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

MON-191 - AWS monitors updated with customizable aggregator

Browse Source
This commit is contained in:
Alexandre Gaillet 2018-04-27 17:04:47 +02:00 committed by Quentin Manfroi
parent a3ecf61909
commit 966a9b5f54
21 changed files with 211 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
cloud/aws/alb/README.md
View File

@ -30,6 +30,7 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| alb_no_healthy_instances_aggregator | Monitor aggregator for ALB no healthy instances [available values: min, max, sum or avg] | string | `min` | no |
| alb_no_healthy_instances_message | Custom message for ALB no healthy instances monitor | string | `` | no |
| alb_no_healthy_instances_silenced | Groups to mute for ALB no healthy instances monitor | map | `<map>` | no |
| alb_no_healthy_instances_timeframe | Monitor timeframe for ALB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_1m` | no |
@ -38,26 +39,31 @@ Inputs
| 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 |
| httpcode_elb_4xx_aggregator | Monitor aggregator for ALB httpcode 4xx [available values: min, max, sum or avg] | string | `min` | no |
| httpcode_elb_4xx_message | Custom message for ALB httpcode 4xx monitor | string | `` | no |
| httpcode_elb_4xx_silenced | Groups to mute for ALB httpcode 4xx monitor | map | `<map>` | no |
| httpcode_elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `80` | no |
| httpcode_elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `60` | no |
| httpcode_elb_4xx_timeframe | Monitor timeframe for ALB httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| httpcode_elb_5xx_aggregator | Monitor aggregator for ALB httpcode 5xx [available values: min, max, sum or avg] | string | `min` | no |
| httpcode_elb_5xx_message | Custom message for ALB httpcode 5xx monitor | string | `` | no |
| httpcode_elb_5xx_silenced | Groups to mute for ALB httpcode 5xx monitor | map | `<map>` | no |
| httpcode_elb_5xx_threshold_critical | loadbalancer 5xxcritical threshold in percentage | string | `80` | no |
| httpcode_elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `60` | no |
| httpcode_elb_5xx_timeframe | Monitor timeframe for ALB httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| httpcode_target_4xx_aggregator | Monitor aggregator for ALB target httpcode 4xx [available values: min, max, sum or avg] | string | `min` | no |
| httpcode_target_4xx_message | Custom message for ALB target httpcode 4xx monitor | string | `` | no |
| httpcode_target_4xx_silenced | Groups to mute for ALB target httpcode 4xx monitor | map | `<map>` | no |
| httpcode_target_4xx_threshold_critical | target 4xx critical threshold in percentage | string | `80` | no |
| httpcode_target_4xx_threshold_warning | target 4xx warning threshold in percentage | string | `60` | no |
| httpcode_target_4xx_timeframe | Monitor timeframe for ALB target httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| httpcode_target_5xx_aggregator | Monitor aggregator for ALB target httpcode 5xx [available values: min, max, sum or avg] | string | `min` | no |
| httpcode_target_5xx_message | Custom message for ALB target httpcode 5xx monitor | string | `` | no |
| httpcode_target_5xx_silenced | Groups to mute for ALB target httpcode 5xx monitor | map | `<map>` | no |
| httpcode_target_5xx_threshold_critical | target 5xx critical threshold in percentage | string | `80` | no |
| httpcode_target_5xx_threshold_warning | target 5xx warning threshold in percentage | string | `60` | no |
| httpcode_target_5xx_timeframe | Monitor timeframe for ALB target httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| latency_aggregator | Monitor aggregator for ALB latency [available values: min, max, sum or avg] | string | `min` | no |
| latency_message | Custom message for ALB latency monitor | string | `` | no |
| latency_silenced | Groups to mute for ALB latency monitor | map | `<map>` | no |
| latency_threshold_critical | latency critical threshold in milliseconds | string | `1000` | no |

