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

MON-80 Update variables' names

Browse Source
This commit is contained in:
Alexandre Gaillet 2017-11-06 10:30:00 +01:00
parent 2593e5fac4
commit e0fa47008a
3 changed files with 173 additions and 156 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
cloud/azure/iothubs/README.md
View File

@ -1,5 +1,5 @@
Azure IOT Hubs DataDog monitors
============================
===============================
How to use this module
----------------------
@ -39,36 +39,37 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| c2d_methods_failed_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `10` | no |
| c2d_methods_failed_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `0` | no |
| c2d_twin_read_failed_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `10` | no |
| c2d_twin_read_failed_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `0` | no |
| c2d_twin_update_failed_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `10` | no |
| c2d_twin_update_failed_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `0` | no |
| d2c_telemetry_egress_dropped_threshold_critical | D2C Telemetry Dropped Failed limit (critical threshold) | string | `1000` | no |
| d2c_telemetry_egress_dropped_threshold_warning | D2C Telemetry Dropped Failed limit (warning threshold) | string | `500` | no |
| d2c_telemetry_egress_fallback_threshold_critical | D2C Telemetry Fallback Failed limit (critical threshold) | string | `1000` | no |
| d2c_telemetry_egress_fallback_threshold_warning | D2C Telemetry Fallback Failed limit (warning threshold) | string | `500` | no |
| d2c_telemetry_egress_invalid_threshold_critical | D2C Telemetry Invalid Failed limit (critical threshold) | string | `1000` | no |
| d2c_telemetry_egress_invalid_threshold_warning | D2C Telemetry Invalid Failed limit (warning threshold) | string | `500` | no |
| d2c_telemetry_egress_orphaned_threshold_critical | D2C Telemetry Orphaned Failed limit (critical threshold) | string | `1000` | no |
| d2c_telemetry_egress_orphaned_threshold_warning | D2C Telemetry Orphaned Failed limit (warning threshold) | string | `500` | no |
| d2c_twin_read_failed_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `10` | no |
| d2c_twin_read_failed_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `0` | no |
| d2c_twin_update_failed_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `10` | no |
| d2c_twin_update_failed_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `0` | no |
| delay | Delay in seconds for the metric evaluation | string | `600` | no |
| dropped_d2c_telemetry_egress_threshold_critical | D2C Telemetry Dropped limit (critical threshold) | string | `1000` | no |
| dropped_d2c_telemetry_egress_threshold_warning | D2C Telemetry Dropped limit (warning threshold) | string | `500` | no |
| environment | Architecture Environment | string | - | yes |
| jobs_failed_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `10` | no |
| jobs_failed_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `0` | no |
| listjobs_failed_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `10` | no |
| listjobs_failed_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `0` | no |
| failed_c2d_methods_rate_threshold_critical | C2D Methods Failed rate limit (critical threshold) | string | `10` | no |
| failed_c2d_methods_rate_threshold_warning | C2D Methods Failed rate limit (warning threshold) | string | `0` | no |
| failed_c2d_twin_read_rate_threshold_critical | C2D Twin Read Failed rate limit (critical threshold) | string | `10` | no |
| failed_c2d_twin_read_rate_threshold_warning | C2D Twin Read Failed rate limit (warning threshold) | string | `0` | no |
| failed_c2d_twin_update_rate_threshold_critical | C2D Twin Update Failed rate limit (critical threshold) | string | `10` | no |
| failed_c2d_twin_update_rate_threshold_warning | C2D Twin Update Failed rate limit (warning threshold) | string | `0` | no |
| failed_d2c_twin_read_rate_threshold_critical | D2C Twin Read Failed rate limit (critical threshold) | string | `10` | no |
| failed_d2c_twin_read_rate_threshold_warning | D2C Twin Read Failed rate limit (warning threshold) | string | `0` | no |
