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

MON-160 - Azure monitors updated

Browse Source
This commit is contained in:
Alexandre Gaillet 2018-04-26 18:27:49 +02:00 committed by Quentin Manfroi
parent 3c3ce6b3ae
commit a56f5ddb39
18 changed files with 279 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
cloud/azure/apimanagement/README.md
View File

@ -33,6 +33,7 @@ Inputs
| failed_requests_silenced | Groups to mute for API Management failed requests monitor | map | `<map>` | no |
| failed_requests_threshold_critical | Maximum acceptable percent of failed requests | string | `90` | no |
| failed_requests_threshold_warning | Warning regarding acceptable percent of failed requests | string | `50` | no |
| failed_requests_timeframe | Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | 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 |
| message | Message sent when a Redis monitor is triggered | string | - | yes |
@ -40,16 +41,20 @@ Inputs
| other_requests_silenced | Groups to mute for API Management other requests monitor | map | `<map>` | no |
| other_requests_threshold_critical | Maximum acceptable percent of other requests | string | `90` | no |
| other_requests_threshold_warning | Warning regarding acceptable percent of other requests | string | `50` | no |
| other_requests_timeframe | Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| status_message | Custom message for API Management status monitor | string | `` | no |
| status_silenced | Groups to mute for API Management status monitor | map | `<map>` | no |
| status_timeframe | Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| successful_requests_message | Custom message for API Management successful requests monitor | string | `` | no |
| successful_requests_silenced | Groups to mute for API Management successful requests monitor | map | `<map>` | no |
| successful_requests_threshold_critical | Minimum acceptable percent of successful requests | string | `10` | no |
| successful_requests_threshold_warning | Warning regarding acceptable percent of successful requests | string | `30` | no |
| successful_requests_timeframe | Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| unauthorized_requests_message | Custom message for API Management unauthorized requests monitor | string | `` | no |
| unauthorized_requests_silenced | Groups to mute for API Management unauthorized requests monitor | map | `<map>` | no |
| unauthorized_requests_threshold_critical | Maximum acceptable percent of unauthorized requests | string | `90` | no |
| unauthorized_requests_threshold_warning | Warning regarding acceptable percent of unauthorized requests | string | `50` | no |
| unauthorized_requests_timeframe | Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

30
cloud/azure/apimanagement/inputs.tf
View File

@ -37,6 +37,12 @@ variable "status_message" {
default = ""
}
variable "status_timeframe" {
description = "Monitor timeframe for API Management status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_requests_silenced" {
description = "Groups to mute for API Management failed requests monitor"
type = "map"
@ -49,6 +55,12 @@ variable "failed_requests_message" {
default = ""
}
variable "failed_requests_timeframe" {
description = "Monitor timeframe for API Management failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_requests_threshold_critical" {
description = "Maximum acceptable percent of failed requests"
default = 90
@ -71,6 +83,12 @@ variable "other_requests_message" {
default = ""
}
variable "other_requests_timeframe" {
description = "Monitor timeframe for API Management other requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "other_requests_threshold_critical" {
description = "Maximum acceptable percent of other requests"
default = 90
@ -93,6 +111,12 @@ variable "unauthorized_requests_message" {
default = ""
}
variable "unauthorized_requests_timeframe" {
description = "Monitor timeframe for API Management unauthorized requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "unauthorized_requests_threshold_critical" {
description = "Maximum acceptable percent of unauthorized requests"
default = 90
@ -115,6 +139,12 @@ variable "successful_requests_message" {
default = ""
}
variable "successful_requests_timeframe" {
description = "Monitor timeframe for API Management successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "successful_requests_threshold_critical" {
description = "Minimum acceptable percent of successful requests"
default = 10

10
cloud/azure/apimanagement/monitors-azure-apimanagement.tf
View File

@ -13,7 +13,7 @@ resource "datadog_monitor" "apimgt_status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(last_5m):avg:azure.apimanagement_service.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
avg(${var.status_timeframe}):avg:azure.apimanagement_service.status{${data.template_file.filter.rendered}} by {resource_group,region,name} < 1
EOF
type = "metric alert"
@ -42,7 +42,7 @@ resource "datadog_monitor" "apimgt_failed_requests" {
message = "${coalesce(var.failed_requests_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.failed_requests_timeframe}): (
avg:azure.apimanagement_service.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) > ${var.failed_requests_threshold_critical}
@ -74,7 +74,7 @@ resource "datadog_monitor" "apimgt_other_requests" {
message = "${coalesce(var.other_requests_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.other_requests_timeframe}): (
avg:azure.apimanagement_service.other_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) > ${var.other_requests_threshold_critical}
@ -106,7 +106,7 @@ resource "datadog_monitor" "apimgt_unauthorized_requests" {
message = "${coalesce(var.unauthorized_requests_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.unauthorized_requests_timeframe}): (
avg:azure.apimanagement_service.unauthorized_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) > ${var.unauthorized_requests_threshold_critical}
@ -138,7 +138,7 @@ resource "datadog_monitor" "apimgt_successful_requests" {
message = "${coalesce(var.successful_requests_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.successful_requests_timeframe}): (
avg:azure.apimanagement_service.successful_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.apimanagement_service.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() * 100
) < ${var.successful_requests_threshold_critical}

