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

Merged in MON-66_fmt (pull request #6)

Browse Source 
MON-66: Terraform HCL re-format (fmt)

Approved-by: Jérôme Respaut <shr3ps@gmail.com>
Approved-by: Laurent Piroelle <laurent.piroelle@fr.clara.net>
Approved-by: Quentin Manfroi <quentin.manfroi@yahoo.fr>
This commit is contained in:
Jérôme Respaut 2017-11-06 09:40:17 +00:00 committed by Quentin Manfroi
commit 3a1ba3323e
13 changed files with 96 additions and 103 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cloud/aws/elb/monitors-elb.tf
View File

@ -122,5 +122,3 @@ resource "datadog_monitor" "ELB_backend_latency" {
tags = ["*"]
}

11
cloud/aws/rds-mysql/monitors-rds_mysql-basics.tf
View File

@ -1,13 +1,9 @@
resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
name = "[${var.env}] rds Cpu high > 90% for 15 min on {{host.identifier}}"
message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group}\n{{/is_recovery}}\n{{#is_warning}}\n${var.ho_escalation_group} \n{{/is_warning}} \n{{#is_warning_recovery}}\n${var.ho_escalation_group}\n{{/is_warning_recovery}}"
count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
query = "avg(last_15m):avg:aws.rds.cpuutilization{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} > 90"
type = "query alert"
@ -33,12 +29,11 @@ resource "datadog_monitor" "rds-mysql_cpu_80_15min" {
resource "datadog_monitor" "mysql_rds_free_space_low" {
name = "[${var.env}] rds free space low < 10 % 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}}\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:${var.env}} by {region,name} / avg:aws.rds.total_storage_space{dd_monitoring:enabled,dd_aws_rds:enabled,env:${var.env}} by {region,name} * 100 < 10"
count = "${var.dd_aws_rds == "enabled" ? 1 : 0 }"
thresholds {
warning = "${var.rds_mem_threshold["warning"]}"
critical = "${var.rds_mem_threshold["critical"]}"
@ -56,6 +51,4 @@ resource "datadog_monitor" "mysql_rds_free_space_low" {
require_full_window = true
new_host_delay = "${var.rds_config["delay"]}"
no_data_timeframe = 20
}
}

5
incubator/monitors-cassandra.tf
View File

@ -1,8 +1,8 @@
resource "datadog_monitor" "datadog_cassandra_down" {
name = "Cassandra service is down"
name = "Cassandra service is down"
message = "{{#is_alert}}\n${var.alert_HNO} \n{{/is_alert}} \n{{#is_recovery}}\n${var.alert_HNO}\n{{/is_recovery}}"
query = "\"cassandra.can_connect\".over(\"cassandra-node\").by(\"host\",\"instance\").last(2).count_by_status()"
type = "service check"
type = "service check"
notify_no_data = false
renotify_interval = 60
@ -36,3 +36,4 @@ renotify_interval = 0
no_data_timeframe = 20
}*/

23
incubator/monitors-gcp-lb.tf
View File

@ -1,8 +1,8 @@
resource "datadog_monitor" "datadog_gcp_lb_request_count" {
name = "GCP LoadBalancer request count changed too fast"
name = "GCP LoadBalancer request count changed too fast"
message = ""
query = "change(sum(last_5m),last_30m):avg:gcp.loadbalancing.http.request_count{*} by {backend_name}.as_count() >= 300"
type = "query alert"
type = "query alert"
notify_no_data = false
renotify_interval = 60
@ -15,15 +15,13 @@ resource "datadog_monitor" "datadog_gcp_lb_request_count" {
notify_no_data = false
renotify_interval = 0
no_data_timeframe = 20
}
resource "datadog_monitor" "datadog_gcp_lb_500" {
name = "GCP LoadBalancer 500 ratio > 5%"
name = "GCP LoadBalancer 500 ratio > 5%"
message = ""
query = "sum(last_10m):avg:gcp.loadbalancing.http.request_count{response_code_class:500} by {backend_name}.as_count() / avg:gcp.loadbalancing.http.request_count{*} by {backend_name}.as_count() > 0.2"
type = "query alert"
type = "query alert"
notify_no_data = false
renotify_interval = 60
@ -36,15 +34,13 @@ resource "datadog_monitor" "datadog_gcp_lb_500" {
notify_no_data = false
renotify_interval = 0
no_data_timeframe = 20
}
resource "datadog_monitor" "datadog_gcp_lb_backend_latency" {
name = "GCP LB backend latency > 2s"
name = "GCP LB backend latency > 2s"
message = ""
query = "min(last_5m):avg:gcp.loadbalancing.http.backend_latencies.avg{*} by {backend_name} > 2000"
type = "metric alert"
type = "metric alert"
notify_no_data = false
renotify_interval = 60
@ -57,15 +53,13 @@ resource "datadog_monitor" "datadog_gcp_lb_backend_latency" {
notify_no_data = false
renotify_interval = 0
no_data_timeframe = 20
}
resource "datadog_monitor" "datadog_gcp_lb_latency" {
name = "GCP LB latency > 5s"
name = "GCP LB latency > 5s"
message = ""
query = "avg(last_5m):avg:gcp.loadbalancing.http.total_latencies.avg{*} > 5000"
type = "query alert"
type = "query alert"
thresholds {
warning = 3000
@ -83,5 +77,4 @@ resource "datadog_monitor" "datadog_gcp_lb_latency" {
notify_no_data = false
renotify_interval = 0
no_data_timeframe = 20
}

