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

MON-81 remove stack

Browse Source
This commit is contained in:
vincent EL KHATIB 2017-11-02 15:54:51 +01:00
parent 64be248b9e
commit 63ba5e54d1
4 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
monitors-linux-basics.tf
View File

@ -3,7 +3,7 @@ resource "datadog_monitor" "cpu_80_15min" {
message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} > ${var.cpu_15_critical}"
query = "min(last_15m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} > ${var.cpu_15_critical}"
type = "query alert"
thresholds {
@ -28,7 +28,7 @@ resource "datadog_monitor" "cpu_95_5min" {
name = "[${var.env}] CPU High > ${var.cpu_5_critical} for 5 min on {{host.name}}"
message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,stack} > ${var.cpu_5_critical}"
query = "min(last_5m):avg:system.cpu.system{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} + avg:system.cpu.user{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region} > ${var.cpu_5_critical}"
type = "query alert"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
@ -54,7 +54,7 @@ resource "datadog_monitor" "datadog_free_disk_space_5" {
name = "[${var.env}] Free disk space < 5% on {{host.name}}"
message = "{{#is_alert}}\n${var.hno_escalation_group}\n{{/is_alert}}\n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}"
query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 5"
query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 5"
type = "query alert"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
@ -80,7 +80,7 @@ resource "datadog_monitor" "datadog_free_disk_space_10" {
name = "[${var.env}] Free disk space < 10% on {{host.name}}"
message = "{{#is_alert}}\n${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${var.ho_escalation_group}\n{{/is_warning_recovery}}"
query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 10"
query = "sum(last_5m):avg:system.disk.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 10"
type = "query alert"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
@ -107,7 +107,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_5" {
name = "[${var.env}] Free disk inodes < 5% on {{host.name}}"
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group} \n{{/is_recovery}}"
query = "sum(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device,stack} * 100 < 5"
query = "sum(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 5"
type = "query alert"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
@ -133,7 +133,7 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
name = "[${var.env}] Free disk inodes < 10% on {{host.name}}"
message = "{{#is_alert}}\n${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${var.ho_escalation_group}\n{{/is_warning_recovery}}"
query = "max(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region,stack} * 100 < 10"
query = "max(last_5m):avg:system.fs.inodes.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region} / avg:system.fs.inodes.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,device,region} * 100 < 10"
type = "query alert"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
@ -182,7 +182,7 @@ resource "datadog_monitor" "datadog_free_memory" {
name = "[${var.env}] Free memory < 5% on {{host.name}}"
message = "Debugging alert - no escalation"
query = "sum(last_1m):avg:system.mem.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region,stack} / avg:system.mem.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region,stack} * 100 < 5"
query = "sum(last_1m):avg:system.mem.free{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region} / avg:system.mem.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region} * 100 < 5"
type = "query alert"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"

4
monitors-rds_mysql-basics.tf
View File

@ -8,7 +8,7 @@ resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} > 90"
query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} > 90"
type = "query alert"
thresholds {
@ -35,7 +35,7 @@ resource "datadog_monitor" "mysql_rds_free_space_low" {
message = "{{#is_alert}}\n${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${var.ho_escalation_group}\n{{/is_warning_recovery}}"
type = "query alert"
query = "avg(last_15m):avg:aws.rds.free_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name,stack} * 100 < 10"
query = "avg(last_15m):avg:aws.rds.free_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} * 100 < 10"
count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"

10
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}}"
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 {loadbalancername,region,stack} == 0"
query = "avg(last_5m):avg:aws.elb.healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} == 0"
type = "query alert"
notify_no_data = "${var.elb_config["notify_no_data"]}"
@ -25,7 +25,7 @@ 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}}"
count = "${var.dd_aws_elb == "enabled" ? 1 : 0 }"
query = "avg(last_5m):avg:aws.elb.un_healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} > 0"
query = "avg(last_5m):avg:aws.elb.un_healthy_host_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > 0"
type = "query alert"
notify_no_data = "${var.elb_config["notify_no_data"]}"
@ -47,7 +47,7 @@ resource "datadog_monitor" "ELB_too_much_5xx_backend" {
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,stack} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} * 100 > ${var.elb_5xx_threshold["critical"]}"
query = "avg(last_5m): avg:aws.elb.httpcode_backend_5xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_5xx_threshold["critical"]}"
type = "query alert"
thresholds {
@ -74,7 +74,7 @@ resource "datadog_monitor" "ELB_too_much_4xx_backend" {
message = "{{#is_alert}}\n${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:${var.env}} by {loadbalancername,region,stack} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region,stack} * 100 > ${var.elb_4xx_threshold["critical"]}"
query = "avg(last_5m): avg:aws.elb.httpcode_backend_4xx{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} / avg:aws.elb.request_count{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} * 100 > ${var.elb_4xx_threshold["critical"]}"
type = "query alert"
thresholds {
@ -101,7 +101,7 @@ resource "datadog_monitor" "ELB_backend_latency" {
message = "{{#is_alert}}\n${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,stack} > ${var.elb_backend_latency["critical"]}"
query = "avg(last_5m):avg:aws.elb.latency{dd_monitoring:enabled,dd_aws_elb:enabled,env:${var.env}} by {loadbalancername,region} > ${var.elb_backend_latency["critical"]}"
type = "query alert"
thresholds {

2
monitors_fpm.tf
View File

@ -4,7 +4,7 @@ resource "datadog_monitor" "php-fpm_process_idle" {
type = "query alert"
query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,stack} / ( avg:php_fpm.processes.idle{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} + avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region,stack} ) > 0.9"
query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} / ( avg:php_fpm.processes.idle{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} + avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} ) > 0.9"
count = "${var.dd_php_fpm == "enabled" ? 1 : 0 }"
thresholds {