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

MON-32 - Free Memory monitors updated to evaluate the metric over a period

Browse Source
This commit is contained in:
Alexandre Gaillet 2018-06-07 11:57:36 +02:00 committed by Quentin Manfroi
parent 983bebcd5f
commit d126e898d3
11 changed files with 82 additions and 214 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
cloud/aws/elasticache/common/README.md
View File

@ -26,6 +26,7 @@ Creates DataDog monitors with the following checks:
* Swap * Swap
* Max connections * Max connections
* No connection * No connection
* Free Memory
Inputs Inputs
------ ------
@ -39,6 +40,12 @@ Inputs
| eviction_time_aggregator | Monitor aggregator for Elasticache eviction [available values: min, max or avg] | string | `min` | no | | eviction_time_aggregator | Monitor aggregator for Elasticache eviction [available values: min, max or avg] | string | `min` | no |
| eviction_timeframe | Monitor timeframe for Elasticache eviction [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no | | eviction_timeframe | Monitor timeframe for Elasticache eviction [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_5m` | no |
| filter_tags | Tags used for filtering | string | - | yes | | filter_tags | Tags used for filtering | string | - | yes |
| free_memory_condition_timeframe | Monitor condition timeframe for Elasticache free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| free_memory_message | Custom message for Elasticache free memory monitor | string | `` | no |
| free_memory_silenced | Groups to mute for Elasticache free memory monitor | map | `<map>` | no |
| free_memory_threshold_critical | Elasticache free memory critical threshold in percentage | string | `300` | no |
| free_memory_threshold_warning | Elasticache free memory warning threshold in percentage | string | `200` | no |
| free_memory_timeframe | Monitor timeframe for Elasticache free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| max_connection_message | Custom message for Elasticache max connection monitor | string | `` | no | | 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_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 | `max` | no | | max_connection_time_aggregator | Monitor aggregator for Elasticache max connection [available values: min, max or avg] | string | `max` | no |
@ -49,12 +56,12 @@ Inputs
| no_connection_time_aggregator | Monitor aggregator for Elasticache no connection [available values: min, max or avg] | string | `min` | no | | 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 | | 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 | | resource | Type of Elasticache used | string | - | yes |
| swap_message | Custom message for Elasticache memcached swap monitor | string | `` | no | | swap_message | Custom message for Elasticache swap monitor | string | `` | no |
| swap_silenced | Groups to mute for Elasticache memcached swap monitor | map | `<map>` | no | | swap_silenced | Groups to mute for Elasticache swap monitor | map | `<map>` | no |
| swap_threshold_critical | Elasticache memcached swap critical threshold in percentage | string | `50` | no | | swap_threshold_critical | Elasticache swap critical threshold in percentage | string | `50` | no |
| swap_threshold_warning | Elasticache memcached swap warning threshold in percentage | string | `0` | no | | swap_threshold_warning | Elasticache 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_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 | | swap_timeframe | Monitor timeframe for Elasticache 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 Related documentation
--------------------- ---------------------

