `avg` | no |
| mysql_threads_timeframe | Monitor timeframe for MySQL threads monitor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_4h` | no |

204
database/mysql/inputs.tf
View File

@ -39,6 +39,12 @@ variable "mysql_availability_silenced" {
default = {}
}
variable "mysql_availability_enabled" {
description = "Flag to enable Mysql availability monitor"
type = "string"
default = "true"
}
variable "mysql_availability_extra_tags" {
description = "Extra tags for Mysql availability monitor"
type = "list"
@ -67,6 +73,30 @@ variable "mysql_availability_no_data_timeframe" {
### MySQL connections ###
#################################
variable "mysql_connection_silenced" {
description = "Groups to mute for MySQL connection monitor"
type = "map"
default = {}
}
variable "mysql_connection_enabled" {
description = "Flag to enable MySQL connection monitor"
type = "string"
default = "true"
}
variable "mysql_connection_extra_tags" {
description = "Extra tags for MySQL connection monitor"
type = "list"
default = []
}
variable "mysql_connection_message" {
description = "Custom message for MySQL connection monitor"
type = "string"
default = ""
}
variable "mysql_connection_threshold_critical" {
default = 80
description = "Maximum critical acceptable percent of connections"
@ -89,27 +119,33 @@ variable "mysql_connection_timeframe" {
default = "last_10m"
}
variable "mysql_connection_silenced" {
description = "Groups to mute MySQL connection monitor"
#################################
### MySQL aborted connects ###
#################################
variable "mysql_aborted_silenced" {
description = "Groups to mute for MySQL aborted connects monitor"
type = "map"
default = {}
}
variable "mysql_connection_message" {
description = "Custom message for MySQL connection monitor"
variable "mysql_aborted_enabled" {
description = "Flag to enable MySQL aborted connects monitor"
type = "string"
default = ""
default = "true"
}
variable "mysql_connection_extra_tags" {
description = "Extra tags for MySQL connection monitor"
variable "mysql_aborted_extra_tags" {
description = "Extra tags for MySQL aborted connects monitor"
type = "list"
default = []
}
#################################
### MySQL aborted connects ###
#################################
variable "mysql_aborted_message" {
description = "Custom message for MySQL aborted connects monitor"
type = "string"
default = ""
}
variable "mysql_aborted_threshold_critical" {
default = 10
@ -133,27 +169,33 @@ variable "mysql_aborted_timeframe" {
default = "last_10m"
}
variable "mysql_aborted_silenced" {
description = "Groups to mute MySQL aborted connects monitor"
#################################
### MySQL slow queries ###
#################################
variable "mysql_slow_silenced" {
description = "Groups to mute for MySQL slow queries monitor"
type = "map"
default = {}
}
variable "mysql_aborted_message" {
description = "Custom message for MySQL aborted connects monitor"
variable "mysql_slow_enabled" {
description = "Flag to enable MySQL slow queries monitor"
type = "string"
default = ""
default = "true"
}
variable "mysql_aborted_extra_tags" {
description = "Extra tags for MySQL aborted connects monitor"
variable "mysql_slow_extra_tags" {
description = "Extra tags for MySQL slow queries monitor"
type = "list"
default = []
}
#################################
### MySQL slow queries ###
#################################
variable "mysql_slow_message" {
description = "Custom message for MySQL slow queries monitor"
type = "string"
default = ""
}
variable "mysql_slow_threshold_critical" {
default = 20
@ -177,27 +219,33 @@ variable "mysql_slow_timeframe" {
default = "last_15m"
}
variable "mysql_slow_silenced" {
description = "Groups to mute MySQL slow queries monitor"
#################################
# MySQL innodb pool efficiency #
#################################
variable "mysql_pool_efficiency_silenced" {
description = "Groups to mute for MySQL innodb buffer pool efficiency monitor"
type = "map"
default = {}
}
variable "mysql_slow_message" {
description = "Custom message for MySQL slow queries monitor"
variable "mysql_pool_efficiency_enabled" {
description = "Flag to enable MySQL innodb buffer pool efficiency monitor"
type = "string"
default = ""
default = "true"
}
variable "mysql_slow_extra_tags" {
description = "Extra tags for MySQL slow queries monitor"
variable "mysql_pool_efficiency_extra_tags" {
description = "Extra tags for MySQL innodb buffer pool efficiency monitor"