36
cloud/aws/alb/inputs.tf
View File

@ -38,6 +38,12 @@ variable "alb_no_healthy_instances_message" {
default = ""
}
variable "alb_no_healthy_instances_aggregator" {
description = "Monitor aggregator for ALB no healthy instances [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "alb_no_healthy_instances_timeframe" {
description = "Monitor timeframe for ALB no healthy instances [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -56,6 +62,12 @@ variable "latency_message" {
default = ""
}
variable "latency_aggregator" {
description = "Monitor aggregator for ALB latency [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "latency_timeframe" {
description = "Monitor timeframe for ALB latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -84,6 +96,12 @@ variable "httpcode_elb_4xx_message" {
default = ""
}
variable "httpcode_elb_4xx_aggregator" {
description = "Monitor aggregator for ALB httpcode 4xx [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "httpcode_elb_4xx_timeframe" {
description = "Monitor timeframe for ALB httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -112,6 +130,12 @@ variable "httpcode_target_4xx_message" {
default = ""
}
variable "httpcode_target_4xx_aggregator" {
description = "Monitor aggregator for ALB target httpcode 4xx [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "httpcode_target_4xx_timeframe" {
description = "Monitor timeframe for ALB target httpcode 4xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -140,6 +164,12 @@ variable "httpcode_elb_5xx_message" {
default = ""
}
variable "httpcode_elb_5xx_aggregator" {
description = "Monitor aggregator for ALB httpcode 5xx [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "httpcode_elb_5xx_timeframe" {
description = "Monitor timeframe for ALB httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -168,6 +198,12 @@ variable "httpcode_target_5xx_message" {
default = ""
}
variable "httpcode_target_5xx_aggregator" {
description = "Monitor aggregator for ALB target httpcode 5xx [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "httpcode_target_5xx_timeframe" {
description = "Monitor timeframe for ALB target httpcode 5xx [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"

32
cloud/aws/alb/monitors-alb.tf
View File

@ -14,8 +14,8 @@ resource "datadog_monitor" "ALB_no_healthy_instances" {
message = "${coalesce(var.alb_no_healthy_instances_message, var.message)}"
query = <<EOF
min(${var.alb_no_healthy_instances_timeframe}): (
min:aws.applicationelb.healthy_host_count{${data.template_file.filter.rendered}} by {region,loadbalancer}
${var.alb_no_healthy_instances_aggregator}(${var.alb_no_healthy_instances_timeframe}): (
${var.alb_no_healthy_instances_aggregator}:aws.applicationelb.healthy_host_count{${data.template_file.filter.rendered}} by {region,loadbalancer}
) <= 0
EOF
@ -43,8 +43,8 @@ resource "datadog_monitor" "ALB_latency" {
message = "${coalesce(var.latency_message, var.message)}"
query = <<EOF
min(${var.latency_timeframe}): (
min:aws.applicationelb.target_response_time.average{${data.template_file.filter.rendered}} by {region,loadbalancer}
${var.latency_aggregator}(${var.latency_timeframe}): (
${var.latency_aggregator}:aws.applicationelb.target_response_time.average{${data.template_file.filter.rendered}} by {region,loadbalancer}
) > ${var.latency_threshold_critical}
EOF
@ -73,10 +73,10 @@ resource "datadog_monitor" "ALB_httpcode_elb_5xx" {
message = "${coalesce(var.httpcode_elb_5xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_elb_5xx_timeframe}): (
${var.httpcode_elb_5xx_aggregator}(${var.httpcode_elb_5xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
${var.httpcode_elb_5xx_aggregator}:aws.applicationelb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(${var.httpcode_elb_5xx_aggregator}:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.httpcode_elb_5xx_threshold_critical}
EOF
@ -106,10 +106,10 @@ resource "datadog_monitor" "ALB_httpcode_elb_4xx" {
message = "${coalesce(var.httpcode_elb_4xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_elb_4xx_timeframe}): (
${var.httpcode_elb_4xx_aggregator}(${var.httpcode_elb_4xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
${var.httpcode_elb_4xx_aggregator}:aws.applicationelb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(${var.httpcode_elb_4xx_aggregator}:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.httpcode_elb_4xx_threshold_critical}
EOF
@ -139,10 +139,10 @@ resource "datadog_monitor" "ALB_httpcode_target_5xx" {
message = "${coalesce(var.httpcode_target_5xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_target_5xx_timeframe}): (
${var.httpcode_target_5xx_aggregator}(${var.httpcode_target_5xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_target_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
${var.httpcode_target_5xx_aggregator}:aws.applicationelb.httpcode_target_5xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(${var.httpcode_target_5xx_aggregator}:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.httpcode_target_5xx_threshold_critical}
EOF
@ -172,10 +172,10 @@ resource "datadog_monitor" "ALB_httpcode_target_4xx" {
message = "${coalesce(var.httpcode_target_4xx_message, var.message)}"
query = <<EOF
min(${var.httpcode_target_4xx_timeframe}): (
${var.httpcode_target_4xx_aggregator}(${var.httpcode_target_4xx_timeframe}): (
default(
min:aws.applicationelb.httpcode_target_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(min:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
${var.httpcode_target_4xx_aggregator}:aws.applicationelb.httpcode_target_4xx{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() /
(${var.httpcode_target_4xx_aggregator}:aws.applicationelb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancer}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.httpcode_target_4xx_threshold_critical}
EOF