| failed_d2c_twin_update_rate_threshold_critical | D2C Twin Update Failed rate limit (critical threshold) | string | `10` | no |
| failed_d2c_twin_update_rate_threshold_warning | D2C Twin Update Failed rate limit (warning threshold) | string | `0` | no |
| failed_jobs_rate_threshold_critical | Jobs Failed rate limit (critical threshold) | string | `10` | no |
| failed_jobs_rate_threshold_warning | Jobs Failed rate limit (warning threshold) | string | `0` | no |
| failed_listjobs_rate_threshold_critical | ListJobs Failed rate limit (critical threshold) | string | `10` | no |
| failed_listjobs_rate_threshold_warning | ListJobs Failed rate limit (warning threshold) | string | `0` | no |
| failed_queryjobs_rate_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `10` | no |
| failed_queryjobs_rate_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `0` | no |
| fallback_d2c_telemetry_egress_threshold_critical | D2C Telemetry Fallback limit (critical threshold) | string | `1000` | no |
| fallback_d2c_telemetry_egress_threshold_warning | D2C Telemetry Fallback limit (warning threshold) | string | `500` | no |
| invalid_d2c_telemetry_egress_threshold_critical | D2C Telemetry Invalid limit (critical threshold) | string | `1000` | no |
| invalid_d2c_telemetry_egress_threshold_warning | D2C Telemetry Invalid limit (warning threshold) | string | `500` | no |
| message | Message sent when an alert is triggered | string | - | yes |
| provider | What is the monitored provider | string | azure | no |
| queryjobs_failed_threshold_critical | QueryJobs Failed rate limit (critical threshold) | string | `10` | no |
| queryjobs_failed_threshold_warning | QueryJobs Failed rate limit (warning threshold) | string | `0` | no |
| service | What is the monitored service | string | storage | no |
| subscription_id | Subscription ID used to tag monitors | string | - | yes |
| orphaned_d2c_telemetry_egress_threshold_critical | D2C Telemetry Orphaned limit (critical threshold) | string | `1000` | no |
| orphaned_d2c_telemetry_egress_threshold_warning | D2C Telemetry Orphaned limit (warning threshold) | string | `500` | no |
| provider | Cloud provider which the monitor and its based metric depend on | string | `azure` | no |
| service | Service monitored by this set of monitors | string | `storage` | no |
| subscription_id | Azure account id used as filter for monitors | string | - | yes |
| use_filter_tags | Filter the data with service tags if true | string | `true` | no |
Related documentation
---------------------

125
cloud/azure/iothubs/inputs.tf
View File

@ -6,24 +6,25 @@ variable "environment" {
variable "subscription_id" {
description = "Azure account id used as filter for monitors"
type = "string"
type = "string"
}
variable "provider" {
description = "Cloud provider which the monitor and its based metric depend on"
type = "string"
default = "azure"
type = "string"
default = "azure"
}
variable "service" {
description = "Service monitored by this set of monitors"
type = "string"
default = "storage"
type = "string"
default = "storage"
}
# Global DataDog
variable "delay" {
description = "Delay in seconds for the metric evaluation"
default = 600
default = 600
}
variable "message" {
@ -36,122 +37,122 @@ variable "use_filter_tags" {
}
# Azure IOT hubs specific
variable "jobs_failed_threshold_warning" {
variable "failed_jobs_rate_threshold_warning" {
description = "Jobs Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "jobs_failed_threshold_critical" {
variable "failed_jobs_rate_threshold_critical" {
description = "Jobs Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "listjobs_failed_threshold_warning" {
variable "failed_listjobs_rate_threshold_warning" {
description = "ListJobs Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "listjobs_failed_threshold_critical" {
variable "failed_listjobs_rate_threshold_critical" {
description = "ListJobs Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "queryjobs_failed_threshold_warning" {
variable "failed_queryjobs_rate_threshold_warning" {
description = "QueryJobs Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "queryjobs_failed_threshold_critical" {
variable "failed_queryjobs_rate_threshold_critical" {
