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

MON-237 - Service Bus monitors updated

Browse Source
This commit is contained in:
Alexandre Gaillet 2018-07-05 10:24:16 +02:00 committed by Laurent Piroelle
parent 44b5153d6b
commit 09dd8a8254
8 changed files with 320 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
cloud/azure/README.md
View File

@ -206,10 +206,24 @@ Inputs
| redis_status_silenced | Groups to mute for Redis status monitor | map | `<map>` | no |
| redis_status_time_aggregator | Monitor aggregator for Redis status [available values: min, max or avg] | string | `max` | no |
| redis_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 |
| servicebus_no_active_connections_message | Custom message for Service Bus status monitor | string | `` | no |
| servicebus_no_active_connections_silenced | Groups to mute for Service Bus status monitor | map | `<map>` | no |
| servicebus_no_active_connections_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `max` | no |
| servicebus_no_active_connections_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| servicebus_server_errors_message | Custom message for Service Bus server errors monitor | string | `` | no |
| servicebus_server_errors_silenced | Groups to mute for Service Bus server errors monitor | map | `<map>` | no |
| servicebus_server_errors_threshold_critical | Critical threshold for Service Bus server errors monitor | string | `90` | no |
| servicebus_server_errors_threshold_warning | Warning threshold for Service Bus server errors monitor | string | `50` | no |
| servicebus_server_errors_timeframe | Monitor timeframe for Service Bus server errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| servicebus_status_message | Custom message for Service Bus status monitor | string | `` | no |
| servicebus_status_silenced | Groups to mute for Service Bus status monitor | map | `<map>` | no |
| servicebus_status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `max` | no |
| servicebus_status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| servicebus_user_errors_message | Custom message for Service Bus user errors monitor | string | `` | no |
| servicebus_user_errors_silenced | Groups to mute for Service Bus user errors monitor | map | `<map>` | no |
| servicebus_user_errors_threshold_critical | Critical threshold for Service Bus user errors monitor | string | `90` | no |
| servicebus_user_errors_threshold_warning | Warning threshold for Service Bus user errors monitor | string | `50` | no |
| servicebus_user_errors_timeframe | Monitor timeframe for Service Bus user errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| sqldatabase_cpu_message | Custom message for SQL CPU monitor | string | `` | no |
| sqldatabase_cpu_silenced | Groups to mute for SQL CPU monitor | map | `<map>` | no |
| sqldatabase_cpu_threshold_critical | CPU usage in percent (critical threshold) | string | `90` | no |

5
cloud/azure/cosmosdb/inputs.tf
View File

@ -22,11 +22,6 @@ variable "delay" {
default = 900
}
variable "subscription_id" {
description = "ID of the subscription"
type = "string"
}
# Azure CosmosDB specific variables
variable "cosmos_db_4xx_requests_message" {
description = "Custom message for Cosmos DB 4xx requests monitor"

32
cloud/azure/cosmosdb/monitors-cosmosdb.tf
View File

@ -12,17 +12,17 @@ resource "datadog_monitor" "cosmos_db_4xx_requests" {
query = <<EOF
sum(last_5m): (default(
( avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:400} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:403} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:404} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:408} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:409} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:410} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:412} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:413} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:429} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:449} by {resource_group,name}.as_count() ) /
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered}} by {resource_group,name}.as_count()
( avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:400} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:403} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:404} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:408} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:409} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:410} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:412} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:413} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:429} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:449} by {resource_group,region,name}.as_count() ) /
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
* 100, 0)
) > ${var.cosmos_db_4xx_request_rate_threshold_critical}
EOF
@ -55,9 +55,9 @@ resource "datadog_monitor" "cosmos_db_5xx_requests" {
query = <<EOF
sum(last_5m): (default(
( avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:500} by {resource_group,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:503} by {resource_group,name}.as_count() ) /
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered}} by {resource_group,name}.as_count()
( avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:500} by {resource_group,region,name}.as_count() +
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered},statuscode:503} by {resource_group,region,name}.as_count() ) /
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
* 100, 0)
) > ${var.cosmos_db_5xx_request_rate_threshold_critical}
EOF
@ -90,7 +90,7 @@ resource "datadog_monitor" "cosmos_db_success_no_data" {
query = <<EOF
avg(last_5m): (
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered}} by {resource_group,name}
avg:azure.cosmosdb.total_requests{${data.template_file.filter.rendered}} by {resource_group,region,name}
) < 0
EOF
@ -119,7 +119,7 @@ resource "datadog_monitor" "cosmos_db_ru_utilization" {
query = <<EOF
avg(last_5m): (
avg:azure.cosmosdb.total_request_units{${data.template_file.filter.rendered},collectionname:${element(keys(var.cosmos_db_ru_utilization_collection),count.index)}} by {resource_group,name} /
avg:azure.cosmosdb.total_request_units{${data.template_file.filter.rendered},collectionname:${element(keys(var.cosmos_db_ru_utilization_collection),count.index)}} by {resource_group,region,name} /
${element(values(var.cosmos_db_ru_utilization_collection),count.index)}
) * 100 > ${var.cosmos_db_ru_utilization_rate_threshold_critical}
EOF