44
cloud/aws/elasticache/common/inputs.tf
View File

@ -93,13 +93,13 @@ variable "no_connection_timeframe" {
} }
variable "swap_silenced" { variable "swap_silenced" {
description = "Groups to mute for Elasticache memcached swap monitor" description = "Groups to mute for Elasticache swap monitor"
type = "map" type = "map"
default = {} default = {}
} }
variable "swap_message" { variable "swap_message" {
description = "Custom message for Elasticache memcached swap monitor" description = "Custom message for Elasticache swap monitor"
type = "string" type = "string"
default = "" default = ""
} }
@ -111,16 +111,48 @@ variable "swap_time_aggregator" {
} }
variable "swap_timeframe" { 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`]" description = "Monitor timeframe for Elasticache swap [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_5m" default = "last_5m"
} }
variable "swap_threshold_warning" { variable "swap_threshold_warning" {
description = "Elasticache memcached swap warning threshold in percentage" description = "Elasticache swap warning threshold in percentage"
default = 0 default = 0
} }
variable "swap_threshold_critical" { variable "swap_threshold_critical" {
description = "Elasticache memcached swap critical threshold in percentage" description = "Elasticache swap critical threshold in percentage"
default = 50 default = 50000000
}
variable "free_memory_silenced" {
description = "Groups to mute for Elasticache free memory monitor"
type = "map"
default = {}
}
variable "free_memory_message" {
description = "Custom message for Elasticache free memory monitor"
type = "string"
default = ""
}
variable "free_memory_condition_timeframe" {
description = "Monitor condition timeframe for Elasticache free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_15m"
}
variable "free_memory_timeframe" {
description = "Monitor timeframe for Elasticache free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_15m"
}
variable "free_memory_threshold_warning" {
description = "Elasticache free memory warning threshold in percentage"
default = -50
}
variable "free_memory_threshold_critical" {
description = "Elasticache free memory critical threshold in percentage"
default = -70
} }

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

@ -110,3 +110,35 @@ resource "datadog_monitor" "elasticache_swap" {
tags = ["env:${var.environment}", "engine:${var.resource}", "team:aws", "provider:aws"] tags = ["env:${var.environment}", "engine:${var.resource}", "team:aws", "provider:aws"]
} }
resource "datadog_monitor" "redis_free_memory" {
name = "[${var.environment}] Elasticache ${var.resource} free memory {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.free_memory_message, var.message)}"
type = "metric alert"
query = <<EOF
pct_change(avg(${var.free_memory_timeframe}),${var.free_memory_condition_timeframe}):
avg:aws.elasticache.freeable_memory{${var.filter_tags}} by {region,cacheclusterid,cachenodeid}
< ${var.free_memory_threshold_critical}
EOF
thresholds {
warning = "${var.free_memory_threshold_warning}"
critical = "${var.free_memory_threshold_critical}"
}
notify_no_data = true
evaluation_delay = "${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.free_memory_silenced}"
tags = ["env:${var.environment}", "engine:${var.resource}", "team:aws", "provider:aws"]
}

7
cloud/aws/elasticache/memcached/README.md
View File

@ -21,7 +21,6 @@ Creates DataDog monitors with the following checks :
* Get Hit * Get Hit
* CPU High * CPU High
* Free memory
Inputs Inputs
------ ------
@ -39,12 +38,6 @@ Inputs
| environment | Infrastructure 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_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 | | 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 |
| free_memory_silenced | Groups to mute for Elasticache memcached free memory monitor | map | `<map>` | no |
| free_memory_threshold_critical | Elasticache memcached free memory critical threshold in percentage | string | `5` | no |
| free_memory_threshold_warning | Elasticache memcached free memory warning threshold in percentage | string | `10` | no |
| free_memory_time_aggregator | Monitor aggregator for Elasticache memcached free memory [available values: min, max or avg] | string | `min` | no |
| free_memory_timeframe | Monitor timeframe for Elasticache memcached free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`] | string | `last_15m` | no |
| get_hits_message | Custom message for Elasticache memcached get hits monitor | string | `` | no | | get_hits_message | Custom message for Elasticache memcached get hits monitor | string | `` | no |
| get_hits_silenced | Groups to mute for Elasticache memcached get hits monitor | map | `<map>` | no | | get_hits_silenced | Groups to mute for Elasticache memcached get hits monitor | map | `<map>` | no |
| get_hits_threshold_critical | Elasticache memcached get hits critical threshold in percentage | string | `10` | no | | get_hits_threshold_critical | Elasticache memcached get hits critical threshold in percentage | string | `10` | no |

33
cloud/aws/elasticache/memcached/inputs.tf
View File

@ -90,36 +90,3 @@ variable "cpu_high_threshold_critical" {
description = "Elasticache memcached cpu high critical threshold in percentage" description = "Elasticache memcached cpu high critical threshold in percentage"
default = 90 default = 90
} }
variable "free_memory_silenced" {
description = "Groups to mute for Elasticache memcached free memory monitor"
type = "map"
default = {}
}
variable "free_memory_message" {
description = "Custom message for Elasticache memcached free memory monitor"
type = "string"
default = ""
}
variable "free_memory_time_aggregator" {
description = "Monitor aggregator for Elasticache memcached free memory [available values: min, max or avg]"
type = "string"
default = "min"
}
variable "free_memory_timeframe" {
description = "Monitor timeframe for Elasticache memcached free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_15m"
}
variable "free_memory_threshold_warning" {
description = "Elasticache memcached free memory warning threshold in percentage"
default = 10
}
variable "free_memory_threshold_critical" {
description = "Elasticache memcached free memory critical threshold in percentage"
default = 5
}

27
cloud/aws/elasticache/memcached/locals.tf
View File

@ -1,27 +0,0 @@
locals {
memory = {
cache.t2.micro = 595926712
cache.t2.small = 1664299827
cache.t2.medium = 3457448673
cache.m3.medium = 2985002270
cache.m3.large = 6496138035
cache.m3.xlarge = 14280766259
cache.m3.2xlarge = 29957396889
cache.m4.large = 6893422510
cache.m4.xlarge = 15333033246
cache.m4.2xlarge = 31890132172
cache.m4.4xlarge = 65262028062
cache.m4.10xlarge = 166043435663
cache.r3.large = 14495514624
cache.r3.xlarge = 30494267801
cache.r3.2xlarge = 62491774156
cache.r3.4xlarge = 126701535232
cache.r3.8xlarge = 254476812288
cache.r4.large = 13207024435
cache.r4.xlarge = 26897232691
cache.r4.2xlarge = 54191749857
cache.r4.4xlarge = 108855946117
cache.r4.8xlarge = 218248763146
cache.r4.16xlarge = 437012922368
}
}

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

@ -80,38 +80,3 @@ resource "datadog_monitor" "memcached_cpu_high" {
tags = ["env:${var.environment}", "engine:memcached", "team:aws", "provider:aws"] tags = ["env:${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)}"
count = "${length(keys(local.memory))}"
type = "metric alert"
query = <<EOF
${var.free_memory_time_aggregator}(${var.free_memory_timeframe}): (
( 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} * 100 ) /
${element(values(local.memory), count.index)}
) < ${var.free_memory_threshold_critical}
EOF
thresholds {
warning = "${var.free_memory_threshold_warning}"
critical = "${var.free_memory_threshold_critical}"
}
notify_no_data = false
evaluation_delay = "${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.free_memory_silenced}"
tags = ["env:${var.environment}", "engine:memcached", "team:aws", "provider:aws"]
}

7
cloud/aws/elasticache/redis/README.md
View File

@ -33,7 +33,6 @@ Creates DataDog monitors with the following checks:
* CPU high * CPU high
* Commands received * Commands received
* Replication lag * Replication lag
* Free memory
Inputs Inputs
------ ------
@ -59,12 +58,6 @@ Inputs
| environment | Infrastructure 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_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 | | 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 |
| free_memory_silenced | Groups to mute for Elasticache redis free memory monitor | map | `<map>` | no |
| free_memory_threshold_critical | Elasticache redis free memory critical threshold in percentage | string | `5` | no |
| free_memory_threshold_warning | Elasticache redis free memory warning threshold in percentage | string | `10` | no |
| free_memory_time_aggregator | Monitor aggregator for Elasticache redis free memory [available values: min, max or avg] | string | `min` | no |
| free_memory_timeframe | Monitor timeframe for Elasticache redis free memory [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 | | message | Message sent when an alert is triggered | string | - | yes |
| nodes | Number of Elasticache nodes | string | - | yes | | nodes | Number of Elasticache nodes | string | - | yes |
| replication_lag_message | Custom message for Elasticache redis replication lag monitor | string | `` | no | | replication_lag_message | Custom message for Elasticache redis replication lag monitor | string | `` | no |