5
cloud/azure/app-services/README.md
View File

@ -36,23 +36,28 @@ Inputs
| http_4xx_requests_silenced | Groups to mute for App Services 4xx requests monitor | map | `<map>` | no |
| http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `90` | no |
| http_4xx_requests_threshold_warning | Warning regarding acceptable percent of 4xx errors | string | `50` | no |
| http_4xx_requests_timeframe | Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| http_5xx_requests_message | Custom message for App Services 5xx requests monitor | string | `` | no |
| http_5xx_requests_silenced | Groups to mute for App Services 5xx requests monitor | map | `<map>` | no |
| http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `90` | no |
| http_5xx_requests_threshold_warning | Warning regarding acceptable percent of 5xx errors | string | `50` | no |
| http_5xx_requests_timeframe | Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| http_successful_requests_message | Custom message for App Services successful requests monitor | string | `` | no |
| http_successful_requests_silenced | Groups to mute for App Services successful requests monitor | map | `<map>` | no |
| http_successful_requests_threshold_critical | Minimum critical acceptable percent of 2xx & 3xx requests | string | `10` | no |
| http_successful_requests_threshold_warning | Warning regarding acceptable percent of 2xx & 3xx requests | string | `30` | no |
| http_successful_requests_timeframe | Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| memory_usage_message | Custom message for App Services memory usage monitor | string | `` | no |
| memory_usage_silenced | Groups to mute for App Services memory usage monitor | map | `<map>` | no |
| memory_usage_threshold_critical | Alerting threshold in Mib | string | `1073741824` | no |
| memory_usage_threshold_warning | Warning threshold in MiB | string | `536870912` | no |
| memory_usage_timeframe | Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| message | Message sent when a monitor is triggered | string | - | yes |
| response_time_message | Custom message for App Services response time monitor | string | `` | no |
| response_time_silenced | Groups to mute for App Services response time monitor | map | `<map>` | no |
| response_time_threshold_critical | Alerting threshold for response time in seconds | string | `10` | no |
| response_time_threshold_warning | Warning threshold for response time in seconds | string | `5` | no |
| response_time_timeframe | Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

30
cloud/azure/app-services/inputs.tf
View File

@ -35,6 +35,12 @@ variable "response_time_message" {
default = ""
}
variable "response_time_timeframe" {
description = "Monitor timeframe for App Services response time [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "response_time_threshold_critical" {
default = 10
description = "Alerting threshold for response time in seconds"
@ -57,6 +63,12 @@ variable "memory_usage_message" {
default = ""
}
variable "memory_usage_timeframe" {
description = "Monitor timeframe for App Services memory usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "memory_usage_threshold_critical" {
default = 1073741824 # 1Gb
description = "Alerting threshold in Mib"
@ -79,6 +91,12 @@ variable "http_4xx_requests_message" {
default = ""
}
variable "http_4xx_requests_timeframe" {
description = "Monitor timeframe for App Services 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "http_4xx_requests_threshold_critical" {
default = 90
description = "Maximum critical acceptable percent of 4xx errors"
@ -101,6 +119,12 @@ variable "http_5xx_requests_message" {
default = ""
}
variable "http_5xx_requests_timeframe" {
description = "Monitor timeframe for App Services 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "http_5xx_requests_threshold_critical" {
default = 90
description = "Maximum critical acceptable percent of 5xx errors"
@ -123,6 +147,12 @@ variable "http_successful_requests_message" {
default = ""
}
variable "http_successful_requests_timeframe" {
description = "Monitor timeframe for App Services successful requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "http_successful_requests_threshold_critical" {
default = 10
description = "Minimum critical acceptable percent of 2xx & 3xx requests"