80
cloud/azure/inputs.tf
View File

@ -930,6 +930,86 @@ variable "servicebus_status_timeframe" {
default = "last_15m"
}
variable "servicebus_no_active_connections_silenced" {
description = "Groups to mute for Service Bus status monitor"
type = "map"
default = {}
}
variable "servicebus_no_active_connections_message" {
description = "Custom message for Service Bus status monitor"
type = "string"
default = ""
}
variable "servicebus_no_active_connections_time_aggregator" {
description = "Monitor aggregator for Service Bus status [available values: min, max or avg]"
type = "string"
default = "max"
}
variable "servicebus_no_active_connections_timeframe" {
description = "Monitor timeframe for Service Bus status [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 "servicebus_server_errors_message" {
description = "Custom message for Service Bus server errors monitor"
type = "string"
default = ""
}
variable "servicebus_server_errors_silenced" {
description = "Groups to mute for Service Bus server errors monitor"
type = "map"
default = {}
}
variable "servicebus_server_errors_timeframe" {
description = "Monitor timeframe for Service Bus server 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 "servicebus_server_errors_threshold_critical" {
description = "Critical threshold for Service Bus server errors monitor"
default = 90
}
variable "servicebus_server_errors_threshold_warning" {
description = "Warning threshold for Service Bus server errors monitor"
default = 50
}
variable "servicebus_user_errors_message" {
description = "Custom message for Service Bus user errors monitor"
type = "string"
default = ""
}
variable "servicebus_user_errors_silenced" {
description = "Groups to mute for Service Bus user errors monitor"
type = "map"
default = {}
}
variable "servicebus_user_errors_timeframe" {
description = "Monitor timeframe for Service Bus user 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 "servicebus_user_errors_threshold_critical" {
description = "Critical threshold for Service Bus user errors monitor"
default = 90
}
variable "servicebus_user_errors_threshold_warning" {
description = "Warning threshold for Service Bus user errors monitor"
default = 50
}
# Azure SQL Database specific variables
variable "sqldatabase_cpu_silenced" {
description = "Groups to mute for SQL CPU monitor"

17
cloud/azure/monitors.tf
View File

@ -230,6 +230,23 @@ module "servicebus" {
status_message = "${var.servicebus_status_message}"
status_timeframe = "${var.servicebus_status_timeframe}"
status_time_aggregator = "${var.servicebus_status_time_aggregator}"
no_active_connections_silenced = "${var.servicebus_no_active_connections_silenced}"
no_active_connections_message = "${var.servicebus_no_active_connections_message}"
no_active_connections_timeframe = "${var.servicebus_no_active_connections_timeframe}"
no_active_connections_time_aggregator = "${var.servicebus_no_active_connections_time_aggregator}"
server_errors_silenced = "${var.servicebus_server_errors_silenced}"
server_errors_message = "${var.servicebus_server_errors_message}"
server_errors_timeframe = "${var.servicebus_server_errors_timeframe}"
server_errors_threshold_critical = "${var.servicebus_server_errors_threshold_critical}"
server_errors_threshold_warning = "${var.servicebus_server_errors_threshold_warning}"
user_errors_silenced = "${var.servicebus_user_errors_silenced}"
user_errors_message = "${var.servicebus_user_errors_message}"
user_errors_timeframe = "${var.servicebus_user_errors_timeframe}"
user_errors_threshold_critical = "${var.servicebus_user_errors_threshold_critical}"
user_errors_threshold_warning = "${var.servicebus_user_errors_threshold_warning}"
}
module "sqldatabase" {

19
cloud/azure/servicebus/README.md
View File

@ -16,7 +16,10 @@ module "datadog-monitors-cloud-azure-servicebus" {
Creates DataDog monitors with the following checks:
- Service Bus is down
- Service status check
- No active connection
- Server errors rate
- User errors rate
## Inputs
@ -27,12 +30,26 @@ 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 |
| no_active_connections_message | Custom message for Service Bus status monitor | string | `` | no |
| no_active_connections_silenced | Groups to mute for Service Bus status monitor | map | `<map>` | no |
| no_active_connections_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `max` | no |
| no_active_connections_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| server_errors_message | Custom message for Service Bus server errors monitor | string | `` | no |
| server_errors_silenced | Groups to mute for Service Bus server errors monitor | map | `<map>` | no |
| server_errors_threshold_critical | Critical threshold for Service Bus server errors monitor | string | `90` | no |
| server_errors_threshold_warning | Warning threshold for Service Bus server errors monitor | string | `50` | no |
| server_errors_timeframe | Monitor timeframe for Service Bus server errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| new_host_delay | Delay in seconds before monitor new resource | string | `300` | no |
| status_extra_tags | Extra tags for Service Bus status monitor | list | `<list>` | no |
| status_message | Custom message for Service Bus status monitor | string | `` | no |
| status_silenced | Groups to mute for Service Bus status monitor | map | `<map>` | no |
| status_time_aggregator | Monitor aggregator for Service Bus status [available values: min, max or avg] | string | `max` | no |
| status_timeframe | Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| user_errors_message | Custom message for Service Bus user errors monitor | string | `` | no |
| user_errors_silenced | Groups to mute for Service Bus user errors monitor | map | `<map>` | no |
| user_errors_threshold_critical | Critical threshold for Service Bus user errors monitor | string | `90` | no |
| user_errors_threshold_warning | Warning threshold for Service Bus user errors monitor | string | `50` | no |
| user_errors_timeframe | Monitor timeframe for Service Bus user errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
## Outputs