type = "list"
default = []
}
#################################
# MySQL innodb pool efficiency #
#################################
variable "mysql_pool_efficiency_message" {
description = "Custom message for MySQL innodb buffer pool efficiency monitor"
type = "string"
default = ""
}
variable "mysql_pool_efficiency_threshold_critical" {
default = 20
@ -221,27 +269,33 @@ variable "mysql_pool_efficiency_timeframe" {
default = "last_1h"
}
variable "mysql_pool_efficiency_silenced" {
description = "Groups to mute MySQL innodb buffer pool efficiency monitor"
#################################
# MySQL innodb pool utilization #
#################################
variable "mysql_pool_utilization_silenced" {
description = "Groups to mute for MySQL innodb buffer pool utilization monitor"
type = "map"
default = {}
}
variable "mysql_pool_efficiency_message" {
description = "Custom message for MySQL innodb buffer pool efficiency monitor"
variable "mysql_pool_utilization_enabled" {
description = "Flag to enable MySQL innodb buffer pool utilization monitor"
type = "string"
default = ""
default = "true"
}
variable "mysql_pool_efficiency_extra_tags" {
description = "Extra tags for MySQL innodb buffer pool efficiency monitor"
variable "mysql_pool_utilization_extra_tags" {
description = "Extra tags for MySQL innodb buffer pool utilization monitor"
type = "list"
default = []
}
#################################
# MySQL innodb pool utilization #
#################################
variable "mysql_pool_utilization_message" {
description = "Custom message for MySQL innodb buffer pool utilization monitor"
type = "string"
default = ""
}
variable "mysql_pool_utilization_threshold_critical" {
default = 90
@ -265,27 +319,33 @@ variable "mysql_pool_utilization_timeframe" {
default = "last_4h"
}
variable "mysql_pool_utilization_silenced" {
description = "Groups to mute MySQL innodb buffer pool utilization monitor"
#################################
### MySQL threads ###
#################################
variable "mysql_threads_silenced" {
description = "Groups to mute for mysql threads monitor"
type = "map"
default = {}
}
variable "mysql_pool_utilization_message" {
description = "Custom message for MySQL innodb buffer pool utilization monitor"
variable "mysql_threads_enabled" {
description = "Flag to enable mysql threads monitor"
type = "string"
default = ""
default = "true"
}
variable "mysql_pool_utilization_extra_tags" {
description = "Extra tags for MySQL innodb buffer pool utilization monitor"
variable "mysql_threads_extra_tags" {
description = "Extra tags for MySQL threads monitor"
type = "list"
default = []
}
#################################
### MySQL threads ###
#################################
variable "mysql_threads_message" {
description = "Custom message for MySQL threads monitor"
type = "string"
default = ""
}
variable "mysql_threads_threshold_critical" {
default = 1
@ -346,27 +406,33 @@ variable "mysql_threads_timeframe" {
default = "last_4h"
}
variable "mysql_threads_silenced" {
description = "Groups to mute mysql threads monitor"
#################################
### MySQL queries ###
#################################
variable "mysql_queries_silenced" {
description = "Groups to mute for mysql queries monitor"
type = "map"
default = {}
}
variable "mysql_threads_message" {
description = "Custom message for MySQL threads monitor"
variable "mysql_queries_enabled" {
description = "Flag to enable mysql queries monitor"
type = "string"
default = ""
default = "true"
}
variable "mysql_threads_extra_tags" {
description = "Extra tags for MySQL threads monitor"
variable "mysql_queries_extra_tags" {
description = "Extra tags for MySQL queries monitor"
type = "list"
default = []
}
#################################
### MySQL queries ###
#################################
variable "mysql_queries_message" {
description = "Custom message for MySQL queries monitor"
type = "string"
default = ""
}
variable "mysql_queries_threshold_critical" {
default = 1
@ -426,21 +492,3 @@ variable "mysql_queries_timeframe" {
type = "string"
default = "last_4h"
}
variable "mysql_queries_silenced" {
description = "Groups to mute mysql queries monitor"
type = "map"
default = {}
}
variable "mysql_queries_message" {
description = "Custom message for MySQL queries monitor"
type = "string"
default = ""
}
variable "mysql_queries_extra_tags" {
description = "Extra tags for MySQL queries monitor"
type = "list"
default = []
}

