Introduction
To continue the article from Event-Driven AWS: Implementing Choreography Pattern, the best approach is to practically implement the event flow we've discussed.
1. AWS EventBridge Setup
Create an Event Bus
You can create a dedicated Event Bus in EventBridge to handle all events related to your aircraft booking system.
aws events create-event-bus --name AircraftBookingBus
Define EventBridge Rules
You will create rules that route events to the appropriate service targets (like Lambda functions, SQS queues, or Step Functions).
Example rule to listen for the BookingCreated event and route it to the Payment Service:
aws events put-rule
--name PaymentProcessingRule --event-bus-name AircraftBookingBus
--event-pattern '{"source": ["aircraft.booking"], "detail-type": ["BookingCreated"]}'
Example Event Patterns for EventBridge Rules
Rule for BookingCreatedRule (Target: Payment Service)
{
"source": ["aircraft.booking"],
"detail-type": ["BookingCreated"]
}
Rule for PaymentConfirmedRule (Target: Seat Assignment Service)
{
"source": ["aircraft.payment"],
"detail-type": ["PaymentConfirmed"]
}
Rule for TicketIssuedRule (Target: Ticket Service)
{
"source": ["aircraft.seat-assignment"],
"detail-type": ["SeatAssigned"]
}
You can similarly create rules for PaymentConfirmed and SeatAssigned events, and route them to the corresponding services.
Set Targets for EventBridge Rules
After defining the rules, you need to specify which service (e.g., Lambda) should be triggered by each event.
Example: Route the BookingCreated event to a Lambda function that handles payment:
aws events put-targets --rule BookingCreatedRule --targets \\
"Id"="1","Arn"="<Lambda-Payment-Service-ARN>"
2. Services flow
Booking is Created
The Booking Service creates a booking and publishes an event called BookingCreated to EventBridge.
{
"source": "aircraft.booking",
"detail-type": "BookingCreated",
"detail": {
"bookingId": "B123",
"customerId": "CUST001",
"flightId": "FLIGHT001",
"amount": 300
}
}
The EventBridge BookingCreatedRule has a rule that listens for BookingCreated events where the source is aircraft.booking.
Payment Service Receives BookingCreated
Upon receiving the event, the Payment Service processes the payment and publishes either a PaymentConfirmed or PaymentFailed event based on the outcome.
{
"source": "aircraft.payment",
"detail-type": "PaymentConfirmed",
"detail": {
"status": "SUCCESS",
"bookingId": "B123",
"customerId": "CUST001",
"paymentId": "PAY001"
}
}
Seat Assignment Service Receives PaymentConfirmed
The Seat Assignment Service listens for the PaymentConfirmed event as well. When a new booking is created, it assigns a seat to the customer and publishes a SeatAssigned event.
SeatAssigned event
{
"source": "aircraft.seat-assignment",
"detail-type": "SeatAssigned",
"detail": {
"bookingId": "B123",
"customerId": "CUST001",
"seat": "12A"
}
}
3. Create Lambda Functions for Each Service
Create the necessary Lambda functions (or use SQS, Step Functions, etc.) to handle events for each service, such as Payment, Seat Assignment, Ticket, and Notifications.
Here is an example in python for Seat Assignment Service :
import json
import boto3
from datetime import datetime
eventbridge = boto3.client('events')
dynamodb = boto3.resource('dynamodb')
table = dynamodb.Table('PaymentTable')
def lambda_handler(event, context):
payment_status = event['detail']['status']
booking_id = event['detail']['bookingId']
customer_id = event['detail']['customerId']
flight_id = event['detail']['flightId']
amount = event['detail']['amount']
if payment_status == 'SUCCESS':
# Store information details in DynamoDB
table.put_item(
Item={
'CustomerID': customer_id,
'BookingID': booking_id,
'flightID': flight_id,
'Timestamp': str(datetime.now(datetime.timezone.utc))
}
)
# Publish event to EventBridge for next step (Ticket Service)
eventbridge.put_events(
Entries=[
{
'Source': 'aircraft.seat-assignment',
'DetailType': 'SeatAssigned',
'Detail': json.dumps({'bookingId': booking_id, 'customerId': customer_id, 'seat': '12A'}),
'EventBusName': 'AircraftBookingBus'
}
]
)
print(f"Seat Assigmed for {customer_id}. Stored in DynamoDB and event sent.")
else:
print(f"Seat Assigmed failed for {customer_id}.")
return {
'statusCode': 200,
'body': json.dumps('Payment Lambda executed successfully')
}
Conclusion
In conclusion, the implementation of the AWS event-driven choreography pattern enables seamless integration and coordination between microservices using events. By leveraging services like EventBridge and Lambda functions, various components like booking, payment, and seat assignment services can operate asynchronously, improving scalability and decoupling. This architecture is highly flexible and supports business processes efficiently while ensuring that each service reacts to specific events without requiring direct interactions, enhancing the overall system's maintainability and robustness.
Top comments (0)