description = "QueryJobs Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "c2d_methods_failed_threshold_warning" {
variable "failed_c2d_methods_rate_threshold_warning" {
description = "C2D Methods Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "c2d_methods_failed_threshold_critical" {
variable "failed_c2d_methods_rate_threshold_critical" {
description = "C2D Methods Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "c2d_twin_read_failed_threshold_warning" {
variable "failed_c2d_twin_read_rate_threshold_warning" {
description = "C2D Twin Read Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "c2d_twin_read_failed_threshold_critical" {
variable "failed_c2d_twin_read_rate_threshold_critical" {
description = "C2D Twin Read Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "c2d_twin_update_failed_threshold_warning" {
variable "failed_c2d_twin_update_rate_threshold_warning" {
description = "C2D Twin Update Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "c2d_twin_update_failed_threshold_critical" {
variable "failed_c2d_twin_update_rate_threshold_critical" {
description = "C2D Twin Update Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "d2c_twin_read_failed_threshold_warning" {
variable "failed_d2c_twin_read_rate_threshold_warning" {
description = "D2C Twin Read Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "d2c_twin_read_failed_threshold_critical" {
variable "failed_d2c_twin_read_rate_threshold_critical" {
description = "D2C Twin Read Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "d2c_twin_update_failed_threshold_warning" {
variable "failed_d2c_twin_update_rate_threshold_warning" {
description = "D2C Twin Update Failed rate limit (warning threshold)"
default = 0
default = 0
}
variable "d2c_twin_update_failed_threshold_critical" {
variable "failed_d2c_twin_update_rate_threshold_critical" {
description = "D2C Twin Update Failed rate limit (critical threshold)"
default = 10
default = 10
}
variable "d2c_telemetry_egress_dropped_threshold_warning" {
description = "D2C Telemetry Dropped Failed limit (warning threshold)"
default = 500
variable "dropped_d2c_telemetry_egress_threshold_warning" {
description = "D2C Telemetry Dropped limit (warning threshold)"
default = 500
}
variable "d2c_telemetry_egress_dropped_threshold_critical" {
description = "D2C Telemetry Dropped Failed limit (critical threshold)"
default = 1000
variable "dropped_d2c_telemetry_egress_threshold_critical" {
description = "D2C Telemetry Dropped limit (critical threshold)"
default = 1000
}
variable "d2c_telemetry_egress_orphaned_threshold_warning" {
description = "D2C Telemetry Orphaned Failed limit (warning threshold)"
default = 500
variable "orphaned_d2c_telemetry_egress_threshold_warning" {
description = "D2C Telemetry Orphaned limit (warning threshold)"
default = 500
}
variable "d2c_telemetry_egress_orphaned_threshold_critical" {
description = "D2C Telemetry Orphaned Failed limit (critical threshold)"
default = 1000
variable "orphaned_d2c_telemetry_egress_threshold_critical" {
description = "D2C Telemetry Orphaned limit (critical threshold)"
default = 1000
}
variable "d2c_telemetry_egress_invalid_threshold_warning" {
description = "D2C Telemetry Invalid Failed limit (warning threshold)"
default = 500
variable "invalid_d2c_telemetry_egress_threshold_warning" {
description = "D2C Telemetry Invalid limit (warning threshold)"
default = 500
}
variable "d2c_telemetry_egress_invalid_threshold_critical" {
description = "D2C Telemetry Invalid Failed limit (critical threshold)"
default = 1000
variable "invalid_d2c_telemetry_egress_threshold_critical" {
description = "D2C Telemetry Invalid limit (critical threshold)"
default = 1000
}
variable "d2c_telemetry_egress_fallback_threshold_warning" {
description = "D2C Telemetry Fallback Failed limit (warning threshold)"
default = 500
variable "fallback_d2c_telemetry_egress_threshold_warning" {
description = "D2C Telemetry Fallback limit (warning threshold)"
default = 500
}
variable "d2c_telemetry_egress_fallback_threshold_critical" {
description = "D2C Telemetry Fallback Failed limit (critical threshold)"
default = 1000
variable "fallback_d2c_telemetry_egress_threshold_critical" {
