CCM-16073 - Enhanced callbacks #145
There are no files selected for viewing
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
|
Contributor
There was a problem hiding this comment. Do we want an alarm on storage - e.g. 80% used |
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,178 @@ | ||
| resource "aws_elasticache_serverless_cache" "delivery_state" { | ||
| name = "${local.csi}-delivery-state" | ||
| engine = "redis" | ||
|
Contributor
There was a problem hiding this comment. For cost saving I think we should switch to valkey.
Contributor
There was a problem hiding this comment. Valkey is redis compatible, is half the cost and faster. Can we use that? |
||
| major_engine_version = "7" | ||
| description = "Per-target rate limiting and circuit breaker state for callback delivery" | ||
|
|
||
| snapshot_retention_limit = 0 | ||
|
|
||
| security_group_ids = [aws_security_group.elasticache_delivery_state.id] | ||
| subnet_ids = local.acct.private_subnet_ids | ||
|
|
||
| kms_key_id = module.kms.key_arn | ||
|
|
||
| cache_usage_limits { | ||
| data_storage { | ||
| maximum = 1 | ||
|
Contributor
There was a problem hiding this comment. 1GB is the minimum with redis but can go down to 100mb if we make the valkey switch. |
||
| unit = "GB" | ||
| } | ||
|
|
||
| ecpu_per_second { | ||
| maximum = 1000 | ||
| } | ||
| } | ||
|
|
||
| tags = merge( | ||
| local.default_tags, | ||
| { | ||
| Name = "${local.csi}-delivery-state" | ||
| Description = "Callback delivery rate limiter and circuit breaker state" | ||
| }, | ||
| ) | ||
| } | ||
|
|
||
| resource "aws_security_group" "elasticache_delivery_state" { | ||
| name = "${local.csi}-elasticache-delivery-state" | ||
| description = "Security group for ElastiCache delivery state cluster" | ||
| vpc_id = local.acct.vpc_id | ||
|
|
||
| tags = merge( | ||
| local.default_tags, | ||
| { | ||
| Name = "${local.csi}-elasticache-delivery-state" | ||
| }, | ||
| ) | ||
| } | ||
|
|
||
| resource "aws_vpc_security_group_ingress_rule" "elasticache_from_lambda" { | ||
| security_group_id = aws_security_group.elasticache_delivery_state.id | ||
| referenced_security_group_id = aws_security_group.https_client_lambda.id | ||
| from_port = 6379 | ||
| to_port = 6379 | ||
| ip_protocol = "tcp" | ||
| description = "Allow HTTPS Client Lambda to connect to ElastiCache" | ||
|
|
||
| tags = local.default_tags | ||
| } | ||
|
|
||
| resource "aws_security_group" "https_client_lambda" { | ||
| name = "${local.csi}-https-client-lambda" | ||
| description = "Security group for per-client HTTPS Client Lambda functions" | ||
| vpc_id = local.acct.vpc_id | ||
|
|
||
| tags = merge( | ||
| local.default_tags, | ||
| { | ||
| Name = "${local.csi}-https-client-lambda" | ||
| }, | ||
| ) | ||
| } | ||
|
|
||
| resource "aws_vpc_security_group_egress_rule" "lambda_to_elasticache" { | ||
| security_group_id = aws_security_group.https_client_lambda.id | ||
| referenced_security_group_id = aws_security_group.elasticache_delivery_state.id | ||
| from_port = 6379 | ||
| to_port = 6379 | ||
| ip_protocol = "tcp" | ||
| description = "Allow Lambda to connect to ElastiCache" | ||
|
|
||
| tags = local.default_tags | ||
| } | ||
|
|
||
| resource "aws_vpc_security_group_egress_rule" "lambda_to_https" { | ||
| security_group_id = aws_security_group.https_client_lambda.id | ||
| cidr_ipv4 = "0.0.0.0/0" | ||
| from_port = 443 | ||
| to_port = 443 | ||
| ip_protocol = "tcp" | ||
| description = "Allow Lambda outbound HTTPS for webhook delivery" | ||
|
|
||
| tags = local.default_tags | ||
| } | ||
|
|
||
| resource "aws_cloudwatch_metric_alarm" "elasticache_ecpu_utilisation" { | ||
| alarm_name = "${local.csi}-elasticache-ecpu-utilisation" | ||
| alarm_description = join(" ", [ | ||
| "PERFORMANCE: ElastiCache processing units utilisation is high.", | ||
| "Consider scaling up or optimising Redis commands.", | ||
| ]) | ||
|
|
||
| comparison_operator = "GreaterThanThreshold" | ||
| evaluation_periods = 3 | ||
| metric_name = "ElastiCacheProcessingUnits" | ||
| namespace = "AWS/ElastiCache" | ||
| period = 300 | ||
| statistic = "Average" | ||
| threshold = 80 | ||
| actions_enabled = true | ||
| treat_missing_data = "notBreaching" | ||
|
|
||
| dimensions = { | ||
