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

MON-308 add warning for part of unhealthy instances

Browse Source
This commit is contained in:
Quentin Manfroi 2018-09-26 19:04:53 +02:00
parent d60756a87d
commit 57913a7385
2 changed files with 16 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
cloud/aws/alb/monitors-alb.tf
View File

@ -1,13 +1,15 @@
resource "datadog_monitor" "ALB_no_healthy_instances" {
count = "${var.alb_no_healthy_instances_enabled ? 1 : 0}"
name = "[${var.environment}] ALB no healthy instances"
name = "[${var.environment}] ALB {{#is_alert}}no healthy instances{{/is_alert}}{{#is_warning}}{{value}}% of healthy instances{{/is_warning}}"
type = "metric alert"
message = "${coalesce(var.alb_no_healthy_instances_message, var.message)}"
query = <<EOF
${var.alb_no_healthy_instances_time_aggregator}(${var.alb_no_healthy_instances_timeframe}): (
sum:aws.applicationelb.healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancer}
) < 1
sum:aws.applicationelb.healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancer} / (
sum:aws.applicationelb.healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancer} +
sum:aws.applicationelb.un_healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancer} )
) * 100 < 1
EOF
evaluation_delay = "${var.evaluation_delay}"
@ -15,6 +17,7 @@ resource "datadog_monitor" "ALB_no_healthy_instances" {
thresholds {
critical = 1
warning = 100
}
notify_no_data = true

13
cloud/aws/elb/monitors-elb.tf
View File

@ -1,16 +1,23 @@
resource "datadog_monitor" "ELB_no_healthy_instances" {
count = "${var.elb_no_healthy_instance_enabled ? 1 : 0}"
name = "[${var.environment}] ELB no healthy instances"
name = "[${var.environment}] ELB {{#is_alert}}no healthy instances{{/is_alert}}{{#is_warning}}{{value}}% of healthy instances{{/is_warning}}"
message = "${coalesce(var.elb_no_healthy_instance_message, var.message)}"
query = <<EOF
${var.elb_no_healthy_instance_time_aggregator}(${var.elb_no_healthy_instance_timeframe}): (
sum:aws.elb.healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancername}
) < 1
sum:aws.elb.healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancername} / (
sum:aws.elb.healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancername} +
sum:aws.elb.un_healthy_host_count.maximum${module.filter-tags.query_alert} by {region,loadbalancername} )
) * 100 < 1
EOF
type = "metric alert"
thresholds {
critical = 1
warning = 100
}
notify_no_data = true
evaluation_delay = "${var.evaluation_delay}"
renotify_interval = 0