33
cloud/aws/elasticache/redis/inputs.tf
View File

@ -145,36 +145,3 @@ variable "commands_timeframe" {
description = "Monitor timeframe for Elasticache redis commands [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]" description = "Monitor timeframe for Elasticache redis commands [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_5m" default = "last_5m"
} }
variable "free_memory_silenced" {
description = "Groups to mute for Elasticache redis free memory monitor"
type = "map"
default = {}
}
variable "free_memory_message" {
description = "Custom message for Elasticache redis free memory monitor"
type = "string"
default = ""
}
variable "free_memory_time_aggregator" {
description = "Monitor aggregator for Elasticache redis free memory [available values: min, max or avg]"
type = "string"
default = "min"
}
variable "free_memory_timeframe" {
description = "Monitor timeframe for Elasticache redis free memory [available values: `last_#m` (1, 5, 10, 15, or 30), `last_#h` (1, 2, or 4), or `last_1d`]"
default = "last_15m"
}
variable "free_memory_threshold_warning" {
description = "Elasticache redis free memory warning threshold in percentage"
default = 10
}
variable "free_memory_threshold_critical" {
description = "Elasticache redis free memory critical threshold in percentage"
default = 5
}

26
cloud/aws/elasticache/redis/locals.tf
View File

@ -24,30 +24,4 @@ locals {
cache.r4.8xlarge = 32 cache.r4.8xlarge = 32
cache.r4.16xlarge = 64 cache.r4.16xlarge = 64
} }
memory = {
cache.t2.micro = 595926712
cache.t2.small = 1664299827
cache.t2.medium = 3457448673
cache.m3.medium = 2985002270
cache.m3.large = 6496138035
cache.m3.xlarge = 14280766259
cache.m3.2xlarge = 29957396889
cache.m4.large = 6893422510
cache.m4.xlarge = 15333033246
cache.m4.2xlarge = 31890132172
cache.m4.4xlarge = 65262028062
cache.m4.10xlarge = 166043435663
cache.r3.large = 14495514624
cache.r3.xlarge = 30494267801
cache.r3.2xlarge = 62491774156
cache.r3.4xlarge = 126701535232
cache.r3.8xlarge = 254476812288
cache.r4.large = 13207024435
cache.r4.xlarge = 26897232691
cache.r4.2xlarge = 54191749857
cache.r4.4xlarge = 108855946117
cache.r4.8xlarge = 218248763146
cache.r4.16xlarge = 437012922368
}
} }

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

@ -137,38 +137,3 @@ resource "datadog_monitor" "redis_commands" {
tags = ["env:${var.environment}", "engine:redis", "team:aws", "provider:aws"] tags = ["env:${var.environment}", "engine:redis", "team:aws", "provider:aws"]
} }
resource "datadog_monitor" "redis_free_memory" {
name = "[${var.environment}] Elasticache redis free memory {{#is_alert}}{{{comparator}}} {{threshold}}% ({{value}}%){{/is_alert}}{{#is_warning}}{{{comparator}}} {{warn_threshold}}% ({{value}}%){{/is_warning}}"
message = "${coalesce(var.free_memory_message, var.message)}"
count = "${length(keys(local.memory))}"
type = "metric alert"
query = <<EOF
${var.free_memory_time_aggregator}(${var.free_memory_timeframe}): (
( 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} * 100 ) /
( ${element(values(local.memory), count.index)} / ${var.nodes} )
) < ${var.free_memory_threshold_critical}
EOF
thresholds {
warning = "${var.free_memory_threshold_warning}"
critical = "${var.free_memory_threshold_critical}"
}
notify_no_data = false
evaluation_delay = "${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.free_memory_silenced}"
tags = ["env:${var.environment}", "engine:redis", "team:aws", "provider:aws"]
}