CME-122: Database monitoring and alerting on RD repositories #992
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Plan Result (aat)
Change Result (Click me) # module.db-rd-caseworker-ref-v16.azurerm_monitor_action_group.db-alerts-action-group[0] will be created
+ resource "azurerm_monitor_action_group" "db-alerts-action-group" {
+ enabled = true
+ id = (known after apply)
+ location = "global"
+ name = "action_group-rd-caseworker-ref-api-postgres-db-v16-aat"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-aat"
+ short_name = "action_group"
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "staging"
+ "managedBy" = "Reference Data"
}
+ email_receiver {
+ email_address = (sensitive value)
+ name = "Email Receiver"
+ use_common_alert_schema = true
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_cpu[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_cpu" {
+ auto_mitigate = true
+ description = "Whenever the cpu utilization is greater than 5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_cpu_percent_rd-caseworker-ref-api-postgres-db-v16-aat"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-aat"
+ scopes = [
+ "/subscriptions/1c4f0704-a29e-403d-b719-b90c34ef14c9/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-aat/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-aat",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "staging"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "cpu_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 5
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_memory[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_memory" {
+ auto_mitigate = true
+ description = "Whenever the memory utilization is greater than 5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_memory_percent_rd-caseworker-ref-api-postgres-db-v16-aat"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-aat"
+ scopes = [
+ "/subscriptions/1c4f0704-a29e-403d-b719-b90c34ef14c9/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-aat/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-aat",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "staging"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "memory_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 5
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_storage_utilization[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_storage_utilization" {
+ auto_mitigate = true
+ description = "Whenever the storage utilization is greater than 0.5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_storage_utilization_rd-caseworker-ref-api-postgres-db-v16-aat"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-aat"
+ scopes = [
+ "/subscriptions/1c4f0704-a29e-403d-b719-b90c34ef14c9/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-aat/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-aat",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "staging"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "storage_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 0.5
}
}
Plan: 4 to add, 0 to change, 0 to destroy. |
Plan Result (prod)
Change Result (Click me) # module.db-rd-caseworker-ref-v16.azurerm_monitor_action_group.db-alerts-action-group[0] will be created
+ resource "azurerm_monitor_action_group" "db-alerts-action-group" {
+ enabled = true
+ id = (known after apply)
+ location = "global"
+ name = "action_group-rd-caseworker-ref-api-postgres-db-v16-prod"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-prod"
+ short_name = "action_group"
+ tags = {
+ "application" = "reference-data"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "production"
+ "managedBy" = "Reference Data"
}
+ email_receiver {
+ email_address = (sensitive value)
+ name = "Email Receiver"
+ use_common_alert_schema = true
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_cpu[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_cpu" {
+ auto_mitigate = true
+ description = "Whenever the cpu utilization is greater than 5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_cpu_percent_rd-caseworker-ref-api-postgres-db-v16-prod"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-prod"
+ scopes = [
+ "/subscriptions/8999dec3-0104-4a27-94ee-6588559729d1/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-prod/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-prod",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "production"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "cpu_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 5
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_memory[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_memory" {
+ auto_mitigate = true
+ description = "Whenever the memory utilization is greater than 5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_memory_percent_rd-caseworker-ref-api-postgres-db-v16-prod"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-prod"
+ scopes = [
+ "/subscriptions/8999dec3-0104-4a27-94ee-6588559729d1/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-prod/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-prod",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "production"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "memory_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 5