71
inputs.tf
View File

@ -4,20 +4,23 @@ variable "ho_escalation_group" {}
variable env {}
variable region {}
##linux
variable "dd_linux_basics" {
default = "disabled"
}
variable "linux_basics_config" {
type = "map"
default = {
notify_no_data = false
delay = 900
delay = 900
}
}
variable "dd_custom_cpu" {
type = "map"
default = {
status = "disabled"
}
@ -37,55 +40,64 @@ variable "cpu_15_critical" {
variable "dd_aws_rds" {
default = "disabled"
}
variable "rds_config" {
type = "map"
default = {
notify_no_data = false
delay = 900
}
}
variable "rds_cpu_threshold" {
type = "map"
default = {
warning = 80
critical = 90
}
}
variable "rds_mem_threshold" {
default = {
warning = 20
critical = 10
delay = 900
}
}
variable "rds_cpu_threshold" {
type = "map"
default = {
warning = 80
critical = 90
}
}
variable "rds_mem_threshold" {
default = {
warning = 20
critical = 10
}
}
## ELB
variable "dd_aws_elb" {
default = "disable"
}
variable "elb_config" {
type = "map"
default = {
notify_no_data = false
delay = 900
delay = 900
}
}
variable "elb_5xx_threshold" {
default = {
warning = 5
critical = 10
warning = 5
critical = 10
}
}
variable "elb_4xx_threshold" {
default = {
warning = 5
critical = 10
warning = 5
critical = 10
}
}
variable "elb_backend_latency" {
default = {
warning = 1000
critical = 5000
warning = 1000
critical = 5000
}
}
@ -93,6 +105,7 @@ variable "elb_backend_latency" {
variable "dd_nginx" {
default = "disabled"
}
variable "dd_php_fpm" {
default = "disabled"
}
@ -100,17 +113,21 @@ variable "dd_php_fpm" {
variable "dd_apache" {
default = "disabled"
}
variable "apache_nginx_fpm_config" {
type = "map"
default = {
notify_no_data = false
delay = 900
delay = 900
}
}
variable "php_fpm_busy_threshold" {
type = "map"
default = {
warning = 0.8
critical = 0.9
warning = 0.8
critical = 0.9
}
}
}

5
middleware/apache/monitors-apache.tf
View File

@ -2,14 +2,13 @@ resource "datadog_monitor" "Apache_process" {
name = "[${var.env}] Nginx process is down on {{host.name}}"
message = "{{#is_alert}}\n${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${var.ho_escalation_group}\n{{/is_warning_recovery}}"
type = "service check"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_apache:enabled\",\"process:apache\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
count = "${var.dd_apache == "enabled" ? 1 : 0 }"
thresholds = {
ok = 1
warning = 2
ok = 1
warning = 2
critical = 4
}

5
middleware/nginx/monitors-nginx.tf
View File

@ -2,14 +2,13 @@ resource "datadog_monitor" "Nginx_process" {
name = "[${var.env}] Nginx process is down on {{host.name}}"
message = "{{#is_alert}}\n${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${var.ho_escalation_group}\n{{/is_warning_recovery}}"
type = "service check"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_nginx:enabled\",\"process:nginx\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
count = "${var.dd_nginx == "enabled" ? 1 : 0 }"
thresholds = {
ok = 1
warning = 2
ok = 1
warning = 2
critical = 4
}

7
middleware/php-fpm/monitors-fpm.tf
View File

@ -2,7 +2,6 @@ resource "datadog_monitor" "php-fpm_process_idle" {
name = "[${var.env}] php_fpm busy worker > 90% on {{host.name}}"
message = "{{#is_alert}}\n${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${var.ho_escalation_group}\n{{/is_warning_recovery}}"
type = "query alert"
query = "avg(last_10m):avg:php_fpm.processes.active{dd_monitoring:enabled,dd_php_fpm:enabled,env:${var.env}} by {host,region} / ( 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 = "${var.dd_php_fpm == "enabled" ? 1 : 0 }"
@ -27,19 +26,17 @@ resource "datadog_monitor" "php-fpm_process_idle" {
tags = ["*"]
}
resource "datadog_monitor" "FPM_process" {
name = "[${var.env}] FPM process is down 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}}"
type = "service check"
query = "\"process.up\".over(\"dd_monitoring:enabled\",\"dd_php_fpm:enabled\",\"process:php_fpm\",\"env:${var.env}\").by(\"host\",\"process\", \"app\").last(4).count_by_status()"
count = "${var.dd_nginx == "enabled" ? 1 : 0 }"
thresholds = {
ok = 1
warning = 2
ok = 1
warning = 2
critical = 4
}