8
cloud/azure/app-services/monitors-app_services.tf
View File

@ -44,7 +44,7 @@ resource "datadog_monitor" "appservices_memory_usage_count" {
message = "${coalesce(var.memory_usage_message, var.message)}"
query = <<EOF
avg(last_5m): (
avg(${var.memory_usage_timeframe}): (
avg:azure.app_services.memory_working_set{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.memory_usage_threshold_critical}
EOF
@ -75,7 +75,7 @@ resource "datadog_monitor" "appservices_http_5xx_errors_count" {
message = "${coalesce(var.http_5xx_requests_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.http_5xx_requests_timeframe}): (
avg:azure.app_services.http5xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
) * 100 > ${var.http_5xx_requests_threshold_critical}
@ -107,7 +107,7 @@ resource "datadog_monitor" "appservices_http_4xx_errors_count" {
message = "${coalesce(var.http_4xx_requests_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.http_4xx_requests_timeframe}): (
avg:azure.app_services.http4xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
) * 100 > ${var.http_4xx_requests_threshold_critical}
@ -139,7 +139,7 @@ resource "datadog_monitor" "appservices_http_success_status_rate" {
message = "${coalesce(var.http_successful_requests_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.http_successful_requests_timeframe}): (
(avg:azure.app_services.http2xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +
avg:azure.app_services.http3xx{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()) /
avg:azure.app_services.requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()

3
cloud/azure/eventhub/README.md
View File

@ -32,15 +32,18 @@ Inputs
| errors_rate_silenced | Groups to mute for Event Hub errors monitor | map | `<map>` | no |
| errors_rate_thresold_critical | Errors ratio (percentage) to trigger the critical alert | string | `90` | no |
| errors_rate_thresold_warning | Errors ratio (percentage) to trigger a warning alert | string | `50` | no |
| errors_rate_timeframe | Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_requests_rate_message | Custom message for Event Hub failed requests monitor | string | `` | no |
| failed_requests_rate_silenced | Groups to mute for Event Hub failed requests monitor | map | `<map>` | no |
| failed_requests_rate_thresold_critical | Failed requests ratio (percentage) to trigger the critical alert | string | `90` | no |
| failed_requests_rate_thresold_warning | Failed requests ratio (percentage) to trigger a warning alert | string | `50` | no |
| failed_requests_rate_timeframe | Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | 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 |
| message | Message sent when an alert is triggered | string | - | yes |
| status_message | Custom message for Event Hub status monitor | string | `` | no |
| status_silenced | Groups to mute for Event Hub status monitor | map | `<map>` | no |
| status_timeframe | Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

18
cloud/azure/eventhub/inputs.tf
View File

@ -37,6 +37,12 @@ variable "status_message" {
default = ""
}
variable "status_timeframe" {
description = "Monitor timeframe for Event Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_requests_rate_silenced" {
description = "Groups to mute for Event Hub failed requests monitor"
type = "map"
@ -49,6 +55,12 @@ variable "failed_requests_rate_message" {
default = ""
}
variable "failed_requests_rate_timeframe" {
description = "Monitor timeframe for Event Hub failed requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_requests_rate_thresold_critical" {
description = "Failed requests ratio (percentage) to trigger the critical alert"
default = 90
@ -71,6 +83,12 @@ variable "errors_rate_message" {
default = ""
}
variable "errors_rate_timeframe" {
description = "Monitor timeframe for Event Hub errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "errors_rate_thresold_critical" {
description = "Errors ratio (percentage) to trigger the critical alert"
default = 90

6
cloud/azure/eventhub/monitors-eventhub.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "eventhub_status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(last_5m): avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
avg(${var.status_timeframe}): avg:azure.eventhub_namespaces.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
EOF
type = "metric alert"
@ -36,7 +36,7 @@ resource "datadog_monitor" "eventhub_failed_requests" {
message = "${coalesce(var.failed_requests_rate_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.failed_requests_rate_timeframe}): (
default(
avg:azure.eventhub_namespaces.failed_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.eventhub_namespaces.incoming_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count(),
@ -71,7 +71,7 @@ resource "datadog_monitor" "eventhub_errors" {
message = "${coalesce(var.errors_rate_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.errors_rate_timeframe}): (
default(
(
avg:azure.eventhub_namespaces.internal_server_errors{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() +