4
cloud/aws/apigateway/README.md
View File

@ -31,23 +31,25 @@ Inputs
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| environment | Environment | string | - | yes |
| filter_tags | Tags used for filtering | string | `*` | no |
| http_4xx_requests_aggregator | Monitor aggregator for API Gateway HTTP 4xx requests [available values: min, max, sum or avg] | string | `min` | no |
| http_4xx_requests_message | Custom message for API Gateway HTTP 4xx requests monitor | string | `` | no |
| http_4xx_requests_silenced | Groups to mute for API Gateway HTTP 4xx requests monitor | map | `<map>` | no |
| http_4xx_requests_threshold_critical | Maximum critical acceptable percent of 4xx errors | string | `30` | no |
| http_4xx_requests_threshold_warning | Maximum warning acceptable percent of 4xx errors | string | `15` | no |
| http_4xx_requests_timeframe | Monitor timeframe for API HTTP 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_aggregator | Monitor aggregator for API Gateway HTTP 5xx requests [available values: min, max, sum or avg] | string | `min` | no |
| http_5xx_requests_message | Custom message for API Gateway HTTP 5xx requests monitor | string | `` | no |
| http_5xx_requests_silenced | Groups to mute for API Gateway HTTP 5xx requests monitor | map | `<map>` | no |
| http_5xx_requests_threshold_critical | Maximum critical acceptable percent of 5xx errors | string | `20` | no |
| http_5xx_requests_threshold_warning | Maximum warning acceptable percent of 5xx errors | string | `10` | no |
| http_5xx_requests_timeframe | Monitor timeframe for API HTTP 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 |
| latency_aggregator | Monitor aggregator for API Gateway latency [available values: min, max, sum or avg] | string | `min` | no |
| latency_message | Custom message for API Gateway latency monitor | string | `` | no |
| latency_silenced | Groups to mute for API Gateway latency monitor | map | `<map>` | no |
| latency_threshold_critical | Alerting threshold in milliseconds | string | `800` | no |
| latency_threshold_warning | Warning threshold in milliseconds | string | `400` | no |
| latency_timeframe | Monitor timeframe for API latency [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 |
Related documentation
---------------------

18
cloud/aws/apigateway/inputs.tf
View File

@ -33,6 +33,12 @@ variable "latency_message" {
default = ""
}
variable "latency_aggregator" {
description = "Monitor aggregator for API Gateway latency [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "latency_timeframe" {
description = "Monitor timeframe for API latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -65,6 +71,12 @@ variable "http_5xx_requests_message" {
default = ""
}
variable "http_5xx_requests_aggregator" {
description = "Monitor aggregator for API Gateway HTTP 5xx requests [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "http_5xx_requests_timeframe" {
description = "Monitor timeframe for API HTTP 5xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -97,6 +109,12 @@ variable "http_4xx_requests_message" {
default = ""
}
variable "http_4xx_requests_aggregator" {
description = "Monitor aggregator for API Gateway HTTP 4xx requests [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "http_4xx_requests_timeframe" {
description = "Monitor timeframe for API HTTP 4xx requests [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"

