Unify Storage Backend for Batch and Streaming Computation with Apache Pulsar

1 .Unify Storage Backend for Batch and Streaming Computation with Apache Pulsar Vincent Xie (Bestpay), Jia Zhai (StreamNative) 

2 .About us Vincent (Weisheng) Xie Jia Zhai ❏ Current Director @ Orange Financial ❏ Co-Founder of StreamNative ❏ Previous Tech lead of ML engineering ❏ Apache Pulsar PMC Member team @ Intel ❏ Apache BookKeeper PMC Member 

3 .Agenda ❏ Background ❏ Apache Pulsar ❏ Unified Data Processing ❏ Our Practices ❏ Q&A 

4 .Background Intro 

5 .Orange Financial Orange Financial Services Group (Chinese: 甜橙金融), formerly known as Bestpay, is an affiliate company of China Telecom. It reached 1.13 trillion CNY ($18.37 Billion) transaction volume in 2018, with 500 million registered users and 41.9 million active users. Subsidiaries: Bestpay - a mobile wallet and payment app Jieqian - a consumer loan service Orange Wealth Orange Insurance Orange Credit Orange Financial Cloud 

6 .

7 .Source: iiMedia Research Inc. 

8 .High Industry Penetration Rate Source: China Unionpay 

9 .Source: RSA 

10 .Challenges ❏ High concurrency ❏ > 50M transactions, 1 billion events a day (peek: 35K/s) ❏ Low latency demand ❏ response < 200ms ❏ Large number of batch jobs and streaming jobs 

11 .“A merchant’s total transaction volume ($) within the past month (30days) (current transaction included)” = sum($past_29days) + sum($today_upto_current) batch streaming 

12 .Architecture V1 API Gateway 

13 .Architecture V1 - Lambda Speed/Streaming Layer API Serving Gateway Layer Batch Layer 

14 .Drawbacks ❏ S/W stacks complexity ❏ Realtime / Offline / Serving stacks ❏ Multiple clusters to maintain (Kafka / Hive / Spark / Flink) ❏ Different skill sets to manipulate (Scala / Java / SQL) ❏ Segmented Logics ❏ Historical/Current ❏ Data redundancy ❏ Multiple duplications to move over 

15 .Introduce Apache Pulsar 

16 .What is Apache Pulsar? 

17 . “Flexible Pub/Sub Messaging Backed by durable log storage” 

18 .Pulsar - A cloud-native architecture Stateless Serving Durable Storage 

19 .Pulsar - Segment Centric Storage ❏ Topic Partition (Managed Ledger) ❏ The storage layer for a single topic partition ❏ Segment (Ledger) ❏ Single writer, append-only ❏ Replicated to multiple bookies 

20 .Pulsar - Pub/Sub 

21 .Pulsar - Topic Partitions 

22 .Pulsar - Segments 

23 .Pulsar - Stream 

24 .Pulsar - Stream as a unified view on data 

25 .Pulsar - Two levels of reading API ❏ Pub/Sub (Streaming) ❏ Read data from brokers ❏ Consume / Seek / Receive ❏ Subscription Mode - Failover, Shared, Key_Shared ❏ Reprocessing data by rewinding (seeking) the cursors ❏ Segment (Batch) ❏ Read data from storage (bookkeeper or tiered storage) ❏ Fine-grained Parallelism ❏ Predicate pushdown (publish timestamp) 

26 .Unified Data Processing on Pulsar 

27 .Architecture V2 Spark Structured Streaming Spark SQL API Gateway 

28 .Architecture V2 Spark Structured Streaming Spark SQL API Gateway ❏ Single Data Store (Pulsar) ❏ Single Computing Engine (Spark) ❏ Unified API 

29 .Pulsar-Spark ❏ Deeply integrated with Pulsar schema ❏ Pulsar topics as Structured Streams ❏ Pulsar Connectors for Spark Structured Streaming ❏ Pulsar Connectors for Spark SQL https://github.com/streamnative/pulsar-spark