80
cloud/azure/servicebus/inputs.tf
View File

@ -58,3 +58,83 @@ variable "status_timeframe" {
description = "Monitor timeframe for Service Bus status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_15m"
}
variable "no_active_connections_silenced" {
description = "Groups to mute for Service Bus status monitor"
type = "map"
default = {}
}
variable "no_active_connections_message" {
description = "Custom message for Service Bus status monitor"
type = "string"
default = ""
}
variable "no_active_connections_time_aggregator" {
description = "Monitor aggregator for Service Bus status [available values: min, max or avg]"
type = "string"
default = "max"
}
variable "no_active_connections_timeframe" {
description = "Monitor timeframe for Service Bus status [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 "server_errors_message" {
description = "Custom message for Service Bus server errors monitor"
type = "string"
default = ""
}
variable "server_errors_silenced" {
description = "Groups to mute for Service Bus server errors monitor"
type = "map"
default = {}
}
variable "server_errors_timeframe" {
description = "Monitor timeframe for Service Bus server 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 "server_errors_threshold_critical" {
description = "Critical threshold for Service Bus server errors monitor"
default = 90
}
variable "server_errors_threshold_warning" {
description = "Warning threshold for Service Bus server errors monitor"
default = 50
}
variable "user_errors_message" {
description = "Custom message for Service Bus user errors monitor"
type = "string"
default = ""
}
variable "user_errors_silenced" {
description = "Groups to mute for Service Bus user errors monitor"
type = "map"
default = {}
}
variable "user_errors_timeframe" {
description = "Monitor timeframe for Service Bus user 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 "user_errors_threshold_critical" {
description = "Critical threshold for Service Bus user errors monitor"
default = 90
}
variable "user_errors_threshold_warning" {
description = "Warning threshold for Service Bus user errors monitor"
default = 50
}

95
cloud/azure/servicebus/monitors-service-bus.tf
View File

@ -24,3 +24,98 @@ EOF
tags = ["env:${var.environment}", "type:cloud", "provider:azure", "resource:servicebus", "team:claranet", "created-by:terraform", "${var.status_extra_tags}"]
}
resource "datadog_monitor" "service_bus_no_active_connections" {
name = "[${var.environment}] Service Bus has no active connection"
message = "${coalesce(var.no_active_connections_message, var.message)}"
query = <<EOF
${var.no_active_connections_time_aggregator}(${var.no_active_connections_timeframe}): (
avg:azure.servicebus_namespaces.active_connections_preview{${data.template_file.filter.rendered}} by {resource_group,region,name}
) < 1
EOF
type = "metric alert"
silenced = "${var.no_active_connections_silenced}"
notify_no_data = false
evaluation_delay = "${var.delay}"
renotify_interval = 0
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.delay}"
tags = ["env:${var.environment}", "resource:servicebus", "team:azure", "provider:azure"]
}
resource "datadog_monitor" "service_bus_user_errors" {
name = "[${var.environment}] Service Bus user errors rate is high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.user_errors_message, var.message)}"
query = <<EOF
sum(${var.user_errors_timeframe}): (default(
avg:azure.servicebus_namespaces.user_errors.preview{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.servicebus_namespaces.incoming_requests_preview{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
* 100, 0)
) > ${var.user_errors_threshold_critical}
EOF
type = "metric alert"
thresholds {
critical = "${var.user_errors_threshold_critical}"
warning = "${var.user_errors_threshold_warning}"
}
silenced = "${var.user_errors_silenced}"
notify_no_data = false
evaluation_delay = "${var.delay}"
renotify_interval = 0
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.delay}"
tags = ["env:${var.environment}", "resource:servicebus", "team:azure", "provider:azure"]
}
resource "datadog_monitor" "service_bus_server_errors" {
name = "[${var.environment}] Service Bus server errors rate is high {{#is_alert}}{{comparator}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{comparator}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.server_errors_message, var.message)}"
query = <<EOF
sum(${var.server_errors_timeframe}): (default(
avg:azure.servicebus_namespaces.server_errors.preview{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count() /
avg:azure.servicebus_namespaces.incoming_requests_preview{${data.template_file.filter.rendered}} by {resource_group,region,name}.as_count()
* 100, 0)
) > ${var.server_errors_threshold_critical}
EOF
type = "metric alert"
thresholds {
critical = "${var.server_errors_threshold_critical}"
warning = "${var.server_errors_threshold_warning}"
}
silenced = "${var.server_errors_silenced}"
notify_no_data = false
evaluation_delay = "${var.delay}"
renotify_interval = 0
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.delay}"
tags = ["env:${var.environment}", "resource:servicebus", "team:azure", "provider:azure"]
}