14
cloud/azure/iothubs/README.md
View File

@ -43,55 +43,69 @@ Inputs
| dropped_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `90` | no |
| dropped_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `50` | no |
| dropped_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub dropped d2c telemetry monitor | map | `<map>` | no |
| dropped_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| environment | Architecture Environment | string | - | yes |
| failed_c2d_methods_rate_message | Custom message for IoT Hub failed c2d method monitor | string | `` | no |
| failed_c2d_methods_rate_silenced | Groups to mute for IoT Hub failed c2d methods monitor | map | `<map>` | no |
| failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `90` | no |
| failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `50` | no |
| failed_c2d_methods_rate_timeframe | Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_c2d_twin_read_rate_message | Custom message for IoT Hub failed c2d twin read monitor | string | `` | no |
| failed_c2d_twin_read_rate_silenced | Groups to mute for IoT Hub failed c2d twin read monitor | map | `<map>` | no |
| failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `90` | no |
| failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `50` | no |
| failed_c2d_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_c2d_twin_update_rate_message | Custom message for IoT Hub failed c2d twin update monitor | string | `` | no |
| failed_c2d_twin_update_rate_silenced | Groups to mute for IoT Hub failed c2d twin update monitor | map | `<map>` | no |
| failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `90` | no |
| failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `50` | no |
| failed_c2d_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_d2c_twin_read_rate_message | Custom message for IoT Hub failed d2c twin read monitor | string | `` | no |
| failed_d2c_twin_read_rate_silenced | Groups to mute for IoT Hub failed d2c twin read monitor | map | `<map>` | no |
| failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `90` | no |
| failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `50` | no |
| failed_d2c_twin_read_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_d2c_twin_update_rate_message | Custom message for IoT Hub failed d2c twin update monitor | string | `` | no |
| failed_d2c_twin_update_rate_silenced | Groups to mute for IoT Hub failed d2c twin update monitor | map | `<map>` | no |
| failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `90` | no |
| failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `50` | no |
| failed_d2c_twin_update_rate_timeframe | Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_jobs_rate_message | Custom message for IoT Hub failed jobs monitor | string | `` | no |
| failed_jobs_rate_silenced | Groups to mute for IoT Hub failed jobs monitor | map | `<map>` | no |
| failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `90` | no |
| failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `50` | no |
| failed_jobs_rate_timeframe | Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_listjobs_rate_message | Custom message for IoT Hub failed list jobs monitor | string | `` | no |
| failed_listjobs_rate_silenced | Groups to mute for IoT Hub failed list jobs monitor | map | `<map>` | no |
| failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `90` | no |
| failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `50` | no |
| failed_listjobs_rate_timeframe | Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| failed_queryjobs_rate_message | Custom message for IoT Hub failed query jobs monitor | string | `` | no |
| failed_queryjobs_rate_silenced | Groups to mute for IoT Hub failed query jobs monitor | map | `<map>` | no |
| failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `90` | no |
| failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `50` | no |
| failed_queryjobs_rate_timeframe | Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| filter_tags | Tags used for filtering | string | `*` | no |
| invalid_d2c_telemetry_egress_message | Custom message for IoT Hub invalid d2c telemetry monitor | string | `` | no |
| invalid_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `90` | no |
| invalid_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `50` | no |
| invalid_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub invalid d2c telemetry monitor | map | `<map>` | no |
| invalid_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| message | Message sent when an alert is triggered | string | - | yes |
| orphaned_d2c_telemetry_egress_message | Custom message for IoT Hub orphaned d2c telemetry monitor | string | `` | no |
| orphaned_d2c_telemetry_egress_rate_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `90` | no |
| orphaned_d2c_telemetry_egress_rate_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `50` | no |
| orphaned_d2c_telemetry_egress_silenced | Groups to mute for IoT Hub orphaned d2c telemetry monitor | map | `<map>` | no |
| orphaned_d2c_telemetry_egress_timeframe | Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| status_message | Custom message for IoT Hub status monitor | string | `` | no |
| status_silenced | Groups to mute for IoT Hub status monitor | map | `<map>` | no |
| status_timeframe | Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| too_many_d2c_telemetry_ingress_nosent_message | Custom message for IoT Hub unsent d2c telemetry monitor | string | `` | no |
| too_many_d2c_telemetry_ingress_nosent_silenced | Groups to mute for IoT Hub unsent d2c telemetry monitor | map | `<map>` | no |
| too_many_d2c_telemetry_ingress_nosent_timeframe | Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| total_devices_message | Custom message for IoT Hub total devices monitor | string | `` | no |
| total_devices_silenced | Groups to mute for IoT Hub total devices monitor | map | `<map>` | no |
| total_devices_timeframe | Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

