University of Illinois Urbana-Champaign

New techniques to lower the tail latency in stream processing systems

Du, Guangxiang

Content Files
DU-THESIS-2016.pdf

Permalink

https://hdl.handle.net/2142/90610

Description

Title
New techniques to lower the tail latency in stream processing systems
Author(s)
Du, Guangxiang
Issue Date
2016-04-22
Director of Research (if dissertation) or Advisor (if thesis)
Gupta, Indranil
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Date of Ingest
2016-07-07T19:54:34Z
Keyword(s)
  • tail latency
  • stream processing systems
Abstract
Over the past decade, the demand for real time processing of huge amount of streaming data has emerged and grown rapidly. Apache Storm, Apache Flink, Samza and many other stream processing frameworks have been proposed and implemented to meet this need. Although lots of effort has been made to reduce the average latency of stream processing systems, how to shorten their tail latency has received little attention. This thesis presents a series of novel techniques for reducing the tail latency in stream processing systems like Apache Storm. Concretely, we present three mechanisms: (1) adaptive timeout coupled with selective replay to catch straggler tuples; (2) shared queues among different tasks of the same operator to reduce overall queueing delay; (3) latency feedback-based load balancing, intended to mitigate heterogenous scenarios. We have implemented these techniques in Apache Storm, and present experimental results using sets of micro-benchmarks as well as two topologies from Yahoo! Inc. Our results show improvement in tail latency in the range of 2%-72.9%.
Graduation Semester
2016-05
Type of Resource
text
Permalink
http://hdl.handle.net/2142/90610
Copyright and License Information
Copyright 2016 Guangxiang Du

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois