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

MON-32 - monitors updated with latest fix

Browse Source
This commit is contained in:
Alexandre Gaillet 2018-05-31 12:03:44 +02:00 committed by Quentin Manfroi
parent 9c4f5b4cfd
commit 6c7b90c4db
9 changed files with 92 additions and 147 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
cloud/aws/elasticache/common/README.md
View File

@ -1,5 +1,5 @@
AWS ElasticCache Service DataDog monitors
=========================================
AWS ElastiCache Service DataDog monitors
========================================
How to use this module
----------------------
@ -23,6 +23,7 @@ Purpose
Creates DataDog monitors with the following checks:
* Eviction
* Swap
* Max connections
* No connection
@ -32,7 +33,7 @@ Inputs
| Name | Description | Type | Default | Required |
|------|-------------|:----:|:-----:|:-----:|
| delay | Delay in seconds for the metric evaluation | string | `900` | no |
| environment | Architecture Environment | string | - | yes |
| environment | Infrastructure Environment | string | - | yes |
| eviction_message | Custom message for Elasticache eviction monitor | string | `` | no |
| eviction_silenced | Groups to mute for Elasticache eviction monitor | map | `<map>` | no |
| eviction_time_aggregator | Monitor aggregator for Elasticache eviction [available values: min, max or avg] | string | `min` | no |
@ -40,7 +41,7 @@ Inputs
| filter_tags | Tags used for filtering | string | - | yes |
| max_connection_message | Custom message for Elasticache max connection monitor | string | `` | no |
| max_connection_silenced | Groups to mute for Elasticache max connection monitor | map | `<map>` | no |
| max_connection_time_aggregator | Monitor aggregator for Elasticache max connection [available values: min, max or avg] | string | `min` | no |
| max_connection_time_aggregator | Monitor aggregator for Elasticache max connection [available values: min, max or avg] | string | `max` | no |
| max_connection_timeframe | Monitor timeframe for Elasticache max connection [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 an alert is triggered | string | - | yes |
| no_connection_message | Custom message for Elasticache no connection monitor | string | `` | no |
@ -48,6 +49,12 @@ Inputs
| no_connection_time_aggregator | Monitor aggregator for Elasticache no connection [available values: min, max or avg] | string | `min` | no |
| no_connection_timeframe | Monitor timeframe for Elasticache no connection [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| resource | Type of Elasticache used | string | - | yes |
| swap_message | Custom message for Elasticache memcached swap monitor | string | `` | no |
| swap_silenced | Groups to mute for Elasticache memcached swap monitor | map | `<map>` | no |
| swap_threshold_critical | Elasticache memcached swap critical threshold in percentage | string | `50` | no |
| swap_threshold_warning | Elasticache memcached swap warning threshold in percentage | string | `0` | no |
| swap_time_aggregator | Monitor aggregator for Elasticache memcached swap [available values: min, max or avg] | string | `min` | no |
| swap_timeframe | Monitor timeframe for Elasticache memcached swap [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

35
cloud/aws/elasticache/common/inputs.tf
View File

@ -1,6 +1,6 @@
# Global Terraform
variable "environment" {
description = "Architecture Environment"
description = "Infrastructure Environment"
type = "string"
}
@ -91,3 +91,36 @@ variable "no_connection_timeframe" {
description = "Monitor timeframe for Elasticache no connection [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_5m"
}
variable "swap_silenced" {
description = "Groups to mute for Elasticache memcached swap monitor"
type = "map"
default = {}
}
variable "swap_message" {
description = "Custom message for Elasticache memcached swap monitor"
type = "string"
default = ""
}
variable "swap_time_aggregator" {
description = "Monitor aggregator for Elasticache memcached swap [available values: min, max or avg]"
type = "string"
default = "min"
}
variable "swap_timeframe" {
description = "Monitor timeframe for Elasticache memcached swap [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_5m"
}
variable "swap_threshold_warning" {
description = "Elasticache memcached swap warning threshold in percentage"
default = 0
}
variable "swap_threshold_critical" {
description = "Elasticache memcached swap critical threshold in percentage"
default = 50
}

32
cloud/aws/elasticache/common/monitors-elasticache.tf
View File

@ -78,3 +78,35 @@ resource "datadog_monitor" "elasticache_no_connection" {
tags = ["env:${var.environment}", "engine:${var.resource}", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "elasticache_swap" {
name = "[${var.environment}] Elasticache ${var.resource} swap {{#is_alert}}{{{comparator}}} {{threshold}}MB ({{value}}MB){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}MB ({{value}}MB){{/is_warning}}"
message = "${coalesce(var.swap_message, var.message)}"
type = "metric alert"
query = <<EOF
${var.swap_time_aggregator}(${var.swap_timeframe}): (
avg:aws.elasticache.swap_usage{${var.filter_tags}} by {region,cacheclusterid}
) > ${var.swap_threshold_critical}
EOF
thresholds {
warning = "${var.swap_threshold_warning}"
critical = "${var.swap_threshold_critical}"
}
notify_no_data = false
evaluation_delay = "${var.delay}"
renotify_interval = 0
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = false
new_host_delay = "${var.delay}"
silenced = "${var.swap_silenced}"
tags = ["env:${var.environment}", "engine:${var.resource}", "team:aws", "provider:aws"]
}

13
cloud/aws/elasticache/memcached/README.md
View File

@ -1,5 +1,5 @@
AWS ElasticCache Memcached Service DataDog monitors
===================================================
AWS ElastiCache Memcached Service DataDog monitors
==================================================
How to use this module
----------------------
@ -21,7 +21,6 @@ Creates DataDog monitors with the following checks :
* Get Hit
* CPU High
* Swap
* Free memory
Inputs
@ -37,7 +36,7 @@ Inputs
| cpu_high_timeframe | Monitor timeframe for Elasticache memcached cpu high [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 |
| elasticache_size | Size of the Elasticache instance | string | - | yes |
| environment | Architecture Environment | string | - | yes |
| environment | Infrastructure 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 |
| free_memory_message | Custom message for Elasticache memcached free memory monitor | string | `` | no |
@ -52,12 +51,6 @@ Inputs
| get_hits_threshold_warning | Elasticache memcached get hits warning threshold in percentage | string | `20` | no |
| get_hits_timeframe | Monitor timeframe for Elasticache memcached get hits [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| message | Message sent when an alert is triggered | string | - | yes |
| swap_message | Custom message for Elasticache memcached swap monitor | string | `` | no |
| swap_silenced | Groups to mute for Elasticache memcached swap monitor | map | `<map>` | no |
| swap_threshold_critical | Elasticache memcached swap critical threshold in percentage | string | `50` | no |
| swap_threshold_warning | Elasticache memcached swap warning threshold in percentage | string | `0` | no |
| swap_time_aggregator | Monitor aggregator for Elasticache memcached swap [available values: min, max or avg] | string | `min` | no |
| swap_timeframe | Monitor timeframe for Elasticache memcached swap [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

35
cloud/aws/elasticache/memcached/inputs.tf
View File

@ -1,6 +1,6 @@
# Global Terraform
variable "environment" {
description = "Architecture Environment"
description = "Infrastructure Environment"
type = "string"
}
@ -91,39 +91,6 @@ variable "cpu_high_threshold_critical" {
default = 90
}
variable "swap_silenced" {
description = "Groups to mute for Elasticache memcached swap monitor"
type = "map"
default = {}
}
variable "swap_message" {
description = "Custom message for Elasticache memcached swap monitor"
type = "string"
default = ""
}
variable "swap_time_aggregator" {
description = "Monitor aggregator for Elasticache memcached swap [available values: min, max or avg]"
type = "string"
default = "min"
}
variable "swap_timeframe" {
description = "Monitor timeframe for Elasticache memcached swap [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_5m"
}
variable "swap_threshold_warning" {
description = "Elasticache memcached swap warning threshold in percentage"
default = 0
}
variable "swap_threshold_critical" {
description = "Elasticache memcached swap critical threshold in percentage"
default = 50
}
variable "free_memory_silenced" {
description = "Groups to mute for Elasticache memcached free memory monitor"
type = "map"

36
cloud/aws/elasticache/memcached/monitors-memcached.tf
View File

@ -2,7 +2,7 @@ data "template_file" "filter" {
template = "$${filter}"
vars {
filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_mem:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_elasticache_memcached:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
}
}
@ -81,38 +81,6 @@ resource "datadog_monitor" "memcached_cpu_high" {
tags = ["env:${var.environment}", "engine:memcached", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "memcached_swap" {
name = "[${var.environment}] Elasticache memcached swap {{#is_alert}}{{{comparator}}} {{threshold}}MB ({{value}}MB){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}MB ({{value}}MB){{/is_warning}}"
message = "${coalesce(var.swap_message, var.message)}"
type = "metric alert"
query = <<EOF
${var.swap_time_aggregator}(${var.swap_timeframe}): (
avg:aws.elasticache.swap_usage{${data.template_file.filter.rendered}} by {region,cacheclusterid}
) > ${var.swap_threshold_critical}
EOF
thresholds {
warning = "${var.swap_threshold_warning}"
critical = "${var.swap_threshold_critical}"
}
notify_no_data = false
evaluation_delay = "${var.delay}"
renotify_interval = 0
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = false
new_host_delay = "${var.delay}"
silenced = "${var.swap_silenced}"
tags = ["env:${var.environment}", "engine:memcached", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "memcached_free_memory" {
name = "[${var.environment}] Elasticache memcached free memory {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.free_memory_message, var.message)}"
@ -123,7 +91,7 @@ resource "datadog_monitor" "memcached_free_memory" {
query = <<EOF
${var.free_memory_time_aggregator}(${var.free_memory_timeframe}): (
avg:aws.elasticache.freeable_memory{dd_monitoring:enabled,dd_aws_red:enabled,env:${var.environment},cache_node_type:${element(keys(local.memory), count.index)}} by {region,cacheclusterid,cachenodeid} /
avg:aws.elasticache.freeable_memory{dd_monitoring:enabled,dd_aws_elasticache_memcached:enabled,env:${var.environment},cache_node_type:${element(keys(local.memory), count.index)}} by {region,cacheclusterid,cachenodeid} /
${element(values(local.memory), count.index)}
) * 100 < ${var.free_memory_threshold_critical}
EOF

13
cloud/aws/elasticache/redis/README.md
View File

@ -1,5 +1,5 @@
AWS ElasticCache Redis Service DataDog monitors
===============================================
AWS ElastiCache Redis Service DataDog monitors
==============================================
How to use this module
----------------------
@ -33,7 +33,6 @@ Creates DataDog monitors with the following checks:
* CPU high
* Commands received
* Replication lag
* Swap
* Free memory
Inputs
@ -53,11 +52,11 @@ Inputs
| cpu_high_silenced | Groups to mute for Elasticache redis cpu high monitor | map | `<map>` | no |
| cpu_high_threshold_critical | Elasticache redis cpu high critical threshold in percentage | string | `90` | no |
| cpu_high_threshold_warning | Elasticache redis cpu high warning threshold in percentage | string | `75` | no |
| cpu_high_time_aggregator | Monitor aggregator for Elasticache redis cpu high [available values: min, max or avg] | string | `min` | no |
| cpu_high_time_aggregator | Monitor aggregator for Elasticache redis cpu high [available values: min, max or avg] | string | `avg` | no |
| cpu_high_timeframe | Monitor timeframe for Elasticache redis cpu high [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 |
| elasticache_size | Size of the Elasticache instance | string | - | yes |
| environment | Architecture Environment | string | - | yes |
| environment | Infrastructure 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 |
| free_memory_message | Custom message for Elasticache redis free memory monitor | string | `` | no |
@ -74,10 +73,6 @@ Inputs
| replication_lag_threshold_warning | Elasticache redis replication lag warning threshold in seconds | string | `0` | no |
| replication_lag_time_aggregator | Monitor aggregator for Elasticache redis replication lag [available values: min, max or avg] | string | `min` | no |
| replication_lag_timeframe | Monitor timeframe for Elasticache redis replication lag [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| swap_message | Custom message for Elasticache redis swap monitor | string | `` | no |
| swap_silenced | Groups to mute for Elasticache redis swap monitor | map | `<map>` | no |
| swap_time_aggregator | Monitor aggregator for Elasticache redis swap [available values: min, max or avg] | string | `min` | no |
| swap_timeframe | Monitor timeframe for Elasticache redis swap [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
Related documentation
---------------------