| CacheClusterId = aws_elasticache_serverless_cache.delivery_state.name | ||
| } | ||
|
|
||
| tags = merge( | ||
| local.default_tags, | ||
| { | ||
| Name = "${local.csi}-elasticache-ecpu-utilisation" | ||
| }, | ||
| ) | ||
| } | ||
|
|
||
| resource "aws_cloudwatch_metric_alarm" "elasticache_connections" { | ||
| alarm_name = "${local.csi}-elasticache-connections" | ||
| alarm_description = join(" ", [ | ||
| "RELIABILITY: ElastiCache connection count is high.", | ||
| "Review per-client Lambda connection pool sizing.", | ||
| ]) | ||
|
|
||
| comparison_operator = "GreaterThanThreshold" | ||
| evaluation_periods = 2 | ||
| metric_name = "CurrConnections" | ||
| namespace = "AWS/ElastiCache" | ||
| period = 300 | ||
| statistic = "Maximum" | ||
| threshold = 500 | ||
| actions_enabled = true | ||
| treat_missing_data = "notBreaching" | ||
|
|
||
| dimensions = { | ||
| CacheClusterId = aws_elasticache_serverless_cache.delivery_state.name | ||
| } | ||
|
|
||
| tags = merge( | ||
| local.default_tags, | ||
| { | ||
| Name = "${local.csi}-elasticache-connections" | ||
| }, | ||
| ) | ||
| } | ||
|
|
||
| resource "aws_cloudwatch_metric_alarm" "elasticache_throttled_ops" { | ||
| alarm_name = "${local.csi}-elasticache-throttled-ops" | ||
| alarm_description = join(" ", [ | ||
| "PERFORMANCE: ElastiCache throttled operations detected.", | ||
| "Increase ECPU limit or reduce request rate.", | ||
| ]) | ||
|
|
||
| comparison_operator = "GreaterThanThreshold" | ||
| evaluation_periods = 2 | ||
| metric_name = "ThrottledCmds" | ||
| namespace = "AWS/ElastiCache" | ||
| period = 300 | ||
| statistic = "Sum" | ||
| threshold = 0 | ||
| actions_enabled = true | ||
| treat_missing_data = "notBreaching" | ||
|
|
||
| dimensions = { | ||
| CacheClusterId = aws_elasticache_serverless_cache.delivery_state.name | ||
| } | ||
|
|
||
| tags = merge( | ||
| local.default_tags, | ||
| { | ||
| Name = "${local.csi}-elasticache-throttled-ops" | ||
| }, | ||
| ) | ||
| } | ||
This file contains hidden or 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
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,47 @@ | ||
| module "client_delivery" { | ||
| source = "../../modules/client-delivery" | ||
| for_each = local.config_clients | ||
|
|
||
| project = var.project | ||
| aws_account_id = var.aws_account_id | ||
| region = var.region | ||
| component = var.component | ||
| environment = var.environment | ||
| group = var.group | ||
|
|
||
| client_id = each.key | ||
| client_bus_name = aws_cloudwatch_event_bus.main.name | ||
| kms_key_arn = module.kms.key_arn | ||
|
|
||
| subscriptions = local.client_subscriptions[each.key] | ||
| subscription_targets = local.client_subscription_targets[each.key] | ||
|
|
||
| client_config_bucket = module.client_config_bucket.bucket | ||
| client_config_bucket_arn = module.client_config_bucket.arn | ||
|
|
||
| applications_map_parameter_name = local.applications_map_parameter_name | ||
|
|
||
| lambda_s3_bucket = local.acct.s3_buckets["lambda_function_artefacts"]["id"] | ||
| lambda_code_base_path = local.aws_lambda_functions_dir_path | ||
|
|
||
| force_lambda_code_deploy = var.force_lambda_code_deploy | ||
| log_level = var.log_level | ||
| log_retention_in_days = var.log_retention_in_days | ||
| enable_xray_tracing = var.enable_xray_tracing | ||
|
|
||
| log_destination_arn = local.log_destination_arn | ||
| log_subscription_role_arn = local.acct.log_subscription_role_arn | ||
|
|
||
| elasticache_endpoint = aws_elasticache_serverless_cache.delivery_state.endpoint[0].address | ||
| elasticache_cache_name = aws_elasticache_serverless_cache.delivery_state.name | ||
| elasticache_iam_username = "${var.project}-${var.environment}-${var.component}-elasticache-user" | ||
|
|
||
| mtls_cert_secret_arn = var.mtls_cert_secret_arn | ||
| mtls_test_cert_s3_bucket = var.mtls_test_certs_s3_bucket | ||
| mtls_test_cert_s3_key = var.mtls_test_cert_s3_key | ||
|
|
||
| vpc_subnet_ids = local.acct.private_subnet_ids | ||
| lambda_security_group_id = aws_security_group.https_client_lambda.id | ||
|
|
||
| deploy_mock_clients = var.deploy_mock_clients | ||
| } |
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not related to the phase 2 work but I think we can delete lines 3-6 - those secrets have never been in our repo at any point