8
database/mysql/monitors-mysql.tf
View File

@ -1,4 +1,5 @@
resource "datadog_monitor" "mysql_availability" {
count = "${var.mysql_availability_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql server does not respond"
message = "${coalesce(var.mysql_availability_message, var.message)}"
@ -29,6 +30,7 @@ resource "datadog_monitor" "mysql_availability" {
}
resource "datadog_monitor" "mysql_connection" {
count = "${var.mysql_connection_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql Connections limit {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.mysql_connection_message, var.message)}"
type = "metric alert"
@ -60,6 +62,7 @@ resource "datadog_monitor" "mysql_connection" {
}
resource "datadog_monitor" "mysql_aborted" {
count = "${var.mysql_aborted_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql Aborted connects {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.mysql_aborted_message, var.message)}"
type = "metric alert"
@ -91,6 +94,7 @@ resource "datadog_monitor" "mysql_aborted" {
}
resource "datadog_monitor" "mysql_slow" {
count = "${var.mysql_slow_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql Slow queries {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.mysql_slow_message, var.message)}"
type = "metric alert"
@ -122,6 +126,7 @@ resource "datadog_monitor" "mysql_slow" {
}
resource "datadog_monitor" "mysql_pool_efficiency" {
count = "${var.mysql_pool_efficiency_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql Innodb buffer pool efficiency {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.mysql_pool_efficiency_message, var.message)}"
type = "metric alert"
@ -153,6 +158,7 @@ resource "datadog_monitor" "mysql_pool_efficiency" {
}
resource "datadog_monitor" "mysql_pool_utilization" {
count = "${var.mysql_pool_utilization_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql Innodb buffer pool utilization {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.mysql_pool_utilization_message, var.message)}"
type = "metric alert"
@ -185,6 +191,7 @@ resource "datadog_monitor" "mysql_pool_utilization" {
}
resource "datadog_monitor" "mysql_threads_anomaly" {
count = "${var.mysql_threads_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql threads changed abnormally"
message = "${coalesce(var.mysql_threads_message, var.message)}"
type = "metric alert"
@ -224,6 +231,7 @@ resource "datadog_monitor" "mysql_threads_anomaly" {
}
resource "datadog_monitor" "mysql_queries_anomaly" {
count = "${var.mysql_queries_enabled ? 1 : 0}"
name = "[${var.environment}] Mysql queries changed abnormally"
message = "${coalesce(var.mysql_queries_message, var.message)}"
type = "metric alert"

1
middleware/nginx/README.md
View File

@ -35,6 +35,7 @@ Creates DataDog monitors with the following checks:
| nginx_connect_no_data_timeframe | Nginx status monitor no data timeframe | string | `10` | no |
| nginx_connect_silenced | Groups to mute for Nginx status monitor | map | `<map>` | no |
| nginx_connect_threshold_warning | Nginx status monitor (warning threshold) | string | `3` | no |
| nginx_dropped_enabled | Flag to enable Nginx dropped monitor | string | `true` | no |
| nginx_dropped_extra_tags | Extra tags for Nginx dropped connections monitor | list | `<list>` | no |
| nginx_dropped_message | Custom message for Nginx dropped connections monitor | string | `` | no |
| nginx_dropped_silenced | Groups to mute for Nginx dropped connections monitor | map | `<map>` | no |

6
middleware/nginx/inputs.tf
View File

@ -73,6 +73,12 @@ variable "nginx_dropped_silenced" {
default = {}
}
variable "nginx_dropped_enabled" {
description = "Flag to enable Nginx dropped monitor"
type = "string"
default = "true"
}
variable "nginx_dropped_extra_tags" {
description = "Extra tags for Nginx dropped connections monitor"
type = "list"

1
middleware/nginx/monitors-nginx.tf
View File

@ -30,6 +30,7 @@ resource "datadog_monitor" "datadog_nginx_process" {
}
resource "datadog_monitor" "datadog_nginx_dropped_connections" {
count = "${var.nginx_dropped_enabled ? 1 : 0}"
name = "[${var.environment}] Nginx dropped connections {{#is_alert}}{{{comparator}}} {{threshold}} ({{value}}){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}} ({{value}}){{/is_warning}}"
message = "${coalesce(var.nginx_dropped_message, var.message)}"