84
cloud/azure/iothubs/inputs.tf
View File

@ -32,6 +32,12 @@ variable "status_message" {
default = ""
}
variable "status_timeframe" {
description = "Monitor timeframe for IoT Hub status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "total_devices_silenced" {
description = "Groups to mute for IoT Hub total devices monitor"
type = "map"
@ -44,6 +50,12 @@ variable "total_devices_message" {
default = ""
}
variable "total_devices_timeframe" {
description = "Monitor timeframe for IoT Hub total devices [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "too_many_d2c_telemetry_ingress_nosent_silenced" {
description = "Groups to mute for IoT Hub unsent d2c telemetry monitor"
type = "map"
@ -56,6 +68,12 @@ variable "too_many_d2c_telemetry_ingress_nosent_message" {
default = ""
}
variable "too_many_d2c_telemetry_ingress_nosent_timeframe" {
description = "Monitor timeframe for IoT Hub unsent d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_jobs_rate_silenced" {
description = "Groups to mute for IoT Hub failed jobs monitor"
type = "map"
@ -68,6 +86,12 @@ variable "failed_jobs_rate_message" {
default = ""
}
variable "failed_jobs_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_jobs_rate_threshold_warning" {
description = "Jobs Failed rate limit (warning threshold)"
default = 50
@ -90,6 +114,12 @@ variable "failed_listjobs_rate_message" {
default = ""
}
variable "failed_listjobs_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed list jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_listjobs_rate_threshold_warning" {
description = "ListJobs Failed rate limit (warning threshold)"
default = 50
@ -112,6 +142,12 @@ variable "failed_queryjobs_rate_message" {
default = ""
}
variable "failed_queryjobs_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed query jobs [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_queryjobs_rate_threshold_warning" {
description = "QueryJobs Failed rate limit (warning threshold)"
default = 50
@ -134,6 +170,12 @@ variable "failed_c2d_methods_rate_message" {
default = ""
}
variable "failed_c2d_methods_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed c2d method [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_c2d_methods_rate_threshold_warning" {
description = "C2D Methods Failed rate limit (warning threshold)"
default = 50
@ -156,6 +198,12 @@ variable "failed_c2d_twin_read_rate_message" {
default = ""
}
variable "failed_c2d_twin_read_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed c2d twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_c2d_twin_read_rate_threshold_warning" {
description = "C2D Twin Read Failed rate limit (warning threshold)"
default = 50
@ -178,6 +226,12 @@ variable "failed_c2d_twin_update_rate_message" {
default = ""
}
variable "failed_c2d_twin_update_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed c2d twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_c2d_twin_update_rate_threshold_warning" {
description = "C2D Twin Update Failed rate limit (warning threshold)"
default = 50
@ -200,6 +254,12 @@ variable "failed_d2c_twin_read_rate_message" {
default = ""
}
variable "failed_d2c_twin_read_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed d2c twin read [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_d2c_twin_read_rate_threshold_warning" {
description = "D2C Twin Read Failed rate limit (warning threshold)"
default = 50
@ -222,6 +282,12 @@ variable "failed_d2c_twin_update_rate_message" {
default = ""
}
variable "failed_d2c_twin_update_rate_timeframe" {
description = "Monitor timeframe for IoT Hub failed d2c twin update [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "failed_d2c_twin_update_rate_threshold_warning" {
description = "D2C Twin Update Failed rate limit (warning threshold)"
default = 50
@ -244,6 +310,12 @@ variable "dropped_d2c_telemetry_egress_message" {
default = ""
}
variable "dropped_d2c_telemetry_egress_timeframe" {
description = "Monitor timeframe for IoT Hub dropped d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "dropped_d2c_telemetry_egress_rate_threshold_warning" {
description = "D2C Telemetry Dropped limit (warning threshold)"
default = 50
@ -266,6 +338,12 @@ variable "orphaned_d2c_telemetry_egress_message" {
default = ""
}
variable "orphaned_d2c_telemetry_egress_timeframe" {
description = "Monitor timeframe for IoT Hub orphaned d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "orphaned_d2c_telemetry_egress_rate_threshold_warning" {
description = "D2C Telemetry Orphaned limit (warning threshold)"
default = 50
@ -288,6 +366,12 @@ variable "invalid_d2c_telemetry_egress_message" {
default = ""
}
variable "invalid_d2c_telemetry_egress_timeframe" {
description = "Monitor timeframe for IoT Hub invalid d2c telemetry [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "invalid_d2c_telemetry_egress_rate_threshold_warning" {
description = "D2C Telemetry Invalid limit (warning threshold)"
default = 50

