Distribute Your Microservices Data With Events, CQRS, and Event Sourcing

Distributed Your Microservices Data With Events, CQRS, and Event Sourcing
Edson Yanaga @yanaga

@yanaga 2 @yanaga

@yanaga 3 bit.ly/mono2microdb

@yanaga 4 Code is easy, state is hard

@yanaga 5 HTTP + REST/gRPC/RMI/IIOP Synchronous Data Retrieval on a
Remote Endpoint Client Canonical Source of Information

@yanaga 6 HTTP + REST/gRPC/RMI/IIOP Synchronous Data Retrieval on a
Remote Endpoint Client Canonical Source of Information

@yanaga 7 Latency Availability Performance

@yanaga 8 Cache and/or Polling

@yanaga 9 Eventual Consistency

@yanaga 10 Eventual Consistency

@yanaga 11 First, a look back at the past…

@yanaga 12 How was data managed 10 years ago?

@yanaga 13 Terriﬁed about Entity Beans

@yanaga 14 Hibernate to the rescue!

@yanaga 15 Replacing XML with @Annotations

@yanaga 16 POJOs as an (Anemic) Domain Model

@yanaga 17 Event Sourcing

@yanaga 18 ID CUSTOMER_ID BALANCE 1001 990 1000 1002 991
0 1003 991 -500 1004 992 300 Account

@yanaga 19 ID ACCOUNT_ID TIMESTAMP OP AMOUNT 1 1001 1234567890
C 1000 2 1002 1234567891 C 200 3 1001 1234567900 D 300 4 1001 1234567995 D 150 Transactions

@yanaga 20 Enables you to think in the Events that
happened in the system

@yanaga 21 CQS (Command-Query Separation) “Asking a question should not
change the answer” (Bertrand Meyer)

@yanaga 22 CQRS (Command Query Responsibility Segregation)

@yanaga 23 CQRS (Command Query Responsibility Segregation)

@yanaga 24 ID NAME PHONE ADDRESS BIRTH 1 Burr 222-222-2323
901 South St 12/12/1968 2 Edson 222-333-3434 112 North Dr 03/03/1978 3 John 111-456-4545 666 Iron St 06/06/1966 4 Doe 333-789-7890 777 Boeing Dr 07/07/1977 INSERT INTO CUSTOMER(ID,NAME,PHONE,ADDRESS,BIRTH); SELECT * FROM CUSTOMER;

@yanaga 25 SELECT ID, NAME, PHONE FROM CUSTOMER; SELECT ID,
NAME, ADDRESS FROM CUSTOMER;

@yanaga 26 CQRS with separate data stores

@yanaga 27 SELECT ID, NAME, AGE, AVG_BILL FROM CUSTOMER_REPORT_VIEW; SELECT
ID, PHONE, LAST_PAYMENT_AMOUNT FROM CUSTOMER_BILLING_VIEW;

@yanaga 28 CQRS & Event Sourcing

0 1003 991 -500 1004 992 300 Account ID ACCOUNT_ID TIMESTAMP OP AMOUNT 1 1001 1234567890 C 1000 2 1002 1234567891 C 200 3 1001 1234567900 D 300 4 1001 1234567995 D 150 Transactions

0 1003 991 -500 1004 992 300 Account ID ACCOUNT_ID TIMESTAMP OP AMOUNT 1 1001 1234567890 C 1000 2 1002 1234567891 C 200 3 1001 1234567900 D 300 4 1001 1234567995 D 150 Transactions READ MODEL WRITE MODEL

@yanaga 31 Why CQRS?

@yanaga 32 Performance

@yanaga 33 Now, Back to the Future!

@yanaga 34 Distribution Availability Integration Analytics

@yanaga 35 Canonical Source of Information (Write Data Store) µ

@yanaga 36 Canonical Source of Information (Write Data Store) Read
Data Store Read Data Store µ µ µ

@yanaga 37 Canonical Source of Information (Write Data Store) Read
Data Store Read Data Store µ µ µ Events Events

@yanaga 38 HTTP + REST/gRPC/RMI/IIOP Synchronous Event Retrieval Client Canonical
Source of Information µ µ

@yanaga 39 HTTP + REST/gRPC/RMI/IIOP Synchronous Event Retrieval Client Canonical
Source of Information µ µ

@yanaga 40 AMQP/Kafka Asynchronous Event Propagation Client Canonical Source of
Information µ µ

@yanaga 41 Approaches

@yanaga 42 1st: You need change events (Event Sourcing)

@yanaga 43 Change your application OR Use Debezium

@yanaga 44 2nd: You need to distribute the events

@yanaga 45 Create a REST endpoint for your events using
Quarkus Or Publish the events on ActiveMQ / Kafka

@yanaga 46 3rd: Consume the events and update your local
CQRS data store

@yanaga 47 4th: Use the local data in your local
CQRS data store

@yanaga 48 Thank you!

Distribute Your Microservices Data With Events,...

Distribute Your Microservices Data With Events, CQRS, and Event Sourcing

More Decks by Edson Yanaga

Other Decks in Technology

Featured

Transcript