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

MON-43 add ELB monitors

Browse Source
This commit is contained in:
vincent EL KHATIB 2017-09-12 17:16:15 +02:00
parent e6530c5943
commit 164b8b5f5b
3 changed files with 97 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
inputs.tf
View File

@ -60,8 +60,21 @@ variable "elb_config" {
delay = 900 delay = 900
} }
} }
variable "elb_5xx_threshold" {
default = {
warning = 5
critical = 10
}
}
variable "elb_4xx_threshold" {
default = {
warning = 5
critical = 10
}
}
variable "elb_backend_latency" {
default = {
warning = 1000
critical = 5000
}
}

4
monitors-rds_mysql-basics.tf
View File

@ -8,7 +8,7 @@ resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }" count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env},!dd_custom_rds-mysql:enabled} by {identifier,region} > 90" query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {name,region} > 90"
type = "query alert" type = "query alert"
thresholds { thresholds {
@ -33,7 +33,7 @@ resource "datadog_monitor" "mysql_rds_free_space_low" {
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}" message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
type = "query alert" type = "query alert"
query = "avg(last_15m): avg:aws.rds.free_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env},!dd_custom_rds-mysql:enabled} by {identifier,region} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_rds-mysql_basics:enabled,env:${var.env},!dd_custom_rds-mysql:enabled} by {identifier,region} * 100 < 10" query = "avg(last_15m): avg:aws.rds.free_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {name,region} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_rds-mysql_basics:enabled,env:${var.env},!dd_custom_rds-mysql:enabled} by {identifier,region} * 100 < 10"
count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }" count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"

79
monitors_elb.tf
View File

@ -3,7 +3,7 @@ resource "datadog_monitor" "ELB_no_healthy_instances" {
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}" message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }" count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {identifier,region} == 0" query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} == 0"
type = "query alert" type = "query alert"
notify_no_data = "${var.elb_config["notify_no_data"]}" notify_no_data = "${var.elb_config["notify_no_data"]}"
@ -23,7 +23,7 @@ resource "datadog_monitor" "ELB_unhealthy_instances" {
message = "{{#is_alert}}\n${var.ho_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.ho_escalation_group}\n{{/is_recovery}}" message = "{{#is_alert}}\n${var.ho_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.ho_escalation_group}\n{{/is_recovery}}"
count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }" count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {identifier,region} == 0" query = "avg(last_5m):avg:aws.elb.un_healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > 0"
type = "query alert" type = "query alert"
notify_no_data = "${var.elb_config["notify_no_data"]}" notify_no_data = "${var.elb_config["notify_no_data"]}"
@ -38,4 +38,79 @@ resource "datadog_monitor" "ELB_unhealthy_instances" {
no_data_timeframe = 20 no_data_timeframe = 20
} }
resource "datadog_monitor" "ELB_too_much_5xx_backend" {
name = "[${var.env}] ELB too much 5xx backend err on {{host.identifier}}"
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
query = "avg(last_5m): avg:aws.elb.httpcode_backend_5xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_5xx_threshold["critical"]}"
type = "query alert"
thresholds {
warning = "${var.elb_5xx_threshold["warning"]}"
critical = "${var.elb_5xx_threshold["critical"]}"
}
notify_no_data = "${var.elb_config["notify_no_data"]}"
evaluation_delay = "${var.elb_config["delay"]}"
renotify_interval = 60
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.elb_config["delay"]}"
no_data_timeframe = 20
}
resource "datadog_monitor" "ELB_too_much_4xx_backend" {
name = "[${var.env}] ELB too much 4xx backend err on {{host.identifier}}"
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
query = "avg(last_5m): avg:aws.elb.httpcode_backend_4xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_4xx_threshold["critical"]}"
type = "query alert"
thresholds {
warning = "${var.elb_4xx_threshold["warning"]}"
critical = "${var.elb_4xx_threshold["critical"]}"
}
notify_no_data = "${var.elb_config["notify_no_data"]}"
evaluation_delay = "${var.elb_config["delay"]}"
renotify_interval = 60
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.elb_config["delay"]}"
no_data_timeframe = 20
}
resource "datadog_monitor" "ELB_backend_latency" {
name = "[${var.env}] ELB latency to high on {{host.identifier}}"
message = "{{#is_alert}}\n${var.ho_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.ho_escalation_group}\n{{/is_recovery}}"
count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
query = "avg(last_5m):avg:aws.elb.latency{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > ${var.elb_backend_latency["critical"]}"
type = "query alert"
thresholds {
warning = "${var.elb_backend_latency["warning"]}"
critical = "${var.elb_backend_latency["critical"]}"
}
notify_no_data = "${var.elb_config["notify_no_data"]}"
evaluation_delay = "${var.elb_config["delay"]}"
renotify_interval = 60
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = true
new_host_delay = "${var.elb_config["delay"]}"
no_data_timeframe = 20
}