28
cloud/azure/iothubs/monitors-iothubs.tf
View File

@ -3,7 +3,7 @@ resource "datadog_monitor" "too_many_jobs_failed" {
message = "${coalesce(var.failed_jobs_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_jobs_rate_timeframe}):(
avg:azure.devices_iothubs.jobs.failed{${var.filter_tags}} by {resource_group,region,name}.as_count() /
( avg:azure.devices_iothubs.jobs.failed{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.jobs.completed{${var.filter_tags}} by {resource_group,region,name}.as_count() )
@ -37,7 +37,7 @@ resource "datadog_monitor" "too_many_list_jobs_failed" {
message = "${coalesce(var.failed_listjobs_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_listjobs_rate_timeframe}):(
avg:azure.devices_iothubs.jobs.list_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() /
( avg:azure.devices_iothubs.jobs.list_jobs.success{${var.filter_tags}} by {resource_group,name}.as_count() +
avg:azure.devices_iothubs.jobs.list_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() )
@ -71,7 +71,7 @@ resource "datadog_monitor" "too_many_query_jobs_failed" {
message = "${coalesce(var.failed_queryjobs_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_queryjobs_rate_timeframe}):(
avg:azure.devices_iothubs.jobs.query_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() /
( avg:azure.devices_iothubs.jobs.query_jobs.success{${var.filter_tags}} by {resource_group,name}.as_count() +
avg:azure.devices_iothubs.jobs.query_jobs.failure{${var.filter_tags}} by {resource_group,name}.as_count() )
@ -105,7 +105,7 @@ resource "datadog_monitor" "status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(last_5m):avg:azure.devices_iothubs.status{${var.filter_tags}} by {resource_group,region,name} < 1
avg(${var.status_timeframe}):avg:azure.devices_iothubs.status{${var.filter_tags}} by {resource_group,region,name} < 1
EOF
type = "metric alert"
@ -130,7 +130,7 @@ resource "datadog_monitor" "total_devices" {
message = "${coalesce(var.total_devices_message, var.message)}"
query = <<EOF
avg(last_5m):avg:azure.devices_iothubs.devices.total_devices{${var.filter_tags}} by {resource_group,region,name} == 0
avg(${var.total_devices_timeframe}):avg:azure.devices_iothubs.devices.total_devices{${var.filter_tags}} by {resource_group,region,name} == 0
EOF
type = "metric alert"
@ -155,7 +155,7 @@ resource "datadog_monitor" "too_many_c2d_methods_failed" {
message = "${coalesce(var.failed_c2d_methods_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_c2d_methods_rate_timeframe}):(
avg:azure.devices_iothubs.c2d.methods.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
( avg:azure.devices_iothubs.c2d.methods.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.c2d.methods.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
@ -189,7 +189,7 @@ resource "datadog_monitor" "too_many_c2d_twin_read_failed" {
message = "${coalesce(var.failed_c2d_twin_read_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_c2d_twin_read_rate_timeframe}):(
avg:azure.devices_iothubs.c2d.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
( avg:azure.devices_iothubs.c2d.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.c2d.twin.read.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
@ -223,7 +223,7 @@ resource "datadog_monitor" "too_many_c2d_twin_update_failed" {
message = "${coalesce(var.failed_c2d_twin_update_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_c2d_twin_update_rate_timeframe}):(
avg:azure.devices_iothubs.c2d.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
( avg:azure.devices_iothubs.c2d.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.c2d.twin.update.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
@ -257,7 +257,7 @@ resource "datadog_monitor" "too_many_d2c_twin_read_failed" {
message = "${coalesce(var.failed_d2c_twin_read_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_d2c_twin_read_rate_timeframe}):(
avg:azure.devices_iothubs.d2c.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
( avg:azure.devices_iothubs.d2c.twin.read.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.d2c.twin.read.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
@ -291,7 +291,7 @@ resource "datadog_monitor" "too_many_d2c_twin_update_failed" {
message = "${coalesce(var.failed_d2c_twin_update_rate_message, var.message)}"
query = <<EOF
sum(last_5m):(
sum(${var.failed_d2c_twin_update_rate_timeframe}):(
avg:azure.devices_iothubs.d2c.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() /
( avg:azure.devices_iothubs.d2c.twin.update.failure{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.d2c.twin.update.success{${var.filter_tags}} by {resource_group,region,name}.as_count() )
@ -325,7 +325,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_dropped" {
message = "${coalesce(var.dropped_d2c_telemetry_egress_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.dropped_d2c_telemetry_egress_timeframe}): (
avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() /
(avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
@ -362,7 +362,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_orphaned" {
message = "${coalesce(var.orphaned_d2c_telemetry_egress_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.orphaned_d2c_telemetry_egress_timeframe}): (
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() /
(avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
@ -399,7 +399,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_invalid" {
message = "${coalesce(var.invalid_d2c_telemetry_egress_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.invalid_d2c_telemetry_egress_timeframe}): (
avg:azure.devices_iothubs.d2c.telemetry.egress.invalid{${var.filter_tags}} by {resource_group,region,name}.as_count() /
(avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${var.filter_tags}} by {resource_group,region,name}.as_count() +
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${var.filter_tags}} by {resource_group,region,name}.as_count() +
@ -436,7 +436,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_ingress_nosent" {
message = "${coalesce(var.too_many_d2c_telemetry_ingress_nosent_message, var.message)}"
query = <<EOF
sum(last_5m): (
sum(${var.too_many_d2c_telemetry_ingress_nosent_timeframe}): (
avg:azure.devices_iothubs.d2c.telemetry.ingress.all_protocol{${var.filter_tags}} by {resource_group,region,name}.as_count() -
avg:azure.devices_iothubs.d2c.telemetry.ingress.success{${var.filter_tags}} by {resource_group,region,name}.as_count()
) > 0