description = "D2C Telemetry Fallback limit (critical threshold)"
default = 1000
}

147
cloud/azure/iothubs/monitors-iothubs.tf
View File

@ -15,13 +15,14 @@ resource "datadog_monitor" "too_many_jobs_failed" {
avg:azure.devices_iothubs.jobs.failed{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() /
( avg:azure.devices_iothubs.jobs.failed{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() +
avg:azure.devices_iothubs.jobs.completed{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() )
) * 100 > ${var.jobs_failed_threshold_critical}
) * 100 > ${var.failed_jobs_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.jobs_failed_threshold_warning}"
critical = "${var.jobs_failed_threshold_critical}"
warning = "${var.failed_jobs_rate_threshold_warning}"
critical = "${var.failed_jobs_rate_threshold_critical}"
}
notify_no_data = false
@ -35,7 +36,7 @@ resource "datadog_monitor" "too_many_jobs_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_list_jobs_failed" {
@ -47,13 +48,14 @@ resource "datadog_monitor" "too_many_list_jobs_failed" {
avg:azure.devices_iothubs.jobs.list_jobs.failure{${data.template_file.filter.rendered}} by {resource_group,name}.as_count() /
( avg:azure.devices_iothubs.jobs.list_jobs.success{${data.template_file.filter.rendered}} by {resource_group,name}.as_count() +
avg:azure.devices_iothubs.jobs.list_jobs.failure{${data.template_file.filter.rendered}} by {resource_group,name}.as_count() )
) * 100 > ${var.listjobs_failed_threshold_critical}
) * 100 > ${var.failed_listjobs_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.listjobs_failed_threshold_warning}"
critical = "${var.listjobs_failed_threshold_critical}"
warning = "${var.failed_listjobs_rate_threshold_warning}"
critical = "${var.failed_listjobs_rate_threshold_critical}"
}
notify_no_data = false
@ -67,7 +69,7 @@ resource "datadog_monitor" "too_many_list_jobs_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_query_jobs_failed" {
@ -79,13 +81,14 @@ resource "datadog_monitor" "too_many_query_jobs_failed" {
avg:azure.devices_iothubs.jobs.query_jobs.failure{${data.template_file.filter.rendered}} by {resource_group,name}.as_count() /
( avg:azure.devices_iothubs.jobs.query_jobs.success{${data.template_file.filter.rendered}} by {resource_group,name}.as_count() +
avg:azure.devices_iothubs.jobs.query_jobs.failure{${data.template_file.filter.rendered}} by {resource_group,name}.as_count() )
) * 100 > ${var.queryjobs_failed_threshold_critical}
) * 100 > ${var.failed_queryjobs_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.queryjobs_failed_threshold_warning}"
critical = "${var.queryjobs_failed_threshold_critical}"
warning = "${var.failed_queryjobs_rate_threshold_warning}"
critical = "${var.failed_queryjobs_rate_threshold_critical}"
}
notify_no_data = false
@ -99,7 +102,7 @@ resource "datadog_monitor" "too_many_query_jobs_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "status" {
@ -109,7 +112,8 @@ resource "datadog_monitor" "status" {
query = <<EOF
avg(last_5m):avg:azure.devices_iothubs.status{${data.template_file.filter.rendered}} by {name,resource_group} < 1
EOF
type = "query alert"
type = "query alert"
notify_no_data = true
evaluation_delay = "${var.delay}"
@ -122,7 +126,7 @@ resource "datadog_monitor" "status" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "total_devices" {
@ -132,7 +136,8 @@ resource "datadog_monitor" "total_devices" {
query = <<EOF
avg(last_5m):avg:azure.devices_iothubs.devices.total_devices{${data.template_file.filter.rendered}} by {name,resource_group} == 0
EOF
type = "query alert"
type = "query alert"
notify_no_data = true
evaluation_delay = "${var.delay}"
@ -145,7 +150,7 @@ resource "datadog_monitor" "total_devices" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_c2d_methods_failed" {
@ -157,13 +162,14 @@ resource "datadog_monitor" "too_many_c2d_methods_failed" {
avg:azure.devices_iothubs.c2d.methods.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() /
( avg:azure.devices_iothubs.c2d.methods.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() +
avg:azure.devices_iothubs.c2d.methods.success{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() )
) * 100 > ${var.c2d_methods_failed_threshold_critical}
