feat: add CloudWatch metrics for Lambda behaviour #683
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
Add CloudWatch metric filters for the following Lambda functions: - Form archiver - Reliability - Response archiver - Submission These will be used to build out dashboards and create healthcheck alarms if success metrics are not observed consistenly. Add succes log events and a `status` property to the form-archiver and response-archiver Lambda functions.
⚠ Terrform update availableTerraform: 1.8.5 (using 1.6.6)
Terragrunt: 0.59.3 (using 0.54.8) |
Staging: alarms✅ Terraform Init: Plan: 18 to add, 0 to change, 2 to destroyShow summary
Show planResource actions are indicated with the following symbols:
+ create
- destroy
Terraform will perform the following actions:
# aws_cloudwatch_log_metric_filter.healthcheck["ClientSubmitFailed"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "Forms"
+ name = "ClientSubmitFailed"
+ pattern = "Attempted response submission for Form ID"
+ metric_transformation {
+ default_value = "0"
+ name = "ClientSubmitFailed"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ClientSubmitSuccess"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "Forms"
+ name = "ClientSubmitSuccess"
+ pattern = "Response submitted for Form ID"
+ metric_transformation {
+ default_value = "0"
+ name = "ClientSubmitSuccess"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["FormArchiverFailed"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Archive_Form_Templates"
+ name = "FormArchiverFailed"
+ pattern = "{$.status = \"failed\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "FormArchiverFailed"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["FormArchiverSuccess"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Archive_Form_Templates"
+ name = "FormArchiverSuccess"
+ pattern = "{$.status = \"success\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "FormArchiverSuccess"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["FormArchiverWarn"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Archive_Form_Templates"
+ name = "FormArchiverWarn"
+ pattern = "{$.level = \"warn\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "FormArchiverWarn"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["FormsClientSubmitFailed"] will be destroyed
# (because key ["FormsClientSubmitFailed"] is not in for_each map)
- resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
- id = "FormsClientSubmitFailed" -> null
- log_group_name = "Forms" -> null
- name = "FormsClientSubmitFailed" -> null
- pattern = "Attempted response submission for Form ID" -> null
- metric_transformation {
- default_value = "0" -> null
- dimensions = {} -> null
- name = "FormsClientSubmitFailed" -> null
- namespace = "forms" -> null
- unit = "Count" -> null
- value = "1" -> null
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["FormsClientSubmitSuccess"] will be destroyed
# (because key ["FormsClientSubmitSuccess"] is not in for_each map)
- resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
- id = "FormsClientSubmitSuccess" -> null
- log_group_name = "Forms" -> null
- name = "FormsClientSubmitSuccess" -> null
- pattern = "Response submitted for Form ID" -> null
- metric_transformation {
- default_value = "0" -> null
- dimensions = {} -> null
- name = "FormsClientSubmitSuccess" -> null
- namespace = "forms" -> null
- unit = "Count" -> null
- value = "1" -> null
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ReliabilityFailed"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Reliability"
+ name = "ReliabilityFailed"
+ pattern = "{$.status = \"failed\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "ReliabilityFailed"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ReliabilityNotifySendFailed"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Reliability"
+ name = "ReliabilityNotifySendFailed"
+ pattern = "Failed to send submission through GC Notify"
+ metric_transformation {
+ default_value = "0"
+ name = "ReliabilityNotifySendFailed"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ReliabilityNotifySendSuccess"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Reliability"
+ name = "ReliabilityNotifySendSuccess"
+ pattern = "Successfully sent submission through GC Notify"
+ metric_transformation {
+ default_value = "0"
+ name = "ReliabilityNotifySendSuccess"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ReliabilitySuccess"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Reliability"
+ name = "ReliabilitySuccess"
+ pattern = "{$.status = \"success\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "ReliabilitySuccess"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ReliabilityVaultSaveFailed"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Reliability"
+ name = "ReliabilityVaultSaveFailed"
+ pattern = "Failed to save submission to Vault"
+ metric_transformation {
+ default_value = "0"
+ name = "ReliabilityVaultSaveFailed"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ReliabilityVaultSaveSuccess"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Reliability"
+ name = "ReliabilityVaultSaveSuccess"
+ pattern = "Successfully saved submission to Vault"
+ metric_transformation {
+ default_value = "0"
+ name = "ReliabilityVaultSaveSuccess"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ReliabilityWarn"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Reliability"
+ name = "ReliabilityWarn"
+ pattern = "{$.level = \"warn\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "ReliabilityWarn"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ResponseArchiverFailed"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Response_Archiver"
+ name = "ResponseArchiverFailed"
+ pattern = "{$.status = \"failed\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "ResponseArchiverFailed"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ResponseArchiverSuccess"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Response_Archiver"
+ name = "ResponseArchiverSuccess"
+ pattern = "{$.status = \"success\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "ResponseArchiverSuccess"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["ResponseArchiverWarn"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Response_Archiver"
+ name = "ResponseArchiverWarn"
+ pattern = "{$.level = \"warn\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "ResponseArchiverWarn"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["SubmissionFailed"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Submission"
+ name = "SubmissionFailed"
+ pattern = "{$.status = \"failed\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "SubmissionFailed"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["SubmissionSuccess"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Submission"
+ name = "SubmissionSuccess"
+ pattern = "{$.status = \"success\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "SubmissionSuccess"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
# aws_cloudwatch_log_metric_filter.healthcheck["SubmissionWarn"] will be created
+ resource "aws_cloudwatch_log_metric_filter" "healthcheck" {
+ id = (known after apply)
+ log_group_name = "/aws/lambda/Submission"
+ name = "SubmissionWarn"
+ pattern = "{$.level = \"warn\"}"
+ metric_transformation {
+ default_value = "0"
+ name = "SubmissionWarn"
+ namespace = "forms"
+ unit = "Count"
+ value = "1"
}
}
Plan: 18 to add, 0 to change, 2 to destroy.
Warning: Argument is deprecated
with module.athena_bucket.aws_s3_bucket.this,
on .terraform/modules/athena_bucket/S3/main.tf line 8, in resource "aws_s3_bucket" "this":
8: resource "aws_s3_bucket" "this" {
Use the aws_s3_bucket_server_side_encryption_configuration resource instead
(and 3 more similar warnings elsewhere)
─────────────────────────────────────────────────────────────────────────────
Saved the plan to: plan.tfplan
To perform exactly these actions, run the following command to apply:
terraform apply "plan.tfplan"
Show Conftest resultsWARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_event_rule.codedeploy_sns"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_log_group.notify_slack"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.ELB_5xx_error_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.UnHealthyHostCount-TargetGroup1"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.UnHealthyHostCount-TargetGroup2"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.alb_ddos"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.audit_log_dead_letter_queue_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.cognito_login_outside_canada_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.cognito_signin_exceeded"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.ddos_detected_forms_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.ddos_detected_route53_warn[0]"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.forms_cpu_utilization_high_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.forms_memory_utilization_high_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.reliability_dead_letter_queue_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.response_time_warn"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.route53_ddos[0]"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.twoFa_verification_exceeded"]
WARN - plan.json - main - Missing Common Tags: ["aws_cloudwatch_metric_alarm.vault_data_integrity_check_lambda_iterator_age"]
WARN - plan.json - main - Missing Common Tags: ["aws_iam_role.notify_slack_lambda"]
WARN - plan.json -... |
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.
Summary
Add CloudWatch metric filters for the following Lambda functions:
These will be used to build out dashboards and create health check alarms if success metrics are not observed consistency.
Add success log events and a
statusproperty to the form-archiver and response-archiver Lambda functions.Related