16
cloud/aws/apigateway/monitors-api.tf
View File

@ -5,8 +5,8 @@ resource "datadog_monitor" "API_Gateway_latency" {
message = "${coalesce(var.latency_message, var.message)}"
query = <<EOF
min(${var.latency_timeframe}): (
min:aws.apigateway.latency{${var.filter_tags}} by {region,apiname}
${var.latency_aggregator}(${var.latency_timeframe}): (
${var.latency_aggregator}:aws.apigateway.latency{${var.filter_tags}} by {region,apiname}
) > ${var.latency_threshold_critical}
EOF
@ -36,10 +36,10 @@ resource "datadog_monitor" "API_http_5xx_errors_count" {
message = "${coalesce(var.http_5xx_requests_message, var.message)}"
query = <<EOF
min(${var.http_5xx_requests_timeframe}): (
${var.http_5xx_requests_aggregator}(${var.http_5xx_requests_timeframe}): (
default(
min:aws.apigateway.5xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(min:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
${var.http_5xx_requests_aggregator}:aws.apigateway.5xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(${var.http_5xx_requests_aggregator}:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.http_5xx_requests_threshold_critical}
EOF
@ -70,10 +70,10 @@ resource "datadog_monitor" "API_http_4xx_errors_count" {
message = "${coalesce(var.http_4xx_requests_message, var.message)}"
query = <<EOF
min(${var.http_4xx_requests_timeframe}): (
${var.http_4xx_requests_aggregator}(${var.http_4xx_requests_timeframe}): (
default(
min:aws.apigateway.4xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(min:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
${var.http_4xx_requests_aggregator}:aws.apigateway.4xxerror{${var.filter_tags}} by {region,apiname}.as_count() /
(${var.http_4xx_requests_aggregator}:aws.apigateway.count{${var.filter_tags}} by {region,apiname}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.http_4xx_requests_threshold_critical}
EOF

3
cloud/aws/elasticsearch/README.md
View File

@ -29,18 +29,21 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| cpu_aggregator | Monitor aggregator for ES cluster cpu [available values: min, max, sum or avg] | string | `avg` | no |
| cpu_message | Custom message for ES cluster cpu monitor | string | `` | no |
| cpu_silenced | Groups to mute for ES cluster 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 ES cluster cpu [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| diskspace_aggregator | Monitor aggregator for ES cluster diskspace [available values: min, max, sum or avg] | string | `avg` | no |
| diskspace_message | Custom message for ES cluster diskspace monitor | string | `` | no |
| diskspace_silenced | Groups to mute for ES cluster diskspace monitor | map | `<map>` | no |
| diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |
| diskspace_threshold_warning | Disk free space in percent (warning threshold) | string | `20` | no |
| diskspace_timeframe | Monitor timeframe for ES cluster diskspace [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 |
| es_cluster_status_aggregator | Monitor aggregator for ES cluster status [available values: min, max, sum or avg] | string | `max` | no |
| es_cluster_status_message | Custom message for ES cluster status monitor | string | `` | no |
| es_cluster_status_silenced | Groups to mute for ES cluster status monitor | map | `<map>` | no |
| es_cluster_status_timeframe | Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_30m` | no |

18
cloud/aws/elasticsearch/inputs.tf
View File

@ -38,6 +38,12 @@ variable "es_cluster_status_message" {
default = ""
}
variable "es_cluster_status_aggregator" {
description = "Monitor aggregator for ES cluster status [available values: min, max, sum or avg]"
type = "string"
default = "max"
}
variable "es_cluster_status_timeframe" {
description = "Monitor timeframe for ES cluster status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -60,6 +66,12 @@ variable "diskspace_message" {
default = ""
}
variable "diskspace_aggregator" {
description = "Monitor aggregator for ES cluster diskspace [available values: min, max, sum or avg]"
type = "string"
default = "avg"
}
variable "diskspace_timeframe" {
description = "Monitor timeframe for ES cluster diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -88,6 +100,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_aggregator" {
description = "Monitor aggregator for ES cluster cpu [available values: min, max, sum or avg]"
type = "string"
default = "avg"
}
variable "cpu_timeframe" {
description = "Monitor timeframe for ES cluster cpu [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"