) * 100 > ${var.failed_c2d_methods_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.c2d_methods_failed_threshold_warning}"
critical = "${var.c2d_methods_failed_threshold_critical}"
warning = "${var.failed_c2d_methods_rate_threshold_warning}"
critical = "${var.failed_c2d_methods_rate_threshold_critical}"
}
notify_no_data = false
@ -177,7 +183,7 @@ resource "datadog_monitor" "too_many_c2d_methods_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_c2d_twin_read_failed" {
@ -189,13 +195,14 @@ resource "datadog_monitor" "too_many_c2d_twin_read_failed" {
avg:azure.devices_iothubs.c2d.twin.read.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() /
( avg:azure.devices_iothubs.c2d.twin.read.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() +
avg:azure.devices_iothubs.c2d.twin.read.success{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() )
) * 100 > ${var.c2d_twin_read_failed_threshold_critical}
) * 100 > ${var.failed_c2d_twin_read_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.c2d_twin_read_failed_threshold_warning}"
critical = "${var.c2d_twin_read_failed_threshold_critical}"
warning = "${var.failed_c2d_twin_read_rate_threshold_warning}"
critical = "${var.failed_c2d_twin_read_rate_threshold_critical}"
}
notify_no_data = false
@ -209,7 +216,7 @@ resource "datadog_monitor" "too_many_c2d_twin_read_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_c2d_twin_update_failed" {
@ -221,13 +228,14 @@ resource "datadog_monitor" "too_many_c2d_twin_update_failed" {
avg:azure.devices_iothubs.c2d.twin.update.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() /
( avg:azure.devices_iothubs.c2d.twin.update.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() +
avg:azure.devices_iothubs.c2d.twin.update.success{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() )
) * 100 > ${var.c2d_twin_update_failed_threshold_critical}
) * 100 > ${var.failed_c2d_twin_update_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.c2d_twin_update_failed_threshold_warning}"
critical = "${var.c2d_twin_update_failed_threshold_critical}"
warning = "${var.failed_c2d_twin_update_rate_threshold_warning}"
critical = "${var.failed_c2d_twin_update_rate_threshold_critical}"
}
notify_no_data = false
@ -241,7 +249,7 @@ resource "datadog_monitor" "too_many_c2d_twin_update_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_d2c_twin_read_failed" {
@ -253,13 +261,14 @@ resource "datadog_monitor" "too_many_d2c_twin_read_failed" {
avg:azure.devices_iothubs.d2c.twin.read.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() /
( avg:azure.devices_iothubs.d2c.twin.read.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() +
avg:azure.devices_iothubs.d2c.twin.read.success{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() )
) * 100 > ${var.d2c_twin_read_failed_threshold_critical}
) * 100 > ${var.failed_d2c_twin_read_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.d2c_twin_read_failed_threshold_warning}"
critical = "${var.d2c_twin_read_failed_threshold_critical}"
warning = "${var.failed_d2c_twin_read_rate_threshold_warning}"
critical = "${var.failed_d2c_twin_read_rate_threshold_critical}"
}
notify_no_data = false
@ -273,7 +282,7 @@ resource "datadog_monitor" "too_many_d2c_twin_read_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_d2c_twin_update_failed" {
@ -285,13 +294,14 @@ resource "datadog_monitor" "too_many_d2c_twin_update_failed" {
avg:azure.devices_iothubs.d2c.twin.update.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() /
( avg:azure.devices_iothubs.d2c.twin.update.failure{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() +
avg:azure.devices_iothubs.d2c.twin.update.success{${data.template_file.filter.rendered}} by {name,resource_group}.as_count() )
) * 100 > ${var.d2c_twin_update_failed_threshold_critical}
) * 100 > ${var.failed_d2c_twin_update_rate_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.d2c_twin_update_failed_threshold_warning}"
critical = "${var.d2c_twin_update_failed_threshold_critical}"
warning = "${var.failed_d2c_twin_update_rate_threshold_warning}"
critical = "${var.failed_d2c_twin_update_rate_threshold_critical}"
}
notify_no_data = false