4
cloud/azure/redis/README.md
View File

@ -33,6 +33,7 @@ Inputs
| evictedkeys_limit_silenced | Groups to mute for Redis evicted keys monitor | map | `<map>` | no |
| evictedkeys_limit_threshold_critical | Evicted keys limit (critical threshold) | string | `100` | no |
| evictedkeys_limit_threshold_warning | Evicted keys limit (warning threshold) | string | `0` | no |
| evictedkeys_limit_timeframe | Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | 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 |
| message | Message sent when a Redis monitor is triggered | string | - | yes |
@ -40,12 +41,15 @@ Inputs
| percent_processor_time_silenced | Groups to mute for Redis processor monitor | map | `<map>` | no |
| percent_processor_time_threshold_critical | Processor time percent (critical threshold) | string | `80` | no |
| percent_processor_time_threshold_warning | Processor time percent (warning threshold) | string | `60` | no |
| percent_processor_time_timeframe | Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| server_load_rate_message | Custom message for Redis server load monitor | string | `` | no |
| server_load_rate_silenced | Groups to mute for Redis server load monitor | map | `<map>` | no |
| server_load_rate_threshold_critical | Server CPU load rate (critical threshold) | string | `90` | no |
| server_load_rate_threshold_warning | Server CPU load rate (warning threshold) | string | `70` | no |
| server_load_rate_timeframe | Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| status_message | Custom message for Redis status monitor | string | `` | no |
| status_silenced | Groups to mute for Redis status monitor | map | `<map>` | no |
| status_timeframe | Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

24
cloud/azure/redis/inputs.tf
View File

@ -37,6 +37,12 @@ variable "status_message" {
default = ""
}
variable "status_timeframe" {
description = "Monitor timeframe for Redis status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "evictedkeys_limit_silenced" {
description = "Groups to mute for Redis evicted keys monitor"
type = "map"
@ -49,6 +55,12 @@ variable "evictedkeys_limit_message" {
default = ""
}
variable "evictedkeys_limit_timeframe" {
description = "Monitor timeframe for Redis evicted keys [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "evictedkeys_limit_threshold_warning" {
description = "Evicted keys limit (warning threshold)"
default = 0
@ -71,6 +83,12 @@ variable "percent_processor_time_message" {
default = ""
}
variable "percent_processor_time_timeframe" {
description = "Monitor timeframe for Redis processor [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "percent_processor_time_threshold_critical" {
description = "Processor time percent (critical threshold)"
default = 80
@ -93,6 +111,12 @@ variable "server_load_rate_message" {
default = ""
}
variable "server_load_rate_timeframe" {
description = "Monitor timeframe for Redis server load [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "server_load_rate_threshold_critical" {
description = "Server CPU load rate (critical threshold)"
default = 90

8
cloud/azure/redis/monitors-azure-redis.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "status" {
message = "${coalesce(var.status_message, var.message)}"
query = <<EOF
avg(last_5m):avg:azure.cache_redis.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
avg(${var.status_timeframe}):avg:azure.cache_redis.status{${data.template_file.filter.rendered}} by {resource_group,region,name} != 1
EOF
type = "metric alert"
@ -36,7 +36,7 @@ resource "datadog_monitor" "evictedkeys" {
message = "${coalesce(var.evictedkeys_limit_message, var.message)}"
query = <<EOF
avg(last_5m): (
avg(${var.evictedkeys_limit_timeframe}): (
avg:azure.cache_redis.evictedkeys{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.evictedkeys_limit_threshold_critical}
EOF
@ -68,7 +68,7 @@ resource "datadog_monitor" "percent_processor_time" {
message = "${coalesce(var.percent_processor_time_message, var.message)}"
query = <<EOF
avg(last_5m): (
avg(${var.percent_processor_time_timeframe}): (
avg:azure.cache_redis.percent_processor_time{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.percent_processor_time_threshold_critical}
EOF
@ -100,7 +100,7 @@ resource "datadog_monitor" "server_load" {
message = "${coalesce(var.server_load_rate_message, var.message)}"
query = <<EOF
avg(last_5m): (
avg(${var.server_load_rate_timeframe}): (
avg:azure.cache_redis.server_load{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.server_load_rate_threshold_critical}
EOF

