Keeping an eye on cloud spendings in AWS or any other cloud service
provider is one of the most important parts of every project team's
work. This can be tedious when following the AWS recommendation and best
practice to split workloads over more than one AWS account. Consolidated
billing -- a feature of AWS Organization would help in this case -- but
access to the main/billing account is very often not granted to project
teams and departments for good reason.
In this article, a solution is presented which allows to automatically
collect billing information from various accounts to present them in a
concise format in one or more AWS Quicksight dashboards. Before starting
to go into the details, let's look shortly on the available AWS services
for cost management and the difficulty when working with more than one
account.
AWS Cost Management Platform and Consolidated Billing
AWS provides a complete toolset consisting of AWS Billing, Cost
Explorer, and other sub services. They offer functionalities to get a
focused overview about costs and usages as well as tools to drill down
into the details of most services. The tooling is sufficient to get the
job done when working with one AWS account even though the user
experience might not be as awesome as provided by other more dedicated
and focused 3^rd^ party tools. Special IAM permissions are needed to
access all this information to tackle the governance part as well.
AWS Organization which rules all AWS accounts associated with it
provides some extended functionalities (aka. Consolidated billing) to
centralize cost monitoring and management. However, in most companies
and large enterprises only very few people are allowed to access the
billing account. This does not help a project lead to get the required
information easily. Depending on the number of AWS accounts used by
team, someone who is allowed has either to login into every account
regularly and check the costs or rely on "Cost and Usage" reports which
can be exported automatically to S3. These reports are very detailed
(maybe too much for simple use cases) and require some custom tooling to
extract the required information.
AWS has published a solution called Cloud Intelligence
Dashboards -- a collection of Quicksight dashboards which are among other data sources based on these cost and usage reports. Beside this one, company internal cost control tools -- sometimes bases on the same AWS services -- exist and can be "rented". All these solutions have their advantages and use cases -- but also drawbacks (mostly related to their costs and sometimes also due to overly large IAM permission requirements).
An approach for simple use cases
Sometimes it is fully sufficient to present some information in a
concise manner to stay informed about the general trends and total
amounts. In case something reveals to be strange or not to be in the
expected range, a more detailed analysis can be performed using for
instance the AWS tooling mentioned above.
Following this idea, Step Functions, Lambda, S3 and Quicksight powers a
small application which retrieves cost related data for every designated
AWS account and stores it as a JSON file in S3. Quicksight which
supports S3 as a data source directly reads this data and provides it to
build one or more dashboards displaying various cost related diagrams
and tables. This workflow (which is shown below) is triggered by an
EventBridge rule regularly (e.g., once a day) so that up-to-date
information is available.
The „Data preparation" step provides the AWS account ids and names as input for the following Map State.
The Map State starts for every array element (= AWS account) an
instance of a Lambda function which assumes an IAM role in the
relevant account and queries the AWS Cost Center and AWS Budget APIs
to collect the required information: total current costs, costs per
service, cost forecasts...
@logger.inject_lambda_context(log_event=True)
@tracer.capture_lambda_handler
def lambda_handler(event, context):
validate_input(event)
assumed_role_session = assume_role(
session,
f'arn:aws:iam::{event["account_id"]}:role/{ROLE_NAME}',
region_name="eu-central-1",
)
client = assumed_role_session.client("ce")
budget_client = assumed_role_session.client("budgets")
now = arrow.utcnow()
first_day_of_current_month, end_date = get_start_and_end_date(now)
cost_response = client.get_cost_and_usage(
TimePeriod={
"Start": first_day_of_current_month.format(date_format),
"End": end_date.format(date_format),
},
Granularity="MONTHLY",
Metrics=["UnblendedCost"],
)
cost_per_service = client.get_cost_and_usage(
TimePeriod={
"Start": first_day_of_current_month.format(date_format),
"End": end_date.format(date_format),
},
Granularity="MONTHLY",
Metrics=["UnblendedCost"],
GroupBy=[{"Type": "DIMENSION", "Key": "SERVICE"}],
)
…
payload = {
"date": now.format(date_format),
"current_month": now.month,
"current_year": now.year,
"account_name": f'{event["account_name"].upper()}',
"current_costs": f'{float(cost_response["ResultsByTime"][0]["Total"]["UnblendedCost"]["Amount"]):.2f}',
"forecasted_costs": f"{float(forecasted_cost):.2f}",
"budget": f'{float(budget_response["Budgets"][0]["BudgetLimit"]["Amount"]):.2f}',
"account_id": f'{event["account_id"]}',
}
for item in service_costs:
payload = payload | item
return {"statusCode": 200, "body": json.dumps(payload)}
The outcome of the Map State is an array consisting of the cost data retrieved from every AWS account.