1
system/generic/monitors-custom-cpu.tf
View File

@ -22,4 +22,3 @@ resource "datadog_monitor" "cpu_custom" {
require_full_window = true
no_data_timeframe = 20
}

53
system/linux/monitors-linux-basics.tf
View File

@ -30,7 +30,7 @@ resource "datadog_monitor" "cpu_95_5min" {
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}"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
thresholds {
critical = "${var.cpu_5_critical}"
@ -51,12 +51,12 @@ resource "datadog_monitor" "cpu_95_5min" {
}
resource "datadog_monitor" "datadog_free_disk_space_5" {
name = "[${var.env}] Free disk space < 5% on {{host.name}}"
name = "[${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:${var.env},!dd_custom_cpu:enabled} by {host,region,device} / avg:system.disk.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled} by {host,region,device} * 100 < 5"
type = "query alert"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
thresholds {
critical = 5
@ -164,22 +164,20 @@ resource "datadog_monitor" "datadog_free_disk_space_inodes_10" {
# type = "query alert"
# count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
# notify_no_data = "${var.linux_basics_config["notify_no_data"]}"
# evaluation_delay = "${var.linux_basics_config["delay"]}"
# new_host_delay = "${var.linux_basics_config["delay"]}"
# renotify_interval = 60
# notify_audit = false
# timeout_h = 0
# include_tags = true
# locked = false
# require_full_window = true
# no_data_timeframe = 20
# notify_no_data = "${var.linux_basics_config["notify_no_data"]}"
# evaluation_delay = "${var.linux_basics_config["delay"]}"
# new_host_delay = "${var.linux_basics_config["delay"]}"
# renotify_interval = 60
# notify_audit = false
# timeout_h = 0
# include_tags = true
# locked = false
# require_full_window = true
# no_data_timeframe = 20
# }
resource "datadog_monitor" "datadog_free_memory" {
name = "[${var.env}] Free memory < 5% on {{host.name}}"
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} / avg:system.mem.total{dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_memory:enabled} by {host,region} * 100 < 5"
@ -208,18 +206,21 @@ resource "datadog_monitor" "datadog_free_memory" {
# name = "Host unreachable"
# message = "{{#is_alert}}\n${var.hno_escalation_group} \n{{/is_alert}} \n{{#is_recovery}}\n${var.hno_escalation_group} \n{{/is_recovery}}"
# query = "datadog.agent.up.over(dd_monitoring:enabled,dd_linux_basics:enabled,env:${var.env},!dd_custom_cpu:enabled).last(1).count_by_status()"
# type = "service check"
# count = "${var.dd_linux_basics == "enabled" ? 1 : 0}"
# notify_no_data = "${var.linux_basics_config["notify_no_data"]}"
# evaluation_delay = "${var.linux_basics_config["delay"]}"
# new_host_delay = "${var.linux_basics_config["delay"]}"
# renotify_interval = 60
# notify_audit = false
# timeout_h = 0
# include_tags = true
# locked = false
# require_full_window = true
# no_data_timeframe = 20
# notify_no_data = "${var.linux_basics_config["notify_no_data"]}"
# evaluation_delay = "${var.linux_basics_config["delay"]}"
# new_host_delay = "${var.linux_basics_config["delay"]}"
# renotify_interval = 60
# notify_audit = false
# timeout_h = 0
# include_tags = true
# locked = false
# require_full_window = true
# no_data_timeframe = 20
# }

4
testing/dummy/dummy.tf
View File

@ -1,3 +1 @@
resource "null_resource" "test-migration" {}
resource "null_resource" "test-migration" {}

2
testing/inputs.tf
View File

@ -5,6 +5,7 @@ variable region {}
variable "critical_escalation_group" {
default = "@pagerduty_HODummy"
}
variable "warning_escalation_group" {
default = "@pagerduty_HNODummy"
}
@ -19,4 +20,3 @@ variable "dd_linux_basics" {
variable "dd_aws_rds" {
default = "enabled"
}

10
testing/modules.tf
View File

@ -1,14 +1,12 @@
module "datadog-monitors" {
source = "git::ssh://git@bitbucket.org/morea/terraform.feature.datadog.git"
env = "${var.environment}"
region = "${var.region}"
env = "${var.environment}"
region = "${var.region}"
critical_escalation_group = "${var.critical_escalation_group}"
warning_escalation_group = "${var.warning_escalation_group}"
dd_aws_rds = "${var.dd_aws_rds}"
dd_linux_basics = "${var.dd_linux_basics}"
dd_aws_rds = "${var.dd_aws_rds}"
dd_linux_basics = "${var.dd_linux_basics}"
}