4
cloud/azure/sql-database/README.md
View File

@ -31,18 +31,22 @@ Inputs
| cpu_silenced | Groups to mute for SQL CPU monitor | map | `<map>` | no |
| cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |
| cpu_threshold_warning | CPU usage in percent (warning threshold) | string | `80` | no |
| cpu_timeframe | Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| deadlock_message | Custom message for SQL Deadlock monitor | string | `` | no |
| deadlock_silenced | Groups to mute for SQL Deadlock monitor | map | `<map>` | no |
| deadlock_threshold_critical | Amount of Deadlocks (critical threshold) | string | `1` | no |
| deadlock_timeframe | Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| diskspace_message | Custom message for SQL disk space monitor | string | `` | no |
| diskspace_silenced | Groups to mute for SQL disk space monitor | map | `<map>` | no |
| diskspace_threshold_critical | Disk space used in percent (critical threshold) | string | `90` | no |
| diskspace_threshold_warning | Disk space used in percent (warning threshold) | string | `80` | no |
| diskspace_timeframe | Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| dtu_message | Custom message for SQL DTU monitor | string | `` | no |
| dtu_silenced | Groups to mute for SQL DTU monitor | map | `<map>` | no |
| dtu_threshold_critical | Amount of DTU used (critical threshold) | string | `90` | no |
| dtu_threshold_warning | Amount of DTU used (warning threshold) | string | `85` | no |
| dtu_timeframe | Monitor timeframe for SQL DTU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| environment | Architecture Environment | string | - | yes |
| 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 |

24
cloud/azure/sql-database/inputs.tf
View File

@ -37,6 +37,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_timeframe" {
description = "Monitor timeframe for SQL CPU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_15m"
}
variable "cpu_threshold_warning" {
description = "CPU usage in percent (warning threshold)"
default = "80"
@ -59,6 +65,12 @@ variable "diskspace_message" {
default = ""
}
variable "diskspace_timeframe" {
description = "Monitor timeframe for SQL disk space [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_15m"
}
variable "diskspace_threshold_warning" {
description = "Disk space used in percent (warning threshold)"
default = "80"
@ -81,6 +93,12 @@ variable "dtu_message" {
default = ""
}
variable "dtu_timeframe" {
description = "Monitor timeframe for SQL DTU [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_15m"
}
variable "dtu_threshold_warning" {
description = "Amount of DTU used (warning threshold)"
default = "85"
@ -103,6 +121,12 @@ variable "deadlock_message" {
default = ""
}
variable "deadlock_timeframe" {
description = "Monitor timeframe for SQL Deadlock [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
default = "last_5m"
}
variable "deadlock_threshold_critical" {
description = "Amount of Deadlocks (critical threshold)"
default = "1"

8
cloud/azure/sql-database/monitors-sql-database-basics.tf
View File

@ -11,7 +11,7 @@ resource "datadog_monitor" "sql-database_cpu_90_15min" {
message = "${coalesce(var.cpu_message, var.message)}"
query = <<EOF
avg(last_15m): (
avg(${var.cpu_timeframe}): (
avg:azure.sql_servers_databases.cpu_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.cpu_threshold_critical}
EOF
@ -44,7 +44,7 @@ resource "datadog_monitor" "sql-database_free_space_low" {
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg(${var.diskspace_timeframe}): (
avg:azure.sql_servers_databases.storage_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.diskspace_threshold_critical}
EOF
@ -76,7 +76,7 @@ resource "datadog_monitor" "sql-database_dtu_consumption_high" {
type = "metric alert"
query = <<EOF
avg(last_15m): (
avg(${var.dtu_timeframe}): (
azure.sql_servers_databases.dtu_consumption_percent{${data.template_file.filter.rendered}} by {resource_group,region,name}
) > ${var.dtu_threshold_critical}
EOF
@ -108,7 +108,7 @@ resource "datadog_monitor" "sql-database_deadlocks_count" {
type = "metric alert"
query = <<EOF
sum(last_5m): (
sum(${var.deadlock_timeframe}): (
avg:azure.sql_servers_databases.deadlock{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
) > ${var.deadlock_threshold_critical}
EOF