[
{
"date": "2023-02-09",
"current_month": 2,
"current_year": 2023,
"account_name": "Test",
"current_costs": "152.49",
"forecasted_costs": "468.10",
"budget": "700.00",
"account_id": "11111111111x",
"Amazon DynamoDB": 10.0002276717,
"AWS CloudTrail": 3.0943441333,
"AWS Lambda": 30.24534433,
"AWS Key Management Service": 1.8699148608,
"AWS Step Functions": 32,5439809890,
"Amazon Relational Database Service": 16.1240975116,
…
},
{}
]
This data is stored as JSON file in a S3 bucket in the last workflow
step. Every file name contains the current date to make them unique.
Apart from the StepFunctions workflow and the Lambda function which can
for instance run in a dedicated AWS account to simplify the permission
management, an IAM role needs to be deployed to every account whose
costs should be retrieved. This role must trust the Lambda function and
contain the necessary permissions to query AWS Cost Center and AWS
Budget. An example written in Terraform is given below.
module "iam_assume_role_sts" {
source = "terraform-aws-modules/iam/aws//modules/iam-assumable-role"
version = ">= 4.7.0"
role_name = "query-cost-center-role"
trusted_role_arns = [
var.query_cost_center_lambda_role_arn
]
create_role = true
role_requires_mfa = false
custom_role_policy_arns = [
module.query_cost_center_policy.arn
]
}
module "query_cost_center_policy" {
source = "terraform-aws-modules/iam/aws//modules/iam-policy"
version = ">= 4.7.0"
name = "Query-cost-center-policy"
path = "/"
description = "This policy allows to query the AWS CostCenter"
policy = data.aws_iam_policy_document.query_cost_center_policy.json
}
data "aws_iam_policy_document" "query_cost_center_policy" {
statement {
actions = [
"ce:GetCostAndUsage",
"ce:GetCostForecast"
]
resources = ["*"]
}
statement {
actions = [
"budgets:ViewBudget"
]
resources = [
"arn:aws:budgets::${data.aws_caller_identity.current.account_id}:budget/project_budget"
]
}
}
Data visualization with Quicksight*
Quicksight supports S3 as a direct data source -- only a manifest file
containing a description of the data stored in the bucket is needed.
This is quite handy for data whose structure does not change or only
very seldom.
A more involving setup including AWS Glue and AWS Athena might be
beneficial in cases where either a lot of details (not only basic cost
information) are queried, or a lot of different AWS services are used
over time in the different AWS accounts. It might happen that Quicksight
runs into problems when trying to load this kind of data as it is going
to change constantly, and the manifest file requires a lot of updates. A
Glue Crawler combined with an Athena table might be the better approach
in such a scenario.
As soon as a new dataset based on the S3 bucket has been created, one or
several dashboards can be implemented. They can represent some overview
data like it is done in the example below or go into more detail --
depending on the specific requirements. How to create these dashboards
is out of scope of this article but Quicksight offers enough tooling to
start from simple to go a long way to sophisticated information display.
A Quicksight dashboard can either be shared with individuals in need of
this information or a scheduled email notification can be established.
Quicksight will sent a mail to all specified recipients which can
include an image of the dashboard as well as some data in CSV format.
This feature helps a lot it is not always necessary to login to keep the
costs under control. Simply by receiving an automated message for
instance every day or just once a week can already help to stay
informed.
Wrapping up
Cost monitoring is an important topic for every project -- from small to
large. AWS offers various tools to stay up to date but this task is
getting tedious when following AWS best practice and separating an
application into different stages and AWS accounts. There are 3rd party
or company-internal tools available which helps to overcome this
situation, but it is not always possible to use them (especially in an
enterprise setup) or they come with their own drawbacks.
This blog post has presented a small-scale application which offers
enough information and details to monitor the costs generated by small
to medium size projects. It has its own limitations as it might not be
powerful enough when dealing with tens or even hundreds of AWS accounts
-- but this is normally not the typical setup of a project.
Photo credits
Photo of Anna Nekrashevich: https://www.pexels.com/de-de/foto/lupe-oben-auf-dem-dokument-6801648/
Top comments (0)