14
cloud/aws/elasticsearch/monitors-elasticsearch.tf
View File

@ -18,9 +18,9 @@ resource "datadog_monitor" "es_cluster_status" {
type = "metric alert"
query = <<EOF
max(${var.es_cluster_status_timeframe}): (
avg:aws.es.cluster_statusred{${data.template_file.filter.rendered}} by {region,name} * 2 +
(avg:aws.es.cluster_statusyellow{${data.template_file.filter.rendered}} by {region,name} + 0.1)
${var.es_cluster_status_aggregator}(${var.es_cluster_status_timeframe}): (
${var.es_cluster_status_aggregator}:aws.es.cluster_statusred{${data.template_file.filter.rendered}} by {region,name} * 2 +
(${var.es_cluster_status_aggregator}:aws.es.cluster_statusyellow{${data.template_file.filter.rendered}} by {region,name} + 0.1)
) >= 2
EOF
@ -52,8 +52,8 @@ resource "datadog_monitor" "es_free_space_low" {
type = "metric alert"
query = <<EOF
avg(${var.diskspace_timeframe}): (
avg:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
${var.diskspace_aggregator}(${var.diskspace_timeframe}): (
${var.diskspace_aggregator}:aws.es.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
(${var.es_cluster_volume_size}*1000) * 100
) < ${var.diskspace_threshold_critical}
EOF
@ -86,8 +86,8 @@ resource "datadog_monitor" "es_cpu_90_15min" {
type = "metric alert"
query = <<EOF
avg(${var.cpu_timeframe}): (
avg:aws.es.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
${var.cpu_aggregator}(${var.cpu_timeframe}): (
${var.cpu_aggregator}:aws.es.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
) > ${var.cpu_threshold_critical}
EOF

6
cloud/aws/elb/README.md
View File

@ -32,31 +32,37 @@ Inputs
|------|-------------|:----:|:-----:|:-----:|
| artificial_requests_count | Number of false requests used to mitigate false positive in case of low trafic | string | `5` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| elb_4xx_aggregator | Monitor aggregator for ELB 4xx errors [available values: min, max, sum or avg] | string | `min` | no |
| elb_4xx_message | Custom message for ELB 4xx errors monitor | string | `` | no |
| elb_4xx_silenced | Groups to mute for ELB 4xx errors monitor | map | `<map>` | no |
| elb_4xx_threshold_critical | loadbalancer 4xx critical threshold in percentage | string | `10` | no |
| elb_4xx_threshold_warning | loadbalancer 4xx warning threshold in percentage | string | `5` | no |
| elb_4xx_timeframe | Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_5xx_aggregator | Monitor aggregator for ELB 5xx errors [available values: min, max, sum or avg] | string | `min` | no |
| elb_5xx_message | Custom message for ELB 5xx errors monitor | string | `` | no |
| elb_5xx_silenced | Groups to mute for ELB 5xx errors monitor | map | `<map>` | no |
| elb_5xx_threshold_critical | loadbalancer 5xx critical threshold in percentage | string | `10` | no |
| elb_5xx_threshold_warning | loadbalancer 5xx warning threshold in percentage | string | `5` | no |
| elb_5xx_timeframe | Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_4xx_aggregator | Monitor aggregator for ELB backend 4xx errors [available values: min, max, sum or avg] | string | `min` | no |
| elb_backend_4xx_message | Custom message for ELB backend 4xx errors monitor | string | `` | no |
| elb_backend_4xx_silenced | Groups to mute for ELB backend 4xx errors monitor | map | `<map>` | no |
| elb_backend_4xx_threshold_critical | loadbalancer backend 4xx critical threshold in percentage | string | `10` | no |
| elb_backend_4xx_threshold_warning | loadbalancer backend 4xx warning threshold in percentage | string | `5` | no |
| elb_backend_4xx_timeframe | Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_5xx_aggregator | Monitor aggregator for ELB backend 5xx errors [available values: min, max, sum or avg] | string | `min` | no |
| elb_backend_5xx_message | Custom message for ELB backend 5xx errors monitor | string | `` | no |
| elb_backend_5xx_silenced | Groups to mute for ELB backend 5xx errors monitor | map | `<map>` | no |
| elb_backend_5xx_threshold_critical | loadbalancer backend 5xx critical threshold in percentage | string | `10` | no |
| elb_backend_5xx_threshold_warning | loadbalancer backend 5xx warning threshold in percentage | string | `5` | no |
| elb_backend_5xx_timeframe | Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_latency_aggregator | Monitor aggregator for ELB backend latency [available values: min, max, sum or avg] | string | `min` | no |
| elb_backend_latency_critical | latency critical threshold in seconds | string | `5` | no |
| elb_backend_latency_message | Custom message for ELB backend latency monitor | string | `` | no |
| elb_backend_latency_silenced | Groups to mute for ELB backend latency monitor | map | `<map>` | no |
| elb_backend_latency_timeframe | Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| elb_backend_latency_warning | latency warning threshold in seconds | string | `1` | no |
| elb_no_healthy_instance_aggregator | Monitor aggregator for ELB no healty instance [available values: min, max, sum or avg] | string | `min` | no |
| elb_no_healthy_instance_message | Custom message for ELB no healty instance monitor | string | `` | no |
| elb_no_healthy_instance_silenced | Groups to mute for ELB no healty instance monitor | map | `<map>` | no |
| elb_no_healthy_instance_timeframe | Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |

