Website for DSPA Spring 2021
This project is maintained by vasia
*Note: This schedule is tentative.
Make sure to become familiar with the Official Semester Dates.
Some of the critical Semester Dates are:
Date | Topic | Slides | Note |
---|---|---|---|
01/26 | Course introduction | dspa21-1.pdf | Reading: The 8 Requirements of Real-Time Stream Processing Video: Beyond Analytics: the Evolution of Stream Processing Systems (SIGMOD'20 Tutorial) - PART I |
01/28 | Stream processing fundamentals | dspa21-2.pdf | Videos: The Evolution of (Open Source) Data Processing by Aljoscha Krettek |
02/01 | Deadline: Project selection | ||
02/02 | Stream ingestion and pub/sub systems | dspa21-3.pdf | Follow the Flink setup tutorial and the Kafka quickstart (steps 1-5). |
02/04 | Hands-on: Introduction to Apache Flink and Kafka | Project teams announcement | |
02/09 | Hands-on: Flink's DataStream API | dspa21-4.pdf | |
02/11 | Notions of time and progress | dspa21-5.pdf | Reading: Streaming 102: The world beyond batch Watermarks, Tables, Event Time, and the Dataflow Model |
02/16 | No class | Substitute Monday | |
02/18 | Windows and triggers | dspa21-6.pdf | Video: Efficient Window Aggregation with Stream Slicing |
02/19 | Project Deliverable #1: Design Document | ||
02/23 | Hands-on: Windows | ||
02/25 | Hands-on: Windows (part 2) | ||
03/02 | State management | dspa21-7.pdf | Videos: Managing State in Apache Flink - Tzu-Li (Gordon) Tai and Webinar: Deep Dive on Apache Flink State - Seth Wiesman |
03/04 | Hands-on: State Management | ||
03/08 | Project Deliverable #2: Pre-recorded Midterm project demo | ||
03/09 | Midterm Demos | Project Deliverable #2: Live Midterm project demo | |
03/11 | High-availability, recovery semantics, and guarantees | dspa21-8.pdf | Reading: An example run of the Chandy-Lamport snapshot algorithm |
03/16 | Exactly-once fault-tolerance in Apache Flink | dspa21-9.pdf | Videos: Incremental checkpoints Unaligned checkpoints |
03/18 | No class | Wellness Day | |
03/23 | Hands-on: Fault-tolerance & reconfiguration | dspa21-10.pdf | |
03/25 | Flow control and load shedding | dspa21-11.pdf | Video: Improving throughput and latency with Flink's network stack |
03/29 | Deadline: Paper reviews | ||
03/30 | Elasticity and state migration | dspa21-12.pdf | |
04/01 | Streaming optimizations | dspa21-13.pdf | |
04/06 | Streaming optimizations (cont.) | ||
04/07 | Deadline: Paper presentation videos | ||
04/08 | Team #1 & Team #3: Paper presentation | TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control & Analyzing Efficient Stream Processing on Modern Hardware | |
04/13 | Team #6 & Team #7: Paper presentation | EdgeWise: A Better Stream Processing Engine for the Edge & Shared Arrangements: practical inter-query sharing for streaming dataflows | |
04/15 | Team #8: Paper presentation | Turbine: Facebook’s Service Management Platform for Stream Processing | |
04/20 | Guest Lecture: Evaluating Complex Queries on Streaming Graphs | Anil Paçaci, University of Waterloo | |
04/22 | Hacking day | ||
04/27 | Course recap | ||
04/29 | Final Project Demos | Project Deliverable #3: Demos and posters |