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_storage_utilization[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_storage_utilization" {
+ auto_mitigate = true
+ description = "Whenever the storage utilization is greater than 0.5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_storage_utilization_rd-caseworker-ref-api-postgres-db-v16-prod"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-prod"
+ scopes = [
+ "/subscriptions/8999dec3-0104-4a27-94ee-6588559729d1/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-prod/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-prod",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "production"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "storage_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 0.5
}
}
Plan: 4 to add, 0 to change, 0 to destroy. |
lukasz-wolski
previously approved these changes
Dec 5, 2024
rapolaskaseliscgi
previously approved these changes
Dec 5, 2024
SammiChong
dismissed stale reviews from rapolaskaseliscgi and lukasz-wolski
via
67d4a0f
|
Adding low thresholds to test emails are sending. |
AntonyLeons
previously approved these changes
Dec 6, 2024
kiran-yenigala-hmcts
requested changes
Dec 6, 2024
lukasz-wolski
approved these changes
Dec 6, 2024
Plan Result (ithc)
Change Result (Click me) # module.db-rd-caseworker-ref-v16.azurerm_monitor_action_group.db-alerts-action-group[0] will be created
+ resource "azurerm_monitor_action_group" "db-alerts-action-group" {
+ enabled = true
+ id = (known after apply)
+ location = "global"
+ name = "action_group-rd-caseworker-ref-api-postgres-db-v16-ithc"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-ithc"
+ short_name = "action_group"
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "ithc"
+ "managedBy" = "Reference Data"
}
+ email_receiver {
+ email_address = (sensitive value)
+ name = "Email Receiver"
+ use_common_alert_schema = true
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_cpu[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_cpu" {
+ auto_mitigate = true
+ description = "Whenever the cpu utilization is greater than 5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_cpu_percent_rd-caseworker-ref-api-postgres-db-v16-ithc"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-ithc"
+ scopes = [
+ "/subscriptions/7a4e3bd5-ae3a-4d0c-b441-2188fee3ff1c/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-ithc/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-ithc",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "ithc"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "cpu_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 5
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_memory[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_memory" {
+ auto_mitigate = true
+ description = "Whenever the memory utilization is greater than 5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_memory_percent_rd-caseworker-ref-api-postgres-db-v16-ithc"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-ithc"
+ scopes = [
+ "/subscriptions/7a4e3bd5-ae3a-4d0c-b441-2188fee3ff1c/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-ithc/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-ithc",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "ithc"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "memory_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 5
}
}
# module.db-rd-caseworker-ref-v16.azurerm_monitor_metric_alert.db_alert_storage_utilization[0] will be created
+ resource "azurerm_monitor_metric_alert" "db_alert_storage_utilization" {
+ auto_mitigate = true
+ description = "Whenever the storage utilization is greater than 0.5%"
+ enabled = true
+ frequency = "PT1H"
+ id = (known after apply)
+ name = "db_storage_utilization_rd-caseworker-ref-api-postgres-db-v16-ithc"
+ resource_group_name = "rd-caseworker-ref-api-postgres-db-v16-data-ithc"
+ scopes = [
+ "/subscriptions/7a4e3bd5-ae3a-4d0c-b441-2188fee3ff1c/resourceGroups/rd-caseworker-ref-api-postgres-db-v16-data-ithc/providers/Microsoft.DBforPostgreSQL/flexibleServers/rd-caseworker-ref-api-postgres-db-v16-ithc",
]
+ severity = 1
+ tags = {
+ "application" = "reference-data"
+ "autoShutdown" = "true"
+ "builtFrom" = "https://github.com/HMCTS/rd-caseworker-ref-api.git"
+ "businessArea" = "CFT"
+ "contactSlackChannel" = "#ref-data-support"
+ "environment" = "ithc"
+ "managedBy" = "Reference Data"
}
+ target_resource_location = (known after apply)
+ target_resource_type = (known after apply)
+ window_size = "P1D"
+ action {
+ action_group_id = (known after apply)
}
+ criteria {
+ aggregation = "Average"
+ metric_name = "storage_percent"
+ metric_namespace = "Microsoft.DBforPostgreSQL/flexibleServers"
+ operator = "GreaterThan"
+ skip_metric_validation = false
+ threshold = 0.5
}
}
Plan: 4 to add, 0 to change, 0 to destroy. |
SabinaHMCTS
approved these changes
Dec 9, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
JIRA link (if applicable)
https://tools.hmcts.net/jira/browse/CME-247
Change description
Does this PR introduce a breaking change? (check one with "x")