36
cloud/aws/elb/inputs.tf
View File

@ -37,6 +37,12 @@ variable "elb_no_healthy_instance_message" {
default = ""
}
variable "elb_no_healthy_instance_aggregator" {
description = "Monitor aggregator for ELB no healty instance [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "elb_no_healthy_instance_timeframe" {
description = "Monitor timeframe for ELB no healty instance [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -55,6 +61,12 @@ variable "elb_4xx_message" {
default = ""
}
variable "elb_4xx_aggregator" {
description = "Monitor aggregator for ELB 4xx errors [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "elb_4xx_timeframe" {
description = "Monitor timeframe for ELB 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -83,6 +95,12 @@ variable "elb_5xx_message" {
default = ""
}
variable "elb_5xx_aggregator" {
description = "Monitor aggregator for ELB 5xx errors [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "elb_5xx_timeframe" {
description = "Monitor timeframe for ELB 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -111,6 +129,12 @@ variable "elb_backend_4xx_message" {
default = ""
}
variable "elb_backend_4xx_aggregator" {
description = "Monitor aggregator for ELB backend 4xx errors [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "elb_backend_4xx_timeframe" {
description = "Monitor timeframe for ELB backend 4xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -139,6 +163,12 @@ variable "elb_backend_5xx_message" {
default = ""
}
variable "elb_backend_5xx_aggregator" {
description = "Monitor aggregator for ELB backend 5xx errors [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "elb_backend_5xx_timeframe" {
description = "Monitor timeframe for ELB backend 5xx errors [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -167,6 +197,12 @@ variable "elb_backend_latency_message" {
default = ""
}
variable "elb_backend_latency_aggregator" {
description = "Monitor aggregator for ELB backend latency [available values: min, max, sum or avg]"
type = "string"
default = "min"
}
variable "elb_backend_latency_timeframe" {
description = "Monitor timeframe for ELB backend latency [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"