25
cloud/aws/elasticache/redis/inputs.tf
View File

@ -1,6 +1,6 @@
# Global Terraform
variable "environment" {
description = "Architecture Environment"
description = "Infrastructure Environment"
type = "string"
}
@ -96,29 +96,6 @@ variable "cpu_high_threshold_critical" {
default = 90
}
variable "swap_silenced" {
description = "Groups to mute for Elasticache redis swap monitor"
type = "map"
default = {}
}
variable "swap_message" {
description = "Custom message for Elasticache redis swap monitor"
type = "string"
default = ""
}
variable "swap_time_aggregator" {
description = "Monitor aggregator for Elasticache redis swap [available values: min, max or avg]"
type = "string"
default = "min"
}
variable "swap_timeframe" {
description = "Monitor timeframe for Elasticache redis swap [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_5m"
}
variable "replication_lag_silenced" {
description = "Groups to mute for Elasticache redis replication lag monitor"
type = "map"

35
cloud/aws/elasticache/redis/monitors-redis.tf
View File

@ -2,11 +2,11 @@ data "template_file" "filter" {
template = "$${filter}"
vars {
filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_red:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
filter = "${var.filter_tags_use_defaults == "true" ? format("dd_monitoring:enabled,dd_aws_elasticache_redis:enabled,env:%s", var.environment) : "${var.filter_tags_custom}"}"
}
}
module "datadog-monitors-aws-elasticcache-common" {
module "datadog-monitors-aws-elasticache-common" {
source = "../common"
message = "${var.message}"
@ -59,7 +59,7 @@ resource "datadog_monitor" "redis_cpu_high" {
query = <<EOF
${var.cpu_high_time_aggregator}(${var.cpu_high_timeframe}): (
avg:aws.elasticache.cpuutilization{dd_monitoring:enabled,dd_aws_red:enabled,env:${var.environment},cache_node_type:${element(keys(local.core), count.index)}} by {region,cacheclusterid,cachenodeid}
avg:aws.elasticache.cpuutilization{dd_monitoring:enabled,dd_aws_elasticache_redis:enabled,env:${var.environment},cache_node_type:${element(keys(local.core), count.index)}} by {region,cacheclusterid,cachenodeid}
) > ${var.cpu_high_threshold_critical / element(values(local.core), count.index)}
EOF
@ -78,33 +78,6 @@ resource "datadog_monitor" "redis_cpu_high" {
tags = ["env:${var.environment}", "engine:redis", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "redis_swap" {
name = "[${var.environment}] Elasticache redis is starting to swap ({{value}}MB)"
message = "${coalesce(var.swap_message, var.message)}"
type = "metric alert"
query = <<EOF
${var.swap_time_aggregator}(${var.swap_timeframe}): (
avg:aws.elasticache.swap_usage{${data.template_file.filter.rendered}} by {region,cacheclusterid}
) > 0
EOF
notify_no_data = false
evaluation_delay = "${var.delay}"
renotify_interval = 0
notify_audit = false
timeout_h = 0
include_tags = true
locked = false
require_full_window = false
new_host_delay = "${var.delay}"
silenced = "${var.swap_silenced}"
tags = ["env:${var.environment}", "engine:redis", "team:aws", "provider:aws"]
}
resource "datadog_monitor" "redis_replication_lag" {
name = "[${var.environment}] Elasticache redis replication lag {{#is_alert}}{{{comparator}}} {{threshold}}s ({{value}}s){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}s ({{value}}s){{/is_warning}}"
message = "${coalesce(var.replication_lag_message, var.message)}"
@ -175,7 +148,7 @@ resource "datadog_monitor" "redis_free_memory" {
query = <<EOF
${var.free_memory_time_aggregator}(${var.free_memory_timeframe}): (
avg:aws.elasticache.freeable_memory{dd_monitoring:enabled,dd_aws_red:enabled,env:${var.environment},cache_node_type:${element(keys(local.memory), count.index)}} by {region,cacheclusterid,cachenodeid} /
avg:aws.elasticache.freeable_memory{dd_monitoring:enabled,dd_aws_elasticache_redis:enabled,env:${var.environment},cache_node_type:${element(keys(local.memory), count.index)}} by {region,cacheclusterid,cachenodeid} /
( ${element(values(local.memory), count.index)} / ${var.nodes} )
) * 100 < ${var.free_memory_threshold_critical}
EOF