@ -305,7 +315,7 @@ resource "datadog_monitor" "too_many_d2c_twin_update_failed" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_d2c_telemetry_egress_dropped" {
@ -315,13 +325,14 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_dropped" {
query = <<EOF
sum(last_5m): (
avg:azure.devices_iothubs.d2c.telemetry.egress.dropped{${data.template_file.filter.rendered}} by {name,resource_group}.as_count()
) > ${var.d2c_telemetry_egress_dropped_threshold_critical}
) > ${var.dropped_d2c_telemetry_egress_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.d2c_telemetry_egress_dropped_threshold_warning}"
critical = "${var.d2c_telemetry_egress_dropped_threshold_critical}"
warning = "${var.dropped_d2c_telemetry_egress_threshold_warning}"
critical = "${var.dropped_d2c_telemetry_egress_threshold_critical}"
}
notify_no_data = false
@ -335,7 +346,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_dropped" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_d2c_telemetry_egress_orphaned" {
@ -345,13 +356,14 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_orphaned" {
query = <<EOF
sum(last_5m): (
avg:azure.devices_iothubs.d2c.telemetry.egress.orphaned{${data.template_file.filter.rendered}} by {name,resource_group}.as_count()
) > ${var.d2c_telemetry_egress_orphaned_threshold_critical}
) > ${var.orphaned_d2c_telemetry_egress_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.d2c_telemetry_egress_orphaned_threshold_warning}"
critical = "${var.d2c_telemetry_egress_orphaned_threshold_critical}"
warning = "${var.orphaned_d2c_telemetry_egress_threshold_warning}"
critical = "${var.orphaned_d2c_telemetry_egress_threshold_critical}"
}
notify_no_data = false
@ -365,7 +377,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_orphaned" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_d2c_telemetry_egress_invalid" {
@ -375,13 +387,14 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_invalid" {
query = <<EOF
sum(last_5m): (
avg:azure.devices_iothubs.d2c.telemetry.egress.invalid{${data.template_file.filter.rendered}} by {name,resource_group}.as_count()
) > ${var.d2c_telemetry_egress_invalid_threshold_critical}
) > ${var.invalid_d2c_telemetry_egress_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.d2c_telemetry_egress_invalid_threshold_warning}"
critical = "${var.d2c_telemetry_egress_invalid_threshold_critical}"
warning = "${var.invalid_d2c_telemetry_egress_threshold_warning}"
critical = "${var.invalid_d2c_telemetry_egress_threshold_critical}"
}
notify_no_data = false
@ -395,7 +408,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_invalid" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_d2c_telemetry_egress_fallback" {
@ -405,13 +418,14 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_fallback" {
query = <<EOF
sum(last_5m): (
avg:azure.devices_iothubs.d2c.telemetry.egress.fallback{${data.template_file.filter.rendered}} by {name,resource_group}.as_count()
) > ${var.d2c_telemetry_egress_fallback_threshold_critical}
) > ${var.fallback_d2c_telemetry_egress_threshold_critical}
EOF
type = "query alert"
type = "query alert"
thresholds {
warning = "${var.d2c_telemetry_egress_fallback_threshold_warning}"
critical = "${var.d2c_telemetry_egress_fallback_threshold_critical}"
warning = "${var.fallback_d2c_telemetry_egress_threshold_warning}"
critical = "${var.fallback_d2c_telemetry_egress_threshold_critical}"
}
notify_no_data = false
@ -425,7 +439,7 @@ resource "datadog_monitor" "too_many_d2c_telemetry_egress_fallback" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}
resource "datadog_monitor" "too_many_d2c_telemetry_ingress_nosent" {
@ -438,7 +452,8 @@ resource "datadog_monitor" "too_many_d2c_telemetry_ingress_nosent" {
avg:azure.devices_iothubs.d2c.telemetry.ingress.success{${data.template_file.filter.rendered}} by {name,resource_group}.as_count()
) > 0
EOF
type = "query alert"
type = "query alert"
notify_no_data = false
evaluation_delay = "${var.delay}"
@ -451,5 +466,5 @@ resource "datadog_monitor" "too_many_d2c_telemetry_ingress_nosent" {
new_host_delay = "${var.delay}"
no_data_timeframe = 20
tags = ["env:${var.environment}","resource:${var.service}","team:${var.provider}"]
tags = ["env:${var.environment}", "resource:${var.service}", "team:${var.provider}"]
}