32
cloud/aws/elb/monitors-elb.tf
View File

@ -11,8 +11,8 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}"
query = <<EOF
min(${var.elb_no_healthy_instance_timeframe}): (
min:aws.elb.healthy_host_count{${data.template_file.filter.rendered}} by {region,loadbalancername}
${var.elb_no_healthy_instance_aggregator}(${var.elb_no_healthy_instance_timeframe}): (
${var.elb_no_healthy_instance_aggregator}:aws.elb.healthy_host_count{${data.template_file.filter.rendered}} by {region,loadbalancername}
) < 1
EOF
@ -38,10 +38,10 @@ resource "datadog_monitor" "ELB_too_much_4xx" {
message = "${coalesce(var.elb_4xx_message, var.message)}"
query = <<EOF
min(${var.elb_4xx_timeframe}): (
${var.elb_4xx_aggregator}(${var.elb_4xx_timeframe}): (
default(
min:aws.elb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() + ${var.artificial_requests_count}),
${var.elb_4xx_aggregator}:aws.elb.httpcode_elb_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() /
(${var.elb_4xx_aggregator}:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername}.as_count() + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_4xx_threshold_critical}
EOF
@ -73,10 +73,10 @@ resource "datadog_monitor" "ELB_too_much_5xx" {
message = "${coalesce(var.elb_5xx_message, var.message)}"
query = <<EOF
min(${var.elb_5xx_timeframe}): (
${var.elb_5xx_aggregator}(${var.elb_5xx_timeframe}): (
default(
min:aws.elb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
${var.elb_5xx_aggregator}:aws.elb.httpcode_elb_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(${var.elb_5xx_aggregator}:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_5xx_threshold_critical}
EOF
@ -108,10 +108,10 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
message = "${coalesce(var.elb_backend_4xx_message, var.message)}"
query = <<EOF
min(${var.elb_backend_4xx_timeframe}): (
${var.elb_backend_4xx_aggregator}(${var.elb_backend_4xx_timeframe}): (
default(
min:aws.elb.httpcode_backend_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
${var.elb_backend_4xx_aggregator}:aws.elb.httpcode_backend_4xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(${var.elb_backend_4xx_aggregator}:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_backend_4xx_threshold_critical}
EOF
@ -143,10 +143,10 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
message = "${coalesce(var.elb_backend_5xx_message, var.message)}"
query = <<EOF
min(${var.elb_backend_5xx_timeframe}): (
${var.elb_backend_5xx_aggregator}(${var.elb_backend_5xx_timeframe}): (
default(
min:aws.elb.httpcode_backend_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(min:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
${var.elb_backend_5xx_aggregator}:aws.elb.httpcode_backend_5xx{${data.template_file.filter.rendered}} by {region,loadbalancername} /
(${var.elb_backend_5xx_aggregator}:aws.elb.request_count{${data.template_file.filter.rendered}} by {region,loadbalancername} + ${var.artificial_requests_count}),
0) * 100
) > ${var.elb_backend_5xx_threshold_critical}
EOF
@ -178,8 +178,8 @@ resource "datadog_monitor" "ELB_backend_latency" {
message = "${coalesce(var.elb_backend_latency_message, var.message)}"
query = <<EOF
min(${var.elb_backend_latency_warning}): (
min:aws.elb.latency{${data.template_file.filter.rendered}} by {region,loadbalancername}
${var.elb_backend_latency_aggregator}(${var.elb_backend_latency_warning}): (
${var.elb_backend_latency_aggregator}:aws.elb.latency{${data.template_file.filter.rendered}} by {region,loadbalancername}
) > ${var.elb_backend_latency_critical}
EOF

2
cloud/aws/kinesis-firehose/README.md
View File

@ -22,12 +22,14 @@ Creates DataDog monitors with the following checks :
Inputs
------
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| environment | 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 |
| incoming_records_aggregator | Monitor aggregator for Kinesis Firehorse incoming records [available values: min, max, sum or avg] | string | `sum` | no |
| incoming_records_message | Custom message for Kinesis Firehorse incoming records monitor | string | `` | no |
| incoming_records_silenced | Groups to mute for Kinesis Firehorse incoming records monitor | map | `<map>` | no |
| incoming_records_timeframe | Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |

6
cloud/aws/kinesis-firehose/inputs.tf
View File

@ -38,6 +38,12 @@ variable "incoming_records_message" {
default = ""
}
variable "incoming_records_aggregator" {
description = "Monitor aggregator for Kinesis Firehorse incoming records [available values: min, max, sum or avg]"
type = "string"
default = "sum"
}
variable "incoming_records_timeframe" {
description = "Monitor timeframe for incoming records metrics evaluation [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_15m"

4
cloud/aws/kinesis-firehose/monitors-kinesis-firehose.tf
View File

@ -14,8 +14,8 @@ resource "datadog_monitor" "firehose_incoming_records" {
type = "metric alert"
query = <<EOF
sum(${var.incoming_records_timeframe}): (
avg:aws.firehose.incoming_records{${data.template_file.filter.rendered}} by {region,deliverystreamname}
${var.incoming_records_aggregator}(${var.incoming_records_timeframe}): (
${var.incoming_records_aggregator}:aws.firehose.incoming_records{${data.template_file.filter.rendered}} by {region,deliverystreamname}
) <= 0
EOF

2
cloud/aws/rds/README.md
View File

@ -25,12 +25,14 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| cpu_aggregator | Monitor aggregator for RDS CPU usage [available values: min, max, sum or avg] | string | `avg` | no |
| cpu_message | Custom message for RDS CPU usage monitor | string | `` | no |
| cpu_silenced | Groups to mute for RDS CPU usage 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 RDS CPU usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| diskspace_aggregator | Monitor aggregator for RDS free diskspace [available values: min, max, sum or avg] | string | `avg` | no |
| diskspace_message | Custom message for RDS free diskspace monitor | string | `` | no |
| diskspace_silenced | Groups to mute for RDS free diskspace monitor | map | `<map>` | no |
| diskspace_threshold_critical | Disk free space in percent (critical threshold) | string | `10` | no |

12
cloud/aws/rds/inputs.tf
View File

@ -38,6 +38,12 @@ variable "cpu_message" {
default = ""
}
variable "cpu_aggregator" {
description = "Monitor aggregator for RDS CPU usage [available values: min, max, sum or avg]"
type = "string"
default = "avg"
}
variable "cpu_timeframe" {
description = "Monitor timeframe for RDS CPU usage [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"
@ -66,6 +72,12 @@ variable "diskspace_message" {
default = ""
}
variable "diskspace_aggregator" {
description = "Monitor aggregator for RDS free diskspace [available values: min, max, sum or avg]"
type = "string"
default = "avg"
}
variable "diskspace_timeframe" {
description = "Monitor timeframe for RDS free diskspace [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"

10
cloud/aws/rds/monitors-rds.tf
View File

@ -14,8 +14,8 @@ resource "datadog_monitor" "rds_cpu_90_15min" {
type = "metric alert"
query = <<EOF
avg(${var.cpu_timeframe}): (
avg:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
${var.cpu_aggregator}(${var.cpu_timeframe}): (
${var.cpu_aggregator}:aws.rds.cpuutilization{${data.template_file.filter.rendered}} by {region,name}
) > ${var.cpu_threshold_critical}
EOF
@ -46,9 +46,9 @@ resource "datadog_monitor" "rds_free_space_low" {
type = "metric alert"
query = <<EOF
avg(${var.diskspace_timeframe}): (
avg:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
avg:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
${var.diskspace_aggregator}(${var.diskspace_timeframe}): (
${var.diskspace_aggregator}:aws.rds.free_storage_space{${data.template_file.filter.rendered}} by {region,name} /
${var.diskspace_aggregator}:aws.rds.total_storage_space{${data.template_file.filter.rendered}} by {region,name} * 100
) < ${var.diskspace_threshold_critical}
EOF

1
cloud/aws/vpn/README.md
View File

@ -29,6 +29,7 @@ Inputs
| 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 |
| vpn_status_aggregator | Monitor aggregator for VPN status [available values: min, max, sum or avg] | string | `avg` | no |
| vpn_status_message | Custom message for VPN status monitor | string | `` | no |
| vpn_status_silenced | Groups to mute for VPN status monitor | map | `<map>` | no |
| vpn_status_timeframe | Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |

6
cloud/aws/vpn/inputs.tf
View File

@ -36,6 +36,12 @@ variable "vpn_status_message" {
default = ""
}
variable "vpn_status_aggregator" {
description = "Monitor aggregator for VPN status [available values: min, max, sum or avg]"
type = "string"
default = "avg"
}
variable "vpn_status_timeframe" {
description = "Monitor timeframe for VPN status [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
type = "string"

4
cloud/aws/vpn/monitors-vpn.tf
View File

@ -11,8 +11,8 @@ resource "datadog_monitor" "VPN_status" {
message = "${coalesce(var.vpn_status_message, var.message)}"
query = <<EOF
avg(${var.vpn_status_timeframe}): (
avg:aws.vpn.tunnel_state{${data.template_file.filter.rendered}} by {region,name}
${var.vpn_status_aggregator}(${var.vpn_status_timeframe}): (
${var.vpn_status_aggregator}:aws.vpn.tunnel_state{${data.template_file.filter.rendered}} by {region,name}
) < 1
EOF